open/ms-ai-architect
1
0
Fork 0
Code Issues Pull requests Releases Activity
ms-ai-architect/scripts/kb-eval/data/judge-pass-manifest.json

7850 lines
583 KiB
JSON
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"_meta": {
"purpose": "R7–R10 full-pass judge ledger: one record per never-verified reference file — born-verified pass (surgical stamp) or flagged (R11 work-list). Durable per file.",
"derived_from": "scripts/kb-update/data/full-pass-worklist.json (243 due, all never-verified)",
"cadence": "R7–R10 (5 økter × ~49, 8–10 samtidige)",
"batch": "R7.1",
"count": 143,
"generated": "2026-07-18"
},
"files": [
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-365-governance-and-deployment.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/office365/servicedescriptions/microsoft-agent-365/microsoft-agent-365#feature-availability",
"evidence_quote": "Detect suspicious agent activity, receive alerts, and allow blocking for tool invocations for agents | Defender | No | Yes | Yes",
"reason": "The risk-column aggregation part is grounded, but the agent risk/governance features carry Yes in both the 'Microsoft Enterprise 7' AND the standalone 'Agent 365' columns (registry page ties the Risks column to 'licensed subscription', not E7), so the load-bearing 'kun ... E7' exclusivity is contradicted.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md",
"line": 43,
"claim": "Risks Column (aggregerte high-severity risks fra Entra, Defender og Purview per agent) er kun tilgjengelig med Microsoft 365 E7-lisens.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-365-governance-and-deployment.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-365/admin/manage/agent-actions",
"evidence_quote": "**Install and uninstall** ... **Block and unblock** ... **Delete** ... **Start and stop** ... **Assign a new owner** ... **Publish to store** ... **Reject submission**",
"reason": "The canonical actions page enumerates 7 agent actions, not the claimed 11; 'Activate' and 'Approve Updates' are absent and the actual set differs (Start/stop, Reject submission, Install/uninstall present; Pin/Export are registry-list actions elsewhere).",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md",
"line": 49,
"claim": "Admin Center tilbyr 11 lifecycle management actions: Publish | Activate | Deploy | Pin | Block | Remove | Delete | Approve Updates | Manage Ownerless Agents | Reassign | Export Inventory.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-365-governance-and-deployment.md#15",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/microsoft-365-copilot/extensibility/copilot-studio-experience",
"evidence_quote": "If you don't have a Copilot license, you can use Copilot Credits or a pay-as-you-go plan to access either experience. You can also use Agent Builder in Microsoft 365 Copilot for free to build agents grounded on web knowledge only.",
"reason": "The doc says Agent Builder can be used for free (web-knowledge agents) or via Copilot Credits/pay-as-you-go without a Copilot license, contradicting the claim that a Microsoft 365 Copilot license is required to create agents.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md",
"line": 321,
"claim": "Agent Builder krever Microsoft 365 Copilot-lisens for å opprette agenter.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-365-governance-and-deployment.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/extensibility/prerequisites",
"evidence_quote": "If you want to build agents that are grounded on organizational data via SharePoint or Copilot connectors, you need to either set up pay-as-you-go billing in your tenant or purchase a Copilot Studio license.",
"reason": "The pay-as-you-go alternative is grounded, but the other required license is a Copilot Studio license (or Microsoft 365 Copilot add-on), not a 'Power Apps/Power Automate premium license' as the claim states, so a load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md",
"line": 322,
"claim": "Copilot Studio Agents krever Power Apps/Power Automate premiumlisens ELLER Pay-as-you-go.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-autonomy-and-control-governance.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-autonomy-and-control-governance.md#16",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/agent-framework/support/faq",
"evidence_quote": "",
"reason": "Learn confirms Agent Framework is open source and on GitHub but no Learn page states the specific MIT license, so the MIT value cannot be confirmed.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-autonomy-and-control-governance.md",
"line": 331,
"claim": "Microsoft Agent Framework er open source under MIT-lisens.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-evaluation-testing-frameworks.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/agent-evaluate-sdk?view=foundry-classic",
"evidence_quote": "The Azure AI Evaluation SDK and evaluators marked (preview) in this article are currently in public preview everywhere.",
"reason": "Two-part claim: the agent-evaluators-are-preview part holds, but the load-bearing part 'Azure AI Evaluation SDK is GA' is contradicted — the page states the SDK is in public preview everywhere, so one wrong load-bearing part fails the whole claim.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md",
"line": 4,
"claim": "Azure AI Evaluation SDK er GA, mens de agent-spesifikke evaluatorene er i Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-evaluation-testing-frameworks.md#6",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators?view=foundry",
"evidence_quote": "For complex evaluation that requires refined reasoning, we recommend `gpt-5-mini` for its balance of performance, cost, and efficiency.",
"reason": "The current Foundry agent-evaluators page recommends gpt-5-mini for complex evaluation; the claim's gpt-4.1-mini (the old classic-page guidance) has been superseded.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md",
"line": 56,
"claim": "Microsoft anbefaler gpt-4.1-mini som judge-modell for kompleks evaluering.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-evaluation-testing-frameworks.md#8",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators?view=foundry",
"evidence_quote": "Agent evaluators support the following tools: File Search, Function Tool (user-defined tools), MCP, Knowledge-based MCP. The following tools currently have limited support. Avoid using `tool_call_accuracy` ... if your agent conversation includes calls to these tools: Azure AI Search, Bing Grounding, Bing Custom Search, SharePoint Grounding, Code Interpreter, Fabric Data Agent, Web Search",
"reason": "The current agent-evaluators page supersedes the classic 9-tool list: tool_call_accuracy now fully supports only File Search/Function Tool/MCP/Knowledge-based MCP, explicitly advises avoiding it for 6 of the claimed tools, and no longer lists OpenAPI.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md",
"line": 82,
"claim": "ToolCallAccuracyEvaluator støtter disse tool-typene i Foundry Agent Service: File Search | Azure AI Search | Bing Grounding | Bing Custom Search | SharePoint Grounding | Code Interpreter | Fabric Data Agent | OpenAPI | Function Tool.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-evaluation-testing-frameworks.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/agent-evaluate-sdk?view=foundry-classic",
"evidence_quote": "",
"reason": "The cited page uses an `api_version` environment-variable placeholder (no hardcoded value) and neither it nor the reasoning-models docs state '2024-08-01-preview' for reasoning-model configuration; no Learn page confirms or contradicts the value.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md",
"line": 256,
"claim": "Azure OpenAI api_version for reasoning-modell-konfigurasjon er 2024-08-01-preview.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-memory-and-context-management.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/data-location",
"evidence_quote": "Historical activity data for agents: Activity data, including conversation logs, is stored in the geographic region of the end user's Exchange mailbox.",
"reason": "The SK/Foundry/Agent Framework/M365 parts check out, but Copilot Studio conversation history/logs are stored Microsoft-managed in M365 (Exchange mailbox), not in an opt-in customer Cosmos DB — one load-bearing part is contradicted.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md",
"line": 49,
"claim": "Minnearkitekturer per plattform: Semantic Kernel Agents (ChatHistoryAgentThread; Mem0Provider, Vector Stores) | Foundry Agent Service (managed session context; Managed Memory Store preview) | Microsoft Agent Framework (ChatHistoryProvider in-memory/Cosmos; ChatHistoryMemoryProvider, Mem0Provider, Redis) | Copilot Studio (session-variabler; Conversation history opt-in Cosmos DB) | M365 Copilot (Microsoft-managed).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-memory-and-context-management.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/dotnet/api/microsoft.semantickernel.memory.imemorystore",
"evidence_quote": "Microsoft.SemanticKernel.Memory.VolatileMemoryStore",
"reason": "Four items match, but the legacy in-memory IMemoryStore implementation is VolatileMemoryStore — 'InMemoryMemoryStore' is absent from the derived-type enumeration, so the stated identifier is wrong.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md",
"line": 61,
"claim": "Legacy Memory Stores i Semantic Kernel: InMemoryMemoryStore | Azure AI Search | Cosmos DB (NoSQL/MongoDB) | PostgreSQL | SQL Server.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-memory-and-context-management.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-limits-quotas-capacity",
"evidence_quote": "",
"reason": "Basic and Standard S1 tiers exist, but no Microsoft page states a '50M vectors for production' capacity for S1 — vector limits are expressed in GB, so the specific vector count is unsourced.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md",
"line": 385,
"claim": "Azure AI Search tilbys i Basic-tier og Standard S1-tier, der S1 støtter 50M vektorer for produksjon.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-a2a-protocol.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/agent-framework/hosting/agent-to-agent",
"evidence_quote": "The A2A protocol defines two transport bindings. Both are supported: | HTTP+JSON | MapA2AHttpJson | ... | JSON-RPC | MapA2AJsonRpc | JSON-RPC 2.0 over HTTP.",
"reason": "MS Learn documents the two A2A transport bindings as HTTP+JSON and JSON-RPC (Foundry's transport table marks gRPC as absent), contradicting the claim's load-bearing 'multi-protocol bindings (JSON-RPC og gRPC)'.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md",
"line": 46,
"claim": "A2A v1.0 har fire hovednyheter: Signed Agent Cards | multi-tenancy | multi-protocol bindings (JSON-RPC og gRPC) | versjonsforhandling (v0.3→v1.0).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-a2a-protocol.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/tools/agent-to-agent",
"evidence_quote": "| Microsoft Foundry support | Python SDK | C# SDK | JavaScript SDK | Java SDK | REST API | ... | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ |",
"reason": "The Usage support table marks Java SDK ✔️ (with a full Java sample using com.azure:azure-ai-agents:2.2.0), contradicting the claim's load-bearing assertion that Java is not supported.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md",
"line": 294,
"claim": "Foundry støtter A2A via SDK-ene Python | C# | TypeScript | REST API; Java er ikke støttet per februar 2026.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-a2a-protocol.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/agent-framework/integrations/a2a",
"evidence_quote": "",
"reason": "agent-framework-a2a (--pre) and @microsoft/teams.a2a (npm) appear verbatim on MS Learn, but no page states the exact identifiers azure-ai-projects[agents] or a pip package microsoft-teams-a2a; the full package list cannot be confirmed and nothing contradicts it.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md",
"line": 642,
"claim": "A2A SDK-pakker: agent-framework-a2a (--pre/preview) | azure-ai-projects[agents] | @microsoft/teams.a2a (npm) | microsoft-teams-a2a (pip).",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 14,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-communication.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/agent-framework/user-guide/hosting/agent-to-agent-integration",
"evidence_quote": "A2A is a standardized protocol that supports: Agent discovery through agent cards, Message-based communication between agents, Long-running agentic processes via tasks, Cross-platform interoperability between different agent frameworks",
"reason": "A2A's architecture comprises Agent Card, Client Agent and Remote Agent over direct HTTP/JSON-RPC; 'Message Broker' and 'Agent Registry API' are not A2A core components, so two load-bearing list items are wrong.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"line": 35,
"claim": "A2A-arkitekturens kjernekomponenter: A2A Protocol | Agent Card | Client Agent | Remote Agent | Agent Registry API | Message Broker.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-communication.md#8",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/event-grid/quotas-limits",
"evidence_quote": "Publish rate for a custom or a partner topic (ingress) | 5,000 events or 5 MB per second (whichever comes first)",
"reason": "Event Grid's documented throughput is 5,000 events/sec per topic, orders of magnitude below the claimed 10 million events per second; the 'millions of events per second' figure belongs to Event Hubs, not Event Grid.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"line": 134,
"claim": "Azure Event Grid støtter real-time event routing på 10 millioner events per sekund.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-communication.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "",
"evidence_quote": "",
"reason": "Norway East and Norway West are valid Azure regions, but no learn.microsoft.com page states a recommendation to use them specifically for hosting local A2A agents in Norway.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"line": 422,
"claim": "For hosting av lokale agenter i Norge anbefales Azure-regionene Norway East og Norway West.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-communication.md#13",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/entra/agent-id/what-is-microsoft-entra-agent-id",
"evidence_quote": "Agent ID is available for all Microsoft Entra customers.",
"reason": "The Agent Registry is part of Microsoft Entra Agent ID, which is available to all Entra customers; Entra ID P2 is required only for 'ID Protection for agents', not to use the Agent Registry, contradicting the P2-required claim.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"line": 435,
"claim": "Microsoft Entra ID P2 kreves for å bruke Agent Registry.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/agent-to-agent-communication.md#14",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/entra/identity/monitoring-health/reference-reports-data-retention",
"evidence_quote": "Audit logs | Seven days | 30 days | 30 days",
"reason": "Entra ID P2 audit logs are retained 30 days, not 90; the 90-day figure applies to risky sign-ins (a security signal), not audit logs.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md",
"line": 437,
"claim": "Entra ID P2 audit logs har 90 dagers retention.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/durable-task/durable-functions/durable-functions-versions",
"evidence_quote": "",
"reason": "The current overview and versions pages present Durable Functions as a production, versioned extension (v3.x 'Current (recommended)', v1.x 'End of support') with no preview label, but no fetched Learn page explicitly states the 'generally available (GA)' status the claim asserts.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 4,
"claim": "Kjerneteknologien Durable Functions er merket GA (generelt tilgjengelig).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#2",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/durable-task/durable-functions/durable-functions-overview",
"evidence_quote": "",
"reason": "No Learn page states the claimed 'three primary approaches' taxonomy; it is the author's editorial synthesis, not an enumeration any authoritative page grounds.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 27,
"claim": "Microsoft-stakken tilbyr tre primære tilnærminger til autonomous workflow automation: Durable Functions | Power Automate med AI Builder | Azure Logic Apps.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#3",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/connectors/custom-connectors/",
"evidence_quote": "",
"reason": "Learn states 'over 1,000 connectors'; no fetched page states the claimed '1,400+' figure, and 'over 1,000' neither confirms nor contradicts a 1,400+ lower bound.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 48,
"claim": "Power Automate har 1400+ connectors.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#9",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/power-automate/organization-q-and-a",
"evidence_quote": "a paid or trial Power Automate Premium (previously Power Automate per user with attended RPA) or a Power Automate Process plan (previously Power Automate per flow)",
"reason": "'Per flow' is the legacy name for the Process license (renamed), so listing 'Per flow' and 'Process' as two distinct current license types is not the current taxonomy — the current standalone types are Premium (per user) and Process.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 495,
"claim": "Power Automate lisenstyper: Per user | Per flow | Process (RPA desktop flows, unattended automation).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#10",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/ai-builder/credit-management",
"evidence_quote": "Power Automate Premium | 5,000 | Maximum = 1,000,000 AI Builder credits per tenant.",
"reason": "The per-user license (Power Automate Premium) includes 5,000 AI Builder credits, not 40,000; the 40,000 figure is the Power Platform requests-per-24-hours limit, not AI Builder credits.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 497,
"claim": "Power Automate Per user-lisens inkluderer 40 000 AI Builder credits per måned.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/autonomous-workflow-automation-patterns.md#11",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/power-platform/admin/api-request-limits-allocations",
"evidence_quote": "If a cloud flow has a per flow plan (legacy), the flow can make 250,000 Power Platform requests across all users of the flow in a 24-hour period.",
"reason": "The per-flow license entitlement is framed as 250,000 Power Platform requests per 24 hours (and the plan is legacy); there is no '15,000 cloud flow runs per month' entitlement — the monthly-run-quota frame has been replaced by the per-24-hour requests model.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/autonomous-workflow-automation-patterns.md",
"line": 498,
"claim": "Power Automate Per flow-lisens inkluderer 15 000 cloud flow runs per måned og 250 000 API requests.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/computer-using-agents-cua.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/whats-new",
"evidence_quote": "September 2025 ... (Preview) Automate tasks in desktop applications on Windows using Computer-Using Agents (CUA) ... May 2026 ... (General availability) Computer use is now generally available",
"reason": "Documented public preview is September 2025, not 2025-05-27; the preview-date part is contradicted, so the multi-part claim fails.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md",
"line": 35,
"claim": "Copilot Studio Computer Use (som verktøy i agenter) var public preview fra 2025-05-27 og ble GA 2026-05-07.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/computer-using-agents-cua.md#5",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/how-to/computer-use",
"evidence_quote": "1. Click 2. DoubleClick 3. Drag 4. KeyPress 5. Move 6. Screenshot 7. Scroll 8. Type 9. Wait",
"reason": "The canonical ComputerActionType enum is click/double_click/drag/keypress/move/screenshot/scroll/type/wait; the claim's load-bearing action names 'key' (should be keypress) and 'navigate' (no such action) are wrong.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md",
"line": 75,
"claim": "CUA støtter handlingstypene: screenshot | click | double_click | type | key | scroll | drag | navigate.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/computer-using-agents-cua.md#13",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/tools/browser-automation",
"evidence_quote": "pip install \"azure-ai-projects>=2.0.0\" ... <artifactId>azure-ai-agents</artifactId> <version>2.2.0</version>",
"reason": "Current setup requires azure-ai-projects>=2.0.0 (Python) / azure-ai-agents 2.2.0 (Java); the claimed azure-ai-agents 1.2.0b2 is a superseded beta that no longer appears.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md",
"line": 218,
"claim": "Browser Automation-oppsett i Foundry krever azure-ai-agents >= 1.2.0b2.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 30,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#6",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/migrate-hosted-agent-preview",
"evidence_quote": "As of `azure-ai-projects` 2.3.0 on the GA `v1` API, hosted agents are generally available and this header is no longer required.",
"reason": "Hosted agents are now generally available, contradicting the claimed Public Preview status.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 68,
"claim": "Hosted agents (din egen kode/container) er i Public Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/agents/how-to/triggers",
"evidence_quote": "Trigger an agent by using Logic Apps (preview) (classic)",
"reason": "Logic Apps trigger integration is labeled preview (both classic and the new Logic Apps agent-action doc), not GA as claimed.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 72,
"claim": "Logic Apps-triggerintegrasjon er GA.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/migrate",
"evidence_quote": "Deep Research | Yes (Public Preview) | No (Recommendation: Deep Research model with Web Search tool)",
"reason": "The list asserts current built-in tools but includes Deep Research (deprecated/removed in new Foundry) and Morningstar (absent from the current tool catalog), so it describes a superseded classic tool set.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 187,
"claim": "Innebygde verktøy i Foundry Agent Service: Code Interpreter | File Search | Grounding with Bing Search | Bing Custom Search | SharePoint | Azure Functions | Azure Logic Apps | OpenAPI tool | MCP tool | Deep Research tool | Fabric Data Agent | Morningstar tool.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/concepts/tool-catalog",
"evidence_quote": "Image Generation (preview) ... Browser Automation (preview) ... Computer Use (preview) ... Microsoft Fabric (preview) ... SharePoint (preview)",
"reason": "SharePoint being preview is correct, but the claim's load-bearing 'other built-in tools are GA' is false since Image Generation, Browser Automation, Computer Use and Microsoft Fabric are also preview.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 193,
"claim": "SharePoint-verktøyet er i Preview (de øvrige innebygde verktøyene er GA).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/migrate",
"evidence_quote": "MCP | Yes (Public Preview) | Yes (GA)",
"reason": "MCP reached GA only in the new Foundry; in classic (its June 2025 debut) it was Public Preview, so 'GA (June 2025)' is wrong on the date part.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 197,
"claim": "MCP tool (koble til remote MCP-servere) er GA (juni 2025).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#17",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/agents/how-to/tools-classic/deep-research",
"evidence_quote": "The Deep Research tool is deprecated.",
"reason": "The Deep Research tool was Public Preview and is now deprecated/'No' in new Foundry — never GA — contradicting the claimed GA status.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 198,
"claim": "Deep Research tool (o3-deep-research + Bing) er GA (juni 2025).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-agent-service-ga.md#22",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/concepts/limits-quotas-regions?view=foundry",
"evidence_quote": "West Central US | Yes | Yes | No",
"reason": "The Agents column is Yes for 30 regions; the named regions are all present but the stated total of 19 is contradicted by 30.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-agent-service-ga.md",
"line": 340,
"claim": "Foundry Agent Service er tilgjengelig i 19 regioner totalt, inkludert Norway East | Sweden Central | West Europe | Germany West Central | France Central | Switzerland North | UK South | East US / East US 2.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/foundry-workflows-visual-orchestration.md#2",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/concepts/workflow",
"evidence_quote": "Because workflows are no longer a separate agent type, you run the result by deploying it as a hosted agent",
"reason": "The claim's three-agent-type taxonomy (Prompt-based | Workflow | Hosted) is superseded: the live docs state workflows are no longer a separate agent type and the development-lifecycle page enumerates exactly two agent types (Prompt-based and Hosted).",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md",
"line": 33,
"claim": "Workflows er ett av tre agenttyper i Foundry: Prompt-based | Workflow | Hosted (preview, containeriserte agenter)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-workflows-visual-orchestration.md#6",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/concepts/tool-catalog",
"evidence_quote": "The following table lists all built-in tools available in Foundry Agent Service. | Web search | Code Interpreter | Custom Code Interpreter (preview) | File Search | Azure AI Search | Azure Functions | Function calling | Image Generation (preview) | Browser Automation (preview) | Computer Use (preview) | Microsoft Fabric (preview) | SharePoint (preview)",
"reason": "The canonical tool catalog enumerates the built-in and custom tools (Code Interpreter, Azure AI Search, MCP, and Bing/Web search are present) but Key Vault is absent — in Foundry docs Key Vault is a secret-store connection, not a tool in the agent tool catalog, so one asserted list member does not exist.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md",
"line": 274,
"claim": "Verktøy tilgjengelige i agent-noder i workflows (samme katalog som enkelt-agenter): Code Interpreter, Bing Search, Azure AI Search, Key Vault, MCP-servere",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-workflows-visual-orchestration.md#8",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/logic-apps/add-agent-action-create-run-workflow",
"evidence_quote": "Azure Logic Apps supports 1,400+ connectors and native, built-in data operations, so agents can integrate with many Microsoft and non-Microsoft services or products.",
"reason": "The docs attach the 1,400+ figure to connectors, not triggers, and state no '400+ enterprise connectors' count anywhere — the enterprise-connector category is described as a small set (SAP, IBM MQ, IBM 3270) with Salesforce classified as a Standard connector, so the claim's organizing units and figures do not match the source.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md",
"line": 306,
"claim": "Azure Logic Apps: 1400+ triggere (HTTP, Events, Schedule, Queues, SaaS) | 400+ enterprise-koblinger (SAP, Salesforce, AS2, EDI)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/foundry-workflows-visual-orchestration.md#14",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry",
"evidence_quote": "Use these definitions to interpret the dashboard: Token usage ... Latency ... Run success rate ... Evaluation metrics ... Red teaming results",
"reason": "The dashboard's canonical metric enumeration lists Token usage, Latency, Run success rate, Evaluation metrics, and Red teaming results — 'Error rate' is not among the dashboard metrics (it appears only in a note about onboarding external custom agents), so one asserted list member is absent.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md",
"line": 391,
"claim": "Agent Monitoring Dashboard-metrikker: Token usage | Latency | Run success rate | Error rate | Evaluation metrics",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/multi-agent-orchestration-patterns.md",
"batch": "R7.2",
"judged_at": "2026-07-23",
"per_file_verdict": "flagged",
"claim_count": 7,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/multi-agent-orchestration-patterns.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/agent-framework/overview/",
"evidence_quote": "",
"reason": "No fetched learn.microsoft.com page states a GA (or preview) status for Agent Framework workflow orchestrations; the overview marks only the Go SDK as public preview while Python ships stable 1.x, so the exact 'GA' status value for the orchestrations feature is not stated anywhere.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/multi-agent-orchestration-patterns.md",
"line": 4,
"claim": "Microsoft Agent Framework sine workflow-orkestreringer (multi-agent orchestration) har status GA.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/multi-agent-orchestration-patterns.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/extensibility/copilot-studio-experience",
"evidence_quote": "Both Agent Builder in Microsoft 365 Copilot and Copilot Studio are included with a Microsoft 365 Copilot add-on license for authenticated users. If you don't have a Copilot license, you can use Copilot Credits or a pay-as-you-go plan to access either experience.",
"reason": "The Microsoft 365 Copilot inclusion part holds, but the load-bearing 'Power Apps per-user plan' inclusion is absent from and contradicted by the canonical Copilot Studio licensing enumeration — one wrong load-bearing part fails the whole claim.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/multi-agent-orchestration-patterns.md",
"line": 567,
"claim": "Copilot Studio Agents er inkludert i Power Apps per-user plan og Microsoft 365 Copilot (med messages/day-grenser).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 8,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/semantic-kernel-agents-implementation.md#1",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/agent-framework/overview/agent-framework-overview",
"evidence_quote": "dotnet add package Microsoft.Agents.AI.Foundry --prerelease",
"reason": "The canonical overview and support pages state no '1.0' version, no GA status, and no 2026-04-03 date anywhere on Learn, and the live getting-started still instructs installing prerelease packages (--prerelease for .NET, 'pip install --pre agent-framework-foundry' in the migration guide; Go explicitly 'in public preview'), so the asserted GA/production-ready status is absent from the pages that would state it and contradicted by current prerelease packaging.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md",
"line": 4,
"claim": "Microsoft Agent Framework 1.0 nådde GA 3. april 2026; produksjonsklart open-source rammeverk (.NET + Python)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/semantic-kernel-agents-implementation.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/agent-framework/workflows/",
"evidence_quote": "Multi-Agent Orchestration: Built-in patterns for coordinating multiple AI agents, including sequential, concurrent, hand-off, and magentic.",
"reason": "The MAF workflows page lists only four built-in patterns (Group Chat is absent) and states no 'stable (GA) in MAF 1.0' status anywhere, while the cited Semantic Kernel orchestration page carries the banner 'Agent Orchestration features in the Agent Framework are in the experimental stage' — the five-pattern and GA-stability load-bearing parts both fail even though checkpointing/HITL are documented.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md",
"line": 9,
"claim": "De fem orkestreringsmønstrene Sequential, Concurrent, Handoff, Group Chat og Magentic er stabile (GA) i MAF 1.0 med streaming, checkpointing, human-in-the-loop og pause/resume",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/semantic-kernel-agents-implementation.md#8",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/agent-framework/support/",
"evidence_quote": "",
"reason": "Learn pages confirm both are open-source with GitHub repositories but no learn.microsoft.com page states the MIT license for either Semantic Kernel or Agent Framework; the license terms live in the GitHub repos, which are outside the allowed source.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md",
"line": 417,
"claim": "Semantic Kernel: MIT License | Microsoft Agent Framework: MIT License",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 13,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/agent-orchestration/tool-use-and-function-calling-patterns.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling",
"evidence_quote": "Basic function calling with tools - All the models that support parallel function calling ... o3-mini (2025-01-31) - o1 (2024-12-17)",
"reason": "o1 and o3-mini are listed only under Basic function calling (additional to the parallel-supporting set), not under Parallel function calling, so the claim that o1/o3-mini support parallel calling is contradicted.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md",
"line": 39,
"claim": "Parallell funksjonskalling (flere funksjoner i én respons) støttes av modellene: GPT-4 | GPT-4o | GPT-5-serien | o1/o3-mini.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/agent-orchestration/tool-use-and-function-calling-patterns.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/databricks/mlflow3/genai/tracing/integrations/semantic-kernel",
"evidence_quote": "",
"reason": "Microsoft Learn describes Semantic Kernel as a lightweight, open source SDK but no learn.microsoft.com page states the specific MIT license (that appears only in the GitHub repo), so the MIT-license value cannot be confirmed on learn.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md",
"line": 414,
"claim": "Semantic Kernel (plugins, auto-invocation) er open source under MIT-lisens.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/tool-use-and-function-calling-patterns.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/agents/overview",
"evidence_quote": "",
"reason": "Foundry Agent Service is described as a managed Azure platform accessed via Azure subscription, RBAC/Entra, and a consumption cost model (per-call inference + tool usage); no learn page states a Microsoft Foundry license requirement, so the license claim is unsourced.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md",
"line": 416,
"claim": "Foundry Agent Service (managed agents, built-in tools) krever Microsoft Foundry-lisens.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/agent-orchestration/tool-use-and-function-calling-patterns.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/billing-licensing",
"evidence_quote": "To use Copilot Studio, you need one of the following configurations: - Copilot Studio user license (free of charge)... - Copilot Studio authors role in Power Platform admin center... - Microsoft 365 Copilot license - Copilot Studio trial license.",
"reason": "The canonical enumeration of Copilot Studio access does not include Power Apps/Power Automate Premium; the Copilot-Studio-license branch is valid but the stated Power Apps/Power Automate Premium alternative is not a documented Copilot Studio licensing path, so one load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md",
"line": 417,
"claim": "Copilot Studio (Actions, Plugins) krever Power Apps/Power Automate Premium eller Copilot Studio-lisens.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/apim-ai-gateway-overview.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 7,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/apim-ai-gateway-overview.md#2",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/api-management/api-management-policies",
"evidence_quote": "Limit large language model API token usage | Prevents large language model (LLM) API usage spikes by limiting LLM tokens per calculated key.",
"reason": "The canonical policy reference's AI gateway and rate-limiting tables enumerate only llm-token-limit, llm-emit-token-metric, llm-semantic-cache-lookup/store and llm-content-safety — azure-openai-token-limit and azure-openai-emit-token-metric are absent, and their doc URLs now redirect to the llm-* pages (which cover OpenAI, Anthropic and Google Vertex APIs), so the claimed dual azure-openai-*/llm-* taxonomy describes a superseded policy split.",
"file": "skills/ms-ai-engineering/references/api-management/apim-ai-gateway-overview.md",
"line": 82,
"claim": "Token-policies i APIM: azure-openai-token-limit (Azure OpenAI) | llm-token-limit (alle LLM-er) | azure-openai-emit-token-metric | llm-emit-token-metric",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/apim-authentication-oauth-managed-identity.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 6,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/apim-authentication-oauth-managed-identity.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/role-based-access-control",
"evidence_quote": "Cognitive Services OpenAI User - Cognitive Services OpenAI Contributor - Cognitive Services Contributor - Cognitive Services Usages Reader",
"reason": "The canonical Azure OpenAI RBAC page enumerates the fourth role as 'Cognitive Services Usages Reader' (subscription-level quota viewing), not a generic 'Reader (lese)' role, and shows Cognitive Services Contributor is not 'full tilgang' (it cannot access quota or make inference API calls with Microsoft Entra ID) — two stated load-bearing parts fail, so the whole claim is not grounded.",
"file": "skills/ms-ai-engineering/references/api-management/apim-authentication-oauth-managed-identity.md",
"line": 94,
"claim": "RBAC-roller for Azure OpenAI: Cognitive Services OpenAI User (bruke deployments) | Cognitive Services OpenAI Contributor (opprette/administrere deployments) | Cognitive Services Contributor (full tilgang) | Reader (lese)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/apim-azure-front-door-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 9,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/apim-vs-direct-access-comparison.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 8,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/backend-pool-management.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/backend-pool-management.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/reference/tables/apimanagementgatewayllmlog",
"evidence_quote": "ApiVersion, CompletionTokens, CorrelationId, DeploymentName, IsStreamCompletion, ModelName, OperationName, PromptTokens, Region, RequestId, RequestMessages, ResponseMessages, SequenceNumber, TimeGenerated, TotalTokens, Type",
"reason": "The canonical ApiManagementGatewayLlmLog schema page enumerates all columns and confirms TotalTokens, PromptTokens, and CompletionTokens, but no BackendUrl column exists in that enumeration — a stated, load-bearing column name a reader would copy into a KQL query is wrong, so the whole claim fails under R8/R2 despite the other parts holding.",
"file": "skills/ms-ai-engineering/references/api-management/backend-pool-management.md",
"line": 405,
"claim": "Log Analytics-tabellen ApiManagementGatewayLlmLog finnes med kolonner TotalTokens, PromptTokens, CompletionTokens, BackendUrl (og ApiManagementGatewayLogs med BackendResponseCode)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/caching-strategies-apim-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/caching-strategies-apim-ai.md#4",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/azure-openai-enable-semantic-caching",
"evidence_quote": "",
"reason": "The page requires an Embeddings API deployment for semantic caching but names no specific model; no fetched Microsoft Learn page states text-embedding-ada-002 or newer as a requirement for APIM semantic caching, and nothing contradicts it.",
"file": "skills/ms-ai-engineering/references/api-management/caching-strategies-apim-ai.md",
"line": 156,
"claim": "Semantisk caching krever en embeddings-deployment med modellen text-embedding-ada-002 eller nyere.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/api-management/caching-strategies-apim-ai.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/api-management/api-management-policies",
"evidence_quote": "Get cached responses of large language model API requests (llm-semantic-cache-lookup-policy) ... Store responses of large language model API requests to cache (llm-semantic-cache-store-policy)",
"reason": "The authoritative policy reference (Caching and AI gateway sections) enumerates only llm-semantic-cache-lookup and llm-semantic-cache-store; the claimed azure-openai-semantic-cache-lookup and azure-openai-semantic-cache-store policies are absent from the enumeration and their URLs redirect to the llm-* pages, so two load-bearing parts fail.",
"file": "skills/ms-ai-engineering/references/api-management/caching-strategies-apim-ai.md",
"line": 183,
"claim": "APIM tilbyr semantiske caching-policyer: azure-openai-semantic-cache-lookup | azure-openai-semantic-cache-store | llm-semantic-cache-lookup | llm-semantic-cache-store.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/cost-tracking-apim-policies.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 6,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/developer-portal-ai-apis.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 8,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/genai-gateway-policies.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/genai-gateway-policies.md#7",
"judge_verdict": "not_grounded",
"rule": "R1",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/api-management-howto-llm-logs",
"evidence_quote": "Messages larger than 32 KB are split and logged in 32-KB chunks with sequence numbers for later reconstruction. Request messages and response messages can't exceed 2 MB each.",
"reason": "The claim states an up-to-32768-bytes-each ceiling, but 32768 bytes (32 KB) is only the example log size and single-entry/chunk threshold; the actual per-message logging maximum is 2 MB, so the stated ceiling is superseded (upper-bound).",
"file": "skills/ms-ai-engineering/references/api-management/genai-gateway-policies.md",
"line": 394,
"claim": "LLM-logging i APIM kan logge prompts og completions med inntil 32768 bytes hver.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/api-management/genai-gateway-policies.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/llm-emit-token-metric-policy",
"evidence_quote": "- **Policy sections:** inbound",
"reason": "The claim assigns llm-emit-token-metric to the Outbound section, but its documented policy section is inbound (and the example places it in the inbound block); one load-bearing part of the multi-part taxonomy is contradicted.",
"file": "skills/ms-ai-engineering/references/api-management/genai-gateway-policies.md",
"line": 611,
"claim": "GenAI-spesifikke APIM-policyer: llm-content-safety (Inbound) | llm-token-limit (Inbound) | llm-semantic-cache-lookup (Inbound) | llm-semantic-cache-store (Outbound) | llm-emit-token-metric (Outbound).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/logging-analytics-ai-traffic.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/logging-analytics-ai-traffic.md#2",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/templates/microsoft.apimanagement/service/loggers",
"evidence_quote": "resource symbolicname 'Microsoft.ApiManagement/service/loggers@2025-09-01-preview'",
"reason": "The current/Latest API version for these resource types is 2025-09-01-preview (stable 2024-05-01); 2023-09-01-preview is a superseded older entry in the version list, so the claimed version is outdated per R4.",
"file": "skills/ms-ai-engineering/references/api-management/logging-analytics-ai-traffic.md",
"line": 49,
"claim": "Bicep-/ARM-resurstypene Microsoft.ApiManagement/service/loggers og service/apis/diagnostics bruker API-versjon 2023-09-01-preview.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/multi-region-ai-gateway-design.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 9,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/request-response-transformation-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 8,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/request-response-transformation-ai.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/api-management/api-management-policies",
"evidence_quote": "## Transformation | Set request method | Set status code | Set variable | Set body | Set HTTP header | Set query string parameter | Rewrite URL | Convert JSON to XML | Convert XML to JSON | Find and replace string in body | Mask URLs in content | Transform XML using an XSLT | Return response | Mock response",
"reason": "The canonical policy reference enumerates the Transformation category as ~14 policies (and under ~70 total across all categories); '75+ transformation policies' is absent from the authoritative enumeration, contradicting the claim.",
"file": "skills/ms-ai-engineering/references/api-management/request-response-transformation-ai.md",
"line": 26,
"claim": "Azure API Management (APIM) tilbyr over 75 innebygde policies for transformasjon av forespørsler og svar.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 8,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/api-management/security-hardening-ai-gateway.md#2",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/api-management/genai-gateway-capabilities",
"evidence_quote": "",
"reason": "The Security and safety section lists capabilities (managed identity auth, OAuth, Azure AI Content Safety policy) but no Microsoft Learn page states a count of over 20 security policies; the aggregate count is unsourced and not refutable.",
"file": "skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md",
"line": 25,
"claim": "Azure API Management som AI gateway tilbyr over 20 sikkerhetspolicies, fra IP-filtrering og sertifikatvalidering til AI-spesifikk innholdsmoderasjon og prompt injection-forebygging.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/api-management/security-hardening-ai-gateway.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/entra/global-secure-access/how-to-ai-prompt-injection-protection",
"evidence_quote": "Prompt Injection Protection: Blocks adversarial prompts and jailbreak attempts before they reach AI models. Prevents unauthorized actions and sensitive data exfiltration. Works across any device, browser, or application for uniform enforcement.",
"reason": "The GSA-delivered feature is named Prompt Injection Protection (not Prompt Shields), and its enumerated protections cover jailbreak, data exfiltration, and network-level enforcement but not indirect injection detection (a separate Azure AI Content Safety documents-shield capability), so a load-bearing part fails.",
"file": "skills/ms-ai-engineering/references/api-management/security-hardening-ai-gateway.md",
"line": 210,
"claim": "Microsoft Prompt Shields (levert via Microsoft Entra Global Secure Access) tilbyr: Jailbreak-deteksjon | Indirect injection-deteksjon | Data exfiltration-blokkering | nettverksnivå-enforcement (uavhengig av applikasjonskode).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/api-management/streaming-support-apim.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 5,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/api-management/versioning-ai-api-endpoints.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 5,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-api-best-practices.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/supported-languages#error-handling",
"evidence_quote": "The following errors are automatically retired twice by default with a brief exponential backoff: Connection Errors, 408 Request Timeout, 429 Rate Limit, >=500 Internal Errors",
"reason": "The claim asserts Python, .NET and Go all retry up to 3 times, but the live page states the Python (and JS) OpenAI SDK retries twice by default — only the .NET client classes retry 'up to three more times' — so a load-bearing part is contradicted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md",
"line": 87,
"claim": "Azure OpenAI SDK-er (Python, .NET, Go) retrier automatisk 408|429|500|502|503|504 — opptil 3 ganger med eksponentiell backoff",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-api-best-practices.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing",
"evidence_quote": "With Reservations, you commit to payment for a fixed number of PTUs over a one-month or one-year term, and in return, you receive a discounted effective $/PTU/hr rate.",
"reason": "The claim asserts 1-year (~37%) and 3-year (~57%) commitment discounts, but the live billing page states reservation terms are one-month or one-year only — no 3-year term exists, and no discount percentages are documented ('The discount varies by model family and term length').",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md",
"line": 627,
"claim": "Provisioned reservation-rabatter: 1-årig commitment ~37%|3-årig commitment ~57%",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-api-best-practices.md#11",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/foundry-models/supported-languages",
"evidence_quote": "Azure AI Inference beta SDK is deprecated and will be retired on August 26, 2026. Switch to the generally available OpenAI/v1 API with a stable OpenAI SDK.",
"reason": "The claim's organizing frame — azure-ai-inference/Azure.AI.Inference/@azure/ai-inference as the Foundry-supporting SDKs — is superseded: the Azure AI Inference SDK family is deprecated (the migration table maps openai as the replacement for azure-ai-inference, retiring May 30, 2026) and Microsoft directs to the OpenAI SDKs, even though the Go openai-go part is still correct.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md",
"line": 482,
"claim": "SDK-er som støtter Microsoft Foundry: Python azure-ai-inference + openai (Azure-variant)|.NET Azure.AI.Inference + Azure.AI.OpenAI|JS/TS @azure/openai + @azure/ai-inference|Go github.com/openai/openai-go (med Azure endpoint)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-cost-optimization.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-cost-optimization.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-sizing",
"evidence_quote": "The following Fireworks on Microsoft Foundry models support both Global and US Data Zone provisioned throughput.",
"reason": "The claim asserts PTU is only for Azure OpenAI, but the live sizing page publishes provisioned-throughput deployment parameters for non-OpenAI Foundry Models (Llama-3.3-70B-Instruct, DeepSeek-R1, DeepSeek-V3-0324, and the Fireworks model family), so the load-bearing 'kun for Azure OpenAI' exclusivity is superseded even though PTU still doesn't apply to classic AI Services like Speech or Vision.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-cost-optimization.md",
"line": 177,
"claim": "PTU er kun for Azure OpenAI — ikke for øvrige Azure AI Services",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-enterprise-architecture.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/reliability/reliability-ai-search",
"evidence_quote": "Tier: Your service must be on the Basic tier or higher ... Number of replicas: Your service must have at least two replicas",
"reason": "The claim asserts Standard tier or higher plus minimum 3 replicas, but the live page states zone redundancy requires only Basic tier or higher and at least two replicas (3 replicas is the read-write SLA condition, not the zone-redundancy requirement), so two load-bearing values are contradicted even though the no-built-in-DR part holds.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"line": 81,
"claim": "Azure AI Search zone redundancy krever Standard tier eller høyere + minimum 3 replicas; ingen built-in disaster recovery (krever manuell gjenoppbygging eller support-kontakt)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-enterprise-architecture.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models#model-summary-table-and-region-availability",
"evidence_quote": "| norwayeast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |",
"reason": "The claim says no Azure OpenAI region exists in Norway, but the canonical model/region availability table lists norwayeast with standard regional deployments of gpt-4.1, o3-mini, o1, gpt-4o and more (gpt-4o was available there well before 2026-02), directly refuting the non-existence claim.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"line": 364,
"claim": "Ingen Azure OpenAI-region i Norge per 2026-02; nærmeste regioner er Sweden Central og West Europe",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-enterprise-architecture.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/api-management-features",
"evidence_quote": "Multi-region deployment | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✔️ | ❌ ... Scale units | ❌ (automatic scaling) | 1 | 2 | 10 | 4 | 10 | 12 per region | 30",
"reason": "The live tier comparison contradicts multiple load-bearing parts: multi-region deployment is Premium-only (the claim gives it to Standard), Basic allows 2 scale units (claim says 1 unit max), and Premium classic is 12 units per region; the per-tier call volumes are not stated on the page either.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"line": 435,
"claim": "APIM-tiers: Developer (1M calls, ingen SLA) | Basic (1M calls, SLA, 1 unit max) | Standard (10M calls, multi-region, 4 units) | Premium (unlimited, multi-region, VNet, 10+ units)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-enterprise-architecture.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities",
"evidence_quote": "APPLIES TO: All API Management tiers ... Currently, the backend circuit breaker isn't supported in the Consumption tier of API Management.",
"reason": "The circuit-breaker-not-in-Consumption part is confirmed on the backends page, but the second load-bearing part 'Standard tier minimum for AI gateway' is contradicted: the AI gateway page applies to all API Management tiers (with per-capability variation), so no Standard-minimum exists.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"line": 440,
"claim": "APIM circuit breaker er ikke tilgjengelig i Consumption tier; Standard tier minimum for AI gateway",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-enterprise-architecture.md#14",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/prompt-caching",
"evidence_quote": "Prompt caching is enabled by default for all supported models. There's no opt-out support for prompt caching.",
"reason": "The claim describes prompt caching for Azure OpenAI as a planned, not-yet-available feature, but the live page documents it as shipped, enabled by default, with discounted cache-read pricing and extended 24h retention on newer models — the status is superseded.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md",
"line": 427,
"claim": "Caching (prompt caching) for Azure OpenAI omtales som planlagt feature (ikke tilgjengelig ennå)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-governance-compliance.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-governance-compliance.md#6",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-security-built-in",
"evidence_quote": "",
"reason": "The current data-residency section confirms object names (indexes, fields, indexers) appear in telemetry logs processed outside the selected region for Microsoft support, but no live learn.microsoft.com page states the claimed 1.5-year global retention period, so the specific retention value can be neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-governance-compliance.md",
"line": 114,
"claim": "Telemetry logs (objektnavn som indexer, skillsets) lagres globalt i 1,5 år for Microsoft-support (unntak fra Geography-residency)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-governance-compliance.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/azure-monitor/logs/data-retention-configure",
"evidence_quote": "The default retention period of Analytics tables in a Log Analytics workspace is 30 days. You can change the default analytics period of Analytics tables up to two years by modifying the workspace-level data retention setting.",
"reason": "The claim asserts a 90-day Log Analytics default, but the live page states the default retention is 30 days (adjustable up to 730), contradicting the load-bearing default-value part even though the 30-730 range roughly holds.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-governance-compliance.md",
"line": 139,
"claim": "Diagnostic logs standard retention: 90 dager (Log Analytics default), justerbar 30-730 dager",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-governance-compliance.md#9",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/key-vault/managed-hsm/firmware-update",
"evidence_quote": "the HSM firmware for both Managed HSM and Azure Key Vault Premium are officially upgraded to a modern version validated to FIPS 140-3 level 3 standard",
"reason": "The claim asserts FIPS 140-2 Level 3 for HSM-backed Key Vault, but live docs state both Key Vault Premium and Managed HSM are now validated to FIPS 140-3 Level 3 (portfolio table lists both as FIPS 140-3 Level 3), so the certification version is superseded.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-governance-compliance.md",
"line": 220,
"claim": "Keys kan lagres i HSM-backed Key Vault for FIPS 140-2 Level 3",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-governance-compliance.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/purview/dlp-microsoft-teams",
"evidence_quote": "Office 365 and Microsoft 365 E3 include DLP protection for SharePoint, OneDrive, and Exchange.",
"reason": "The claim's load-bearing part 'DLP Policies krever E5/F5-lisens' is contradicted — E3 includes DLP for SharePoint/OneDrive/Exchange (E5/F5 is only needed for Teams chat and Endpoint DLP), and the M365 license comparison also shows DSPM for AI included at E3/E5, undercutting the 'ikke i standard lisens' part, so the bundled licensing claim fails even though the audit-included and pay-as-you-go parts hold.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-governance-compliance.md",
"line": 557,
"claim": "Purview-lisensiering: DLP Policies krever E5/F5-lisens (eller pay-as-you-go) | Sensitivity Labels krever E3/E5 | DSPM for AI ikke i standard lisens (pay-as-you-go tilgjengelig) | Audit (Unified Log) inkludert",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-monitoring-logging.md#3",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/logs/data-retention-configure",
"evidence_quote": "By default, all tables in a Log Analytics workspace retain data for 30 days, except for log tables with 90-day default retention.",
"reason": "The claim says Log Analytics retention is 90 days free then paid, but the page states the default is 30 days (31 days included in the ingestion price), with 90-day free retention applying only to specific tables (Usage, AzureActivity, Application Insights App* tables).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md",
"line": 100,
"claim": "Log Analytics data retention: 90 dager gratis, deretter betalt",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-monitoring-logging.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/openai/monitor-openai-reference",
"evidence_quote": "Azure OpenAI Requests: Number of calls made to the Azure OpenAI API over a period of time ... `AzureOpenAIRequests`",
"reason": "Four of the six names (TokenTransaction, GeneratedTokens, ProcessedPromptTokens, ActiveTokens) match the canonical metric reference, but the request metric is named `AzureOpenAIRequests` (not `Requests`) and no `Http429` metric exists anywhere in the enumeration (429s surface via the StatusCode dimension), so two load-bearing copy-into-code names are wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md",
"line": 294,
"claim": "Azure OpenAI metric-navn: TokenTransaction | GeneratedTokens | ProcessedPromptTokens | ActiveTokens (PTU) | Requests | Http429",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-monitoring-logging.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/app/application-insights-faq",
"evidence_quote": "The default Pay-as-you-go Log Analytics pricing tier includes 5 GB per month of free data allowance per billing account.",
"reason": "The 5 GB/month free allowance is confirmed, but it is granted per billing account, not per subscription as the claim asserts - the scoping unit is a load-bearing part and it is contradicted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md",
"line": 394,
"claim": "Application Insights: 5 GB/måned gratis data ingestion per subscription",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-monitoring-logging.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-bot-framework-composer-capture-telemetry",
"evidence_quote": "Telemetry offers insights into your agent by tracking: Logged messages and events sent to and from your agent, Topics to trigger during user conversations, Custom telemetry events that you can send from your topics",
"reason": "The canonical Copilot Studio telemetry page confirms the App Insights connection and conversation analytics but enumerates only messages/events, topics, and custom events - no LUIS intent recognition or QnA Maker query latency (those belong to Bot Framework SDK bots, and QnA Maker was retired 31 March 2025), so two load-bearing parts fail.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md",
"line": 332,
"claim": "Copilot Studio-bottar kan kobles til Application Insights for conversation analytics, LUIS intent recognition performance og QnA Maker query latency",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-networking-security.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-networking-security.md#8",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-virtual-networks",
"evidence_quote": "",
"reason": "Neither the cited networking page nor any Microsoft Learn page found via search states a pricing-tier prerequisite (S0/Basic or higher, Free tier excluded) for private endpoints/IP firewall/service endpoints on AI Services, so the tier requirement can be neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-networking-security.md",
"line": 404,
"claim": "Nettverkssikkerhet (private endpoints, IP firewall, service endpoints) krever Basic tier (S0) eller høyere; Free tier ikke støttet",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-networking-security.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/power-platform/admin/virtual-network-support-whitepaper",
"evidence_quote": "The new architecture eliminated costs and limitations associated with on-premises data gateways. ... a connector workload can access the target resource or endpoint inside the same virtual network.",
"reason": "The claim asserts Power Automate/Power Apps 'require' an on-premises data gateway and that custom connectors 'must' use the public endpoint, but live docs document Power Platform Virtual Network support (subnet delegation) letting connectors reach private-endpoint resources directly without a gateway — the 'krever'/'må' load-bearing parts describe a superseded state.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-networking-security.md",
"line": 316,
"claim": "Power Automate/Power Apps mot private endpoints krever On-premises data gateway; Azure Relay hybrid connection ikke støttet direkte; custom connector må bruke public endpoint med IP firewall",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-vs-foundry-tools-selection.md#2",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/personalizer/what-is-personalizer",
"evidence_quote": "Starting 20 September 2023 you won't be able to create new Personalizer resources. The Personalizer service is being retired 1 October 2026.",
"reason": "The claim states Personalizer IS retired, but the live page states it is BEING retired on 1 October 2026 (still ~2.5 months away), i.e. deprecated/retiring, a different status value.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md",
"line": 58,
"claim": "Personalizer er utgått (retired)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-vs-foundry-tools-selection.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "| GPT-5.6 series | **NEW** `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` |",
"reason": "The claim's load-bearing part 'GPT-5.5 nyest' is superseded: the live model page lists the GPT-5.6 series (2026-07-09) as the newest flagship series (and also a GPT-5.3 series the claim omits).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md",
"line": 145,
"claim": "Azure OpenAI modellserie 2026-06: GPT-5-generasjonen (GPT-5/5.1/5.2/5.4/5.5 + -mini/-nano/-codex) er flaggskip for reasoning/chat; GPT-5.5 nyest",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-vs-foundry-tools-selection.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/bot-service/file-format/bot-builder-qna-file-format",
"evidence_quote": "Azure AI QnA Maker will be retired on 31 March 2025. ... Custom question answering, a feature of Azure AI Language, is the updated version of the QnA Maker service.",
"reason": "The retirement part is correct (31 March 2025 has passed), but the load-bearing replacement part is wrong: the documented successor is custom question answering in Azure AI Language, not 'Language Understanding' (LUIS), which is itself a retired product.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md",
"line": 387,
"claim": "QnA Maker er utgått (retired); erstattes av Language Understanding for FAQ-bots",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/ai-services-vs-foundry-tools-selection.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/agents/how-to/agent-365",
"evidence_quote": "Microsoft 365 licensing that supports Microsoft Agent 365. Agent 365 works best with Microsoft E5, and at least one user in your organization must have a qualifying Microsoft Agent 365 license such as Microsoft 365 Copilot.",
"reason": "The Azure-subscription part holds, but the load-bearing licensing threshold is stated differently: the docs require a qualifying Agent 365 license such as Microsoft 365 Copilot (works best with E5), not 'M365 E3 or higher' — an E3 license alone does not meet the documented requirement.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md",
"line": 559,
"claim": "Agent-publisering til Agent 365 krever M365 E3 eller høyere (Azure subscription + M365 E3/E5)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 14,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-image-analysis.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/faq",
"evidence_quote": "The free (S0) tier only allows 20 transactions per minute. Upgrade to the S1 tier to get up to 20 transactions per second.",
"reason": "The 'up to 20 requests/second on the Standard (S1) tier' part is grounded, but the stated '10-20 requests/sekund per tier' range is contradicted for the free tier, which allows only 20 transactions per minute (about 0.33/s), and no Learn page states a 10 rps tier for Azure AI Vision.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md",
"line": 122,
"claim": "Rate limits: 10-20 requests/sekund per tier (opp til 20 requests/sekund per Standard tier)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-image-analysis.md#10",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/custom-vision-service/limits-and-quotas",
"evidence_quote": "Min labeled images per Tag, Classification (50+ recommended) | 5 | 5",
"reason": "The claim overstates a recommendation as a requirement: the Custom Vision limits page sets the enforced minimum at 5 labeled images per tag for classification and 15 for object detection (50+ recommended), while the 30-images figure appears in quickstarts only as guidance ('you should use at least 30 images per tag'), so Custom Vision does not require 30.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md",
"line": 154,
"claim": "Custom Vision krever trening med minimum 30 bilder per tag",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-image-analysis.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-image-analysis",
"evidence_quote": "To use the Image Analysis APIs, you must create your Azure Vision in Foundry Tools resource in a supported region. The Image Analysis features are available in the following regions:",
"reason": "The canonical region-availability enumeration for the Image Analysis features this file covers lists 13 regions (East US, West US, West US 2, France Central, North Europe, West Europe, Sweden Central, Switzerland North, Australia East, Southeast Asia, East Asia, Korea Central, Japan East) and neither Norway East nor Norway West appears, so the claimed Norway availability is absent from the enumerating page.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md",
"line": 271,
"claim": "Azure AI Vision er tilgjengelig i Norway East og Norway West",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-image-analysis.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/faq",
"evidence_quote": "",
"reason": "The FAQ confirms the Standard tier is named S1 and quickstarts confirm an F0 free tier exists, but no fetched or searched learn.microsoft.com page states the 0-5000 free transactions/month figure, which lives only on the JS-rendered Azure pricing page.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md",
"line": 281,
"claim": "Azure AI Vision Free tier (F0): 0-5000 transaksjoner/måned gratis; Standard tier heter S1",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 13,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-ocr-processing.md#8",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/ai-builder/prebuilt-text-recognition",
"evidence_quote": "",
"reason": "Learn confirms the AI Builder text recognition prebuilt model exists with OCR and Power Automate integration, but no Learn page states it uses Azure Vision OCR under the hood ('uses state-of-the-art optical character recognition (OCR)' names no engine), so the load-bearing engine attribution can be neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md",
"line": 201,
"claim": "AI Builder tilbyr en Text Recognition prebuilt model som bruker Azure Vision OCR under panseret (Power Automate-integrasjon)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-ocr-processing.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/computer-vision/ocr-data-privacy-security",
"evidence_quote": "Deletes data: The input data and results are deleted within 24 hours and not used for any other purpose.",
"reason": "The cited privacy page states input data and results are deleted within 24 hours, contradicting the claimed 48-hour retention (48 hours appears in docs only as the Operation-Location URL expiry, not data retention), so a load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md",
"line": 248,
"claim": "OCR data retention: input-bilder og ekstrahert tekst lagres midlertidig i 48 timer (operation-location URL), deretter slettet automatisk; ingen permanent lagring av kundedata",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/azure-ai-vision-ocr-processing.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/service-limits?view=doc-intel-4.0.0",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states the monthly free allowances (5,000 transactions or 500 pages); the DI service-limits page defers 'monthly allowances' for F0 to the JS-rendered Azure pricing page, which is the expected source_silent case for pricing values.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md",
"line": 272,
"claim": "Gratisnivåer: Azure Vision v4.0 Read OCR 5000 transaksjoner/måned gratis (Standard S1) | Document Intelligence Read 500 sider/måned gratis (Standard S0)",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/content-understanding-multimodal-analysis.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements",
"evidence_quote": "This model may miss transitions that are visually gradual.",
"reason": "Uniform keyframe sampling, minimum one per shot, deterministic shot output, and 'first shot always starts at 0 ms' all check out, but the load-bearing claim that the service detects gradual transitions is contradicted — the page explicitly warns the model may miss visually gradual transitions.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md",
"line": 150,
"claim": "Keyframes samples uniformt fra hver camera shot, minimum én per shot, deterministisk utvalg; cameraShotTimesMs angir startpunkt per shot (første shot starter alltid ved 0 ms); detekterer abrupte og gradvise overganger",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/content-understanding-multimodal-analysis.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer",
"evidence_quote": "You pay per input unit processed: Documents: Per 1,000 pages; Audio and Video: Per minute.",
"reason": "The capability parts hold (Video Indexer celebrity/observed-people/live-stream support confirmed on insights and overview pages; CU GA lacks face identification), but the load-bearing pricing contrast is wrong: CU's GA pricing charges per-page/per-minute content extraction meters plus token-based generative charges, so 'CU prises token-basert' vs VI's minute-based pricing describes a superseded (preview-era) billing frame.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md",
"line": 242,
"claim": "Content Understanding vs Video Indexer: CU har ikke face recognition (kun face description via Limited Access) og ikke real-time analyse; Video Indexer har celebrity + custom faces, live video streaming, observed people tracking (bounding boxes); CU prises token-basert, Video Indexer page/minute-basert",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/content-understanding-multimodal-analysis.md#11",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-understanding/tutorial/logic-apps",
"evidence_quote": "You can use the free pricing tier (F0) to try the service, then upgrade to a paid tier for production.",
"reason": "The claim asserts no free tier exists, but a live Learn tutorial states a free pricing tier (F0) can be used to try Content Understanding, directly contradicting the non-existence claim.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md",
"line": 482,
"claim": "Free tier er ikke tilgjengelig for Content Understanding; krever betalt Azure subscription",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/content-understanding-multimodal-analysis.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-contentunderstanding-readme",
"evidence_quote": "Content Understanding operations are asynchronous long-running operations. The workflow is: 1. Begin Analysis - Start the analysis operation (returns immediately with an operation location) 2. Poll for Results - Poll the operation location until the analysis completes",
"reason": "The claim asserts a webhook-based async-completion feature exists in preview, but the canonical async-operation documentation (SDK readme, REST quickstart 'Poll the URL every 1–2 seconds until status is Succeeded') enumerates only Operation-Location polling and no CU page mentions webhooks at all — absence from the enumerating pages is evidence the feature does not exist.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md",
"line": 547,
"claim": "Webhooks for async completion er preview-feature, ikke GA (per Feb 2026)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-custom-models.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-custom-models.md#7",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/train/composed-models?view=doc-intel-4.0.0",
"evidence_quote": "The **2024-11-30 (GA)** implementation of the `model compose` operation replaces the implicit classification from the earlier versions with an explicit classification step and adds conditional routing. ... **Assigned custom model maximum expanded to 500**.",
"reason": "The claim describes the legacy behavior the compose how-to explicitly marks as 'only applies to v3.1 and previous versions': in current v4.0 the limit is 500 (not 200) and the automatic best-match classification is replaced by an explicitly trained classifier.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-custom-models.md",
"line": 89,
"claim": "Composed models: kombiner opptil 200 custom models til én modell-ID; Document Intelligence klassifiserer dokumentet automatisk og velger best match",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-custom-models.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/ai-builder/create-form-processing-model",
"evidence_quote": "**General documents**: Previously known as *unstructured*, this option is ideal for any kind of documents, especially when there's no set structure, or when the format is complex. ... This model is powerful, but has long training time. ... **Overlapping fields**: v4.0 supports overlapping fields in custom models",
"reason": "The canonical AI Builder page enumerates a 'General documents' (unstructured, long training time) model type alongside 'Fixed template documents' and lists v4.0 features (overlapping fields, signature detection, table confidence) that Document Intelligence documents as neural-only capabilities, contradicting the claim that AI Builder supports only template models.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-custom-models.md",
"line": 250,
"claim": "AI Builder custom models (Document Processing) støtter kun template models, ikke neural (per januar 2026)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-custom-models.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/train/custom-lifecycle?view=doc-intel-4.0.0",
"evidence_quote": "The model is configured to expire two years after its creation for all requests utilizing a GA API to build it.",
"reason": "No Microsoft Learn page states a 90-day storage period for Document Intelligence custom models; the lifecycle page states GA-trained models expire two years after creation, a differing value for the claimed model lifetime.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-custom-models.md",
"line": 368,
"claim": "Custom models lagres i 90 dager uten kostnad",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#2",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/language-support/prebuilt?view=doc-intel-4.0.0",
"evidence_quote": "The following tables list the available language and locale support by model and feature ... Model ID: prebuilt-bankStatement | English (United States) en-US",
"reason": "The canonical language-support page has no uniform 27-language figure and its per-model frame contradicts one: support ranges from en-US only (bankStatement, check, contract, tax, mortgage) to ~40 languages (invoice) to 100+ (thermal receipts), so 'prebuilt models support 27 languages' matches no current enumeration.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 30,
"claim": "Prebuilt-modellene støtter 27 språk",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/model-overview?view=doc-intel-4.0.0",
"evidence_quote": "prebuilt-check.us | ✓ | ✓",
"reason": "Six of the seven model IDs match the page's model analysis features table, but the bank-check model ID is prebuilt-check.us, not prebuilt-check as claimed - a copy-into-code SKU string, so one load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 40,
"claim": "Financial Services prebuilt-modeller: prebuilt-invoice | prebuilt-receipt | prebuilt-bankStatement | prebuilt-creditCard | prebuilt-check | prebuilt-contract | prebuilt-payStub.us",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/model-overview?view=doc-intel-4.0.0",
"evidence_quote": "prebuilt-marriageCertificate.us | ✓ | ✓",
"reason": "The tax and ID model IDs match (prebuilt-tax.us.w2/.1098/.1099/.1040 and prebuilt-tax.us all appear), but the marriage-certificate model ID is prebuilt-marriageCertificate.us, not prebuilt-marriageCertificate as claimed - one load-bearing SKU string is wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 52,
"claim": "Identity & Tax prebuilt-modeller: prebuilt-idDocument | prebuilt-healthInsuranceCard.us | prebuilt-marriageCertificate | prebuilt-tax.us.w2 | prebuilt-tax.us.1098 | prebuilt-tax.us.1099 | prebuilt-tax.us.1040 | prebuilt-tax.us (unified)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/model-overview?view=doc-intel-4.0.0",
"evidence_quote": "| Closing Disclosure | Extract closing, transaction costs, and loan details. | prebuilt-mortgage.us.closingDisclosure |",
"reason": "prebuilt-mortgage.us.1003/.1004/.1005/.1008 match the page, but the fifth model ID is prebuilt-mortgage.us.closingDisclosure, not prebuilt-mortgage.us.disclosure as claimed.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 65,
"claim": "US Mortgage prebuilt-modeller: prebuilt-mortgage.us.1003 | prebuilt-mortgage.us.1004 | prebuilt-mortgage.us.1005 | prebuilt-mortgage.us.1008 | prebuilt-mortgage.us.disclosure",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/model-overview?view=doc-intel-4.0.0",
"evidence_quote": "All the capabilities for the general document model are available in the layout model. The general model is no longer supported.",
"reason": "prebuilt-read and prebuilt-layout descriptions are grounded, but the page states the general document model (prebuilt-document) is no longer supported in v4.0 (its 2024-11-30 column reads 'Supported in layout model'), so presenting it as a current basic model contradicts the source.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 77,
"claim": "Grunnleggende modeller: prebuilt-read (OCR: tekst, linjer, ord, språkdeteksjon) | prebuilt-layout (tabeller, selection marks, seksjoner, valgfrie key-value pairs) | prebuilt-document (key-value pairs, tabeller, selection marks)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/ai-builder/credit-management",
"evidence_quote": "AI Builder credits coming from the AI Builder add-on (1,000,000 credits per add-on) and AI Builder credits coming from licenses with seeded capacity (like Power Automate premium, which brings 5,000 credits) are gathered at the tenant level.",
"reason": "The premium-feature part holds, but the 1M-credits part is contradicted: 1,000,000 credits come only from the purchased AI Builder capacity add-on, while Power Apps/Automate licenses seed just 250-5,000 credits (and seeded credits are removed November 1, 2026); the DI v3.1 part was not confirmed either.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 234,
"claim": "AI Builder bruker Document Intelligence v3.1 (ikke alltid v4.0); Premium-lisens påkrevd for AI Builder; 1M AI Builder credits inkludert i visse Power Apps/Automate-lisenser",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/service-limits?view=doc-intel-4.0.0",
"evidence_quote": "Analyze transactions Per Second limit | 1 | 15 (default value) ... Max number of pages (Analysis) | 2 | 2000",
"reason": "F0 2 pages/document, S0 2,000 pages, and S0 15 TPS all match, but the F0 rate limit is stated as 1 analyze transaction per second, not '20 calls/min' as claimed (and the 500 pages/month allowance appears only on the JS-rendered pricing page), so one load-bearing part is contradicted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 391,
"claim": "Free (F0): 500 sider/måned, 2 sider per dokument, 20 calls/min | Standard (S0): 2 000 sider per dokument, 15 TPS",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/faq?view=doc-intel-4.0.0",
"evidence_quote": "Your data is then deleted 24 hours from the time that you submit an analyze request. If you would like the data deleted sooner, you can call the delete analyze response.",
"reason": "The documented standard retention is 24 hours (deletable sooner via the Delete Analyze Result API), not 30 days as claimed - the immediate-deletion part holds but the retention value is contradicted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 355,
"claim": "Standard 30-dagers oppbevaring av dokumenter i Document Intelligence (kan slettes umiddelbart etter prosessering)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/document-intelligence-prebuilt-models.md#12",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/document-intelligence/train/custom-lifecycle?view=doc-intel-4.0.0",
"evidence_quote": "The model is configured to expire two years after its creation for all requests utilizing a GA API to build it.",
"reason": "The retraining-need part holds, but the page states a uniform two-year expiration (also two years for preview-trained models), not the claimed '12-24 months' - no 12-month expiry exists, so the stated interval contradicts the documented value.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md",
"line": 488,
"claim": "Custom models utløper (slutter å virke) etter 12–24 måneder; krever retraining-schedule",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/language-services-custom-text-classification.md#7",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/extensibility/overview",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states whether custom text classification can or cannot be integrated directly into M365 Copilot or names the Copilot Studio/Power Automate workaround; this architectural claim is neither confirmed nor contradicted by any canonical page found.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"line": 266,
"claim": "Custom Text Classification kan ikke integreres direkte i M365 Copilot (Copilot bruker forhåndstrente modeller); workaround via Copilot Studio-bot eller Power Automate-flow",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-custom-text-classification.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/responsible-ai/language-service/data-privacy",
"evidence_quote": "Data sent in synchronous or asynchronous calls may be temporarily stored by Language for up to 48 hours only and is purged thereafter. ... To prevent this temporary storage of input data, the LoggingOptOut query parameter can be set accordingly.",
"reason": "The claim asserts no logging of runtime text and a 15-minute response cache, but the live page states input data may be temporarily stored for up to 48 hours by default (opt-out via LoggingOptOut); the no-logging and 15-minute parts are contradicted even though the LoggingOptOut parameter exists.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"line": 300,
"claim": "Tekst sendt til runtime-API logges ikke, men respons caches i 15 min (kan deaktiveres med loggingOptOut: true)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-custom-text-classification.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/service-limits",
"evidence_quote": "F | Training time | One hour per month ... F | Prediction Calls | 5,000 text records per month ... Count of deployments per project (free tier) | 0 | 1",
"reason": "The 5,000 text records/month and max 1 deployment parts are confirmed, but F0 training is limited to one hour per month (Unlimited applies only to the S tier), contradicting the claimed unlimited training; one load-bearing part wrong fails the whole claim.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"line": 366,
"claim": "Free tier (F0): 5000 text records per måned for Prediction API | trening ubegrenset | maks 1 deployment per prosjekt",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-custom-text-classification.md#11",
"judge_verdict": "not_grounded",
"rule": "R1",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/service-limits",
"evidence_quote": "125,000 characters. You can send up to 25 documents as long as they collectively don't exceed 125,000 characters",
"reason": "The claim states a ceiling of 10 documents per request, but the live limits page states up to 25 documents per request; the stated maximum is superseded (upper-bound rule, no ratio leniency).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"line": 376,
"claim": "Batch API: opptil 10 dokumenter per request",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-custom-text-classification.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/language-support",
"evidence_quote": "Custom text classification supports .txt files in the following languages:",
"reason": "The canonical language-support enumeration lists 93 languages (Afrikaans through Zulu), fewer than the claimed 100+; the multilingual option only covers these same supported languages, so the asserted floor is not met.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md",
"line": 401,
"claim": "Custom Classification støtter 100+ språk (multilingual-funksjonalitet)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-question-answering.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/language-services-question-answering.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/question-answering/concepts/azure-resources",
"evidence_quote": "",
"reason": "The cited page only states that CQA's management and prediction services are colocated in the same region; neither it nor any Learn page found via search states (or contradicts) that the Azure AI Search resource must be in the same region as the Language resource or that cross-region replication is disallowed.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-question-answering.md",
"line": 388,
"claim": "Cross-region replication er ikke tillatt i CQA; Azure AI Search må være i samme region som Language resource",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-question-answering.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "",
"evidence_quote": "",
"reason": "The F0 5,000-text-records/month allowance and S-tier unlimited hosted calls are Azure pricing-page (JS-rendered) values; no learn.microsoft.com page found states them (the CQA limits page only notes F0 upload is limited to three files).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-question-answering.md",
"line": 465,
"claim": "Language resource med CQA: Free (F0) 5000 text records/måned | Standard (S) ubegrensede hosted calls",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/overview",
"evidence_quote": "Key phrase extraction retires from Azure Language on March 31, 2029.",
"reason": "The 2029-03-31 retirement of sentiment/opinion/custom-text-classification and the Foundry migration path check out, but the claim's load-bearing part that Key Phrase Extraction is unaffected is contradicted - its overview shows it also retires 2029-03-31.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"line": 8,
"claim": "Sentiment Analysis, Opinion Mining og Custom Text Classification avvikles 2029-03-31; PII Detection, Key Phrase Extraction og Language Detection er ikke berørt; migrasjonssti er Microsoft Foundry-modeller",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support",
"evidence_quote": "Total supported language codes: 94",
"reason": "The 94-language count is confirmed and Norwegian/Finnish/Swedish/Danish appear, but the full enumeration contains no Sami language, so the asserted Sami support is absent from the canonical list (R2).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"line": 66,
"claim": "Key Phrase Extraction støtter 94 språk (inkl. norsk, samisk, finsk, svensk, dansk); introduksjonen sier 94+ språk",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#7",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/language-service/custom-named-entity-recognition/how-to/use-containers",
"evidence_quote": "The free account is limited to 5,000 text records per month and only the Free and Standard pricing tiers are valid for containers.",
"reason": "Container docs explicitly allow the free (F0) tier ('the free (F0) or standard (S) pricing tier'), directly contradicting the claim that Standard S is required and F0 is unsupported for containers.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"line": 163,
"claim": "Docker-containere krever Standard S tier; Free F0 tier støttes ikke for containere",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#8",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/language-service/concepts/data-limits",
"evidence_quote": "All other preconfigured features (synchronous) | 5,120 as measured by StringInfo.LengthInTextElements",
"reason": "The synchronous per-document maximum is 5,120 characters and a text record is measured as 1,000 characters - neither matches the claimed '5000 characters per text record' (exact-value mismatch).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"line": 181,
"claim": "Maks 5000 tegn per text record; større dokumenter må splittes",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/language-services-text-analytics.md#9",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/concepts/regional-support",
"evidence_quote": "NorwayEast | Yes | Yes (Prediction supported)",
"reason": "NorwayEast (Oslo) is an enumerated supported region - fully supported for custom question answering and prediction-supported for CLU, Custom NER and Custom text classification, with preconfigured features available in all supported regions - contradicting the claim that Norway does not support Language Services.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md",
"line": 283,
"claim": "Azure Norway-datasentre (Oslo, Stavanger) støtter ikke Language Services per 2026-02; nærmeste regioner er West Europe (Nederland) og North Europe (Irland)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speaker-recognition.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 8,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-speaker-recognition.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/speech-sdk",
"evidence_quote": "By downloading any of the Azure Speech in Foundry Tools SDKs, you acknowledge its license. For more information, see: - Microsoft software license terms for the Speech SDK",
"reason": "The Speech SDK is governed by proprietary 'Microsoft software license terms for the Speech SDK', not open source or MIT; the load-bearing open-source/MIT assertion is contradicted (only the separate GitHub code samples are open source).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speaker-recognition.md",
"line": 403,
"claim": "Speech SDK er gratis, open source med MIT-lisens",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 14,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-services-quotas-and-limits",
"evidence_quote": "Maximum file size for audio input | Not applicable | 1 GB",
"reason": "The best-effort 30-min/24-hr scheduling and lexical+display output hold, but batch transcription has a documented 1 GB maximum file size, contradicting the claim's unlimited file size (ubegrenset filstoerrelse).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md",
"line": 39,
"claim": "Batch transcription: asynkron prosessering 30 min - 24 timer (best-effort scheduling); output JSON med lexical + display form; ubegrenset filstørrelse",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create",
"evidence_quote": "Up to two channels are supported unless diarization is enabled... Diarization is only supported on single-channel (mono) audio.",
"reason": "The claim inverts the condition: the source states 2 channels are supported UNLESS diarization is enabled, and with diarization only mono (1 channel) is supported, so max 2 channels IF diarization enabled is contradicted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md",
"line": 65,
"claim": "Speaker diarization: maksimalt 2 kanaler hvis diarization er aktivert; støttes ikke på tvers av flere kanaler samtidig",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-speech-to-text.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/fast-transcription-create",
"evidence_quote": "The supported audio input locales with current multi-lingual model are: de-DE, en-AU, en-CA, en-GB, en-IN, en-US, es-ES, es-MX, fr-CA, fr-FR, it-IT, ja-JP, ko-KR, pt-BR, and zh-CN.",
"reason": "The 15-locale list matches exactly, but the multilingual model is documented as a generally available feature of the GA fast transcription API (no preview designation anywhere on the page), so the load-bearing preview status is wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md",
"line": 74,
"claim": "Multi-lingual transcription er preview og støtter 15 språk: de-DE, en-AU, en-CA, en-GB, en-IN, en-US, es-ES, es-MX, fr-CA, fr-FR, it-IT, ja-JP, ko-KR, pt-BR, zh-CN",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 14,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis",
"evidence_quote": "The Batch synthesis API is generally available.",
"reason": "The load-bearing status part is wrong: the claim says the Batch Synthesis REST API is preview, but the page states it is generally available (the >10 min and REST-only parts hold, but R8 condemns the whole claim).",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md",
"line": 134,
"claim": "Batch Synthesis REST API er preview; for lange lydfiler (>10 min); real-time synthesis har <10 min audio-lengde og SDK-støtte, batch er REST API only",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#10",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/previous-year-release-notes",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states that Azure Speech TTS is not native in M365 Copilot or that it integrates via Power Automate custom connectors; this is an unstated architectural assertion, so it cannot be confirmed or refuted.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md",
"line": 248,
"claim": "TTS er ikke native i M365 Copilot per januar 2026; integreres via custom connectors (Power Automate)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/speech-services-text-to-speech.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/speech-services-quotas-and-limits",
"evidence_quote": "Maximum number of transactions per time period for standard voices and custom voices | 20 transactions per 60 seconds",
"reason": "The '0.5M characters/month' and 'S0 for production' parts hold, but the load-bearing figure '5 audio requests/month' is unsupported and contradicted: the F0 free tier is character-based (0.5M chars/month) with a rate limit of 20 transactions per 60 seconds, not a 5-request monthly cap.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md",
"line": 396,
"claim": "Free tier (F0): 5 audio requests/month og 0.5M characters/month; S0 tier for produksjon",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/overview",
"evidence_quote": "Custom Translator | Build customized models to translate domain- and industry-specific language | Custom Translator portal (https://portal.customtranslator.azure.ai/) . Tip: Use Microsoft Foundry (https://ai.azure.com/) for text and synchronous document translation operations via a no-code interface.",
"reason": "The no-code Custom Translator workflow (upload/BLEU/deploy) lives in the dedicated Custom Translator portal, not Microsoft Foundry; the docs explicitly scope Microsoft Foundry's no-code interface to text and synchronous document translation only, contradicting the load-bearing location assertion.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md",
"line": 194,
"claim": "Custom Translator er tilgjengelig i Microsoft Foundry (klassisk portal) for no-code workflows med document upload, BLEU-sammenligning og deployment management",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#9",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/responsible-ai/translator/data-privacy-security",
"evidence_quote": "",
"reason": "Translator's EU Data Boundary support exists via the European endpoint (a Microsoft commitment, not a 'certification'), but the canonical data/privacy page does not state that baseline NMT models are trained on global data or that custom models use only the customer's data, so those distinctive training-provenance assertions cannot be confirmed.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md",
"line": 228,
"claim": "Microsoft Translator har EU Data Boundary-sertifisering; baseline NMT-modeller er trent på global data, custom-modeller bruker kun kundens data",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/azure-ai-services/translator-custom-neural-models.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/custom-translator/concepts/sentence-alignment",
"evidence_quote": "Free (F0) subscription training has a maximum limit of 2,000,000 characters.",
"reason": "The Free (F0) tier does support Custom Translator training (capped at 2,000,000 characters; and the free tier has the same features and functionality as the paid plans), contradicting the load-bearing claim that Custom Translator is not supported on F0.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-custom-neural-models.md",
"line": 280,
"claim": "Custom Translator støttes ikke på Free (F0) tier (kun baseline-modeller); Standard (S1) gir full støtte med ubegrenset antall workspaces, projects og modeller",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/document-translation/overview",
"evidence_quote": "**Pricing**: Calculated on a per-image basis. For more information, see [Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/translator).",
"reason": "Resource requirement (Foundry, not standalone Translator) and the translateTextWithinImage options parameter are confirmed, but the load-bearing 'additional cost based on Azure Vision pricing' is unsupported - Microsoft prices image translation per-image via the Translator pricing page, not Azure Vision pricing.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md",
"line": 70,
"claim": "Oversettelse av bildetekst i .docx/.pptx (batch) krever Azure AI Services multi-service resource (ikke standalone Translator) + parameter \"translateTextWithinImage\": true i options-feltet; tilleggskostnad basert på Azure Vision-prising",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#8",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/service-limits",
"evidence_quote": "Synchronous operation limits | Document size | <= 10 MB. Asynchronous (batch) operation limits | Document size | <= 40 MB.",
"reason": "Service limits set the synchronous document-size limit at <=10 MB, not <40 MB; 40 MB is the per-document batch limit, so the claimed sync/batch threshold is wrong.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md",
"line": 162,
"claim": "Synchronous single-file translation er egnet for filer < 40 MB (batch anbefalt for filstørrelse > 40 MB)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/solutions/translator-pro/overview",
"evidence_quote": "The app is currently available for Azure Translator resources created in the following regions ... Norway | Norway East (`norwayeast`)",
"reason": "Contradicted: the Azure Translator resource region list includes Norway East, so a Norway region does exist for Translator, refuting the claim that it does not.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md",
"line": 252,
"claim": "Norway-region finnes ikke for Translator — bruk West Europe eller North Europe for geografisk nærhet",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/azure-ai-services/translator-document-translation.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/translator/document-translation/how-to-guides/use-rest-api-programmatically",
"evidence_quote": "\"summary\": { \"total\": 1, \"failed\": 0, \"success\": 0, \"inProgress\": 1, \"notYetStarted\": 0, \"cancelled\": 0, \"totalCharacterCharged\": 1355, \"totalImageScansSucceeded\": 2, \"totalImageScansFailed\": 0 }",
"reason": "totalCharacterCharged is returned inside the JSON response body 'summary' object, not in response headers as the claim's load-bearing location asserts.",
"file": "skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md",
"line": 359,
"claim": "totalCharacterCharged returneres i response headers for cost tracking",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/cross-cloud-data-integration.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 6,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/cross-cloud-data-integration.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/onelake/create-gcs-shortcut",
"evidence_quote": "Fabric uses Hash-based Message Authentication Code (HMAC) keys to access Google Cloud storage. These keys are associated with a user or service account. ... The supported delegated credential is an HMAC key and secret for a Service account or User account.",
"reason": "The taxonomy's source list is correct, but one load-bearing part is contradicted: the claim maps Google Cloud Storage auth to 'service account JSON', while the canonical GCS shortcut page states GCS shortcuts authenticate via an HMAC Key (Access ID + Secret), not a service-account JSON key file; one wrong load-bearing part makes the whole claim not_grounded.",
"file": "skills/ms-ai-engineering/references/data-engineering/cross-cloud-data-integration.md",
"line": 40,
"claim": "OneLake shortcut-kilder med shortcut-type og autentisering: Azure Data Lake Gen2 (ADLS shortcut, service principal/account key) | Amazon S3 (S3 shortcut, IAM access key/secret) | Google Cloud Storage (GCS shortcut, service account JSON) | S3-kompatibel (S3-compatible shortcut, access key/secret) | On-premises (via On-premises Data Gateway/OPDG) | Annen Fabric-tenant (OneLake shortcut, data sharing invitation).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-anonymization-privacy.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 5,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-anonymization-privacy.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/concepts/entity-categories",
"evidence_quote": "To retrieve this entity type, specify NOIdentityNumber in the piiCategories request parameter.",
"reason": "The claim lists exact Azure piiCategories codes, but NorwayIdentityNumber is wrong (the page's code is NOIdentityNumber) and HealthcareEntities is absent from the entire PII/PHI code enumeration, so load-bearing parts of the multi-part code list are contradicted.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-anonymization-privacy.md",
"line": 367,
"claim": "Azure Language PII-entitetskategorier (Azure-koder): NorwayIdentityNumber | Person | Address | PhoneNumber | Email | InternationalBankingAccountNumber | Organization | HealthcareEntities.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-cataloging-discovery.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-cataloging-discovery.md#4",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/purview/data-map-classification-supported-list",
"evidence_quote": "",
"reason": "The canonical supported-classifications page lists these classifications only by display name (Norway identification number, Credit card number, Email, U.S. phone number); best-practices confirms formal names carry a MICROSOFT prefix but no fetched page publishes the exact qualified identifier strings claimed, so they cannot be verified verbatim.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-cataloging-discovery.md",
"line": 131,
"claim": "Purview har innebygde klassifiseringer identifisert som: MICROSOFT.GOVERNMENT.NORWAY.NATIONAL.ID.NUMBER | MICROSOFT.FINANCIAL.CREDIT_CARD_NUMBER | MICROSOFT.PERSONAL.EMAIL | MICROSOFT.PERSONAL.PHONE_NUMBER.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/data-factory/compute-linked-services",
"evidence_quote": "The Update Resource URL for an ML Studio (classic) Web Service endpoint used to update the predictive Web Service with trained model file",
"reason": "The Update Resource activity is an ML Studio (classic) web-service model-update mechanism (uploads a .ilearner trained model), not a batch/online-endpoint feature; the claim's 'batch endpoints only / online via ARM or SDK' framing mischaracterizes the activity.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 232,
"claim": "Azure ML Update Resource activity støtter kun batch endpoints; online endpoints krever ARM templates eller Azure ML SDK via Notebook Activity",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/power-platform/admin/security/secure-web-ai-gateway-agents",
"evidence_quote": "The following connectors currently support secure web and AI gateway Copilot Studio agents ... Azure Data Factory",
"reason": "An Azure Data Factory connector (first-party, Microsoft) is enumerated among connectors supported for Copilot Studio agents, contradicting the claim that Copilot Studio has no native Data Factory connector.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 297,
"claim": "Copilot Studio har ikke native Data Factory connector (per Feb 2026)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#9",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/data-factory/connector-overview",
"evidence_quote": "",
"reason": "No Learn page states that Data Factory can or cannot directly call AI Builder models; AI Builder is absent from the ADF connector list but a negative-existence claim cannot be grounded from silence.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 341,
"claim": "Data Factory kan ikke direkte kalle AI Builder-modeller (per Feb 2026)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#10",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/data-factory/quickstart-create-data-factory",
"evidence_quote": "",
"reason": "The metadata-stored-in-region behavior is confirmed, but no fetched Learn page enumerates ADF's specific regional availability in Norway East/West (Norway West is a restricted region), so the region-support assertion is unverified.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 357,
"claim": "Azure Data Factory støtter Norway East/West regions (metadata lagres i region)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/admin/region-availability",
"evidence_quote": "Europe | Norway West | (Power BI: yes) | (All Fabric workloads: no) | Power BI only region",
"reason": "Norway West is a Power BI-only region where all Fabric workloads are unavailable, so Fabric capacity is NOT available there, contradicting the load-bearing Norway West part of the claim.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 358,
"claim": "Fabric capacity er tilgjengelig i Norway West/East per Q1 2026 (OneLake-data residency følger capacity-region)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-factory-ai-pipelines.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/data-factory/frequently-asked-questions",
"evidence_quote": "Azure Data Factory is certified for a range of compliance certifications, including SOC 1, 2, 3, HIPAA BAA, and HITRUST.",
"reason": "Azure Data Factory IS certified for HIPAA BAA, directly contradicting the claim's load-bearing assertion that ADF is not HIPAA BAA-compliant.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-factory-ai-pipelines.md",
"line": 605,
"claim": "Azure Data Factory er ikke HIPAA BAA-compliant (per Feb 2026); Azure Synapse Pipelines er HIPAA-certified (samme teknologi)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-mesh-patterns.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-mesh-patterns.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/fabric/governance/domains",
"evidence_quote": "There are three roles involved in the creation and management of domains: Fabric admin (or higher)... Domain admin... Domain contributor",
"reason": "Canonical domains page enumerates exactly three domain roles; the claim's Data Producer and Data Consumer are absent from the enumeration, so the 5-role list is not grounded.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-mesh-patterns.md",
"line": 60,
"claim": "Roller i Fabric domenestyring: Fabric Admin | Domain Admin | Domain Contributor | Data Producer | Data Consumer.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-pipeline-orchestration.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 8,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-pipeline-orchestration.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/data-factory/pipeline-runs",
"evidence_quote": "You can start a pipeline run in three ways: On-demand runs ... Scheduled runs ... Event-based runs.",
"reason": "Canonical enumerating page lists only three trigger types (On-demand, Scheduled, Event-based); 'Tumbling Window' is absent and the count is three, not four.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-pipeline-orchestration.md",
"line": 39,
"claim": "Fabric Data Factory har fire trigger-typer: Schedule | Tumbling Window | Event-based | On-demand.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-quality-ai-frameworks.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-model-monitoring",
"evidence_quote": "",
"reason": "Each of the four named tools is a real Microsoft data-quality mechanism, but no single learn.microsoft.com page enumerates them as the four main tracks for data quality in AI; the four-way taxonomy is author synthesis, neither stated nor contradicted.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"line": 34,
"claim": "Microsoft-stacken tilbyr fire hovedspor for data quality management i AI: Microsoft Purview Data Quality | Azure Machine Learning Model Monitoring | Microsoft Fabric data quality | Azure Databricks expectations (Delta Live Tables/DLT).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/data-quality-ai-frameworks.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/purview/unified-catalog-data-quality-supported-sources-file-formats",
"evidence_quote": "Amazon S3 | Yes | Yes | No | Supported via Fabric shortcut ... Supported file formats: Delta ... Parquet ... Iceberg Avro ... Iceberg Orc",
"reason": "The canonical supported-sources page enumerates supported sources/formats; the claim overstates them: AWS RDS is not listed at all and CSV is not a supported file format (only Delta/Parquet/Iceberg).",
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"line": 75,
"claim": "Microsoft Purview Data Quality støtter multi-cloud datakilder: Azure (Blob Storage | ADLS Gen2 | Azure SQL DB | Synapse | Fabric Lakehouse i Delta/Iceberg-format) | AWS (S3 med Parquet/CSV/Delta | RDS) | GCP (BigQuery).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-quality-ai-frameworks.md#10",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-model-monitoring",
"evidence_quote": "Model performance: Classification (preview) ... Accuracy, Precision, and Recall ... Model performance: Regression (preview) ... Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE)",
"reason": "The model performance signal enumerates Accuracy/Precision/Recall (classification) and MAE/MSE/RMSE (regression); F1 and AUC asserted by the claim are absent from the enumeration.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"line": 97,
"claim": "Azure ML Model Monitoring 'Model performance'-signalet bruker metrikkene: Accuracy | Precision | Recall | F1 | AUC | MAE | RMSE.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-quality-ai-frameworks.md#15",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/purview/register-scan-azure-machine-learning",
"evidence_quote": "This integration between Azure Machine Learning and Microsoft Purview applies an auto push model that, once the Azure Machine Learning workspace has been registered in Microsoft Purview, the metadata from workspace is pushed to Microsoft Purview automatically on a daily basis.",
"reason": "The claim asserts no native Azure ML-Purview integration exists, but Microsoft Learn documents a first-party auto-push integration (metadata pushed daily), directly contradicting the claim; preview status does not make it nonexistent.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"line": 285,
"claim": "Det finnes ingen native integrasjon mellom Azure ML og Microsoft Purview (per 2026-02).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/data-quality-ai-frameworks.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/materialized-lake-views/overview-materialized-lake-view",
"evidence_quote": "PySpark authoring (Preview): Create, refresh, and replace views from Fabric notebooks using DataFrameWriter. PySpark-authored views support: Data quality constraints",
"reason": "The claim asserts all four tools are GA, but Fabric materialized lake views (the Fabric data-quality mechanism) was announced as preview and its PySpark authoring path for data quality constraints is still marked Preview, so the GA-for-all part fails.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-quality-ai-frameworks.md",
"line": 583,
"claim": "Microsoft Purview Data Quality, Azure ML Model Monitoring, Fabric data quality og Databricks DLT expectations er alle GA (production-ready per 2026-02).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-sampling-labeling.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 5,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/data-sampling-labeling.md#3",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-create-image-labeling-projects",
"evidence_quote": "Labeling projects are administered in Azure Machine Learning. Use the Data Labeling page in Machine Learning to manage your projects.",
"reason": "Existence claim fails: the canonical labeling-project creation page describes only studio-UI creation (Add project), and the azure.ai.ml SDK reference enumerates AutoML job classes (ImageClassificationJob/ImageClassificationMultilabelJob) with no DataLabelingJob entity, no labeling_job_type field, and no ImageClassificationMulticlass task-type value.",
"file": "skills/ms-ai-engineering/references/data-engineering/data-sampling-labeling.md",
"line": 280,
"claim": "Azure ML SDK v2 (azure.ai.ml) tilbyr DataLabelingJob-entiteten for å opprette datamerkingsprosjekter, med labeling_job_type-verdien ImageClassificationMulticlass for bildeklassifisering.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/data-versioning-lineage.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 5,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/dataverse-ai-integration.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/dataverse-ai-integration.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/databricks/ingestion/lakeflow-connect/d365-reference",
"evidence_quote": "The Dynamics 365 connector maps Dataverse data types to Delta Lake data types. ... | Money | DECIMAL(19,4) | ... | DateTime | TIMESTAMP | ... | Lookup | STRING | ... | Picklist (Option Set) | INTEGER |",
"reason": "The Dataverse-to-Delta-Lake type-mapping enumeration confirms Lookup, Picklist (OptionSet), Money and DateTime but has no Customer or PartyList row, so two claimed mapped types are absent from the enumerating page.",
"file": "skills/ms-ai-engineering/references/data-engineering/dataverse-ai-integration.md",
"line": 123,
"claim": "Dataverse-datatyper med Delta Lake-mapping: Lookup | OptionSet | Money | DateTime | Customer | PartyList.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/dataverse-ai-integration.md#8",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/power-apps/maker/data-platform/azure-synapse-link-transition-from-fno",
"evidence_quote": "Dataverse triggers data update jobs every 15 minutes and depending on the volume of data changes, you might see updated Parquet files within 15 to 45 minutes.",
"reason": "The Fabric link update/poll frequency is documented as every 15 minutes, not every 2 minutes; the claimed value contradicts the source (exact-value rule).",
"file": "skills/ms-ai-engineering/references/data-engineering/dataverse-ai-integration.md",
"line": 229,
"claim": "Link to Fabric-synkronisering poller Dataverse hvert 2. minutt for inkrementelle endringer.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/delta-lake-parquet-optimization.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 6,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/delta-lake-parquet-optimization.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/delta-optimization-and-v-order",
"evidence_quote": "",
"reason": "Fetched the V-Order optimization page and searched broadly; no learn.microsoft.com page states a GA/generally-available status for Delta-Parquet optimization or V-Order, and no preview marker contradicts it, so the GA status can be neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/data-engineering/delta-lake-parquet-optimization.md",
"line": 4,
"claim": "Delta Lake- og Parquet-formatoptimalisering (inkludert V-Order) i Microsoft Fabric har status GA (generelt tilgjengelig).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/delta-lake-parquet-optimization.md#3",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/spark-monitoring-best-practices",
"evidence_quote": "Target 128 MB to 1 GB per file depending on table size, with row groups of 1-2 million rows.",
"reason": "The 128 MB figure is the target per-file size, not the row group size; Fabric expresses row group size in rows (1-2 million), so the claim mislabels file size as row group size - a unit/frame mismatch.",
"file": "skills/ms-ai-engineering/references/data-engineering/delta-lake-parquet-optimization.md",
"line": 131,
"claim": "Standard Parquet row group-størrelse i Microsoft Fabric er 128 MB.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/delta-lake-parquet-optimization.md#4",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/delta-optimization-and-v-order",
"evidence_quote": "",
"reason": "No learn.microsoft.com page documents Fabric's per-datatype automatic Parquet encoding selection (Delta Binary Packed / Dictionary / Plain / Run Length mapping); the V-Order docs mention dictionary encoding only generically, so the specific mapping cannot be confirmed or refuted.",
"file": "skills/ms-ai-engineering/references/data-engineering/delta-lake-parquet-optimization.md",
"line": 144,
"claim": "Parquet velger automatisk encoding-strategi per datatype i Fabric: Integer/Long → Delta Binary Packed | String (lav kardinalitet) → Dictionary | String (høy kardinalitet) → Plain | Boolean → Run Length | Timestamp → Delta Binary Packed.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/etl-vs-elt-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 6,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/etl-vs-elt-ai.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/onelake/onelake-medallion-lakehouse-architecture",
"evidence_quote": "The three medallion layers are: bronze (raw data), silver (enriched data), and gold (curated data). ... Gold (Curated): Organize for reports and dashboards.",
"reason": "Bronze/Silver check out but the source characterizes the Gold layer as curated data for reports and dashboards, not 'ML-features' — a stated, load-bearing part contradicted by the source (R8).",
"file": "skills/ms-ai-engineering/references/data-engineering/etl-vs-elt-ai.md",
"line": 51,
"claim": "Fabric Lakehouse-medaljongarkitektur består av tre lag: Bronze (rådata i Delta Lake) | Silver (validert) | Gold (ML-features).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/fabric-lakehouse-architecture.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/fabric-lakehouse-architecture.md#6",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/lakehouse-overview",
"evidence_quote": "",
"reason": "The cited overview documents integration only with 'Power BI, pipelines, dataflows, and other Fabric items'; no fetched learn.microsoft.com page enumerates the specific nine-item integration set (Azure ML, Microsoft Foundry, Copilot Studio, Databricks, Synapse, ADF, Purview, Key Vault), and none is contradicted, so the enumeration is unverifiable.",
"file": "skills/ms-ai-engineering/references/data-engineering/fabric-lakehouse-architecture.md",
"line": 174,
"claim": "Fabric Lakehouse har dokumenterte integrasjonspunkter med: Azure Machine Learning | Microsoft Foundry | Copilot Studio | Power BI | Azure Databricks | Synapse Analytics | Azure Data Factory | Microsoft Purview | Azure Key Vault.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/fabric-lakehouse-architecture.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/enterprise/licenses",
"evidence_quote": "Premium Per User (PPU) doesn't provision a Fabric capacity. Although PPU provides access to most Power BI Premium features, it doesn't enable you to create or run non-Power BI Fabric items (such as lakehouses, warehouses, or notebooks). To use Fabric workloads beyond Power BI, you need an F capacity or a Trial Fabric capacity.",
"reason": "The F SKU / CU part (F64, F128) is correct, but the load-bearing claim that Fabric Capacity is licensed 'as Premium Per User' is contradicted PPU is a per-user license that doesn't provision a Fabric capacity, so one load-bearing part fails.",
"file": "skills/ms-ai-engineering/references/data-engineering/fabric-lakehouse-architecture.md",
"line": 244,
"claim": "Fabric Capacity lisensieres kapasitetsbasert som F SKU (CU-basert, f.eks. F64 og F128) eller som Premium Per User.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/feature-stores-engineering.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 4,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/feature-stores-engineering.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-what-is-managed-feature-store",
"evidence_quote": "",
"reason": "Fetched the cited concept page and searched whats-new and the cloud-parity feature table; the page documents managed feature store fully with no preview marker, but no learn.microsoft.com page states 'generally available'/GA verbatim, so the GA status is unsourced (no contradiction either).",
"file": "skills/ms-ai-engineering/references/data-engineering/feature-stores-engineering.md",
"line": 4,
"claim": "Azure Machine Learning Managed Feature Store er GA (generelt tilgjengelig).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/feature-stores-engineering.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/data-science/data-wrangler",
"evidence_quote": "This table summarizes the operations that Data Wrangler currently supports:",
"reason": "The PROSE rule-based suggestions and Copilot natural-language-to-code parts are confirmed on Microsoft Learn, but the cited enumerating page lists only about 19 operations (Sort, Filter, One-hot encode ... Flash Fill), contradicting 'over 300 transformasjoner' - one load-bearing part is wrong so the whole claim fails.",
"file": "skills/ms-ai-engineering/references/data-engineering/feature-stores-engineering.md",
"line": 298,
"claim": "Data Wrangler i Fabric tilbyr over 300 transformasjoner, AI-drevne forslag (PROSE) og Copilot for naturlig språk til kode.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/lakehouse-architecture-design.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 4,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/lakehouse-architecture-design.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/data-engineering/delta-optimization-and-v-order",
"evidence_quote": "In Microsoft Fabric, V-Order is disabled by default for all newly created workspaces to optimize performance for write-heavy data engineering workloads.",
"reason": "The write-time Parquet-optimization descriptor holds, but the load-bearing status part is contradicted: the page states V-Order is disabled by default in new Fabric workspaces, whereas the claim asserts it is enabled by default.",
"file": "skills/ms-ai-engineering/references/data-engineering/lakehouse-architecture-design.md",
"line": 295,
"claim": "V-Order er aktivert som standard i Microsoft Fabric ved skriving til Delta-tabeller (skrive-tids-optimalisering av Parquet-filer som gir raskere lesing for alle Fabric-engines).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/lakehouse-architecture-design.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/delta-lake-deletion-vectors",
"evidence_quote": "Deletion vectors are enabled by default starting in Fabric Spark runtime 2.0 (Delta 4.1).",
"reason": "The deletion-vectors capability (soft-delete without rewrite) is grounded, but the version part is contradicted: default enablement starts in Fabric Spark runtime 2.0, not from Runtime 1.2 and newer as the claim states.",
"file": "skills/ms-ai-engineering/references/data-engineering/lakehouse-architecture-design.md",
"line": 302,
"claim": "Deletion Vectors (raskere DELETE/UPDATE uten rewrite) er automatisk aktivert i Fabric fra Runtime 1.2 og nyere.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/lakehouse-architecture-design.md#3",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/data-engineering/liquid-clustering",
"evidence_quote": "",
"reason": "The canonical liquid-clustering page grounds 'It replaces static Hive-style partitioning and manual Z-Order maintenance' and CLUSTER BY enablement, but states no GA or preview release stage for the feature, so the claim's headline GA status is neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/data-engineering/lakehouse-architecture-design.md",
"line": 303,
"claim": "Liquid Clustering er GA i Fabric, erstatter partisjonering/Z-Order og aktiveres manuelt med CLUSTER BY.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/master-data-management-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 5,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/master-data-management-ai.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/purview/data-governance-master-data-management",
"evidence_quote": "",
"reason": "The MDM-in-Purview page describes MDM only as partner integrations (CluedIn, Profisee, Reltio, Semarchy) and never states a GA or preview status; the Purview feature-availability and whats-new pages enumerate feature statuses but do not list master data management, so no page confirms or contradicts Status GA.",
"file": "skills/ms-ai-engineering/references/data-engineering/master-data-management-ai.md",
"line": 4,
"claim": "Master Data Management-kapabiliteten i Microsoft Purview er generelt tilgjengelig (Status: GA).",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/microsoft-purview-governance.md#2",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/purview/data-governance-overview",
"evidence_quote": "data governance involves two primary solutions: Data Map, Unified Catalog",
"reason": "Data Map is a peer solution, not a component of Unified Catalog.",
"file": "skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md",
"line": 39,
"claim": "Purview Unified Catalog består av komponentene Data Map | Unified Catalog | Governance Domains | Data Products | Business Glossary.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/microsoft-purview-governance.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/purview/data-map-lineage-fabric",
"evidence_quote": "For all Fabric items besides Power BI, only item level metadata and lineage can be scanned",
"reason": "Item-level-only lineage contradicts Dataflow Gen2 all-transformations and activity-level pipeline lineage.",
"file": "skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md",
"line": 175,
"claim": "Støttede lineage-typer: Data Factory Pipeline (Copy Activity | Data Flow) | Dataflow Gen2 (alle transformasjoner) | Notebook (Lakehouse-til-Lakehouse) | Lakehouse (tabell-nivå metadata) | Power BI (Semantic Model → Report → Dashboard) | Azure Data Factory (Copy | Data Flow | SSIS).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/microsoft-purview-governance.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/purview/legacy/how-to-policies-data-owner-azure-sql-db",
"evidence_quote": "actions are currently enabled: Read. Modify isn't supported at this point",
"reason": "Claim says Modify for Azure SQL but page says Modify unsupported.",
"file": "skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md",
"line": 240,
"claim": "Purview Data Owner Policy-typer og støttede kilder: Read (Azure SQL | ADLS Gen2 | Fabric) | Modify (Azure SQL | ADLS Gen2) | Data Use (Fabric workspaces).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/onelake-data-strategy.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/onelake-data-strategy.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/fabric/onelake/onelake-shortcuts",
"evidence_quote": "You can create shortcuts in lakehouses and Kusto Query Language (KQL) databases.",
"reason": "Canonical enumeration of shortcut-hosting item types is Lakehouse, KQL database (plus Eventhouse database shortcuts); the claim asserts Warehouse and Mirrored Databases host shortcuts, which are absent from that enumeration (they are shortcut targets, not shortcut-hosting items).",
"file": "skills/ms-ai-engineering/references/data-engineering/onelake-data-strategy.md",
"line": 54,
"claim": "Item-typer som støtter shortcuts: Lakehouse (Tables/ og Files/) | KQL Database (Shortcuts/-folder, behandles som external tables) | Warehouse (via SQL analytics endpoint, read-only) | Mirrored Databases (Azure Databricks Mirrored Catalog, Mirrored Databases).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/onelake-data-strategy.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/onelake/security/data-access-control-model",
"evidence_quote": "Lakehouse | Yes | GA | Spark notebooks | Yes | GA | SQL Analytics Endpoint in user's identity access mode | Yes | GA | Semantic models using Direct Lake on OneLake mode | Yes | GA | Eventhouse | RLS only | Public preview",
"reason": "The GA engines match, but the load-bearing status that Eventhouse (and data warehouse external tables) is Planned is contradicted: the live table lists Eventhouse RLS/CLS as Public preview and data warehouse external tables are not in the table, so one status part is wrong.",
"file": "skills/ms-ai-engineering/references/data-engineering/onelake-data-strategy.md",
"line": 198,
"claim": "RLS/CLS-filtrering er GA for Lakehouse, Spark notebooks, SQL Analytics Endpoint (user's identity mode) og Semantic models (DirectLake on OneLake); Planned for Eventhouse og Data warehouse external tables.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/onelake-data-strategy.md#17",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/onelake/security/data-access-control-model",
"evidence_quote": "",
"reason": "No learn.microsoft.com page (OneLake security limitations, best-practices, or shortcut-security) states cross-region shortcuts are unsupported with OneLake security; the only same-region shortcut limitation found is specific to the Iceberg-tables-with-OneLake feature, not to OneLake security, so it cannot be confirmed or refuted.",
"file": "skills/ms-ai-engineering/references/data-engineering/onelake-data-strategy.md",
"line": 226,
"claim": "Cross-region shortcuts støttes ikke med OneLake security.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/real-time-streaming-ai.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "pass",
"claim_count": 7,
"verified": "2026-07-24",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/schema-evolution-management.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 7,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/schema-evolution-management.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/delta/feature-compatibility",
"evidence_quote": "| [Liquid clustering](../clustering) | 7 | 3 | 1 | Reader and writer (1) |",
"reason": "Page states Liquid clustering requires minReaderVersion 3 (minWriterVersion 7 is correct); the claim asserts minReaderVersion 2, so the reader-version load-bearing part is contradicted.",
"file": "skills/ms-ai-engineering/references/data-engineering/schema-evolution-management.md",
"line": 74,
"claim": "I Delta Lake krever Liquid Clustering delta.minReaderVersion 2 og delta.minWriterVersion 7.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/schema-evolution-management.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/delta/type-widening",
"evidence_quote": "| `DATE` | `TIMESTAMP_NTZ` |",
"reason": "Six of seven widenings match, but the page lists the DATE target as TIMESTAMP_NTZ (a distinct type), not TIMESTAMP as the claim asserts; DATE->TIMESTAMP is not a supported type widening, so a stated load-bearing sub-item is contradicted.",
"file": "skills/ms-ai-engineering/references/data-engineering/schema-evolution-management.md",
"line": 175,
"claim": "Delta Lake støtter følgende trygge type-utvidelser (type widening): BYTE → SHORT | SHORT → INT | INT → LONG | LONG → DECIMAL (betinget) | FLOAT → DOUBLE | DATE → TIMESTAMP | DECIMAL(p,s) → DECIMAL(p',s') (hvis p'>=p og s'>=s).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/schema-evolution-management.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/data-engineering/schema-evolution",
"evidence_quote": "Type widening: Supported in Databricks Runtime 16.4 and above with `schemaEvolutionMode` set to `addNewColumnsWithTypeWidening`. Supported data type changes are widened automatically.",
"reason": "Delta Connector, Streaming Tables, Materialized Views and Delta Tables all match, but the claim asserts Auto Loader type-utvidelse 'nei' while the live page states Auto Loader type widening is supported in DBR 16.4+, contradicting a stated load-bearing part.",
"file": "skills/ms-ai-engineering/references/data-engineering/schema-evolution-management.md",
"line": 409,
"claim": "Schema evolution-støtte per komponent i Delta Lake/Fabric: Auto Loader (nye kolonner ja ved restart, rename ja ved restart, drop soft delete, type-utvidelse nei) | Delta Connector (nye kolonner via mergeSchema, rename/drop via column mapping, type widening ja) | Streaming Tables (nye kolonner/rename/drop/type widening ja) | Materialized Views (alle endringer krever full recompute) | Delta Tables (nye kolonner/rename/drop/type-utvidelse ja via auto/DDL).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/synthetic-data-generation.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 5,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/synthetic-data-generation.md#2",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/openai/concepts/use-your-data",
"evidence_quote": "",
"reason": "The cited use-your-data (classic) page states no api-version at all; 2024-12-01-preview is a real Azure OpenAI api-version per the lifecycle changelog, but no Learn page states this integration uses that specific version and none contradicts it, so the usage is unsourced.",
"file": "skills/ms-ai-engineering/references/data-engineering/synthetic-data-generation.md",
"line": 48,
"claim": "Azure OpenAI-integrasjonen bruker API-versjon 2024-12-01-preview.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/synthetic-data-generation.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation",
"evidence_quote": "The preview includes two generator types:",
"reason": "The canonical enumerating page lists only two generator types (Simple Q&A and Tool use); the claim asserts three, adding a 'Conversation' generator type that is absent from the enumeration.",
"file": "skills/ms-ai-engineering/references/data-engineering/synthetic-data-generation.md",
"line": 89,
"claim": "Microsoft Foundry data-generering tilbyr tre generatortyper: Simple Q&A (JSONL messages) | Tool Use (JSONL tool calls) | Conversation (JSONL conversation).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/data-engineering/zero-etl-fabric-patterns.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/fundamentals/whats-new-archive",
"evidence_quote": "Open mirroring, now generally available, is designed to be extensible, customizable, and open.",
"reason": "Database mirroring being GA is defensible, but the load-bearing part that Open Mirroring is in Preview is contradicted: the What's new archive designates open mirroring as generally available (May 2025), not preview.",
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"line": 4,
"claim": "Database Mirroring i Microsoft Fabric er GA, mens Open Mirroring er i Preview for enkelte kilder.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/zero-etl-fabric-patterns.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/mirroring/azure-cosmos-db",
"evidence_quote": "Mirroring does not use Azure Cosmos DB's analytical store or change feed as a change data capture source.",
"reason": "The claim asserts Azure Cosmos DB CDC mechanism is the Change Feed API, but the Cosmos DB mirroring page explicitly states mirroring does not use change feed as a change data capture source; one load-bearing part of the taxonomy is contradicted (R8).",
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"line": 505,
"claim": "CDC-mekanisme og latens per kilde: SQL Server = Change Feed / transaction log scanning (15+ sek) | PostgreSQL = Logical replication via azure_cdc-extension (15+ sek) | Azure Cosmos DB = Change Feed API (15+ sek) | Snowflake = Snowflake Streams API (30+ sek).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/zero-etl-fabric-patterns.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/fabric/mirroring/open-mirroring-partners-ecosystem",
"evidence_quote": "",
"reason": "Microsoft Learn documents MongoDB only as an existing open-mirroring partner integration and publishes no forward-looking roadmap date; no page states MongoDB mirroring is planned for Q2 2026 or was announced at Ignite 2025, so the roadmap claim can neither be confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"line": 607,
"claim": "MongoDB-mirroring til Fabric er planlagt Q2 2026 (annonsert på Microsoft Ignite 2025).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/data-engineering/zero-etl-fabric-patterns.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/fundamentals/whats-new-archive",
"evidence_quote": "SAP Datasphere Mirroring and Copy Job support (Preview) ... now supports Mirroring for SAP Datasphere and Copy Job support for SAP Datasphere as preview features.",
"reason": "The claim states SAP mirroring via SAP Datasphere is GA, but the What's new archive designates SAP Datasphere Mirroring (and Copy Job support) as Preview, not GA; the load-bearing GA status is contradicted (R8).",
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"line": 608,
"claim": "SAP-kilder (S/4HANA, BW/4HANA m.fl.) mirrores til OneLake via SAP-mirroring (GA, via SAP Datasphere); Copy job auto-partition for SAP HANA er i preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/data-engineering/zero-etl-fabric-patterns.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/fabric/mirroring/overview",
"evidence_quote": "Azure Database for MySQL (preview) | Database mirroring",
"reason": "The claim states MySQL is supported via Open Mirroring, but the overview lists Azure Database for MySQL under Database mirroring (confirmed by REST SourceType AzureMySql, distinct from GenericMirror/open mirroring); the load-bearing mechanism is contradicted (R8).",
"file": "skills/ms-ai-engineering/references/data-engineering/zero-etl-fabric-patterns.md",
"line": 610,
"claim": "MySQL-mirroring støttes p.t. kun for Azure Database for MySQL via Open Mirroring.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/ab-testing-llm-applications.md#2",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-studio/how-to/develop/flow-evaluate-sdk#built-in-evaluators",
"evidence_quote": "",
"reason": "The cited page grounds parts (BLEU/ROUGE rule-based scorers, LLM-as-judge evaluators) but no learn.microsoft.com page states this 4-category Microsoft-approaches taxonomy, and business metrics (conversion rate, task completion, bounce rate) is not a Microsoft-documented eval category; synthesis is neither stated nor contradicted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"line": 88,
"claim": "Microsoft-tilnærminger for evaluering av LLM-eksperimenter: LLM-as-judge (Microsoft Foundry evaluators, Databricks judges) | Rule-based scorers (BLEU, ROUGE, exact match) | Human evaluation (Microsoft Foundry thumbs up/down, red teaming) | Business metrics (conversion rate, task completion, bounce rate).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/ab-testing-llm-applications.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-endpoints-online?view=azureml-api-2",
"evidence_quote": "Compute type | Managed by the service | Customer-managed Kubernetes cluster",
"reason": "Data collection (DataCollector) and Azure Monitor/App Insights monitoring check out, but Kubernetes-based deployment (AKS) is the SEPARATE Kubernetes online endpoint type, not a managed-online-endpoint capability (managed = Managed by the service); one load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"line": 232,
"claim": "Azure Machine Learning managed online endpoints støtter: Kubernetes-basert deployment (AKS) | Serverless compute | Data collection via DataCollector | Monitoring via Azure Monitor og Application Insights.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/ab-testing-llm-applications.md#5",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/what-is-foundry",
"evidence_quote": "Brand | Azure AI Studio / Azure AI Foundry | Microsoft Foundry",
"reason": "The Evolution-of-Foundry table states Microsoft Foundry previous brand was Azure AI Studio / Azure AI Foundry, not Azure OpenAI Studio (a distinct predecessor product); the claim names the wrong prior name.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"line": 260,
"claim": "Microsoft Foundry het tidligere Azure OpenAI Studio (navnet er omdøpt).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/ab-testing-llm-applications.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/evaluate-results",
"evidence_quote": "To compare two or more runs, select the runs you want to compare and start the process.",
"reason": "Pre-built evaluators, custom evaluators and batch evaluation are grounded, but Foundry A/B comparison is the Compare feature (statistical t-testing side-by-side); no Scorecards A/B-comparison feature is documented on the canonical evaluation page, so the stated mechanism in that load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"line": 262,
"claim": "Microsoft Foundry Evaluations tilbyr: Pre-built evaluators (groundedness, relevance, safety) | Custom evaluators med egne prompts | Batch evaluation på validation sets | A/B comparison via Scorecards.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/ab-testing-llm-applications.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/eval-monitor/concepts/judges/",
"evidence_quote": "RelevanceToQuery, RetrievalRelevance, Safety, RetrievalGroundedness, Correctness, RetrievalSufficiency, Guidelines, ExpectationsGuidelines, ToolCallCorrectness, ToolCallEfficiency",
"reason": "Correctness, RelevanceToQuery, RetrievalGroundedness and ToolCallEfficiency are all in the built-in-judges enumeration, but Fluency is absent from the canonical MLflow 3 scorer/judge list; absence from the enumerating page makes the claimed scorer not_grounded.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md",
"line": 471,
"claim": "MLflow 3 har et utvidet scorer-sett: Correctness | RelevanceToQuery | RetrievalGroundedness | ToolCallEfficiency | Fluency.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/automated-retraining-pipelines.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 9,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/automated-retraining-pipelines.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-machine-learning-cloud-parity?view=azureml-api-2",
"evidence_quote": "Differential privacy SmartNoise toolkit | OSS",
"reason": "The authoritative Azure ML feature-availability page lists differential privacy (SmartNoise toolkit) with status 'OSS', a category distinct from its 'Preview' and 'GA' labels; the 'not fully GA' part holds but the stated 'preview' status is contradicted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/automated-retraining-pipelines.md",
"line": 700,
"claim": "Differential privacy i Azure ML er i preview, ikke fullt GA.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/azure-ml-pipelines-orchestration.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-ml-pipelines",
"evidence_quote": "",
"reason": "Page presents pipelines as a current v2 feature (Python SDK azure-ai-ml v2 current) with no preview banner but never states the status token GA/generally available, so the exact status value is unsourced.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md",
"line": 4,
"claim": "Azure Machine Learning pipelines har status GA (generelt tilgjengelig).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/azure-ml-pipelines-orchestration.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-manage-inputs-outputs-pipeline?view=azureml-api-2",
"evidence_quote": "environment: azureml://registries/azureml/environments/sklearn-1.5/labels/latest",
"reason": "The base image openmpi4.1.0-ubuntu22.04:latest is current and grounded, but the claimed curated environment sklearn-1.0 is superseded; current pipeline docs reference sklearn-1.5, so one load-bearing part (the version) is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md",
"line": 105,
"claim": "Curated environment sklearn-1.0 og standard base-image mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04:latest brukes for pipeline-komponentmiljøer.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/azure-ml-pipelines-orchestration.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-ml-pipelines",
"evidence_quote": "",
"reason": "Azure ML regional availability/data residency is enumerated on the JS-rendered azure.microsoft.com Products available by region page (not fetchable); Norway East is plausible but Azure ML availability in the limited Norway West region cannot be confirmed or refuted from any learn.microsoft.com quote.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md",
"line": 425,
"claim": "Azure ML data residency for offentlig sektor i Norge tilbys i Azure-regionene Norway East og Norway West.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ci-cd-for-ml-models.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/ci-cd-for-ml-models.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-azure-machine-learning-v2?view=azureml-api-2",
"evidence_quote": "Azure Machine Learning supports the following types of compute: 1. Compute instance ... 2. Compute cluster ... 3. Serverless compute ... 4. Inference cluster ... 5. Attached compute.",
"reason": "Compute Instance and Compute Cluster are compute types, but Managed Endpoints and Batch Endpoints are endpoint/deployment types absent from the canonical compute-types enumeration - two load-bearing members of the taxonomy are miscategorized.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/ci-cd-for-ml-models.md",
"line": 542,
"claim": "Azure ML compute-typer for CI/CD omfatter Compute Instance | Compute Cluster | Managed Endpoints | Batch Endpoints.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/cost-optimization-mlops-pipelines.md",
"batch": "R7.2",
"judged_at": "2026-07-24",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/cost-optimization-mlops-pipelines.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-manage-optimize-cost?view=azureml-api-2",
"evidence_quote": "Enable idle shutdown (preview) to save on cost when the VM is idle for a specified time period. Set up a schedule to automatically start and stop the compute instance (preview) when not in use to save cost.",
"reason": "Claim says both GA, but the live cost page marks both idle shutdown and scheduled start/stop as (preview) - both load-bearing status parts contradicted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/cost-optimization-mlops-pipelines.md",
"line": 67,
"claim": "Compute instance idle shutdown og scheduled start/stop er begge GA (generelt tilgjengelig).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-yaml-monitor?view=azureml-api-2",
"evidence_quote": "Allowed categorical metric names: `jensen_shannon_distance`, `chi_squared_test`, `population_stability_index`",
"reason": "Pearson's Chi-Squared Test stemmer, men Euclidean Distance er fraværende fra den kanoniske kategoriske metrikklisten for v2 model monitoring — den er en v1 Dataset Monitor-metrikk (how-to-monitor-datasets), ikke en v2 drift detection-metrikk.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 50,
"claim": "For kategoriske features bruker Azure ML drift detection disse metrikkene: Pearson's Chi-Squared Test | Euclidean Distance (beregnet på empiriske fordelinger av kategoriske kolonner).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#9",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-monitor-model-performance?view=azureml-api-2",
"evidence_quote": "spark_compute = ServerlessSparkCompute( instance_type=\"standard_e4s_v3\", runtime_version=\"3.4\" )",
"reason": "Den siterte siden bruker runtime_version \"3.4\" i samtlige SDK- og CLI-eksempler; 3.3 er en superseded verdi som kun henger igjen i skjematabellen på reference-yaml-monitor, hvis egne YAML-eksempler også er oppdatert til 3.4.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 112,
"claim": "ServerlessSparkCompute for model monitoring konfigureres med runtime_version \"3.3\" (Spark runtime-versjon).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#10",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-monitor-datasets?view=azureml-api-1",
"evidence_quote": "Data drift (preview) was retired on September 1, 2025. Migrate to Model Monitor for your data drift tasks.",
"reason": "Migreringsanbefalingen stemmer, men statusen er ikke «deprecated»: funksjonen er retired per 1. september 2025 — et senere og handlingsendrende stadium enn deprecation, og eksakt-verdi-regelen gjelder med særlig kraft for status.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 144,
"claim": "Azure ML Dataset Monitors (preview, v1 SDK) er deprecated, og migrering til Model Monitor (v2 SDK) er anbefalt.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-monitor-model-performance?view=azureml-api-2",
"evidence_quote": "Schedule model monitoring jobs to run on serverless Spark compute pools.",
"reason": "Workspace (v2) og Blob Storage stemmer, men den bærende compute-delen er feil: både how-to-siden og skjemaet krever Spark pool («Description of compute resources for Spark pool to run monitoring job»), «managed compute cluster» er ikke et alternativ, og Application Insights står ikke i prerequisites for v2 model monitoring.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 191,
"claim": "Data drift monitoring krever: Azure ML workspace (v2 API) | compute (serverless Spark eller managed compute cluster) | datastore for production inference data (Azure Blob Storage eller ADLS Gen2) | valgfritt Application Insights for custom metrics logging.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/observability",
"evidence_quote": "Scheduled evaluation: Scheduled quality and safety evaluation using test datasets to detect system drift",
"reason": "Første del holder (Foundry har egen gen-AI-monitorering med groundedness, relevance og fluency), men den kanoniske observability-siden lister kun Evaluation, Monitoring og Tracing og «system drift» via planlagt evaluering på testdatasett — drift detection for grounding data i RAG er fraværende.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 218,
"claim": "Microsoft Foundry har egen monitoring for generativ AI med generation quality metrics: groundedness | relevance | fluency, og støtter drift detection for grounding data i RAG-scenarier.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#19",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side sier at model monitoring er inkludert uten separat lisens eller at Azure ML-workspacet i seg selv er kostnadsfritt; kostnadssiden beskriver kun at medfølgende ressurser (ACR, Blob Storage, Key Vault, Azure Monitor) og compute påløper etter forbruk.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 286,
"claim": "Data drift monitoring er inkludert i Azure Machine Learning uten separat lisens; Azure ML workspace har ingen kostnad i seg selv, mens compute og storage faktureres separat (consumption-based).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#20",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-yaml-monitor?view=azureml-api-2",
"evidence_quote": "**Optional** for basic model monitoring that uses recent past production data as comparison baseline and has 3 monitoring signals: data drift, prediction drift, and data quality.",
"reason": "Den kanoniske opplistingen gir out-of-box nøyaktig tre signaler (data drift, prediction drift, data quality) — feature attribution drift og custom signals er fraværende og krever advanced- eller custom-oppsett, hvilket how-to-siden bekrefter.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 388,
"claim": "Out-of-box model monitoring-signaler for online endpoints er: Data quality | Data drift | Prediction drift | Feature attribution drift | Custom signals (brukerdefinerte metrics via Python-skript).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#21",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-monitor-model-performance?view=azureml-api-2",
"evidence_quote": "You can monitor models that you deploy to Azure Machine Learning batch endpoints or models you deploy outside Azure Machine Learning.",
"reason": "Siden definerer «advanced» som flere signaler, trenings-/valideringsdata som referanse og topp-N-features, mens modeller utenfor Azure ML og batch endpoints hører til et eget oppsett («Set up model monitoring for production data») — claimets kategorimapping av Advanced er dermed feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 395,
"claim": "Oppsettsalternativene for model monitoring er: Out-of-box (automatisk konfigurert for Azure ML online endpoints, ingen konfigurasjon påkrevd) | Advanced (custom monitoring for modeller deployet utenfor Azure ML, batch endpoints eller eksternt) | Azure Event Grid-integrasjon for ruting av alerts.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/data-drift-monitoring-detection.md#22",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-yaml-monitor?view=azureml-api-2",
"evidence_quote": "Allowed numerical metric names: `jensen_shannon_distance`, `normalized_wasserstein_distance`, `population_stability_index`, `two_sample_kolmogorov_smirnov_test`",
"reason": "jensen_shannon_distance er tillatt for både numeriske og kategoriske features (ikke kategoriske alene), metrikken heter «Jensen-Shannon Distance» og ikke divergence, og «Normalized Wasserstein Distance» er det korrekte navnet — mappingen claimet setter opp finnes ikke i dokumentasjonen og motsier claim #3 i samme fil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md",
"line": 400,
"claim": "Statistiske metoder brukt av Azure ML model monitoring: Jensen-Shannon divergence for kategoriske features | Wasserstein distance (Earth Mover's Distance) for numeriske features | Population Stability Index (PSI) for feature-stabilitet.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#3",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/built-in-evaluators",
"evidence_quote": "General purpose evaluators | Coherence | Fluency ... RAG evaluators | Retrieval | Document Retrieval | Groundedness | Groundedness Pro (preview) | Relevance | Response Completeness (preview)",
"reason": "Jeg hentet den kanoniske enumereringen (Built-in evaluators reference) — relevance, groundedness og safety-evaluatorer finnes, men INGEN «Correctness»-evaluator er oppført i noen kategori (Correctness er en MLflow-scorer, ikke en Foundry-evaluator); fraværet er bevis mot eksistenspåstanden.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 93,
"claim": "Foundry Agent Evaluation utfører evaluering med LLM judges for correctness | relevance | groundedness | safety.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-monitor-model-performance?view=azureml-api-2",
"evidence_quote": "spark_compute = ServerlessSparkCompute(instance_type=\"standard_e4s_v3\", runtime_version=\"3.4\")",
"reason": "instance_type standard_e4s_v3 stemmer, men siden angir runtime_version \"3.4\" i alle eksempler (YAML og SDK) — claimets 3.3 er en gammel verdi; én bærende del er feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 176,
"claim": "Azure ML model monitoring kan kjøre på ServerlessSparkCompute med instance_type standard_e4s_v3 og runtime_version 3.3.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#7",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/databricks/mlflow3/genai/",
"evidence_quote": "MLflow 3 for GenAI provides these key pieces for efficient development, deployment, and continuous improvement: Tracing ... Built-in and custom LLM judges and scorers ... Review apps for expert feedback ... Automated evaluation and monitoring ... App and prompt versioning",
"reason": "Den siterte kanoniske siden definerer forbedringssyklusen med FEM nøkkelelementer; ingen Learn-side definerer en «10-stegs» syklus med de ti navngitte stegene claimet lister.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 241,
"claim": "MLflow for GenAI definerer en 10-stegs kontinuerlig forbedringssyklus: Production App (traces) | User Feedback (thumbs up/down) | Monitor & Score (LLM judges) | Identify Issues (Trace UI) | Domain Expert Review (Review App) | Build Eval Dataset | Tune Scorers | Evaluate New Versions | Compare Results (MLflow evaluation runs) | Deploy or Iterate.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-data-collection?view=azureml-api-2",
"evidence_quote": "Azure Machine Learning Data collector provides real-time logging of input and output data from models that are deployed to managed online endpoints or Kubernetes online endpoints. Azure Machine Learning stores the logged inference data in Azure blob storage.",
"reason": "Model Monitor, retraining via pipelines og blue-green på managed online endpoints holder, men datainnsamlingen skjer via Data collector til Azure Blob Storage — Azure ML har ingen «inference tables» (det er et Databricks-begrep); én bærende del er feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 443,
"claim": "Feedback loop-komponentene i Azure Machine Learning er: Data collection via inference tables på managed endpoints | Monitoring via Model Monitor | Alerting via Azure Monitor Alerts (e-post/webhook ved threshold breach) | Retraining via Azure ML Pipelines | A/B-testing via staging endpoints | Deployment via Managed Online Endpoints med blue-green deployment.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/observability",
"evidence_quote": "Microsoft Foundry provides three core capabilities that work together to deliver comprehensive observability across the AI application lifecycle: Evaluation ... Monitoring ... Tracing",
"reason": "Foundry Observability-dashboardet og AI red teaming agent står på siden, men den kanoniske Foundry-enumereringen inneholder verken Review App, «Agent Evaluation» eller MLflow Datasets i Unity Catalog — det er Databricks-MLflow-komponenter, ikke Microsoft Foundry-komponenter.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 471,
"claim": "Feedback loop-komponentene for GenAI i Microsoft Foundry er: MLflow Tracing (Databricks, span-nivå telemetri) | Review App (thumbs up/down og tekstlig feedback) | Agent Evaluation (LLM judges) | Microsoft Foundry Observability (dashboard for kvalitetstrender, latens, feil) | MLflow Datasets i Unity Catalog (versjonerte testsett) | AI Red Teaming Agent (adversarial testing for sikkerhet).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/ai-builder/feedback-loop",
"evidence_quote": "Select Feedback loop and add the documents that could improve your model. Tag these new documents and retrain the model.",
"reason": "Power Automate-ruting på confidence score og Dataverse-lagring stemmer, men feedback loop legger IKKE reviewede samples automatisk til treningssettet — dokumentene må velges, tagges og modellen retrenes manuelt; SharePoint nevnes heller ikke som lagring (siden sier eksplisitt Dataverse-tabellen «AI Builder Feedback Loop»).",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 552,
"claim": "Feedback loop-komponentene i Power Platform AI er: Power Automate (ruting av low-confidence predictions til human review) | Dataverse / SharePoint (lagring av feedback-data) | AI Builder Feedback Loop (legger reviewede samples automatisk til treningssettet) | AI Builder (manuell/planlagt retraining).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/well-architected/sustainability/sustainability-cost-optimization-recommendations",
"evidence_quote": "",
"reason": "Learn omtaler «lower-carbon regions» som prinsipp (WAF sustainability, Sustainable AI design) men navngir ingen regioner; ingen learn.microsoft.com-side utpeker Sweden Central eller Norway East som low-carbon — karbonintensitetsdata publiseres utenfor Learn (Emissions Impact Dashboard / carbon optimization), så verken bekreftelse eller motbevis finnes.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 607,
"claim": "Sweden Central og Norway East angis som low-carbon Azure-regioner for karbonbevisst deployment.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#13",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-azure-machine-learning-v2?view=azureml-api-2",
"evidence_quote": "",
"reason": "STANDARD_DS3_v2 opptrer kun som generisk eksempelstørrelse for compute cluster/instance, og AutoML-CV-siden anbefaler NCsv3-serien generelt; ingen Learn-side foreskriver disse SKU-ene knyttet til daglig tabular- vs. ukentlig CV-retraining — mappingen er udokumentert, ikke motsagt.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 639,
"claim": "Compute-SKU-ene som brukes til retraining i Azure Machine Learning er Standard_DS3_v2 (4 vCPU) for daglig retraining av tabular ML og GPU-SKU-en NC6s_v3 for ukentlig retraining av computer vision-modeller.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#14",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "When you create resources for an Azure Machine Learning workspace, you also create resources for other Azure services. They are: Azure Container Registry basic account, Azure Blob Storage (general purpose v2), Azure Key Vault, Azure Monitor ... Each VM is billed per hour that it runs.",
"reason": "Den kanoniske «full billing model»-siden beskriver hele faktureringsmodellen uten NOEN edition/tier — «Azure ML Enterprise» finnes ikke (Basic/Enterprise-editionene er utgått); per-use compute-delen stemmer, men den navngitte SKU-en gjør ikke det.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 663,
"claim": "Azure ML Enterprise er inkludert i Azure-subscription og faktureres som per-use compute pricing.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/feedback-loops-continuous-improvement.md#16",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/ai-builder/credit-management",
"evidence_quote": "| Power Apps per app | 250 | Maximum = 1,000,000 AI Builder credits per tenant. Per app licenses purchased before November 2022, don't include any credits. |",
"reason": "Per user = 500 stemmer (Power Apps Premium/per user), men gjeldende rad gir Per app 250 kreditter — claimets «ingen kreditter inkludert» matcher kun den tidsstemplede legacy-regelen for lisenser kjøpt før november 2022; feedback loop-støtte per lisenstype er dessuten ikke dokumentert.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md",
"line": 670,
"claim": "Power Platform-lisensene gir følgende AI Builder-kreditter og feedback loop-støtte: Per User = 500 kreditter/mnd med feedback loop-støtte | Per App = ingen kreditter inkludert og ingen feedback loop-støtte (krever Per User) | AI Builder add-on = kreditter kjøpes ekstra, med feedback loop-støtte.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/genaiops-llm-specific-practices.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-information-retrieval",
"evidence_quote": "Semantic ranking works as a secondary reranking step after the initial BM25 or hybrid search.",
"reason": "Vector, full-text and hybrid are confirmed as search types, but the cited page maps semantic ranker differently - it is a reranking step applied after retrieval, and it is absent from the page's own Search types enumeration (vector, full-text, hybrid, manual multiple queries); one load-bearing part of the taxonomy is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md",
"line": 96,
"claim": "Retrieval-metodene i Azure AI Search er vector | full-text | hybrid | semantic ranker.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/genaiops-llm-specific-practices.md#6",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/fine-tuning-cost-management",
"evidence_quote": "After your model is trained, you can deploy it using one of the following hosting options: 1. Standard: pay per-token at the same rate as base model Standard deployments with an additional $1.70/hour hosting fee. Offers regional data residency guarantees.",
"reason": "The source lists four production hosting options for fine-tuned models (Standard, Global Standard, Regional Provisioned Throughput, Developer Tier) where Standard and Global Standard carry an SLA, so PTU is one option among several, not a requirement for production use.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md",
"line": 117,
"claim": "Fine-tuning krever PTU (provisioned throughput) for produksjonsbruk.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/genaiops-llm-specific-practices.md#13",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/deployments-overview",
"evidence_quote": "Foundry provides two deployment options: 1. Standard deployment in Foundry resources - For Foundry Models ... This option is the preferred and most capable deployment path. 2. Managed compute deployment (preview) - Available for all Open Source Software (OSS) models, including models from partner and community, and custom models.",
"reason": "The claim's organizing frame is superseded: current Foundry deployment runs through Standard deployment in Foundry resources or managed compute (billing by token usage or PTU), not via Managed Online Endpoints, which the Prompt Flow migration page treats as an Azure Machine Learning construct with no direct Foundry equivalent.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md",
"line": 164,
"claim": "Deployment i Microsoft Foundry skjer via Managed Online Endpoints med alternativene serverless | PTU | PAYG.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/genaiops-llm-specific-practices.md#16",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/azure-openai-token-limit-policy",
"evidence_quote": "Limit large language model API token usage ... The llm-token-limit policy prevents large language model (LLM) API usage spikes on a per key basis by limiting consumption of language model tokens to either a specified rate (number per minute), a quota over a specified period, or both.",
"reason": "The zone-redundant/multi-region part holds, but the load-bearing policy name does not: the URL for the Azure OpenAI-named policy now serves the renamed policy Limit large language model API token usage (llm-token-limit), and the API Management policy reference AI gateway table lists only Limit large language model API token usage and Emit large language model API token metrics - no policy named Limit Azure OpenAI API token usage.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md",
"line": 211,
"claim": "Azure API Management har innebygde Azure OpenAI-policyer «Limit Azure OpenAI API token usage» | «Emit metrics for consumption», og er sone-redundant og multi-region.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/governance-audit-ml-operations.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 23,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/governance-audit-ml-operations.md#19",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/admin/system-tables/",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side sier at Unity Catalog er inkludert i DBU-forbruket uten ekstra kostnad; den siterte siden omtaler kun gratis systemtabeller, og Databricks-prising ligger paa den JS-rendrede azure.microsoft.com/pricing-siden.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/governance-audit-ml-operations.md",
"line": 411,
"claim": "Databricks Unity Catalog er inkludert i DBU-forbruket uten ekstra kostnad.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/governance-audit-ml-operations.md#22",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/api-management-howto-llm-logs",
"evidence_quote": "",
"reason": "Verken den siterte siden eller genai-gateway-capabilities uttaler seg om lisens-/kostnadsinkludering av LLM-logging; APIM-prising ligger paa den JS-rendrede azure.microsoft.com/pricing-siden (genai-siden sier kun at AI gateway ikke er et separat tilbud og at kapabilitet varierer per tier - ikke en prisingspaastand).",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/governance-audit-ml-operations.md",
"line": 417,
"claim": "LLM-logging er inkludert i Azure API Management-lisensen.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/governance-audit-ml-operations.md#23",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/databricks/ldp/concepts/where-is-dlt",
"evidence_quote": "The product formerly known as Delta Live Tables (DLT) has been updated to Lakeflow pipelines.",
"reason": "Den kanoniske rename-siden sier live at DLT er oppdatert til Lakeflow pipelines, ikke Lakeflow Spark Declarative Pipelines; python-ref bekrefter: In Databricks documentation, the Databricks product is called Lakeflow pipelines, and the open-source framework it extends is Apache Spark Declarative Pipelines (SDP) - selve navnet er paastanden (R7 load-bearing carve-out), saa eksakt-verdi-regelen gjelder fullt ut.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/governance-audit-ml-operations.md",
"line": 506,
"claim": "Delta Live Tables er omdøpt til Lakeflow Spark Declarative Pipelines i Databricks-dokumentasjonen.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 31,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#19",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/batch",
"evidence_quote": "endpoint=\"/chat/completions\", # While passing this parameter is required, the system will read your input file to determine if the chat completions or responses API is needed.",
"reason": "The canonical enumerating page supports only chat completions and the Responses API; its Global Batch and Data Zone Batch model-availability tables list solely chat/reasoning models (gpt-5.x, gpt-4.1, gpt-4o, o3/o4-mini) with no embedding models, and the FAQ entry 'Can I use the batch API for embeddings models?' answers with a non-support statement - so the claimed embeddings and legacy completions support is absent.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 384,
"claim": "Azure OpenAI Batch API støtter chat completions | embeddings | completions.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#20",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-managed-online-endpoints-vm-sku-list?view=azureml-api-2",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states this workload-to-SKU recommendation; Standard_DS3_v2, Standard_NC6s_v3 and Standard_NC24s_v3 appear in the supported managed-online-endpoint SKU list and a deployment example, but nothing recommends them for small tabular / vision / large language model workloads, and PTU is an Azure OpenAI concept rather than an AML compute SKU.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 560,
"claim": "Anbefalte compute-SKU-er for inference er Standard_DS3_v2 (små tabulære modeller, CPU) | Standard_NC6s_v3 (deep learning vision, GPU) | Standard_NC24s_v3 eller PTU (store språkmodeller).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#21",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-endpoints?view=azureml-api-2",
"evidence_quote": "Azure Machine Learning supports standard deployments, online endpoints, and batch endpoints.",
"reason": "The claim's three-way frame is superseded: the current three top-level options are standard deployments, online endpoints and batch endpoints; Kubernetes is documented as a compute type ('Compute type | None (serverless) | Managed compute and Kubernetes | Managed compute and Kubernetes'), not a third endpoint category, and standard deployments are missing from the claim's set.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 623,
"claim": "Azure Machine Learning tilbyr tre deployment-alternativer: Managed Online Endpoints | Batch Endpoints | Kubernetes Endpoints.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#25",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-sql-edge/onnx-overview",
"evidence_quote": "Azure SQL Edge is retired as of September 30, 2025.",
"reason": "The page does document 'native scoring with the PREDICT T-SQL function', but the current effective state of the product is retirement, so presenting Azure SQL Edge in the present tense as an ONNX inferencing option matches a superseded state rather than today's.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 697,
"claim": "Azure SQL Edge bruker T-SQL-funksjonen PREDICT for native ONNX-scoring uten eksterne API-kall.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#27",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-onnx?view=azureml-api-2",
"evidence_quote": "",
"reason": "The cited ONNX page states no license, and a docs search surfaced no learn.microsoft.com page stating ONNX Runtime's MIT license or commercial-use terms; that licensing information lives in the GitHub repository, not on Learn, so the claim can be neither confirmed nor refuted here.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 827,
"claim": "ONNX Runtime er lisensiert under MIT License og er gratis til kommersiell bruk.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#28",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/windows/ai/new-windows-ml/overview",
"evidence_quote": "",
"reason": "Learn documents Windows ML as built into Windows and serviced through Windows Update, but no learn.microsoft.com page states any licensing or cost term for it, so the claim's load-bearing cost assertion ('uten ekstra lisenskostnad') cannot be confirmed or refuted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 832,
"claim": "Windows ML er inkludert i Windows uten ekstra lisenskostnad.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/inferencing-optimization-caching.md#29",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models?view=azureml-api-2",
"evidence_quote": "Image classification (multi-class and multi-label)",
"reason": "The canonical AutoML task-type enumeration is image classification, image classification multi-label, image object detection and image instance segmentation; 'binær' is absent as a task variety and the claim's parenthetical displaces multi-label, which the cited ONNX article itself supports with its own Multi-label image classification tab, so a stated load-bearing part is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md",
"line": 1037,
"claim": "AutoML computer vision-oppgaver med ONNX-støtte er: image classification (binær og multi-class) | object detection | instance segmentation.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/infrastructure-as-code-mlops.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/powershell/dsc/overview",
"evidence_quote": "Microsoft's Desired State Configuration (DSC) is a declarative configuration platform. With DSC, the state of a machine is described using a format that should be clear to understand even if the reader isn't a subject matter expert. Unlike imperative tools, with DSC the definition of an application environment is separate from programming logic that enforces that definition.",
"reason": "Deklarativ/imperativ-rammen og plasseringen av Bicep, ARM-templates og Terraform er grunnet (what-is-infrastructure-as-code + WAF OE:05-definisjonene), men den stated, lastbærende delen «PowerShell DSC = imperativt verktøy» motsies: Microsoft beskriver DSC som en deklarativ konfigurasjonsplattform og kontrasterer den eksplisitt mot imperative verktøy (også: «Configurations declare the state of target devices, rather than writing instructions for how to place devices in that state»).",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md",
"line": 39,
"claim": "IaC-verktøy deles i to hovedtyper: deklarative verktøy (Bicep — Microsofts DSL for Azure som kompilerer til ARM templates | ARM templates (JSON) — Azure Resource Managers native format | Terraform — multi-cloud med Azure provider) og imperative verktøy (Azure CLI-scripts med `az`-kommandoer | PowerShell DSC for VM-konfigurasjon).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/infrastructure-as-code-mlops.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-manage-workspace-terraform",
"evidence_quote": "The following table contains a list of resource providers required by Azure Machine Learning: Microsoft.MachineLearningServices | Microsoft.Storage | Microsoft.ContainerRegistry | Microsoft.KeyVault | Microsoft.Notebooks | Microsoft.ContainerService",
"reason": "Jeg hentet den kanoniske opplistende tabellen (bekreftet identisk pa bade Terraform- og ARM-mal-artikkelen), og Microsoft.Insights - som claimen pastar er pakrevd - star IKKE i den; Microsoft.Network er dessuten kun betinget (managed VNet), mens Microsoft.Notebooks og Microsoft.ContainerService mangler i claimen.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md",
"line": 458,
"claim": "Resource providers som må registreres for Azure ML IaC: Microsoft.MachineLearningServices | Microsoft.Storage | Microsoft.KeyVault | Microsoft.ContainerRegistry | Microsoft.Insights | Microsoft.Network.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/infrastructure-as-code-mlops.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/container-registry/container-registry-skus",
"evidence_quote": "Azure Container Registry offers three Pricing Plan options: Basic, Standard, and Premium.",
"reason": "Geo-replikeringsdelen holder (Premium adds features such as geo-replication), men den stated, lastbærende SKU-oppregningen holder ikke: claimen sier ACR tilbys i Basic og Premium, mens den kanoniske SKU-siden slar fast tre planer inkludert Standard - som «satisfies the needs of many production scenarios» og derfor er beslutningsendrende for kostnad.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md",
"line": 632,
"claim": "Azure Container Registry tilbys i SKU-ene Basic og Premium, der Premium brukes for geo-replikering i produksjon.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/infrastructure-as-code-mlops.md#16",
"judge_verdict": "not_grounded",
"rule": "R1",
"evidence_url": "https://learn.microsoft.com/azure/azure-vmware/sql-server-hybrid-benefit",
"evidence_quote": "Save up to 85% over standard pay-as-you-go rate using Windows Server and SQL Server licenses with Azure Hybrid Benefit.",
"reason": "To av tre deler er bekreftet - lisenstypeverdien Windows_Server (ARM: licenseType: Windows_Server; CLI: --set licenseType=Windows_Server) og kravet om eksisterende Windows Server-lisenser med Software Assurance - men den øvre grensen «opptil 40 %» finnes ikke pa noen learn.microsoft.com-side; Microsofts publiserte tak for Azure Hybrid Benefit er «up to 85%», sa den oppgitte ceilingen er ikke Microsofts dokumenterte verdi (R1, upper bound).",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md",
"line": 644,
"claim": "Azure Hybrid Benefit aktiveres i Terraform via license_type = \"Windows_Server\" og krever eksisterende Windows Server-lisenser; kan gi opptil 40 % lavere VM-kostnad.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#9",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states that Power Platform has (or lacks) built-in continuous LLM production evaluation; the negative gap assertion can be neither confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"line": 667,
"claim": "Power Platform har ingen built-in continuous evaluation for LLM i production (gap per feb 2026)",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#10",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states a Q2 2026 Copilot Studio roadmap item for native Microsoft Foundry evaluation integration; the forward-looking roadmap claim is unverifiable and uncontradicted.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"line": 687,
"claim": "Copilot Studio: ingen out-of-the-box production evaluation; Microsoft roadmap (Q2 2026) inkluderer native integrasjon med Microsoft Foundry evaluation",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/ai-red-teaming-agent",
"evidence_quote": "Supported attack strategies: UnicodeConfusable, UnicodeSubstitution, Url, Jailbreak, Indirect Jailbreak, Tense, Multi turn, Crescendo",
"reason": "The capability and jailbreak strategy hold, but the load-bearing strategy names prompt_injection and bias_elicitation are absent from the documented supported attack strategies, so a stated part is wrong.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"line": 421,
"claim": "azure.ai.evaluation tilbyr AIRedTeamingAgent for automatiserte adversarial scans (attack strategies: jailbreak, prompt_injection, bias_elicitation)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme",
"evidence_quote": "Built-in evaluators are out of box evaluators provided by Microsoft: ... GroundednessEvaluator, RelevanceEvaluator, ... ViolenceEvaluator, SexualEvaluator, ... QAEvaluator, ContentSafetyEvaluator",
"reason": "The canonical azure.ai.evaluation SDK enumeration lists evaluators and simulators but contains no PIIMaskingPreprocessor; the named class is absent, so the existence claim is not grounded.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"line": 744,
"claim": "azure.ai.evaluation tilbyr PIIMaskingPreprocessor med mask_types (email, phone, ssn, name)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/llm-evaluation-production.md#18",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme",
"evidence_quote": "Azure AI Evaluation client library for Python - version 1.18.2",
"reason": "The live SDK reference states version 1.18.2, superseding the claimed v1.17.0.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md",
"line": 1125,
"claim": "Azure AI Evaluation SDK versjon v1.17.0 (per research-dato 2026-06-19)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-fundamentals-overview.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/reliability/regions-list",
"evidence_quote": "Access to this region is restricted to support specific customer scenarios, such as disaster recovery within a specific geographic area. To request access to a restricted region for your Azure subscription, see Azure region access request process.",
"reason": "Norway East er en full region med tilgjengelighetssoner, men den kanoniske regionslisten merker Norway West som begrenset region — tilgang må søkes om og er forbeholdt scenarioer som katastrofegjenoppretting — så den andre bærende delen (Norway West er tilgjengelig for datalagring) motsies av kilden.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md",
"line": 264,
"claim": "Data må lagres i EU/Norge, og Azure-regionene Norway East og Norway West er tilgjengelige for dette.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-fundamentals-overview.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-use-serverless-compute?view=azureml-api-2",
"evidence_quote": "You can use it to run all types of jobs by using Azure Machine Learning studio, the Python SDK, and Azure CLI.",
"reason": "Begge bærende deler svikter: siden er merket v2 (current) uten preview- eller nyhetsmerking og serverless er standard når compute utelates (If no compute target is specified for command, sweep, and AutoML jobs, the compute defaults to serverless compute), og den anbefales for alle jobbtyper inkludert distribuert trening — ikke spesifikt for mindre workloads.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md",
"line": 305,
"claim": "Serverless compute i Azure Machine Learning omtales som en ny funksjon, anbefalt for mindre workloads.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-fundamentals-overview.md#17",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/mlops-maturity-model",
"evidence_quote": "The MLOps maturity model encompasses five levels of technical capability.",
"reason": "Modellen har fem nivåer med navnene No MLOps, DevOps but no MLOps, Automated training, Automated model deployment og Full MLOps automated operations; verken antallet (claimen sier fire) eller navnene (Manual, Partial automation, Full CI/CD, Full MLOps with monitoring) finnes på siden — rammen claimen beskriver er erstattet.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md",
"line": 351,
"claim": "MLOps maturity model beskrives med trinnene Manual | Partial automation | Full CI/CD | Full MLOps with monitoring.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 31,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-security-access-control.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-setup-customer-managed-keys?view=azureml-api-2",
"evidence_quote": "Set Key type to RSA. We recommend selecting at least 3072 for the RSA key size.",
"reason": "Nøkkeltypen RSA er instruert, men 3072 bit er en anbefaling (We recommend selecting at least 3072), ikke et krav; claimens lastbærende del må være minimum 3072 bit gjør en anbefaling om til en obligatorisk grense.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"line": 304,
"claim": "CMK-nøkkelen for Azure ML workspace må være en RSA-nøkkel på minimum 3072 bit.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-security-access-control.md#16",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-data-encryption?view=azureml-api-2",
"evidence_quote": "",
"reason": "Den siterte siden sier kun at Azure Machine Learning uses Transport Layer Security (TLS) uten å oppgi versjon; ingen Learn-side fastslår TLS 1.2 for alle de fire kommunikasjonsveiene (kun Kubernetes online endpoints er eksplisitt dokumentert med TLS 1.2), og ingen side oppgir en motstridende versjon.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"line": 340,
"claim": "All kommunikasjon i Azure ML bruker TLS 1.2 (workspace til storage account, workspace til compute, Studio til workspace API og inference-klienter til online endpoints).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-security-access-control.md#22",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/compliance/offerings/cloud-services-in-audit-scope",
"evidence_quote": "",
"reason": "Learn oppgir ikke tjenestenivå-omfanget: siden om tjenester i revisjonsomfang henviser til Appendiks A og B i et PDF-dokument på Service Trust Portal, så verken ISO 27001, ISO 27018 eller SOC 2 Type II bekreftes eller avkreftes for Azure Machine Learning på learn.microsoft.com.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"line": 632,
"claim": "Azure Machine Learning er sertifisert mot ISO 27001 | ISO 27018 | SOC 2 Type II.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-security-access-control.md#23",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/reference-machine-learning-cloud-parity?view=azureml-api-2",
"evidence_quote": "",
"reason": "Ingen Learn-side enumererer regiontilgjengelighet for Azure Machine Learning i offentlig sky (cloud parity-siden dekker Azure Government og 21Vianet); den autoritative listen ligger på azure.microsoft.com Products available by region, utenfor learn.microsoft.com.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"line": 634,
"claim": "Azure Machine Learning er tilgjengelig i norsk region (Oslo/Norway East).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-security-access-control.md#24",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/key-vault/general/overview",
"evidence_quote": "",
"reason": "Key Vault har kun tierne standard og premium, og begge oppgis med customer-managed keys som bruksområde, men verken Azure ML-dokumentasjonen eller Key Vault-sidene stiller et tier-krav for CMK, og lisenspåstanden om managed identities, RBAC og Private Link står ikke på noen Learn-side.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md",
"line": 662,
"claim": "Customer-managed keys i Azure ML krever Azure Key Vault i tier standard eller premium; managed identities, RBAC og Private Link krever ingen egen lisens ut over Azure-abonnementet/infrastrukturkostnad.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 27,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/devops/artifacts/start-using-azure-artifacts",
"evidence_quote": "Azure Artifacts supports multiple package types, including NuGet, npm, Python, Maven, Cargo, and Universal Packages.",
"reason": "NuGet og pip (Python) stemmer, men conda finnes ikke i den kanoniske opplistingen av pakketyper — heller ikke i Feature availability-tabellen (NuGet, dotnet, npm, Maven, Gradle, Python, Cargo, Universal Packages), saa conda-feeden er ikke tilbudt.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 153,
"claim": "Azure Artifacts tilbyr pakkefeeds for NuGet | pip | conda til ML-biblioteker og delte komponenter.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/devops/release-notes/features-timeline-released#azure-devops-services",
"evidence_quote": "June 30 2025 | Azure DevOps MCP Server public preview",
"reason": "Naturlig-spraak-delen stemmer (what-is-azure-devops viser promptene Summarize the current sprint status, List all work items that are blocked og Show the success rate for all pipelines), men den baerende dateringen er feil: MCP-serveren gikk i public preview 30. juni 2025 (sprint 258) og ble GA i sprint 264 i 2025 — ikke en 2026-funksjon.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 155,
"claim": "Azure DevOps MCP Server gir naturlig-språk-spørringer for prosjektstyring (f.eks. «Summarize sprint status», «List blocked work items», «Show pipeline success rates») og er en 2026-funksjon.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#10",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-devops-machine-learning",
"evidence_quote": "- task: AzureMLJobWaitTask@1",
"reason": "Den kanoniske siden for Azure Pipelines mot Azure Machine Learning dokumenterer kun AzureMLJobWaitTask@1 fra Machine Learning-utvidelsen, og modellutrulling skjer via pipeline-YAML og az ml CLI (deploy-online-endpoint-pipeline.yml paa den siterte siden); ingen learn-side nevner en oppgave AzureMLModelDeploy@1.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 204,
"claim": "Azure Pipelines-oppgaven for modellutrulling til Azure Machine Learning er AzureMLModelDeploy@1.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/devops/artifacts/start-using-azure-artifacts",
"evidence_quote": "Azure Artifacts supports multiple package types, including NuGet, npm, Python, Maven, Cargo, and Universal Packages.",
"reason": "Private Python-feeds stemmer, men conda-pakkehosting finnes ikke i pakketype-opplistingen, og Docker image registry (Azure Container Registry) samt dependency security scanning er ikke Azure Artifacts-kapabiliteter — kapabilitetslisten paa what-is-azure-devops er upstream sources, versjonering, tilgangskontroll, build-integrasjon og kodesoek.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 262,
"claim": "Azure Artifacts har kapabilitetene private Python-pakkefeeds | conda-pakkehosting | Docker image registry (Azure Container Registry) | dependency security scanning.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#17",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/machine-learning-operations-v2",
"evidence_quote": "| Model tester | R | R, KVR | R | R | R | R | LAR | MR |",
"reason": "Owner-delen stemmer (kun platform technical support og CI/CD processes har O i produksjonstabellen), men RBAC-tabellene gir data scientists ADS (Machine Learning Data Scientist) — ikke Contributor — paa dev-workspacet, og model testers har Reader i preproduksjon og ingen workspace-rolle i produksjonsmiljoeene (som ifoelge siden inkluderer staging og test), aldri Contributor.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 425,
"claim": "Anbefalt RBAC for Azure ML-workspaces: dev-workspace - data scientists har Contributor og data analysts har Reader; staging-workspace - model testers har Contributor og data scientists har Reader; produksjons-workspace - kun CI/CD-prosesser og platform support har Owner.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#19",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/concepts/prompt-flow",
"evidence_quote": "Prompt flow in Microsoft Foundry and Azure Machine Learning will be retired on April 20, 2027. Prompt flow is no longer recommended for new development.",
"reason": "Team-samarbeid rundt flows er bekreftet (Debug, share, and iterate your flows with ease through team collaboration), men rammen er superseded: dokumentasjonen plasserer prompt flow i Microsoft Foundry portal (classic) og Azure Machine Learning studio — produktnavnet Azure AI Studio finnes ikke lenger — og prompt flow er dessuten under utfasing med frist 2027-04-20.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 494,
"claim": "Delte prompt flows for team-samarbeid ligger i Azure AI Studio.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#21",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/devops/organizations/security/access-levels",
"evidence_quote": "Stakeholders use drag-and-drop to create and change work items, but they can only change the State field on cards.",
"reason": "Fem gratis brukere med Basic og ubegrenset antall gratis stakeholders stemmer, men den baerende delen read-only-tilgang er feil: den kanoniske access-levels-siden gir Stakeholder tilgang til View My Work Items med add and modify work items, samt oppretting og endring av kort paa boards.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 541,
"claim": "Azure DevOps gratis tier gir opptil 5 brukere med Basic access og ubegrenset antall stakeholders med read-only-tilgang.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#24",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/devops/organizations/projects/migrate-public-project",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side oppgir ubegrensede minutter; den naermeste formuleringen sier bare free runner minutes for public repositories uten tallfesting — GitHub-kvoter dokumenteres paa docs.github.com, saa verdien kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 554,
"claim": "GitHub Actions gir ubegrenset antall minutter for offentlige repositories.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/mlops-teams-collaboration-tools.md#25",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/power-platform/alm/devops-github-actions",
"evidence_quote": "",
"reason": "En learn-side bekrefter 2 000 action minutes per maaned gratis, men ingen learn-side oppgir 500 MB artefaktlagring eller knytter tallene til private repositories — den baerende lagringsverdien kan ikke verifiseres paa learn.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md",
"line": 557,
"claim": "GitHub Actions gratis tier for private repositories gir 2000 minutter per måned og 500 MB lagring for artefakter.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/model-deployment-strategies-azure.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/monitor-azure-machine-learning-reference?view=azureml-api-2",
"evidence_quote": "**Requests Per Minute**The number of requests sent to online endpoint within a minute | `RequestsPerMinute`",
"reason": "RequestLatency og CpuUtilizationPercentage finnes i den kanoniske metrikklisten, men RequestsPerSecond gjør det ikke — metrikken heter `RequestsPerMinute`; ett bærende (og ordrett kopierbart) metrikknavn er dermed feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md",
"line": 538,
"claim": "Azure Monitor eksponerer metrikkene RequestLatency | RequestsPerSecond | CpuUtilizationPercentage for Azure ML online endpoint deployments.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-deployment-strategies-azure.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-troubleshoot-online-endpoints?view=azureml-api-2",
"evidence_quote": "If your bandwidth usage exceeds the limit, your request is delayed. ... Two response trailers are returned if the bandwidth limit is enforced: `ms-azureml-bandwidth-request-delay-ms` ... `ms-azureml-bandwidth-response-delay-ms`",
"reason": "5 MBps-delen stemmer, men den andre bærende delen er feil: kilden sier at overskridelse av båndbreddegrensen forsinker forespørselen (med delay-trailere), mens HTTP 429 er dokumentert for «Too many pending requests» og rate-limit på requests per second — ikke for båndbredde.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md",
"line": 799,
"claim": "Default bandwidth quota for et Azure ML online endpoint er 5 MBps per endpoint; overskridelse gir throttling med HTTP 429-feil.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-deployment-strategies-azure.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "",
"reason": "Ingen Learn-side oppgir at Azure ML-workspacet er gratis eller at man kun betaler for compute/storage; kostnadssiden lister avhengige ressurser (ACR, Blob Storage, Key Vault, Azure Monitor, load balancer, VNet, båndbredde) og henviser prising til den JS-rendrede azure.microsoft.com-siden. (Kun delpåstanden om ingen tilleggsavgift er dekket: «you pay for the compute and networking charges. There's no added surcharge».)",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md",
"line": 817,
"claim": "Azure Machine Learning workspace er gratis (man betaler kun for underliggende compute/storage), og alle deployment-funksjoner som blue-green, mirroring og A/B er inkludert.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 21,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/model-drift-performance-degradation.md#18",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-data-collection?view=azureml-api-2",
"evidence_quote": "",
"reason": "Verken den siterte konseptsiden, concept-data-collection eller concept-plan-manage-cost sier noe om at Data Collector er kostnadsfri eller inkludert i endpoint-kostnaden; prisinformasjon er ikke oppgitt på noen hentet Learn-side.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md",
"line": 457,
"claim": "Azure ML Data Collector medfører ingen ekstra kostnad – den er inkludert i endpoint-kostnaden.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-drift-performance-degradation.md#19",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "",
"reason": "Kostnadssiden beskriver hvilke ressurser som påløper kostnader sammen med workspacet, men ingen hentet Learn-side slår fast at workspace/Event Grid er uten lisenskostnad eller at Azure Monitor er inkludert i subscriptionen slik claimet formulerer det.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md",
"line": 470,
"claim": "Azure ML Workspace har ingen lisenskostnad (pay-per-use for compute/storage), Event Grid har ingen lisenskostnad (pay-per-event), og Azure Monitor er inkludert i Azure-subscriptions.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-drift-performance-degradation.md#21",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/databricks/mlflow3/genai/eval-monitor/concepts/judges/",
"evidence_quote": "| `RelevanceToQuery` | ... | `RetrievalRelevance` | ... | `Safety` | ... | `RetrievalGroundedness` | ... | `Correctness` | ... | `RetrievalSufficiency` | ... | `Guidelines` |",
"reason": "Selve kapabiliteten (samme scorere i utvikling og produksjon) er grunnet, men de navngitte scorerne er lastbærende SDK-identifikatorer: den kanoniske oppregningen av innebygde judges inneholder RetrievalGroundedness og RelevanceToQuery - ingen scorer heter Groundedness eller Relevance i MLflow 3 (de navnene tilhører Azure ML sitt prompt flow GenAI-signal, ikke MLflow-scorerne).",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md",
"line": 684,
"claim": "MLflow 3 production monitoring gjenbruker utviklings-scorerne Groundedness og Relevance på produksjonstraces.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#1",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators",
"evidence_quote": "Similarity | AI-assisted textual similarity measurement.",
"reason": "Gjeldende Foundry-enumerasjon navngir metrikken «Similarity» (SDK-klasse SimilarityEvaluator, nøkkel «similarity»); «GPT similarity» er den utgåtte Prompt Flow-/gpt_-prefiks-benevnelsen, så claimets ramme er en omdøpt/erstattet metrikk.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 37,
"claim": "AI-assisterte kvalitetsmetrikker i Microsoft Foundry omfatter Groundedness | Relevance | Coherence | Fluency | GPT similarity, krever en judge-modell (GPT-3.5+/GPT-4), og kun GPT similarity krever ground truth.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/risk-safety-evaluators",
"evidence_quote": "Unlike LLM-as-judge evaluators such as coherence and fluency, these evaluators run against Microsoft's hosted safety models.",
"reason": "De seks risikonavnene og «krever ikke ground truth» (required inputs: query, response) holder, men den bærende delen «kjøres av en Foundry-hostet GPT-4» motsies: siden sier tjenesten «employs a set of language models» / «hosted safety models» og kontrasterer dem eksplisitt mot GPT-baserte LLM-as-judge-evaluatorer.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 39,
"claim": "Risk & Safety-metrikker i Microsoft Foundry omfatter Self-harm | Hateful content | Violence | Sexual content | Protected material | Indirect attack, krever ikke ground truth, og kjøres av en Foundry-hostet GPT-4.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#4",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app?view=foundry-classic",
"evidence_quote": "**Traces** | Evaluates agent interactions already captured in Application Insights. Select the agent and time range, and the portal retrieves the matching traces for evaluation.",
"reason": "Steg 1-tabellen «Select evaluation target» lister fire mål — Agent, Model, Dataset OG Traces — så den eksakte påstanden om «tre evalueringsmål» er superseded.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 43,
"claim": "Microsoft Foundry støtter tre evalueringsmål: Model | Agent | Dataset.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators",
"evidence_quote": "| Relevance | `query`, `response` | `deployment_name` |",
"reason": "Flere deler stemmer (Groundedness med context, Similarity med ground truth, NLP-metrikker med response+ground truth, safety med query+response), men den bærende delen «Relevance krever query + response + context» motsies — RAG-evaluatortabellen krever kun query og response for Relevance.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 51,
"claim": "Data mapping-krav for Foundry-evaluering: Groundedness og Relevance krever query + response + context; Coherence og Fluency krever query + response; GPT similarity krever query + response + ground truth; F1/BLEU/ROUGE/METEOR krever response + ground truth; safety-metrikker krever query + response.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#6",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/how-to/develop/evaluate-sdk",
"evidence_quote": "",
"reason": "gpt-4o er dokumentert som gyldig judge-deployment, men ingen hentet learn.microsoft.com-side oppgir api_version-verdien 2024-06-01 — model_config-eksemplene bruker gjennomgående miljøvariabler (api_version=os.environ.get(\"AZURE_API_VERSION\")), så verken bekreftelse eller motbevis finnes.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 80,
"claim": "Azure AI Evaluation SDK konfigurerer judge-modellen mot Azure OpenAI med api_version 2024-06-01 og azure_deployment gpt-4o.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#8",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/eval-monitor/concepts/scorers",
"evidence_quote": "Built-in judges also include **Guidelines judges**, built-in judges that check whether responses pass or fail custom natural-language rules, such as style or factuality guidelines.",
"reason": "Siden strukturerer scorers i FIRE tilnærminger (Built-in judges, Custom judges, Code-based scorers, Third-party scorers); Guidelines judges og multi-turn judges er undertyper av built-in judges, og Third-party scorers mangler helt i claimet — claimets fem-type-ramme er erstattet.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 129,
"claim": "MLflow 3 har fem scorer-typer: Built-in judges | Guidelines judges | Custom LLM judges | Code-based scorers | Multi-turn judges.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/eval-monitor/concepts/judges/",
"evidence_quote": "RelevanceToQuery, RetrievalRelevance, Safety, RetrievalGroundedness, Correctness, RetrievalSufficiency, Guidelines, ExpectationsGuidelines, ToolCallCorrectness, ToolCallEfficiency",
"reason": "«Available judges»-tabellen på den kanoniske Built-in LLM judges-siden lister disse ti; verken «Fluency» eller «Equivalence» finnes der — fraværet i den enumererende siden er bevis mot eksistens-påstanden.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 133,
"claim": "MLflow 3 built-in judges omfatter Correctness | RetrievalGroundedness | Safety | RelevanceToQuery | Fluency | Equivalence.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#18",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network",
"evidence_quote": "These regions support the following safety evaluators: Hate and unfairness, Sexual, Violent, Self-harm, Indirect attack, Code vulnerabilities, and Ungrounded attributes.",
"reason": "Den kanoniske regionlisten for risk- og safety-evaluatorer er East US 2, North Central US, France Central, Sweden Central, Switzerland West og Australia East — UK South står ikke der, og claimets «kun»-liste utelater tre faktiske regioner.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 384,
"claim": "AI-assisterte safety-metrikker er kun hostet i regionene East US 2 | France Central | UK South | Sweden Central.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#19",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/confidential-computing/overview-azure-products",
"evidence_quote": "",
"reason": "Den siterte observability-siden nevner ikke confidential computing, og confidential-computing-sidene omtaler VM-/GPU-SKU-er (NCCadsH100v5 m.fl.) uten å si noe om GA-status for LLM judges — påstanden kan verken bekreftes eller motbevises mot learn.microsoft.com.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 405,
"claim": "Azure confidential computing er ikke GA for LLM judges.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#20",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/observability",
"evidence_quote": "",
"reason": "Den siterte siden sier bare at observability-funksjoner «are billed based on consumption as listed in our Azure pricing page» og peker videre til den JS-rendrede prissiden; ingen learn-side slår fast at plattformen er uten lisenskostnad eller at man kun betaler compute/LLM-tokens.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 428,
"claim": "Microsoft Foundry har ingen lisenskostnad for selve plattformen — pay-as-you-go der man kun betaler for compute/LLM-tokens.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#21",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/databricks/admin/account-settings/account",
"evidence_quote": "Azure Databricks is available with two pricing options, Standard and Premium, which offer features for different types of workloads.",
"reason": "Azure Databricks har prisnivåene Standard, Premium (og Trial ved opprettelse) — noe «Enterprise-tier» finnes ikke i den kanoniske enumerasjonen, så tier-påstanden er feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 430,
"claim": "MLflow 3 er inkludert i Databricks-abonnement på Premium- eller Enterprise-tier.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-evaluation-frameworks.md#22",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme?view=azure-python",
"evidence_quote": "",
"reason": "Readme-siden lenker til kildekode og PyPI-pakken, men ingen hentet learn.microsoft.com-side oppgir lisenstype (MIT) eller at SDK-en er gratis å bruke.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md",
"line": 431,
"claim": "Azure AI Evaluation SDK er open source under MIT-lisens og gratis å bruke.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 23,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/how-to-manage-registries?view=azureml-api-2",
"evidence_quote": "",
"reason": "Hverken registry-siden, MLflow-modellregistersiden eller cloud-parity-tabellen merker modellversjonering/registry-håndtering med GA- eller preview-status; fravær av preview-banner er ingen positiv GA-påstand.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 4,
"claim": "Model versioning og registry management i Azure Machine Learning er merket som GA (generelt tilgjengelig).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-share-models-pipelines-across-workspaces-with-registries?view=azureml-api-2",
"evidence_quote": "The registry resource's system-assigned managed identity has `AcrPull` permission on the Azure Container Registry (ACR) instance associated with that registry. When a workspace compute needs to pull an environment image, the AzureML Registry creates and returns an ACR token with an appropriate scope map allowing the image to be pulled by the workspace compute. Neither the workspace nor the compute managed identity has direct access to the registry's ACR.",
"reason": "ACR-token-delen stemmer, men den andre bærende delen er motsagt: AcrPull ligger på registryets egen system-tildelte identitet, og siden sier eksplisitt at verken workspace- eller compute-identiteten har direkte ACR-tilgang - workspace-compute får altså ikke AcrPull-rollen.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 82,
"claim": "Tilgangskontroll mot Azure ML Registry er ACR token-basert, og workspace-compute får `AcrPull`-rollen via registryets managed identity.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-manage-models-mlflow?view=azureml-api-2",
"evidence_quote": "Organizational registries aren't supported for model management with MLflow.",
"reason": "Den andre bærende delen er motsagt: organisasjonsregistre støttes ikke for modellhåndtering via MLflow, så azureml://registries/<navn> er en Azure ML asset-URI (CLI/SDK), ikke en MLflow registry-URI; Learn sier dessuten at MLflow-registry-URI-en har samme format og verdi som workspace-ets tracking-URI, ikke formen azureml://<workspace>.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 263,
"claim": "MLflow Registry URI i Azure ML har to former: `azureml://<workspace>` for workspace-registry | `azureml://registries/<registry-name>` for Azure ML Registry.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#19",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/reliability/regions-list",
"evidence_quote": "Access to this region is restricted to support specific customer scenarios, such as disaster recovery within a specific geographic area. To request access to a restricted region for your Azure subscription, see Azure region access request process.",
"reason": "Norway West er i Europa-tabellen merket med nettopp dette restricted-ikonet (kun Norway East er en åpen region), så Norway West kan ikke uten videre velges som registry-region for data residency; ingen Learn-side lister dessuten Norway East/West som støttede Azure ML Registry-regioner - den ene bærende delen faller.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 344,
"claim": "Azure ML Registry kan konfigureres i regionene Norway East og Norway West for data residency.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#20",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "Bandwidth charges reflect usage; the more data transferred, the greater the charge.",
"reason": "Andre bærende del er motsagt: kostnadssiden lister Azure Container Registry, Key Vault, Azure Monitor, load balancer (rundt $0.33/dag per compute instance), virtuelt nettverk/private endpoints og båndbredde som kostnader i tillegg til compute og storage - kun compute og storage koster stemmer ikke.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 428,
"claim": "Azure Machine Learning er inkludert i Azure-abonnementet uten ekstra lisenskostnad; kun compute og storage koster.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/model-versioning-registry-management.md#21",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-mlflow?view=azureml-api-2",
"evidence_quote": "",
"reason": "Learn omtaler MLflow som an open-source framework / the largest open source AI engineering platform, men ingen learn.microsoft.com-side oppgir Apache 2.0-lisensen eller at MLflow er gratis - lisensverdien kan ikke bekreftes eller avkreftes.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md",
"line": 429,
"claim": "MLflow er open source under Apache 2.0-lisens og gratis.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/monitoring-observability-ml-systems.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 25,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/monitoring-observability-ml-systems.md#24",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/logs/manage-access",
"evidence_quote": "Built-in roles ... Privileged Monitoring Data Reader ... Log Analytics Data Reader ... Log Analytics Reader ... Log Analytics Contributor ... The /read permission is usually granted from a role that includes */read or * permissions, such as the built-in Reader and Contributor roles.",
"reason": "Den kanoniske siden for tilgangsstyring på Log Analytics workspace lister Reader/Contributor, Log Analytics Reader/Contributor/Data Reader og Privileged Monitoring Data Reader, men Monitoring Metrics Publisher er fraværende - den rollen gir kun Microsoft.Insights/Metrics/Write (publisering av metrikker) og er ikke en tilgangsrolle for Log Analytics-workspace, så én bærende del av oppramsingen er feil.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/monitoring-observability-ml-systems.md",
"line": 423,
"claim": "RBAC-roller for tilgangskontroll på Log Analytics workspace: Reader | Contributor | Log Analytics Reader | Monitoring Metrics Publisher.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/mlops-genaiops/monitoring-observability-ml-systems.md#25",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-model-monitoring?view=azureml-api-2",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side omtaler en Model Monitoring v3 eller en Q2 2026-roadmap; konseptsiden og how-to-sidene beskriver kun dagens signaler, og Learn publiserer ikke produktroadmaps, så påstanden kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/monitoring-observability-ml-systems.md",
"line": 663,
"claim": "Azure ML Model Monitoring v3 er på roadmap for Q2 2026.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/prompt-flow-production-deployment.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "pass",
"claim_count": 13,
"verified": "2026-07-18",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-engineering/references/mlops-genaiops/responsible-ai-mlops-integration.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/mlops-genaiops/responsible-ai-mlops-integration.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2",
"evidence_quote": "",
"reason": "Verken den siterte siden eller kostnadssiden (som lister ACR, Blob Storage, Key Vault, Azure Monitor og compute som kostnadsdrivere) sier noe om at Model Registry er uten ekstrakostnad; påstanden kan verken bekreftes eller motbevises på learn.microsoft.com.",
"file": "skills/ms-ai-engineering/references/mlops-genaiops/responsible-ai-mlops-integration.md",
"line": 595,
"claim": "Model Registry er inkludert i Azure Machine Learning-workspace uten ekstrakostnad.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 21,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/agentic-rag-patterns.md#1",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-rag",
"evidence_quote": "The Semantic Kernel Agent RAG functionality is experimental, subject to change, and will only be finalized based on feedback and evaluation.",
"reason": "Claimen sier GA, men den siterte siden merker Semantic Kernel Agent RAG som eksperimentell og endringsutsatt - motsatt status.",
"file": "skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md",
"line": 6,
"claim": "Semantic Kernel-baserte agentic RAG-funksjoner har status GA (generelt tilgjengelig).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/agentic-rag-patterns.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-orchestration/",
"evidence_quote": "| Magentic | Group chat-like orchestration inspired by MagenticOne. | Complex, generalist multi-agent collaboration. |",
"reason": "Siden lister fem støttede orkestreringsmønstre - Concurrent, Sequential, Handoff, Group Chat og Magentic - så claimens uttalte antall fire er en bærende del som motsies av kilden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md",
"line": 176,
"claim": "Semantic Kernel har fire agent orchestration patterns: Sequential | Concurrent | Handoff | Group Chat.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/agentic-rag-patterns.md#21",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns",
"evidence_quote": "| Magentic | Plan-build-execute model. Manager agent builds and adapts a task ledger. | Manager agent assigns and reorders tasks dynamically. | Open-ended problems that don't have a predetermined solution path. | Slow to converge. Stalls on ambiguous goals. |",
"reason": "Jeg hentet den kanoniske enumererende siden (Choose a pattern-tabellen): mønstrene er Sequential, Concurrent (også kalt parallel/fan-out), Group chat, Handoff og Magentic - verken supervisor eller autonomous loop finnes der, og claimen mangler group chat, handoff og magentic.",
"file": "skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md",
"line": 326,
"claim": "AI Agent Design Patterns (Azure Architecture Center) omfatter mønstrene: sequential (pipeline) | parallel fanout | supervisor | autonomous loop.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/azure-ai-search-setup.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "Each index supports up to the following number of documents: 24 billion on Basic, S1, S2, and S3; 2 billion on S3 HD; 288 billion on L1; 576 billion on L2",
"reason": "Per-tier index counts (3/15/50/200/200/10) match the current Index limits table, but the claim per-tier document caps (15M/60M/120M/240M per partition) are legacy values superseded by the current flat 24-billion-per-index document limit - a load-bearing part is contradicted.",
"file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md",
"line": 37,
"claim": "Tier-grenser: Free 10 000 docs / 3 indekser | Basic 15M docs / 15 indekser | S1 60M per partition / 50 indekser | S2 120M per partition / 200 indekser | S3 240M per partition / 200 indekser | L1/L2 120M/240M per partition / 10 indekser",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/azure-ai-search-setup.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-region-support",
"evidence_quote": "You can create an Azure AI Search service in any of the following Azure public regions. ... [Europe: France Central, Germany West Central, Italy North, Norway East, North Europe, Poland Central, Spain Central, Sweden Central, Switzerland North, Switzerland West, UK South, UK West, West Europe]",
"reason": "Norway East appears in the canonical region enumeration but Norway West is absent - the claim that Azure AI Search supports Norway West is contradicted by its absence, so one load-bearing part of the multi-part region claim fails.",
"file": "skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md",
"line": 300,
"claim": "Azure AI Search støtter Norway East og Norway West regioner (data lagres kun i Norge, ingen geo-replikering utenfor EU/EEA)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/chunking-strategies.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 27,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/chunking-strategies.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-textsplit",
"evidence_quote": "The minimum value is 300, the maximum is 50000, and the default value is 5000.",
"reason": "Default for maximumPageLength er 5000 tegn (chunk-artikkelen sier også uttrykkelig 5,000 characters (the default)), ikke 2000; ekvivalensen 2000 tegn ca. 512 tokens er riktig som anbefaling, men den løftebærende default-verdien er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/chunking-strategies.md",
"line": 49,
"claim": "Text Split skill-parameteren `maximumPageLength` har default 2000 tegn, som tilsvarer omtrent 512 tokens.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/chunking-strategies.md#7",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-textsplit",
"evidence_quote": "",
"reason": "Parametertabellen oppgir defaults for maximumPageLength, maximumPagesToTake, defaultLanguageCode og unit, men ingen default for pageOverlapLength - kun at verdien 0 gir ingen overlapp; heller ikke SDK-referansene oppgir en default, og ingen Learn-side motsier 0.",
"file": "skills/ms-ai-engineering/references/rag-architecture/chunking-strategies.md",
"line": 50,
"claim": "Text Split skill-parameteren `pageOverlapLength` har default 0, altså ingen overlapp mellom chunks.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/chunking-strategies.md#22",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-document-intelligence-layout",
"evidence_quote": "",
"reason": "Learn oppgir ingen regionliste for Document Intelligence - både skill-siden og tjenesteoversikten viser til azure.com Product availability by region; verken West Europe-tilgjengeligheten eller fraværet i Norge kan bekreftes eller motbevises på Learn.",
"file": "skills/ms-ai-engineering/references/rag-architecture/chunking-strategies.md",
"line": 253,
"claim": "Document Intelligence er tilgjengelig i West Europe, altså i EU, men ikke i Norge spesifikt.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/chunking-strategies.md#24",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "",
"reason": "Learn oppgir bare at tredjegenerasjons embedding-modeller gir bedre flerspråklig gjenfinning målt med MIRACL; ingen Learn-side lister støttede språk for text-embedding-3, så norsk kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/chunking-strategies.md",
"line": 271,
"claim": "Embedding-modellene i text-embedding-3-serien støtter norsk.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/citation-tracking.md#3",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/openai/references/on-your-data",
"evidence_quote": "Azure OpenAI On Your Data is deprecated and approaching retirement. The service will be retired on October 14, 2026",
"reason": "The claim asserts 'On Your Data' with citation annotations is GA, but the live page states the service is deprecated and retires October 14, 2026 with Microsoft recommending migration to Foundry Agent Service — a superseded status a reader would act on.",
"file": "skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md",
"line": 26,
"claim": "Classic RAG (Azure AI Search + Azure OpenAI, 'On Your Data' med citation annotations) er GA",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/citation-tracking.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/rag-evaluators",
"evidence_quote": "Groundedness Pro uses the Azure AI Content Safety service and returns a boolean result instead of a numeric score",
"reason": "The AACS-delivery part holds, but the load-bearing 'threshold-based scoring' part is contradicted: the live page reserves 'Pass/Fail based on threshold (1-5 scale)' for the other evaluators and states Groundedness Pro returns a boolean True/False instead of a numeric score.",
"file": "skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md",
"line": 213,
"claim": "Groundedness Pro: threshold-basert scoring, leveres av Azure AI Content Safety (per evaluerings-kall)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/agentic-retrieval-overview",
"evidence_quote": "Some agentic retrieval features are generally available in the 2026-04-01 REST API via programmatic access.",
"reason": "Påstandens andre bærende del — «Preview for agentic retrieval» — er superseded: knowledge bases og utvalgte knowledge sources er nå generelt tilgjengelige i 2026-04-01 REST API, så agentic retrieval er ikke lenger ren Preview.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 4,
"claim": "Contextual Retrieval har status GA for custom skill-mønsteret og Preview for agentic retrieval.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#2",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/cognitive-search-custom-skill-interface",
"evidence_quote": "",
"reason": "Hver enkeltkomponent finnes på Learn (Custom Web API skill, Azure OpenAI GPT-4o, Text Merge skill, Azure OpenAI Embedding skill), men ingen learn.microsoft.com-side oppgir denne fire-komponents-dekomponeringen av kontekstuell prefiks-generering — den er forfatterens egen arkitektursammensetning.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 39,
"claim": "Kontekstuell prefiks-generering består av fire komponenter: Custom Web API Skill (Azure Function som mottar chunk + metadata og returnerer kontekstuell prefiks) | LLM (GPT-4o) | Text Merge Skill | Embedding Skill.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#3",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/cognitive-search-create-custom-skill-example",
"evidence_quote": "",
"reason": "Microsofts custom skill-eksempel er et C#-eksempel som wrapper Bing Entity Search API og inneholder ingen Azure OpenAI-klient; verken den siden eller Azure OpenAI API-livssyklussiden oppgir api_version «2024-10-01-preview» for et custom skill-eksempel, og versjonsstrengen er heller ikke motbevist.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 88,
"claim": "Azure OpenAI-klienten i custom skill-eksempelet bruker api_version «2024-10-01-preview».",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#6",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/azure-functions/functions-overview",
"evidence_quote": "| [Consumption plan](consumption-plan) | Legacy serverless plan (Windows only). Use the Flex Consumption plan for new apps. |",
"reason": "Påstanden fester hostingen til Azure Functions consumption plan med Python/C#, men Learn merker nå Consumption som en legacy-plan som kun er Windows — der Python ikke støttes — og henviser nye apper til Flex Consumption; SKU-en påstanden oppgir er dermed en utgått rad.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 201,
"claim": "Custom skill hostes på Azure Functions consumption plan (Python/C#).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#7",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-how-to-semantic-chunking",
"evidence_quote": "",
"reason": "Alle fem skills finnes og rollene stemmer, men Microsofts dokumenterte pipeline er Document Layout → Text Split → Azure OpenAI Embedding; ingen Learn-side oppgir denne fem-trinns-pipelinen med custom kontekst-genereringsskill og Text Merge, og ingen motbeviser den heller.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 210,
"claim": "Den fullstendige skillset-pipelinen består av fem trinn: Document Layout skill (struktur til Markdown) | Text Split skill | Custom Context Generation skill (GPT-4o) | Text Merge skill | Azure OpenAI Embedding skill (text-embedding-3-large).",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/contextual-retrieval.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability",
"evidence_quote": "| gpt-4o | 2024-11-20 | ✅ | - | ✅ | - | - | ✅ | ✅ | ✅ | - |",
"reason": "I Standard/Regional-tabellen for Europa er norwayeast merket ✅ for gpt-4o 2024-11-20, så den bærende delen «Sweden Central som nærmeste region med GPT-4o» er motbevist — Norway East tilbyr selv GPT-4o, selv om EU/EØS-delen holder.",
"file": "skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md",
"line": 227,
"claim": "Azure OpenAI må kjøres i Sweden Central som nærmeste region med GPT-4o; data forblir i EU/EØS.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 25,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/vector-search-how-to-generate-embeddings",
"evidence_quote": "One step involves selecting an embedding model to vectorize your plain text content. The following models are supported: 1. text-embedding-3-small 2. text-embedding-3-large 3. text-embedding-ada-002 4. Cohere-embed-v3-english 5. Cohere-embed-v3-multilingual",
"reason": "GA-delene for Azure OpenAI og Azure AI Search holder, men den kanoniske listen over embedding-modeller Azure tilbyr inneholder verken Multilingual E5 eller Custom embeddings, så Preview-statusen for disse to bærende delene er ikke dekket.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 4,
"claim": "Filen angir status GA for Azure OpenAI og Azure AI Search, og Preview for Multilingual E5 og Custom embeddings.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#7",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/postgresql/extensions/azure-local-ai",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side oppgir dimensjonstall eller token-tak for multilingual-e5-small; den eneste Azure-omtalen (azure_local_ai for PostgreSQL) nevner modellen uten spesifikasjoner og er dessuten pensjonert.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 43,
"claim": "multilingual-e5-small har 384 dimensjoner og maks 512 tokens.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/search/vector-search-how-to-generate-embeddings",
"evidence_quote": "The following models are supported: 1. text-embedding-3-small 2. text-embedding-3-large 3. text-embedding-ada-002 4. Cohere-embed-v3-english 5. Cohere-embed-v3-multilingual",
"reason": "Jeg hentet de kanoniske listene over embedding-modeller Azure tilbyr (Azure AI Search/Foundry-veiviseren og Foundry Models sold by Azure) — multilingual-e5-small og multilingual-e5-large er fraværende i begge, og fraværet er bevis mot at de tilbys via Azure AI med Preview-status.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 43,
"claim": "multilingual-e5-small og multilingual-e5-large har status Preview og tilbys via Azure AI.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#9",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/postgresql/extensions/azure-local-ai",
"evidence_quote": "",
"reason": "Ingen learn.microsoft.com-side oppgir 1024 dimensjoner eller 512 tokens for multilingual-e5-large; modellen omtales ikke i Microsofts dokumentasjon i det hele tatt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 44,
"claim": "multilingual-e5-large har 1024 dimensjoner og maks 512 tokens.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#10",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "The following models are supported for fine-tuning: gpt-4o-mini (2024-07-18), gpt-4o (2024-08-06), gpt-4.1 (2025-04-14), gpt-4.1-mini (2025-04-14), gpt-4.1-nano (2025-04-14), o4-mini (2025-04-16), gpt-5 (2025-08-07), Ministral-3B (2411), Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b",
"reason": "Jeg sjekket den kanoniske listen over modeller som kan finjusteres — den inneholder ingen embedding-modell, så Custom embeddings for domenespesifikk fine-tuning finnes ikke som et Azure-tilbud med status Announced.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 45,
"claim": "Custom embeddings for domene-spesifikk fine-tuning har status Announced, med variabel dimensjonalitet og variabel maks token-kapasitet.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "",
"reason": "Learn oppgir ingen språkantall for OpenAI-embeddings (kun MIRACL- og MTEB-benchmarktall) og sier ingenting om at E5-modellene er optimalisert for flerspråklig kvalitet; verken 100+ språk eller E5-påstanden kan bekreftes eller avkreftes.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 50,
"claim": "OpenAI-embeddingmodellene håndterer 100+ språk, men med fallende kvalitet utenfor engelsk, mens E5-modellene er optimalisert for flerspråklig kvalitet.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#13",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/api-version-lifecycle",
"evidence_quote": "Azure OpenAI API version 2024-10-21 is currently the latest GA API release. This API version is the replacement for the previous 2024-06-01 GA API release.",
"reason": "2024-02-01 er en tidsstemplet, avløst rad: Learn oppgir at 2024-06-01 erstattet 2024-02-01, at 2024-10-21 nå er siste GA, og at v1-API-et anbefales — eksempelets api_version peker på en versjon som siden er skiftet ut.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 60,
"claim": "Azure OpenAI embeddings-kall i eksempelet bruker api_version 2024-02-01.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/knowledge-azure-ai-search",
"evidence_quote": "Copilot Studio supports vectorized indexes using integrated vectorization. Prepare your data and choose an embedded model, then use Import and vectorize data in Azure AI Search to create vector indexes.",
"reason": "Koblingen til Azure AI Search som knowledge source stemmer, men Learn krever at du selv velger embedding-modell og vektoriserer indeksen i Azure AI Search før tilkobling — embeddings genereres altså ikke automatisk ved opplasting, og modellvalget er ikke låst slik claimet påstår.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 247,
"claim": "Copilot Studio kan kobles til Azure AI Search som knowledge source; embeddings genereres automatisk ved opplasting, og standardmodellen (typisk ada-002 eller text-embedding-3-small) kan ikke endres direkte i UI.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#17",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/vector-search-overview",
"evidence_quote": "",
"reason": "Learn omtaler verken self-hosting av Custom embeddings i norske Azure-regioner eller den norske klassifiseringen Høy/Kritisk; anbefalingen kan verken bekreftes eller avkreftes mot Microsoft-dokumentasjon.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 280,
"claim": "Custom embeddings kan self-hostes i Azure Norway-regioner, noe som anbefales for data klassifisert Høy/Kritisk.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/search-howto-reindex",
"evidence_quote": "delete | Removes the entire document from the index. If you want to remove an individual field, use merge instead, setting the field in question to null.",
"reason": "Første del stemmer, men Learn dokumenterer at et enkeltfelt — inkludert et vektorfelt — fjernes selektivt med merge og null uten reindeksering, så den bærende begrensningen claimet påstår er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 289,
"claim": "Azure AI Search støtter sletting av dokumenter, men ikke selektiv sletting av embeddings uten reindeksering.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#19",
"judge_verdict": "not_grounded",
"rule": "R1",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/embeddings",
"evidence_quote": "The maximum input length for the current embedding models is 8,192 tokens. ... If you send an array of inputs in a single embedding request, the maximum array size is 2,048. ... Each /embeddings request has a 300,000-token aggregate limit across all inputs.",
"reason": "Taket claimet setter (maks 8191 tokens totalt per batch-kall) er avløst: 8 192 gjelder per input, mens Learns gjeldende aggregerte grense per forespørsel er 300 000 tokens, og maks array-størrelse er 2 048 — det oppgitte taket binder ikke lenger.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 360,
"claim": "Et batch-kall til embeddings-API-et kan sende ca. 100 dokumenter per API-kall, med maks 8191 tokens totalt.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#22",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "The following models are supported for fine-tuning: gpt-4o-mini (2024-07-18), gpt-4o (2024-08-06), gpt-4.1 (2025-04-14), gpt-4.1-mini (2025-04-14), gpt-4.1-nano (2025-04-14), o4-mini (2025-04-16), gpt-5 (2025-08-07), Ministral-3B (2411), Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b",
"reason": "Jeg hentet den kanoniske listen over modeller som støtter fine-tuning i Foundry — den inneholder kun chat- og tekstmodeller, ingen embedding-modell, og ingen Custom Models-preview for embeddings.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 449,
"claim": "Microsoft Foundry støtter fine-tuning av embedding-modeller via Custom Models, som er i preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#23",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "The following models are supported for fine-tuning: gpt-4o-mini (2024-07-18), gpt-4o (2024-08-06), gpt-4.1 (2025-04-14), gpt-4.1-mini (2025-04-14), gpt-4.1-nano (2025-04-14), o4-mini (2025-04-16), gpt-5 (2025-08-07), Ministral-3B (2411), Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b",
"reason": "text-embedding-3-small og text-embedding-3-large står ikke i Learns liste over finjusterbare modeller, og verken JSON Lines-formatet eller query-document-par for embedding-finjustering er dokumentert.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 453,
"claim": "Fine-tuning av embeddings i Microsoft Foundry støtter modellene text-embedding-3-small | text-embedding-3-large, med treningsdata i JSON Lines-format bestående av query-document pairs.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#24",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "The following models are supported for fine-tuning: gpt-4o-mini (2024-07-18), gpt-4o (2024-08-06), gpt-4.1 (2025-04-14), gpt-4.1-mini (2025-04-14), gpt-4.1-nano (2025-04-14), o4-mini (2025-04-16), gpt-5 (2025-08-07), Ministral-3B (2411), Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b",
"reason": "Embedding-finjustering finnes ikke i den kanoniske listen over finjusterbare modeller, så kravet om minimum 100 positive query-document-par og anbefalingen om 1000+ har ingen dekning i Microsoft-dokumentasjonen.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 455,
"claim": "Fine-tuning av embedding-modeller krever minimum 100 positive query-document-par, med 1000+ som anbefalt antall.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/embedding-models-selection.md#25",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"evidence_quote": "The following models are supported for fine-tuning: gpt-4o-mini (2024-07-18), gpt-4o (2024-08-06), gpt-4.1 (2025-04-14), gpt-4.1-mini (2025-04-14), gpt-4.1-nano (2025-04-14), o4-mini (2025-04-16), gpt-5 (2025-08-07), Ministral-3B (2411), Qwen-32B, Llama-3.3-70B-Instruct, gpt-oss-20b",
"reason": "Foundry tilbyr ikke finjustering av embedding-modeller ifølge den kanoniske listen, og metrikkene Recall@k, NDCG og MRR er ikke dokumentert som evalueringsmetrikker for slike jobber noe sted på learn.microsoft.com.",
"file": "skills/ms-ai-engineering/references/rag-architecture/embedding-models-selection.md",
"line": 457,
"claim": "Evaluering av fine-tunede embedding-modeller i Microsoft Foundry skjer med metrikkene Recall@k | NDCG | MRR mot valideringssett.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#2",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/fabric/fundamentals/whats-new",
"evidence_quote": "June 2026 | Fabric Graph (Generally Available) | Graph in Microsoft Fabric helps you model, visualize, and analyze complex relationships within your data.",
"reason": "LPG-delen stemmer, men statusen matcher en utdatert rad: Fabric fører nå Fabric Graph som Generally Available (juni 2026), mens Public Preview er den arkiverte oktober 2025-raden, og oversiktssiden har ingen preview-merking på selve graph-produktet.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 40,
"claim": "Microsoft Fabric Graph er i Public Preview og bruker Labeled Property Graph (LPG)-modellen.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/cosmos-ai-graph",
"evidence_quote": "By utilizing Cosmos DB's scalability and performance in both document and vector form, CosmosAIGraph enables the creation of sophisticated data models that can answer various data questions and uncover hidden relationships and concepts in semi-structured data.",
"reason": "Den kanoniske siden beskriver CosmosAIGraph som en løsning som bruker Cosmos DB i document- og vector-form, ikke som en multi-model database; den sier ingen steder at document, vector og graph lagres i samme container.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 140,
"claim": "CosmosAIGraph er en multi-model database som lagrer document | vector | graph i samme container.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/cosmos-ai-graph",
"evidence_quote": "It combines traditional database, vector database, and graph database capabilities with AI to manage and query complex data relationships efficiently. To get started, see the CosmosAIGraph repo.",
"reason": "Den kanoniske CosmosAIGraph-siden nevner verken Gremlin API eller SQL API blant grensesnittene; «SQL API» er dessuten det gamle navnet som er erstattet av Azure Cosmos DB for NoSQL.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 143,
"claim": "CosmosAIGraph eksponerer Gremlin API (graph traversal) | SQL API (document queries).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#10",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/search/search-api-preview",
"evidence_quote": "Knowledge bases and select knowledge sources are generally available. However, certain agentic retrieval capabilities remain in preview, including document-level permissions, answer synthesis, configurable retrieval reasoning effort, and multi-turn conversational messages in the retrieve request.",
"reason": "Preview-oversikten sier at knowledge bases nå er generelt tilgjengelige og at kun utvalgte agentic retrieval-funksjoner er igjen i preview, så preview-statusen i påstanden er utdatert.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 150,
"claim": "Knowledge base API i Azure AI Search er en preview-feature for agentic retrieval.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#12",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/legacy-models",
"evidence_quote": "gpt-4 gpt-4-32k - 0314 | | June 6, 2025 | gpt-4o version: 2024-11-20",
"reason": "GPT-4 står i tabellen over pensjonerte modeller (utgått 6. juni 2025, erstattet av gpt-4o), altså en legacy-rad; verken den siterte RAG-guiden eller noen annen Learn-side anbefaler GPT-4 eller «Opus» for kompleks graph-resonnering.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 156,
"claim": "GPT-4 og Opus anbefales for kompleks graph-resonnering (path explanations, multi-hop inferenser).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/privacy/eudb/eu-data-boundary-learn",
"evidence_quote": "",
"reason": "Learn dokumenterer at Norge er et EFTA-land innenfor EU Data Boundary, men ingen learn.microsoft.com-side konkluderer med at GraphRAG-data lagret i en norsk Azure-region oppfyller EU-kravene til dataresidens «under Schrems II» — en slik juridisk vurdering publiseres ikke der.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 190,
"claim": "GraphRAG-data lagret i Azure Norway (oslo-region) oppfyller EU data residency-kravene under Schrems II.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/graphrag-knowledge-graphs.md#15",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/semantic-search-overview",
"evidence_quote": "",
"reason": "Semantic ranker har en gratisplan med «a monthly free request allowance», men verken oversikten eller faktureringssiden tallfester den til 1000 spørringer per måned — tallet ligger kun på den JS-rendrede Azure-prissiden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md",
"line": 227,
"claim": "Semantic ranking i Azure AI Search har en tier på 1000 queries per måned.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/hierarchical-rag-patterns.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 15,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/hierarchical-rag-patterns.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-how-to-define-index-projections",
"evidence_quote": "",
"reason": "Ingen hentet learn.microsoft.com-side oppgir kostnad for index projections: projeksjonssiden nevner bare «Azure AI Search, any tier or region» som forutsetning, og kostnadssidens premium-funksjonstabell verken nevner index projections eller erklærer dem gratis — påstanden kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hierarchical-rag-patterns.md",
"line": 253,
"claim": "Index projections er inkludert i Azure AI Search uten ekstra kostnad.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/hybrid-search-configuration.md#6",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/semantic-how-to-enable-disable",
"evidence_quote": "",
"reason": "Billing-siden og semantic-oversikten omtaler kun en månedlig gratis forespørselskvote uten tall, og tjenestegrensene oppgir ingen fri kvote for semantic ranker; tallet 1000 per måned står ikke på noen Learn-side (det ligger på den JS-rendrede prissiden), selv om delen om betaling etter forbrukt kvote er dekket.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"line": 97,
"claim": "Semantic ranking gir 1000 gratis spørringer per måned; utover dette påløper ekstra kostnad per query.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/hybrid-search-configuration.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-region-support",
"evidence_quote": "Europe: France Central | Germany West Central | Italy North | Norway East | North Europe | Poland Central | Spain Central | Sweden Central | Switzerland North | Switzerland West | UK South | UK West | West Europe",
"reason": "Den kanoniske regionlisten for Azure AI Search fører opp Norway East, men Norway West finnes ikke i oppregningen; fraværet i den autoritative listen motbeviser at tjenesten er tilgjengelig i begge norske regioner.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"line": 167,
"claim": "Azure AI Search er tilgjengelig i regionene Norway East og Norway West.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/hybrid-search-configuration.md#9",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-security-overview",
"evidence_quote": "Azure AI Search stores and processes your data within that geography, but Microsoft might replicate data to other regions within the same geography for high availability. The exception is Brazil South, where data stays within the region.",
"reason": "Garantien er på geografi-nivå, ikke valgt region: Microsoft kan replikere data til andre regioner i samme geografi (og objektnavn kan behandles utenfor valgt region), så region-rammen påstanden bygger på er erstattet; ingen hentet Learn-side sier at EU Data Boundary gjelder for norske Azure AI Search-deployments.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"line": 170,
"claim": "All indeksdata i Azure AI Search forblir i valgt region, og Microsofts EU Data Boundary gjelder for norske deployments.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/hybrid-search-configuration.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/semantic-how-to-enable-disable",
"evidence_quote": "Free (default) | Provides a monthly free request allowance. After the free allowance is consumed, semantic ranker requests return a billing error. | Available on all pricing tiers. || Standard | Pay-as-you-go pricing after the monthly free allowance is consumed. | Requires the Basic tier or higher.",
"reason": "To bærende deler er feil: gratisplanen for semantic ranker er tilgjengelig på ALLE tier (betalt plan krever Basic eller høyere, ikke S1), og vector-search-overview slår fast at vektorsøk er tilgjengelig på alle tier uten ekstra kostnad, så hybrid search krever ikke Basic.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"line": 190,
"claim": "Minimumstier i Azure AI Search: hybrid search (BM25 + vektor) krever Basic | scoring profiles er tilgjengelig på alle tier | semantic ranking krever S1 eller høyere (1000 gratis per måned) | integrert vektorisering krever Basic eller høyere.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/hybrid-search-configuration.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/vector-search-how-to-quantization",
"evidence_quote": "Scalar quantization compresses float values into narrower data types. AI Search currently supports int8, which is 8 bits, reducing vector index size fourfold. Binary quantization converts floats into binary bits, which takes up 1 bit. This results in up to 28 times reduced vector index size.",
"reason": "Begge bærende deler svikter: kvantiseringssiden har ingen preview-merking (vektoroptimaliseringsteknikkene omtales som generelt tilgjengelige), og reduksjonen er firedobbelt for scalar og opptil 28 ganger / 96 % for binary, altså langt over taket opptil 50 %.",
"file": "skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md",
"line": 196,
"claim": "Scalar/binary quantization i Azure AI Search er i preview og reduserer vektorlagring med opptil 50 %.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 13,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/late-chunking-patterns.md#1",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/concepts/model-retirement-schedule",
"evidence_quote": "This section lists the retirement lifecycle for Foundry Models sold by partners via Azure Marketplace.",
"reason": "Ingen learn.microsoft.com-side omtaler «late chunking», og den kanoniske opplistingen av modeller solgt via Azure Marketplace (Anthropic, Cohere, Fireworks, Meta, Microsoft, Mistral AI, Nixtla, NTT Data, StabilityAI) har ingen Jina-oppføring — verken GA- eller Preview-status for late chunking på Azure er dokumentert.",
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"line": 4,
"claim": "Late chunking-støtte er GA i Jina Embeddings og i Preview via Azure Marketplace.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/late-chunking-patterns.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-from-partners",
"evidence_quote": "Foundry Models from partners and community available for deployment (for example, Cohere models) require Azure Marketplace.",
"reason": "Den kanoniske opplistingen av partner-modeller på Azure Marketplace enumererer embedding-modeller (Cohere-embed-v3-english/multilingual) under leverandørene Anthropic, Cohere, Meta, Microsoft, Mistral AI og NTT Data, men Jina Embeddings v3/v4 er fraværende både her og i retirement-planen.",
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"line": 31,
"claim": "Jina Embeddings v3 og v4 er tilgjengelig på Azure via Azure Marketplace.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/late-chunking-patterns.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-from-partners",
"evidence_quote": "| **Model** | **Version** | **francecentral** | **germanywestcentral** | **italynorth** | **norwayeast** | **polandcentral** | **spaincentral** | **swedencentral** | **switzerlandnorth** | **switzerlandwest** | **uksouth** | **ukwest** | **westeurope** |",
"reason": "Den kanoniske region-tabellen for partner-modeller har norwayeast som egen kolonne, men ingen Jina-rad i det hele tatt — ingen Jina Embeddings-deployering i Norway East er dokumentert.",
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"line": 192,
"claim": "Jina Embeddings fra Azure Marketplace kan deployes i Norway East, slik at data forblir i Norge.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/late-chunking-patterns.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-from-partners",
"evidence_quote": "",
"reason": "Ingen hentet learn.microsoft.com-side beskriver Jina Embeddings på Azure, og verken Azure Container Instance-pakking eller consumption-basert prismodell for et slikt tilbud er dokumentert — påstanden kan verken bekreftes eller avkreftes mot Learn.",
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"line": 220,
"claim": "Jina Embeddings på Azure deployes som Azure Container Instance med consumption-basert prismodell.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/late-chunking-patterns.md#13",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-from-partners",
"evidence_quote": "",
"reason": "Ingen hentet learn.microsoft.com-side omtaler kvotemodellen for Jina Embeddings på Azure; at Azure OpenAI-kvote ikke kreves står ikke noe sted, og ingen side oppgir en avvikende verdi.",
"file": "skills/ms-ai-engineering/references/rag-architecture/late-chunking-patterns.md",
"line": 222,
"claim": "Bruk av Jina Embeddings på Azure krever ingen Azure OpenAI-kvote.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-query-odata-filter",
"evidence_quote": "Find all hotels within a given viewport described as a polygon (where Location is a field of type Edm.GeographyPoint).",
"reason": "Attributt-tabellen for de øvrige typene stemmer, men den uttalte, handlingsbærende innsnevringen Edm.GeographyPoint er filterable kun via geo.distance er motbevist: geo.intersects filtrerer også på Edm.GeographyPoint-felt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 37,
"claim": "Metadata-felttyper i Azure AI Search med egenskaper: Edm.String (filterable, facetable, sortable) | Collection(Edm.String) (filterable, facetable) | Edm.Int32/Edm.Int64 (filterable, facetable, sortable) | Edm.DateTimeOffset (filterable, facetable, sortable) | Edm.Boolean (filterable, facetable) | Edm.GeographyPoint (filterable kun via geo.distance, ikke facetable).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/search-faceted-navigation-examples",
"evidence_quote": "Using the latest preview REST API or the Azure portal, you can configure a facet hierarchy using the `>` and `;` operators.",
"reason": "Preview-statusen for hierarkiske facetter er korrekt, men den uttalte, handlingsbærende delen med delimiter og levels er feil: hierarkiet konfigureres med operatorene > og ;, og verken delimiter eller levels finnes blant de gyldige facet-parameterne (count, sort, values, interval, timeoffset).",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 158,
"claim": "Hierarkisk faceted navigation (hierarchical facets med delimiter og levels) er en preview-funksjon i Azure AI Search, ikke GA.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-query-odata-filter",
"evidence_quote": "",
"reason": "Den kanoniske seksjonen Filter size limitations oppgir bevisst ingen tallgrense, bare at hundrevis av klausuler gir risiko for å overskride grensen; ingen Learn-side oppgir en filter-klausulgrense på om lag 1000 (1024/3000 gjelder search-klausuler, ikke filter).",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 260,
"claim": "Azure AI Search har en grense for filter-kompleksitet på om lag 1000 klausuler.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#12",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-how-to-index-sharepoint-online",
"evidence_quote": "",
"reason": "SharePoint-indexer-siden viser kun et eksempel (Title/Price/InStock/Category) med kompatible måltyper og gir ingen mapping for Managed Metadata, Date and Time eller Person or Group; ingen Learn-side oppgir den påståtte kolonnetype-til-Edm-tabellen eller at alle er filterable og facetable.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 270,
"claim": "SharePoint-kolonnetyper mappes til Azure AI Search-typer slik: Single line of text → Edm.String | Choice → Edm.String | Managed Metadata → Collection(Edm.String) | Date and Time → Edm.DateTimeOffset | Person or Group → Collection(Edm.String), alle filterable og facetable.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#13",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-indexer-overview",
"evidence_quote": "",
"reason": "Dataverse står ikke i listen over støttede indexer-datakilder, og datatype-kartet for indexere dekker kun SQL Server og JSON; ingen Learn-side oppgir en Dataverse-til-Edm-mapping som kan bekrefte eller motbevise claimen.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 317,
"claim": "Dataverse-typer mappes til Azure AI Search-typer slik: Choice → Edm.String | Choices (multi-select) → Collection(Edm.String) | Lookup → Edm.String (ID eller Name) | DateTime → Edm.DateTimeOffset.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#14",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/search/search-how-to-index-azure-blob-storage",
"evidence_quote": "Currently, this indexer doesn't support indexing blob index tags.",
"reason": "Den kanoniske enumereringen av standard blob-metadata (metadata_storage_name, _path, _content_type, _last_modified, _size, _content_md5, _sas_token) inneholder ikke metadata_storage_blob_index_tags, og siden slår eksplisitt fast at blob-indexeren ikke støtter indeksering av blob index tags.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 343,
"claim": "Azure AI Search-indexer for Azure Blob Storage eksponerer blob index tags i feltet metadata_storage_blob_index_tags (Edm.String, filterable).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#16",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "Before April 3, 2024 | 2 | 25 | 100 | 200 ... After May 17, 2024 | 15 | 160 | 512 | 1,024",
"reason": "Tallene 2/25/100/200 GB treffer kun den tidsstemplede historiske raden Before April 3, 2024; gjeldende rad for nye tjenester er Basic 15, S1 160, S2 512, S3/HD 1 024 GB.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 435,
"claim": "Maks indeksstørrelse per tier i Azure AI Search: Basic 2 GB | S1 25 GB per partisjon | S2 100 GB per partisjon | S3/S3HD 200 GB per partisjon.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/metadata-management-filtering.md#17",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "Maximum simple fields per index | 1000 | 100 | 1000 | 1000 | 1000 | 1000 | 1000 | 1000 | 1000 ... Basic tier is the only tier with a lower limit of 100 fields per index.",
"reason": "Begge de tallfestede delene er feil: Basic har 100 felt per indeks (ikke 1000), og S3/S3 HD har 1000 (ikke 3000) — 3000 gjelder maks indekser per S3 HD-tjeneste og elementer i komplekse samlinger, ikke felt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md",
"line": 438,
"claim": "Maks antall felt per indeks er 1000 for Basic, S1 og S2, og 3000 for S3/S3HD.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 13,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/multi-index-federation.md#10",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-multi-vector-fields",
"evidence_quote": "This feature is currently in preview. This preview is provided without a service-level agreement and isn't recommended for production workloads.",
"reason": "Claimen sier GA (2025), men den kanoniske siden merker funksjonen som preview i dag, og «Preview features in Azure AI Search» lister «Multivector support» under data plane preview features (Create or Update Index (preview)) — status er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md",
"line": 63,
"claim": "Multi-vector field support i Azure AI Search er GA (2025).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multi-index-federation.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/agentic-retrieval-overview",
"evidence_quote": "The knowledge base sends the subqueries to your knowledge sources. All subqueries run simultaneously and can be keyword, vector, or hybrid search.",
"reason": "Query planning-delen holder («the knowledge base sends your query and conversation history to an LLM, which generates focused subqueries»), men den bærende delen «fremdeles single-index» er motsagt: en knowledge base spør én eller flere knowledge sources (indekserte og eksterne) parallelt — og «Preview» er også superseded, siden «Some agentic retrieval features are generally available in the 2026-04-01 REST API» og preview-oversikten sier «Knowledge bases and select knowledge sources are generally available».",
"file": "skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md",
"line": 64,
"claim": "Agentic Retrieval i Azure AI Search er i Preview og gir LLM-assistert query planning, men er fremdeles single-index.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multi-index-federation.md#13",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-multi-region",
"evidence_quote": "",
"reason": "Claimen beskriver referansefilens eget kodeeksempel (modellvalg gpt-4o-mini via chat.completions), noe ingen learn.microsoft.com-side kan bekrefte eller avkrefte; den siterte siden omtaler ikke query routing eller modellvalg, og søk fant ingen Learn-side som uttaler seg om eksempelet — modellen gpt-4o-mini finnes fortsatt (oppført som Deprecated med retirement 2027-04-14 i retirement-schedule), så ingenting motsier claimen heller.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md",
"line": 187,
"claim": "Eksempelet for LLM-basert query routing bruker modellen gpt-4o-mini via chat.completions-API-et.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 23,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/search/multimodal-search-overview",
"evidence_quote": "In Azure AI Search, retrieving knowledge from images can follow two complementary paths: image verbalization or direct embeddings.",
"reason": "Siden beskriver TO komplementære veier (verbalisering vs. direkte multimodale embeddinger), ikke tre; Content Understanding hører til ekstraksjonsaksen som ett av to anbefalte skills, og den navngitte modellen GPT-4v er avløst og står ikke i listen over støttede modeller for bildeverbalisering.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 28,
"claim": "Azure-stakken tilbyr tre komplementære tilnærminger til multimodal RAG: Image verbalization (GPT-4o/4v konverterer bilder til tekst) | direkte multimodale embeddings (Azure Vision genererer vektorer for bilder og tekst i samme vektorrom) | Azure Content Understanding (konverterer komplekse dokumenter til Markdown).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-document-extraction",
"evidence_quote": "This skill extracts text and images. Text extraction is free. Image extraction is billable by Azure AI Search.",
"reason": "To bærende deler er motsagt: skillen ekstraherer nettopp tekst, og formatlisten omfatter CSV, EML, EPUB, HTML, JSON, Markdown, DOCX, XLSX, PPTX, PDF, RTF, XML m.fl. - ikke kun PDF; kun table extraction er reelt Nei (PDFs only gjelder location metadata, ikke filstøtte).",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 40,
"claim": "Document Extraction-skillen støtter kun PDF, ekstraherer bilder, men ikke tekst og ikke tabeller.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference",
"evidence_quote": "Document analyzers ... Supported configuration options: returnDetails, omitContent, enableOcr, enableLayout, enableFormula, enableBarcode, tableFormat, chartFormat, enableFigureDescription, enableFigureAnalysis, enableAnnotations, annotationFormat, enableSegment, segmentPerPage, estimateFieldSourceAndConfidence, contentCategories",
"reason": "Den kanoniske config-opplistingen har ingen outputContentFormat (det er Document Layout-skillens outputFormat), og feltet heter enableAnnotations i flertall, ikke enableAnnotation - begge er load-bearing API-strenger en leser ville kopiert inn i kode.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 177,
"claim": "Konfigurasjonsparametere for Content Understanding i RAG-pipelines: outputContentFormat=markdown | enableFigureAnalysis=true | enableAnnotation=true | chartFormat=markdown.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-get-started-portal-image-search",
"evidence_quote": "Models for image verbalization ... LLMs: - phi-4 - gpt-4o - gpt-4o-mini - gpt-5 - gpt-5-mini - gpt-5-nano",
"reason": "Den kanoniske opplistingen av modeller for bildeverbalisering inneholder ingen GPT-4v eller vision-preview; modellsiden bekrefter i tillegg at gpt-4 turbo-2024-04-09 er Replacement for all previous GPT-4 preview models (vision-preview, 1106-Preview, 0125-Preview).",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 206,
"claim": "GPT-4v har modellvarianten vision-preview og anbefales til bildeberikelse og summary-generering.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-get-started-portal-image-search",
"evidence_quote": "If you're on a free search service, use fewer than 20 files to stay within the free quota for enrichment processing.",
"reason": "Free tier støtter multimodal (med kvote) - Document Extraction-siden sier også at kostnaden for 20 transaksjoner per indexer per dag absorberes på en gratis søketjeneste; Basic-kravet i quickstarten gjelder managed identity support, ikke multimodal som sådan, så den første bærende delen er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 216,
"claim": "Free tier i Azure AI Search støtter ikke multimodal; minimum Basic tier kreves.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/multimodal-rag.md#19",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-vision-vectorize",
"evidence_quote": "This skill is in preview under Supplemental Terms of Use. The latest preview version of Skillsets - Create Or Update (REST API) supports this feature.",
"reason": "Ingen Learn-side stempler den multimodale pipelinen som GA; oversiktssiden har ingen GA-merking, mens Azure Vision multimodal embeddings-skillen og tilhørende vectorizer er eksplisitt preview, og wizard-genererte indekser følger den nyeste preview-REST-API-en.",
"file": "skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md",
"line": 331,
"claim": "Azure AI Search multimodal pipeline er GA.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 21,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#1",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/well-architected/ai/application-design#implement-multi-layer-caching-strategies",
"evidence_quote": "Result and answer caching: Use this approach to reuse responses for identical or semantically similar queries ... Retrieval and grounding snippet caching: Cache frequently retrieved knowledge fragments and grounding data ... Model output caching: Cache intermediate model outputs that can be reused across requests.",
"reason": "Den kanoniske WAF-siden ramser opp nøyaktig TRE cache-lag (result/answer, retrieval/grounding, model output); embedding caching er fraværende som eget nivå, semantisk caching er innbakt i result/answer-laget, og model output caching mangler i påstanden — fire-nivå-taksonomien stemmer ikke med kilden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 27,
"claim": "Multi-layer caching i RAG dekker fire nivåer: result caching (hele LLM-responser) | retrieval caching (knowledge fragments fra vektorsøk) | embedding caching (forhåndsberegnede vektorrepresentasjoner) | semantic caching (semantisk like prompts).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-pagination-page-layout",
"evidence_quote": "each query is independent and operates on the current view of the data as it exists in the index at query time (in other words, there's no caching or snapshot of results, such as those found in a general purpose database)",
"reason": "Redis-, Cosmos DB- og APIM-delene er dekket av Learn, men den bærende delen «Azure AI Search (innebygd caching av søkeresultater)» motsies direkte: Azure AI Search cacher ikke søkeresultater — den eneste dokumenterte cachen er enrichment cache (preview) for skillset-output i Azure Storage.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 29,
"claim": "Microsoft-stakken tilbyr disse cache-tjenestene for AI-workloads: Azure Cache for Redis (tradisjonell og semantisk caching) | Azure Cosmos DB (semantisk cache med vektorsøk) | Azure AI Search (innebygd caching av søkeresultater) | Azure API Management (semantisk caching for LLM-API-er).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#3",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/well-architected/ai/application-design#implement-multi-layer-caching-strategies",
"evidence_quote": "Result and answer caching: ... Retrieval and grounding snippet caching: Cache frequently retrieved knowledge fragments and grounding data to avoid repeated database and search queries or data API operations. Model output caching: Cache intermediate model outputs that can be reused across requests.",
"reason": "Kilden lister tre cache-lag, ikke fire; «Embedding caching» finnes ikke i den kanoniske oppramsingen, så påstanden om fire lag er ikke dekket.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 37,
"claim": "Multi-layer caching-tabellen lister fire cache-lag: Result caching (cache hele LLM-responser) | Retrieval caching (cache knowledge fragments fra vector search) | Embedding caching (cache forhåndsberegnede embeddings) | Model output caching (cache intermediate model outputs).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/well-architected/ai/application-design#implement-multi-layer-caching-strategies",
"evidence_quote": "Invalidation hooks: Implement cache invalidation triggers for data updates, model changes, and prompt modifications.",
"reason": "Den kanoniske oppramsingen har nøyaktig tre invalideringstriggere; «manual purge (admin-utløst for compliance eller testing)» er fraværende, og søk fant ingen Learn-side som lister manuell purge som en fjerde trigger for AI-caching.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 68,
"claim": "Cache invalidation utløses av fire triggere: data updates (webhook-triggered ved endring i kildedata) | model changes (ved model deployment/retraining) | prompt modifications (ved endring av prompt-template) | manual purge (admin-utløst for compliance eller testing).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-cache-for-redis/cache-overview",
"evidence_quote": "Memory: The Basic and Standard tiers offer 250 MB – 53 GB; the Premium tier 6 GB - 1.2 TB; the Enterprise tier 1 GB - 2 TB, and the Enterprise Flash tier 300 GB - 4.5 TB.",
"reason": "SLA-nivåene (99,9 % Premium / 99,99 % Enterprise) og Premium-kapasiteten holder, men den bærende delen «Enterprise Flash opptil 13 TB» motsies: siden oppgir 300 GB – 4,5 TB for Enterprise Flash.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 186,
"claim": "Azure Cache for Redis-tiers: Premium tier (99,9 % SLA, opptil 120 GB per shard) | Enterprise tier (99,99 % SLA, active-active geo-replikering, Flash-storage-støtte) | Enterprise Flash tier (opptil 13 TB cache-størrelse, 20 % RAM + 80 % NVMe Flash).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#11",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/llm-semantic-cache-lookup-policy",
"evidence_quote": "Use the llm-semantic-cache-lookup policy to perform cache lookup of responses to large language model (LLM) API requests from a configured external cache, based on vector proximity of the prompt to previous requests and a specified score threshold.",
"reason": "Attributtene og vary-by-underelementet stemmer, men policy-navnene er superseded: azure-openai-semantic-cache-lookup/-store heter nå llm-semantic-cache-lookup og llm-semantic-cache-store (den gamle URL-en redirigerer til llm-siden, og eksempel-XML-en på how-to-siden bruker llm-navnene). Navnet ER påstanden (R7s load-bearing-carve-out) — en leser kopierer strengen inn i policy-XML.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 237,
"claim": "APIM-policyene for semantisk cache er azure-openai-semantic-cache-lookup (inbound, med attributtene score-threshold, embeddings-backend-id, embeddings-backend-auth, ignore-system-messages, max-message-count og underelementet vary-by) og azure-openai-semantic-cache-store (outbound, med attributtet duration).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/api-management/llm-semantic-cache-lookup-policy",
"evidence_quote": "Score threshold above 0.2 may lead to cache mismatch. Consider using lower value for sensitive use cases.",
"reason": "Retningsdelen er grunngitt («Lower values require higher semantic similarity for a match»), men den bærende tre-bånds-rubrikken er ikke dokumentert og strider mot Learn-veiledningen: doc-en anbefaler å starte på 0,05 og advarer om cache-mismatch over 0,2, mens påstanden kaller 0,3–0,5 «balanced» og 0,6–0,8 «liberal».",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 253,
"claim": "APIM-attributtet score-threshold er en distanse der lavere verdi gir strengere matching og krever høyere semantisk likhet: 0,1–0,2 = strict matching | 0,3–0,5 = balanced | 0,6–0,8 = liberal matching.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/cosmos-db/how-to-dotnet-vector-index-query",
"evidence_quote": "After you decide on the vector embedding paths, you must add vector indexes to the indexing policy. ... The vector path is added to the excludedPaths section of the indexing policy to ensure optimized performance for insertion.",
"reason": "Multi-region writes, 99,999 % og TTL er grunngitt, men den bærende delen «automatisk indeksering av vektorer» motsies: vektorindeks må defineres eksplisitt i indekseringspolicyen (kun ved container-opprettelse), og vektorstien legges i excludedPaths — altså holdes vektorer utenfor den automatiske indekseringen.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 296,
"claim": "Azure Cosmos DB som semantisk cache gir: global distribusjon med multi-region writes | automatisk indeksering av vektorer | 99,999 % SLA med multi-region-oppsett | innebygd TTL-støtte.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#18",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/redis/entra-for-authentication",
"evidence_quote": "Azure Managed Redis offers a password-free authentication mechanism by integrating with Microsoft Entra ID. Azure Managed Redis caches use Microsoft Entra ID by default. When you create a new cache, managed identity is enabled.",
"reason": "Status-påstanden er utdatert: Entra ID-autentisering er ikke merket preview noe sted på den kanoniske siden (som derimot merker underfunksjonen «Configure custom data access permissions (preview)»), den siterte quickstart-en sier «Microsoft Entra ID is enabled by default», og What's New oppgir at Entra ID for autentisering og RBAC ble tilgjengelig i alle regioner i juni 2023.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 361,
"claim": "Microsoft Entra ID-autentisering for Redis er i preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-caching-optimization.md#19",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-cache-for-redis/cache-best-practices-performance",
"evidence_quote": "| F300 | 384 GB | 8 | 3,200 | 500,000 | 390,000 |",
"reason": "E10 = 12 GB stemmer, men den bærende størrelsen for Enterprise Flash er feil: F300 er 384 GB, ikke 345 GB. I tillegg beskriver Learn Standard-tieren som «An OSS Redis cache running on two VMs in a replicated configuration» (primary + én replica), ikke 2 replicas.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md",
"line": 373,
"claim": "Azure Cache for Redis SKU-er med kapasitet: Basic C0 (250 MB, ingen SLA) | Standard C1 (1 GB, 2 replicas, 99,9 % SLA) | Premium P1 (6 GB, clustering, geo-replikering) | Enterprise E10 (12 GB, active-active, 99,99 % SLA) | Enterprise Flash F300 (345 GB, 20 % RAM + 80 % Flash).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-context-windows.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-context-windows.md#10",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits",
"evidence_quote": "Quota values for global batch are represented in terms of enqueued tokens. ... Global batch: | Model | Enterprise and MCA-E | Default | Monthly credit card-based subscriptions | MSDN subscriptions | Azure for Students, free trials | `gpt-4.1` | 5B | 200M | 50M | 90K | N/A | ... `gpt-4o` | 5B | 200M | 50M | 90K | N/A",
"reason": "The live page organizes batch quota by subscription/agreement type (Enterprise/MCA-E, Default, credit card, MSDN) as enqueued tokens, not per Quota Tier per month, and global batch for gpt-4.1 and gpt-4o is 5B/200M/50M — the claim's ~500M/~30M figures match only the separate Data zone batch table, so both the organizing frame and the headline values are wrong.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-context-windows.md",
"line": 339,
"claim": "Azure OpenAI Batch quota (per Quota Tier): gpt-4.1 ~500M tokens/month (upper tier), ~30M (lower tier); gpt-4o ~500M (upper), ~30M (lower)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-context-windows.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/flow-develop",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states that Prompt Flow shows an estimated token count per node in the flow: the develop-flow page documents a trace view with duration and token cost of the flow (per-node detail is duration), and per-node token_consumption metrics exist only in Application Insights for deployed flows, so the claimed in-flow per-node estimate can neither be confirmed nor refuted.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-context-windows.md",
"line": 273,
"claim": "Prompt Flow (Microsoft Foundry) shows estimated token count per node in the flow",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-core-patterns.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/search/search-region-support",
"evidence_quote": "You can create an Azure AI Search service in any of the following Azure public regions.",
"reason": "Europa-tabellen i den kanoniske regionlisten for Azure AI Search fører opp Norway East, mens Norway West ikke forekommer i noen av regiontabellene — Norway West kan derfor ikke brukes for dataresidens i en RAG-løsning, sa den ene bærende delen av pastanden er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"line": 307,
"claim": "Azure har norske regioner Norway East og Norway West som kan brukes for dataresidens i RAG-løsninger.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-core-patterns.md#13",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/search/search-limits-quotas-capacity",
"evidence_quote": "",
"reason": "Ingen Microsoft Learn-side angir S1 som SKU-en for en RAG-løsning med 10M vektorer; vektorkvoten for S1 (35 GB per partisjon, 12 partisjoner) motsier det heller ikke, sa pastanden kan verken bekreftes eller avkreftes — delen om at Semantic Ranker er et separat tillegg er derimot bekreftet.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"line": 336,
"claim": "Azure AI Search S1-tier er SKU-en angitt for en RAG-løsning med 10M vektorer, og Semantic Ranker kommer som et separat tillegg.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-core-patterns.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/semantic-kernel/memories/",
"evidence_quote": "| Text Embeddings (Experimental) | ✅ | ✅ | ✅ | Example: Text-Embeddings-Ada-002 |",
"reason": "Den siterte siden merker Text Embeddings som Experimental, ikke GA, og Vector Store-funksjonaliteten er merket preview — den ene bærende delen av pastanden motsies dermed direkte.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"line": 423,
"claim": "Semantic Kernel memory og embeddings er GA.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-core-patterns.md#19",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-studio/how-to/flow-develop",
"evidence_quote": "Prompt flow in Microsoft Foundry and Azure Machine Learning will be retired on April 20, 2027. Prompt flow is no longer recommended for new development.",
"reason": "Gjeldende status er pensjonering og ikke anbefalt for ny utvikling, og siden gjelder kun Foundry (classic) — ikke den nye Foundry-portalen; en uforbeholden GA-status beskriver en tilstand som er avløst.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"line": 424,
"claim": "Prompt flow for RAG i Microsoft Foundry er GA.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-core-patterns.md#20",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/agent-framework/overview/",
"evidence_quote": "",
"reason": "Ingen side oppgir en samlet release-status for Microsoft Agent Framework: preview er avgrenset til Go (The Agent Framework for Go is in public preview) og til enkelte prerelease-pakker, mens rammeverket ellers anbefales som støttet migreringsmal for prompt flow og Foundry workflows.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md",
"line": 430,
"claim": "Microsoft Agent Framework har preview-status.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-cost-optimization.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch",
"evidence_quote": "The service aims to process batch requests within 24 hours, but it doesn't expire jobs that take longer.",
"reason": "Separat quota og ingen forstyrrelse av online workloads stemmer, men 24 timer er et target turnaround som siden eksplisitt ikke garanterer (jobber som tar lengre tid utløper ikke) - claimens SLA-påstand er en bærende del som motsies.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md",
"line": 68,
"claim": "Azure OpenAI Batch API har 24-timers SLA og egen separat quota, uten påvirkning på online workloads.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-cost-optimization.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-azure-openai-embedding",
"evidence_quote": "text-embedding-ada-002 | 1536 | 1536 | text-embedding-3-large | 1 | 3072 | text-embedding-3-small | 1 | 1536",
"reason": "ada-002 1536 stemmer, men Learn oppgir minimum 1 dimensjon for både 3-small (1-1536) og 3-large (1-3072), ikke 512 og 1024 som claimen angir, og ingen Learn-side oppgir Multilingual-e5-large med 1024 dimensjoner.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md",
"line": 76,
"claim": "Embedding-modeller og antall dimensjoner: text-embedding-ada-002 1536 | text-embedding-3-small 512-1536 | text-embedding-3-large 1024-3072 | Multilingual-e5-large 1024.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-cost-optimization.md#10",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule",
"evidence_quote": "text-embedding-ada-002 | 2 | GA | 2028-02-09 | —",
"reason": "Livssyklustabellen bruker egne merkelapper Deprecated, Legacy, Retired og GA; ada-002 står som GA (både versjon 1 og 2) med pensjonsdato 2028-02-09, altså verken legacy eller deprecated.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md",
"line": 76,
"claim": "text-embedding-ada-002 er legacy og deprecated.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-cost-optimization.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "Maximum search units (SU) | N/A | 3 SU | 36 SU | 36 SU | 36 SU | 36 SU | 36 SU | 36 SU | N/A",
"reason": "S1-L2 med 36 SU stemmer, men Free står med N/A søkeenheter (ikke 1 SU) og har maksimalt 3 indekser (ikke 1) i indekstabellen; i tillegg sier fotnoten at Basic gir tre partisjoner og tre replikaer, totalt ni SU, for tjenester opprettet etter 3. april 2024 - flere bærende deler er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-cost-optimization.md",
"line": 365,
"claim": "Search Units (SU) per tier i Azure AI Search: Free 1 SU med grense på 1 indeks | Basic 1-3 SU | S1, S2, S3, S3 HD, L1 og L2 1-36 SU.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 14,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#7",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/rest/api/searchservice/create-indexer",
"evidence_quote": "Default is source-specific (1000 for Azure SQL Database and Azure Cosmos DB, 10 for Azure Blob Storage).",
"reason": "The batchSize default is source-specific (1000 for SQL/Cosmos, 10 for Blob), not 1 as the claim asserts.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"line": 570,
"claim": "Indexer batchSize har default 1",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#9",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "Before April 3, 2024 | 2 | 25 | 100 | 200 ... After May 17, 2024 | 15 | 160 | 512",
"reason": "Free 50 MB/3 indexes and index counts match, but Basic 2 GB and S1 25 GB match only the superseded pre-April-3-2024 storage row; current storage is 15 GB (Basic) and 160 GB (S1).",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"line": 612,
"claim": "Azure AI Search lagringsgrenser: Free 50 MB / 3 indexes | Basic 2 GB / 15 indexes | Standard S1 25 GB / 50 indexes",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#10",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://azure.microsoft.com/en-us/pricing/details/ai-document-intelligence/",
"evidence_quote": "",
"reason": "The free-tier 500 pages/month allowance and S0 pay-as-you-go billing are pricing-page values; the authoritative service-limits page defers monthly allowances to the JS-rendered pricing page, so no authoritative Learn docs page states them verbatim.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"line": 616,
"claim": "Document Intelligence tiers: Free 500 sider/måned | Standard S0 pay-as-you-go",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/responsible-ai/openai/limited-access",
"evidence_quote": "all Azure customers are eligible for access to Models sold by Azure ... so customers are not required to submit a registration form unless they are: (a) accessing a model sold by Azure designated as a Limited Access Service, or (b) requesting approval to modify Guardrails",
"reason": "Standard Azure OpenAI usage no longer requires an access application; the blanket requirement the claim asserts is superseded.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"line": 621,
"claim": "Azure OpenAI krever søknad om tilgang (compliance-vurdering)",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-document-preprocessing.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "norwayeast is a supported Azure OpenAI region (row present in the model summary table and region availability)",
"reason": "Azure OpenAI is available in the Norway East region (Norway own data-residency Geo); the claim load-bearing West Europe region for Azure AI Services mechanism for Norway residency is wrong.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md",
"line": 625,
"claim": "Azure OpenAI i Norge: data residency i Norge (West Europe region for Azure AI Services)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#5",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/dotnet/api/azure.search.documents.models.indexdocumentsbatch",
"evidence_quote": "Package: Azure.Search.Documents v12.0.0 … Package: Azure.Search.Documents v12.1.0-beta.1",
"reason": "Den siterte API-siden oppgir Azure.Search.Documents v12.0.0 og v12.1.0-beta.1; claimets v11.7.0 og v11.8.0-beta.1 er avløst av en ny major-versjon.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 42,
"claim": "Azure.Search.Documents SDK er på versjon v11.7.0, med v11.8.0-beta.1 tilgjengelig som beta.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#7",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-how-to-index-sql-database",
"evidence_quote": "For Azure SQL indexers, there are two change detection policies: … \"SqlIntegratedChangeTrackingPolicy\" (applies to tables only) … \"HighWaterMarkChangeDetectionPolicy\" (works for views)",
"reason": "Den kanoniske siden som ville listet policyene oppgir nøyaktig to; claimet lister tre der «Integrated Change Tracking» og «SQL Change Tracking» er samme SQL-integrerte policy — den tredje oppføringen finnes ikke.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 50,
"claim": "Change detection på en Azure AI Search data source støtter High Water Mark | Integrated Change Tracking | SQL Change Tracking.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-howto-schedule-indexers",
"evidence_quote": "(required) The amount of time between the start of two consecutive indexer executions. The smallest interval allowed is 5 minutes, and the longest is 1,440 minutes (24 hours).",
"reason": "5 minutter, 15 minutter, time og dag er gyldige, men den bærende delen «hvert 2. minutt» ligger under minimumsintervallet på 5 minutter og kan ikke settes.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 51,
"claim": "Indexer-schedule i Azure AI Search kan settes til intervaller som hvert 2., 5. og 15. minutt, hver time og hver dag.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#14",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "| Before April 3, 2024 | 2 | 25 | 100 | 200 | 1,024 | 2,048 | N/A | … | After May 17, 2024 ^2^ | 15 | 160 | 512 | 1,024 | 2,048 | 4,096 | N/A |",
"reason": "Kun Basic 15 GB / eldre 2 GB treffer gjeldende rad; S1 25, S2 100, S3 200 og L1 1 TB er verdiene fra den tidsstemplede «Before April 3, 2024»-raden — gjeldende verdier er 160, 512, 1 024 og 2 048 GB.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 161,
"claim": "Storage per partition per tier i Azure AI Search: Basic 15 GB (services opprettet etter april 2024; eldre services 2 GB) | Standard S1 25 GB | Standard S2 100 GB | Standard S3 200 GB | Storage Optimized L1 1 TB.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#18",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/search/monitor-azure-cognitive-search-data-reference",
"evidence_quote": "| **Indexer Processed Files (bytes)** … `DocumentsProcessedBytes` | … | **Document processed count** … `DocumentsProcessedCount` | … | **Storage usage** … `IndexStorageUsage` | … | **Vector Storage usage** … `IndexVectorUsage` | … | **Compute units used** … `PerRequestComputeConsumption` | … | **Search Latency** … `SearchLatency` | … | **Search queries per second** … `SearchQueriesPerSecond` | … | **Skill execution invocation count** … `SkillExecutionCount` | … | **Throttled search queries percentage** … `ThrottledSearchQueriesPercentage` |",
"reason": "Den kanoniske enumerasjonen av metrikker for Microsoft.Search/searchServices inneholder ingen «Indexing Failed Documents» (feilede dokumenter er dimensjonen `Failed` på `DocumentsProcessedCount`), metrikken heter «Throttled search queries percentage» og ikke «Throttled Requests», og Search Latency har ingen p95-aggregering (kun Average/Count/Max/Min/Total).",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 234,
"claim": "Azure Monitor eksponerer metrikkene Queries per Second (QPS) | Indexing Failed Documents | Search Latency (p95) | Throttled Requests for Azure AI Search.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#19",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-region-support",
"evidence_quote": "You can create an Azure AI Search service in any of the following Azure public regions. … Europe … | Norway East​​ | ✅ | ✅ | | ✅ | | |",
"reason": "Jeg sjekket den kanoniske regionslisten: Europa-tabellen har rad for Norway East, men ingen rad for Norway West — Stavanger-regionen mangler helt, så påstanden om to norske regioner er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 266,
"claim": "Azure AI Search er tilgjengelig i de norske regionene Norway East (Oslo) | Norway West (Stavanger).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-enterprise-scale.md#20",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-capacity-planning",
"evidence_quote": "",
"reason": "Ingen Learn-side oppgir QPS-estimat per tier; den siterte kapasitetssiden sier tvert imot at slike retningslinjer ikke finnes («There are no guidelines on how many replicas are needed to accommodate query loads») og henviser til egen benchmarking, så tallene ~15/~15/~60/~120 kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-enterprise-scale.md",
"line": 277,
"claim": "QPS-estimat per tier i Azure AI Search: Basic ~15 | Standard S1 ~15 | Standard S2 ~60 | Standard S3 ~120.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-evaluation-frameworks.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk",
"evidence_quote": "Evaluate your generative AI application locally with the Azure AI Evaluation SDK (preview) (classic)",
"reason": "Den siterte sidens egen tittel merker Azure AI Evaluation SDK som (preview), ikke GA, og delpåstanden om at de agentiske evaluatorene er i Preview holder heller ikke (flere er ikke preview-merket) - kun Groundedness Pro (preview) stemmer, så minst to bærende deler er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md",
"line": 4,
"claim": "Azure AI Evaluation SDK har status GA, mens agentiske evaluatorer og Groundedness Pro er i Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-evaluation-frameworks.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators",
"evidence_quote": "Tool Call Accuracy | Measures the overall quality of tool calls including selection, parameter correctness, and efficiency.",
"reason": "Den kanoniske opplistingen av agent-evaluatorer merker bare noen med (preview) - Task Adherence, Task Completion, Customer Satisfaction, Intent Resolution, Quality Grader - mens Tool Call Accuracy, Tool Selection, Tool Input Accuracy, Tool Output Utilization, Tool Call Success og Task Navigation Efficiency står uten preview-merke; den generelle påstanden om at alle agentiske evaluatorer er i Preview er derfor motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md",
"line": 74,
"claim": "De agentiske evaluatorene i Azure AI Evaluation er i Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-evaluation-frameworks.md#15",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/evaluation-regions-limits-virtual-network",
"evidence_quote": "",
"reason": "Verken den siterte observability-siden, den kanoniske region-/rate-limit-siden eller Foundry-personvernsiden oppgir noen EU-hostet-mot-US-hostet fordeling av LLM-judge-modeller etter arbeidsområdets region; region-sidene lister kun støttede regioner (både US og EU) og sier ingenting som verken bekrefter eller ordrett motsier påstanden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md",
"line": 268,
"claim": "LLM-judges i evaluering bruker EU-hostede modeller for EU/EØS-arbeidsområder, og US-hostede modeller for andre regioner.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-evaluation-frameworks.md#17",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk",
"evidence_quote": "",
"reason": "Den siterte siden sier kun at prompt-ene til kvalitetsevaluatorene er open-sourcet, ikke at SDK-en er gratis, og ingen learn.microsoft.com-side oppgir prising for SDK-en eller at kostnaden utelukkende kommer fra Azure OpenAI-token-bruk for LLM-judge-kall - prisdetaljene ligger bak Azure-prissiden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-evaluation-frameworks.md",
"line": 290,
"claim": "Azure AI Evaluation SDK er gratis (open source); kostnaden kommer fra Azure OpenAI-token-bruk for LLM-judge-kall.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 9,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/whats-new",
"evidence_quote": "Groundedness detection public preview",
"reason": "Claim asserts detection is GA; What's New and the service-limits query-rate table both label it 'Groundedness detection (preview)' / 'public preview' (api-version and correction=preview parts hold, but the GA part is contradicted).",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md",
"line": 4,
"claim": "Groundedness-deteksjon: GA | groundedness correction/mitigating-feature: Preview, api-version 2024-09-15-preview",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/quickstart-groundedness",
"evidence_quote": "In your request to the groundedness detection API, set the 'mitigating' body parameter to true",
"reason": "domain/task/groundingSources/reasoning params all correct, but the current api-version's correction body parameter is named 'mitigating', not 'correction'; one load-bearing API field name is wrong.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md",
"line": 50,
"claim": "Groundedness Detection API-parametre: domain=MEDICAL|GENERIC, task=QnA|Summarization, groundingSources (array), reasoning true/false, correction true",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-hallucination-mitigation.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/how-to/deployment-types#standard",
"evidence_quote": "SKU name in code: Standard ... SKU name in code: ProvisionedManaged",
"reason": "No Azure OpenAI 'E0' tier exists (deployment SKUs are Standard/GlobalStandard/ProvisionedManaged; Content Safety is F0/S0), and Azure AI Search RAG runs on Basic/Free so 'S1 or higher' is not required; load-bearing SKU parts are fabricated/overstated.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md",
"line": 316,
"claim": "Nødvendige ressurser: Azure OpenAI E0-tier | Azure AI Content Safety Standard tier (Groundedness Detection inkludert) | Azure AI Search S1 eller høyere for RAG-indexing",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-iterative-refinement.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/multi-turn-conversation",
"evidence_quote": "var serialized = agent.SerializeSession(session);",
"reason": "WhiteboardProvider-delen er korrekt, men Agent Framework serialiserer sesjonen via agent.SerializeSession(session) / AIAgent.SerializeSessionAsync(session) - det finnes ingen AgentSession.Serialize(); én bærende del av påstanden er dermed feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md",
"line": 41,
"claim": "Session state i Microsoft-stakken dekkes av `AgentSession.Serialize()` (Agent Framework) og `WhiteboardProvider` (Semantic Kernel).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-iterative-refinement.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/multi-turn-conversation",
"evidence_quote": "var serialized = agent.SerializeSession(session);",
"reason": "CreateSessionAsync(), RunAsync(prompt, session) og DeserializeSessionAsync(serialized) stemmer, men serialiseringen skjer via agent.SerializeSession(session) / SerializeSessionAsync på AIAgent - ikke session.Serialize(); den bærende API-strengen er feil selv om returtypen JsonElement er riktig.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md",
"line": 235,
"claim": "Agent Framework tilbyr følgende API for multi-turn-samtaler: `agent.CreateSessionAsync()` | `agent.RunAsync(prompt, session)` | `session.Serialize()` som returnerer `JsonElement` | `agent.DeserializeSessionAsync(serializedSession)`.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-iterative-refinement.md#16",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/concepts/retired-models",
"evidence_quote": "The following models are retired and no longer available for use or for new deployments. | gpt-35-turbo - 0613 | | February 13, 2025 | gpt-35-turbo (0125) gpt-4o-mini | | gpt-4 gpt-4-32k - 0613 | | June 6, 2025 | gpt-4o version: 2024-11-20 |",
"reason": "Både GPT-3.5- og GPT-4-modellene står i pensjonert-listen med gpt-4o-mini og gpt-4o som anbefalt erstatning, og gjeldende retirement schedule inneholder verken gpt-35-turbo eller gpt-4 - anbefalingen beskriver en modellverden som ikke lenger finnes.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md",
"line": 380,
"claim": "Anbefalt modellvalg for kostnadsoptimalisering: GPT-3.5 for oppsummeringer og GPT-4 for svar-generering.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-arc/edge-rag/search-types",
"evidence_quote": "Agentic Retrieval in Foundry Local is currently in PREVIEW.",
"reason": "Filen stempler query understanding-kapabilitetene samlet som GA, men minst én løftebærende del svikter: søketype-siden som filen selv siterer er eksplisitt i PREVIEW, og AI Builder «Create text with GPT» er også merket preview.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 4,
"claim": "Query understanding-kapabilitetene beskrevet i filen er merket med status GA (generelt tilgjengelig).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-synonyms",
"evidence_quote": "If the synonym map exists on the search service, it's used on the next query, with no reindexing or rebuild required.",
"reason": "Synonym maps som query expansion er grunnet, men den løftebærende delen «ved indexing-tid» motsies — siden sier ekspansjonen skjer ved query-tid uten reindeksering («Internally, the synonyms feature rewrites the original query with synonyms by using the OR operator»).",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 55,
"claim": "Azure AI Search støtter synonym maps der man f.eks. definerer «AI, kunstig intelligens, maskinlæring» for automatisk query expansion ved indexing-tid.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#7",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/ai-builder/azure-openai-model-pauto",
"evidence_quote": "This feature is deprecated and isn't be visible anymore.",
"reason": "Cloud-flow-handlingen «Create text with GPT» i Power Automate/AI Builder er utgått og erstattet av «Create text with GPT using a prompt» (siden mai 2025 kalt «Run a prompt»); kun en gated preview-handling i Power Automate for desktop bærer fortsatt det gamle navnet, så claimet treffer en avviklet rad.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 337,
"claim": "Power Automate med AI Builder har handlingen «Create text with GPT» som kan brukes til å klassifisere intent før conditional branching.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#8",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "",
"reason": "Den kanoniske modellsiden omtaler text-embedding-3-large sin flerspråklighet kun via MIRACL-benchmarken (54,9) og oppgir ingen språktelling; ingen learn.microsoft.com-side sier «over 100 språk» for modellen.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 351,
"claim": "Embedding-modellen text-embedding-3-large støtter over 100 språk, slik at spørring og dokumenter på ulike språk matcher i samme vector space.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "The following table describes the semantic ranker throttling limits by tier, subject to available capacity in the region.",
"reason": "Første del holder (synonym-tabellen gir Basic 3 synonym maps), men den løftebærende delen «semantic ranker krever Standard-tier eller høyere» motsies: semantic ranker-tabellens tier-kolonner starter på Basic (2 samtidige forespørsler per search unit), og oversiktssiden sier den kan brukes gratis innenfor free-tier-grenser.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 399,
"claim": "Azure AI Search Basic tier støtter synonym maps, mens semantic ranker krever Standard-tier eller høyere.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/semantic-kernel/overview/",
"evidence_quote": "",
"reason": "Learn beskriver Semantic Kernel som «a lightweight, open-source development kit», men ingen learn.microsoft.com-side oppgir MIT-lisens eller «ingen lisenskostnad» — lisensteksten finnes kun i GitHub-repoet, som er utenfor Learn.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 400,
"claim": "Semantic Kernel er open source under MIT-lisens og har ingen lisenskostnad.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#12",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/billing-licensing",
"evidence_quote": "Starting on September 1, 2025, the common currency for agents changed from *messages* to *Copilot Credits*.",
"reason": "«Inkludert i M365 Copilot» og «standalone» er grunnet på samme side, men måleenheten i claimet er erstattet: sesjoner ble avløst av messages og deretter av Copilot Credits, som nå er «the common currency across Copilot Studio capabilities».",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 401,
"claim": "Copilot Studio lisensieres per bruker/sesjon og er inkludert i M365 Copilot eller tilgjengelig standalone.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-query-understanding.md#14",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-arc/edge-rag/search-types",
"evidence_quote": "The following tables list and describe all parameters you can configure for each search type in Agentic Retrieval.",
"reason": "Den kanoniske parameter-oppramsingen lister kun Temperature, Top-P, Top-N documents, Text strictness og Image strictness — verken query expansion, sub-query generation eller hypothetical answer generation forekommer; siden er dessuten omrammet fra Arc Edge RAG til Agentic Retrieval i Foundry Local.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md",
"line": 576,
"claim": "Azure Arc Edge RAG tilbyr søketype-parametere for query expansion | sub-query generation | hypothetical answer generation.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/rag-security-rbac.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-document-level-access-overview",
"evidence_quote": "SharePoint site groups (preview, starting in the 2026-05-01-preview REST API). Requires extra index configuration.",
"reason": "Claimen påstår at SharePoint-grupper ikke er støttet i preview, men siden lister dem nå som støttede prinsipaltyper fra 2026-05-01-preview; de tre andre gruppetypene stemmer, men denne løftebærende delen er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md",
"line": 250,
"claim": "Støttede gruppetyper for SharePoint ACL (preview): Microsoft Entra security groups (støttet) | Microsoft 365-grupper (støttet) | mail-enabled security groups (støttet) | SharePoint-grupper (ikke støttet i preview).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-security-rbac.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/search/search-region-support",
"evidence_quote": "You can create an Azure AI Search service in any of the following Azure public regions. ... France Central | Germany West Central | Italy North | Norway East | North Europe | Poland Central | Spain Central | Sweden Central | Switzerland North | Switzerland West | UK South | UK West | West Europe",
"reason": "Den kanoniske regionlisten for Azure AI Search fører opp Norway East, men Norway West er fraværende i hele oppregningen - tjenesten tilbys ikke der, så den ene løftebærende halvdelen av regionpåstanden er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md",
"line": 292,
"claim": "Data residency for norsk offentlig sektor løses ved å kjøre Azure AI Search i regionene Norway East/Norway West.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-security-rbac.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/deployment-types",
"evidence_quote": "",
"reason": "Ingen Learn-side anbefaler Sweden Central for norsk offentlig sektor; deployment-types-siden beskriver bare generiske residency-valg (Global, DataZone, Standard/Regional) og opplyser at EU Data Zone også omfatter Norge, så anbefalingen er verken bekreftet eller motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md",
"line": 331,
"claim": "Azure OpenAI anbefales kjørt i Sweden Central med data residency commitment for norsk offentlig sektor.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/rag-security-rbac.md#16",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-indexer-sharepoint-access-control-lists",
"evidence_quote": "Prerequisites - Azure AI Search on a billable tier (Basic or higher) in any region. - SharePoint in Microsoft 365 sites, libraries, folders, and files with configured permissions. - Complete all configuration steps in the SharePoint indexer documentation ... - Configure Microsoft Entra application permissions and a credential appropriate for your scenario. ... - REST API version 2026-05-01-preview or an equivalent preview SDK package.",
"reason": "Den kanoniske forutsetningslisten for SharePoint-ACL-tilnærmingen nevner ingen Microsoft 365 E3/E5-lisens, og SharePoint-tjenestebeskrivelsen viser at SharePoint inngår i langt flere planer (Business Basic/Standard/Premium, Office 365 E1/E3/E5, F1/F3 og standalone SharePoint Plan 1/2) - det påståtte E3/E5-kravet finnes ikke i kilden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md",
"line": 346,
"claim": "SharePoint ACL-tilnærmingen forutsetter SharePoint-lisensiering via Microsoft 365 E3/E5.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/self-reflective-rag.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/self-reflective-rag.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/evaluation-evaluators/rag-evaluators",
"evidence_quote": "Groundedness Pro (preview) | System evaluation | You want a strict groundedness definition powered by Azure AI Content Safety and use our service model ... Response Completeness (preview) | System evaluation | You want to ensure the RAG response doesn't miss critical information (recall aspect) from your ground truth",
"reason": "Siden merker to av seks RAG-evaluatorer eksplisitt som preview (Groundedness Pro og Response Completeness), så den bærende delen «evaluatorene er GA» er motsagt selv om agentic retrieval-delen holder.",
"file": "skills/ms-ai-engineering/references/rag-architecture/self-reflective-rag.md",
"line": 4,
"claim": "Microsoft Foundry-evaluatorene er GA, mens agentic retrieval er i Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/self-reflective-rag.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/evaluation-evaluators/rag-evaluators",
"evidence_quote": "Groundedness - Is the response grounded in the provided context without fabrication? Groundedness Pro - Does the response strictly adhere to the context (Azure AI Content Safety)? Relevance - Does the response accurately address the user's query? Response Completeness (preview) - Does the response cover all critical information from ground truth?",
"reason": "Den kanoniske oppregningen av RAG-evaluatorer inneholder seks evaluatorer og coherence er ikke blant dem (Coherence er kategorisert som general purpose-evaluator), så påstanden om coherence som innebygd RAG-evaluator er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/self-reflective-rag.md",
"line": 29,
"claim": "Microsoft Foundry tilbyr innebygde evaluatorer for RAG-kvalitetsvurdering: groundedness | relevance | coherence — alle med 1-5-skala.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/self-reflective-rag.md#3",
"judge_verdict": "source_silent",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/search/agentic-retrieval-overview",
"evidence_quote": "",
"reason": "Preview-statusen er dekket, men ingen learn.microsoft.com-side oppgir noen tallfestet relevansgevinst; oversiktssiden og transparensnotatet beskriver LLM-assistert query planning uten «40 %», og tallet er bærende (ikke illustrativt), så det kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/self-reflective-rag.md",
"line": 29,
"claim": "Azure AI Search agentic retrieval er i preview og forbedrer retrieval-relevans med opptil 40 % gjennom LLM-assistert query planning.",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/semantic-ranker-reranking.md#14",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/semantic-how-to-enable-disable",
"evidence_quote": "| Free (default) | Provides a monthly free request allowance. After the free allowance is consumed, semantic ranker requests return a billing error. | Available on all pricing tiers. | | Standard | Pay-as-you-go pricing after the monthly free allowance is consumed. | Requires the Basic tier or higher. |",
"reason": "Siden sier gratisplanen er tilgjengelig på alle pricing tiers og at standard-planen krever Basic tier or higher - det finnes ikke noe S1-krav, så tier-terskelen i påstanden er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md",
"line": 171,
"claim": "Bruk av semantic ranking i RAG-mønsteret krever S1-tier.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/semantic-ranker-reranking.md#15",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/agentic-retrieval-overview",
"evidence_quote": "Some agentic retrieval features are generally available in the 2026-04-01 REST API via programmatic access.",
"reason": "Preview-statusen er superseded (deler av agentic retrieval er GA i 2026-04-01), og siden beskriver semantic ranker i pipelinen som L2 reranking - ingen L3-ranking finnes; begge lastbærende deler svikter.",
"file": "skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md",
"line": 184,
"claim": "Agentic Retrieval med LLM-assistert L3-ranking er en preview-funksjon (2025).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/semantic-ranker-reranking.md#17",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-region-support",
"evidence_quote": "| Norway East | ✅ | ✅ | | ✅ | | |",
"reason": "I den kanoniske regionstabellen (kolonner: AI enrichment, Availability zones, Agentic retrieval, Confidential computing, Semantic ranker, Query rewrite) er Semantic ranker-kolonnen tom for Norway East, og Norway West står ikke i Europa-tabellen i det hele tatt - fraværet motbeviser regionpåstanden.",
"file": "skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md",
"line": 230,
"claim": "Semantic ranker er tilgjengelig i regionene Norway East og Norway West, og all prosessering skjer i valgt region uten at data sendes ut av regionen.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/semantic-ranker-reranking.md#18",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/semantic-how-to-enable-disable",
"evidence_quote": "",
"reason": "To-plan-strukturen (Free som default på alle tiers, Standard pay-as-you-go etter gratiskvoten) er bekreftet, men ingen learn.microsoft.com-side oppgir tallet 1000 requests per måned - Learn omtaler kun a monthly free request allowance og henviser til den JS-rendrede prissiden, så kvantumet kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md",
"line": 245,
"claim": "Prismodellen for semantic ranker har to planer: Gratis (1000 semantic ranker-requests per måned, tilgjengelig på alle tier inkludert Free) | Standard (pay-as-you-go per 1000 requests etter gratis kvote).",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/streaming-rag-responses.md#13",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/api-management/forward-request-policy",
"evidence_quote": "timeout | The amount of time in seconds to wait for the HTTP response headers to be returned by the backend service before a timeout error is raised. ... | No | 300",
"reason": "API Management sin standard backend-timeout er 300 sekunder, ikke 30 — den bærende tallverdien i claimet motsies, og siden advarer i tillegg om at verdier over 240 s kanskje ikke honoreres.",
"file": "skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md",
"line": 274,
"claim": "Azure API Management har en standard route timeout på 30 s, som må økes til 300 s+ for SSE-endepunkter.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/streaming-rag-responses.md#14",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/power-automate/limits-and-config",
"evidence_quote": "",
"reason": "Ingen Learn-side sier at Power Automate mangler native SSE-streaming; limits-siden oppgir kun timeout-grenser (120 s synkront), så påstanden kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md",
"line": 295,
"claim": "Power Automate støtter ikke native SSE-streaming.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/streaming-rag-responses.md#15",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/mcp-add-existing-server-to-agent",
"evidence_quote": "Currently, Copilot Studio supports the Streamable transport type. Given that SSE transport is deprecated, Copilot Studio no longer supports SSE for MCP after August 2025.",
"reason": "Den kanoniske siden som teller opp støttede transporter for custom connector-baserte serverkoblinger lister kun Streamable og sier eksplisitt at SSE ikke lenger støttes; ingen Learn-side dokumenterer SSE-streaming for Copilot Studio custom connectors i preview.",
"file": "skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md",
"line": 299,
"claim": "Copilot Studio støtter streaming via SSE for custom connectors (preview).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/streaming-rag-responses.md#17",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/semantic-kernel/support/",
"evidence_quote": "",
"reason": "Kun første del er dekket (Responses-siden krever Azure-abonnement og Foundry-/Azure OpenAI-ressurs); Learn kaller Semantic Kernel open source uten å oppgi MIT, og prisdetaljene for Application Gateway per gateway-time og API Management Consumption-tier ligger på JS-rendrede pricing-sider som ikke kan hentes.",
"file": "skills/ms-ai-engineering/references/rag-architecture/streaming-rag-responses.md",
"line": 369,
"claim": "Lisenskrav: Azure OpenAI krever Azure subscription + OpenAI resource | Semantic Kernel er open source (MIT) uten lisenskostnad | Application Gateway faktureres som Azure-kostnad per gateway-time | API Management har per call/måned-tier (Consumption for lavt volum).",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-index-size",
"evidence_quote": "Vector optimization techniques are generally available. Use capabilities like narrow data types, scalar and binary quantization, and elimination of redundant storage to reduce your vector quota and storage quota consumption.",
"reason": "Hybrid search som GA holder, men den andre lastbærende delen svikter: Learn oppgir scalar quantization som generelt tilgjengelig (GA), ikke preview.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 4,
"claim": "Hybrid search i Azure AI Search er GA, mens scalar quantization er i Preview.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#2",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-create-index",
"evidence_quote": "vectorSearch.algorithms is either hnsw or exhaustiveKnn. These are the Approximate Nearest Neighbors (ANN) algorithms used to organize vector content during indexing.",
"reason": "Den kanoniske opplistingen av vektoralgoritmer nevner kun hnsw og exhaustiveKnn; «Flat indexing (linear scan)» finnes ikke som algoritme i Azure AI Search.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 37,
"claim": "Azure AI Search tilbyr vektoralgoritmene Hierarchical NSW (HNSW, approximate nearest neighbor) | Exhaustive KNN (exact nearest neighbor) | Flat indexing (linear scan).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/hybrid-search-ranking",
"evidence_quote": "If you add vector weighting, the initial scores are subject to a weighting multiplier that increases or decreases the score. The default is 1.0, which means no weighting and the initial score is used as-is in RRF scoring.",
"reason": "Vekting i hybrid search skjer med RRF og parameteren weight (standard 1.0) — noen alpha-parameter finnes ikke i den kanoniske dokumentasjonen, og top har standardverdi 50, ikke 10 («$top ... This defaults to 50» i Search Documents REST).",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 71,
"claim": "Vekting av hybrid scores i Azure AI Search styres av parametrene alpha (balanse mellom vector 1.0 og BM25 0.0, standard 0.5, range 0.0–1.0) | k (antall vektorer fra vector search, standard 50, range 1–1000) | top (totale resultater etter merge, standard 10, range 1–1000).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#8",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "| Search queries (POST /indexes/{index}/docs/search) | Varies by SU count and query complexity | 50 queries/sec (aggregate read throttle per index) |",
"reason": "Den kanoniske throttling-tabellen oppgir ingen grense på 3000 requests per sekund per replika — søkespørringer varierer med antall search units og spørringskompleksitet.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 168,
"claim": "Azure AI Search har en rate limit på 3000 requests per sekund per replika.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#9",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-create-index",
"evidence_quote": "",
"reason": "Learn oppgir at text-embedding-3-large støtter 1 til 3072 dimensjoner (native output 3 072), men ingen side sier at modellen brukes med 1536 dimensjoner i en Azure AI Search-index for standard RAG — verdien er tillatt, men verken bekreftet eller motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 178,
"claim": "Embedding-modellen text-embedding-3-large brukes med 1536 dimensjoner i en Azure AI Search-index for standard RAG.",
"disposition": "unsourced"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#10",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-quantization",
"evidence_quote": "Scalar quantization compresses float values into narrower data types. AI Search currently supports int8, which is 8 bits, reducing vector index size fourfold.",
"reason": "Scalar quantization reduserer datatypen (float32 til int8), ikke antall dimensjoner: 1536 float32 (6 144 byte) blir 1536 int8 (én firedel), ikke 384 int8 / 384 byte — dimensjonsreduksjon er en separat MRL-funksjon (truncationDimension).",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 235,
"claim": "Scalar quantization i Azure AI Search komprimerer vektorer fra 1536 float32 (6 KB) til 384 int8 (384 bytes).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#11",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-index-size",
"evidence_quote": "Vector optimization techniques are generally available. Use capabilities like narrow data types, scalar and binary quantization, and elimination of redundant storage to reduce your vector quota and storage quota consumption.",
"reason": "Scalar quantization er GA (og står ikke i Learn sin liste over preview-funksjoner i Azure AI Search), så statuspåstanden «preview» er motsagt.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 237,
"claim": "Scalar quantization er en preview-funksjon i Azure AI Search (2026).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/knowledge-azure-ai-search",
"evidence_quote": "Select Add knowledge from either the Overview or Knowledge pages, or the Properties of a generative answers node. From the Add knowledge dialog, select Featured. Select Azure AI Search.",
"reason": "Den dokumenterte navigasjonen er Add knowledge → Featured → Azure AI Search (alternativt Data sources → Azure AI Search), ikke «Security & Data → Knowledge sources → Add Azure AI Search»; den lastbærende stien er feil.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 318,
"claim": "Copilot Studio konfigurerer Azure AI Search som kunnskapskilde for Generative answers via Security & Data → Knowledge sources → Add Azure AI Search, uten kontroll over HNSW-parametere (managed service).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#13",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/connectors/azureaisearch/",
"evidence_quote": "| Agentic Search (Preview) | Delete a document | Delete multiple documents | Get index statistics | Get search indexes | Index a document | Index multiple documents | Merge a document | Search vectors | Search vectors with natural language | Semantic Hybrid Search |",
"reason": "Den kanoniske opplistingen av handlinger i Azure AI Search-connectoren inneholder ingen handling som heter «Search documents (semantic)» (nærmeste er «Semantic Hybrid Search»), og connectoren stiller ingen krav om et felt ved navn contentVector.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 324,
"claim": "AI Builder i Power Automate støtter semantic search via Azure AI Search-connectoren med handlingen «Search documents (semantic)», som krever en index med contentVector-felt.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#16",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity",
"evidence_quote": "| After May 17, 2024 ^2^ | 15 | 160 | 512 | 1,024 | 2,048 | 4,096 | N/A |",
"reason": "Lagringstallene 2/25/100/200 GB matcher kun den daterte legacy-raden «Before April 3, 2024»; gjeldende grenser er 15/160/512/1024 GB, og replika-tallene er også feil (Basic 3, S1–S3 12, ikke 1/3/6/12).",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 368,
"claim": "Azure AI Search tilbys i tierne Basic (2 GB storage, 3 queries/sek, 1 replica) | S1 (25 GB, 15 queries/sek, 3 replicas) | S2 (100 GB, 60 queries/sek, 6 replicas) | S3 (200 GB, 60 queries/sek, 12 replicas).",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#17",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/semantic-how-to-enable-disable",
"evidence_quote": "| Free (default) | Provides a monthly free request allowance. After the free allowance is consumed, semantic ranker requests return a billing error. | Available on all pricing tiers. |",
"reason": "Gratisplanen for semantic ranker er tilgjengelig på alle pristiers (standardplanen krever Basic eller høyere), ikke bare S1 og oppover, og ingen Learn-side oppgir et gratistak på 50 000 spørringer per måned.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 384,
"claim": "Semantic Ranker er inkludert i S1 og høyere tiers, med et gratis usage cap på 50 000 queries per måned.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#18",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/power-platform/admin/powerapps-flow-licensing-faq",
"evidence_quote": "Licensed by tenant, Microsoft Copilot Studio entitles a tenant to 25,000 messages per month.",
"reason": "Lisensen gir 25 000 meldinger per tenant per måned, ikke 20 000.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 385,
"claim": "Integrasjon med Copilot Studio krever Copilot Studio-lisens med 20 000 meldinger per måned.",
"disposition": "outdated"
},
{
"id": "ms-ai-engineering/rag-architecture/vector-indexing-techniques.md#19",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-create-index",
"evidence_quote": "vectorSearch.algorithms.m is the bi-directional link count. Default is 4. The range is 4 to 10.",
"reason": "HNSW-parameteren for koblinger heter m, ikke maxConnections — navnet er selve påstanden (lastbærende API-identifikator), så R7 sin leniens for illustrerende tall gjelder ikke, selv om efSearch og \"exhaustive\": true stemmer.",
"file": "skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md",
"line": 433,
"claim": "I hybrid search-indekser er HNSW standard ANN-algoritme med efSearch og maxConnections som tunbare parametere, mens eKNN (exhaustive K-Nearest Neighbors) gir fullstendig søk og aktiveres med \"exhaustive\": true i spørringen.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/alerting-strategies-escalation.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/fundamentals/service-limits",
"evidence_quote": "1,000 email actions in an action group.No more than 100 emails every hour for each email address per region.",
"reason": "1000 email actions per action group holds, but the rate limit is 100 emails/hour per email address per region, not 1000 emails/hour per action group; the load-bearing rate part is contradicted.",
"file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md",
"line": 49,
"claim": "Email-notifications: opptil 1000 mottakere per action group; rate limit 1000 emails per hour per action group",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/alerting-strategies-escalation.md#12",
"judge_verdict": "source_silent",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/best-practices-alerts",
"evidence_quote": "Azure Monitor activity alerts, service health alerts, and resource health alerts are free.",
"reason": "First part (activity/service health/resource health alerts free of charge) is grounded, but the load-bearing 'first 10 metric alert rules free per subscription' figure is stated on no official learn page (pricing is JS-rendered) and is not contradicted either, so the composite cannot be grounded.",
"file": "skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md",
"line": 447,
"claim": "Activity Log alerts, Service Health alerts og Resource Health alerts er gratis (ingen kostnad per rule/evaluering); first 10 metric alert rules free per subscription",
"disposition": "unsourced"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 21,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-smart-detections-migration",
"evidence_quote": "You can trigger the smart detection migration to alerts for a specific Application Insights resource by using ARM templates.",
"reason": "De tre metodene stemmer (portal, Azure CLI, ARM-maler), men den bærende presiseringen «ARM templates for batch-migrering» er motsagt: ARM-malene er scoped til én bestemt ressurs, mens batch («Migrate all Application Insights resources in this subscription» / subscription-scope i CLI-body) er portal- og CLI-veien.",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 78,
"claim": "Migrering av smart detection til alerts kan gjøres på tre måter: Azure Portal (manuell migrering) | Azure CLI med REST API | ARM templates for batch-migrering.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#16",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/defender-for-cloud/alerts-ai-workloads",
"evidence_quote": "Detected credential theft attempts on an Azure AI model deployment ... A Jailbreak attempt on an Azure AI model deployment was blocked by Azure AI Content Safety Prompt Shields ... Corrupted AI application\\model\\data directed a phishing attempt at a user ... Suspected wallet attack - volume anomaly ... Access anomaly in AI resource",
"reason": "Den kanoniske alert-oversikten for AI-workloads enumererer langt flere enn tre kategorier og inneholder ingen «Model Inference Anomalies» eller «Data Exfiltration Patterns»; oversiktssiden lister truslene som «data leakage, data poisoning, jailbreak, credential theft, and more», så tre-kategori-taksonomien er ikke Microsofts.",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 341,
"claim": "Microsoft Defender for AI dekker tre AI-spesifikke deteksjonskategorier: Jailbreak Attempt Detection | Model Inference Anomalies | Data Exfiltration Patterns.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#17",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/templates/microsoft.security/pricings",
"evidence_quote": "AIPromptEvidence - Exposes the prompts passed between the user and the AI model as alert evidence ... Available for AI plan. ... pricingTier | Indicates whether the Defender plan is enabled on the selected scope ... 'Free''Standard' (required)",
"reason": "Kommandoen az security pricing create og tier Standard stemmer, men planen heter «AI» i API-et (jf. «Available for AI plan», på linje med CloudPosture/Containers/VirtualMachines) — ingen Learn-side navngir en «AIServices»-plan, og plannavnet er nettopp strengen leseren kopierer inn i CLI-kallet.",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 363,
"claim": "Defender for AI aktiveres med az security pricing create, plannavn AIServices og tier Standard.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#19",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/anomaly-detector/overview",
"evidence_quote": "We recommend migrating to Microsoft Fabric, which integrates the open-source microsoft/anomaly-detector, or to the open-source anomaly-detector project directly.",
"reason": "Den kanoniske siden som ville enumerert alternativene anbefaler Microsoft Fabric eller open source anomaly-detector; ingen av de fire oppgitte alternativene (Azure ML model monitoring, Azure Monitor KQL, Stream Analytics, egne ML-modeller) står der.",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 374,
"claim": "Alternativer etter retirement av Azure AI Anomaly Detector: Azure ML model monitoring | Azure Monitor KQL-baserte funksjoner | Azure Stream Analytics | custom modeller i Azure ML.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#20",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/real-time-intelligence/anomaly-detection",
"evidence_quote": "A Python plugin enabled on that same Eventhouse ... Select the Python 3.11.7 DL plugin and select Done ... Tests multiple anomaly detection algorithms ... A list of recommended algorithms, ranked by their effectiveness for your data.",
"reason": "Eventhouse-Python-plugin-delen stemmer, men den kanoniske RTI-siden (og modell-spesifikasjonssiden, som lister TSB-AD-/MS-utviklede modeller) nevner ikke SimpleDetectAnomalies fra synapse.ml.services — den SynapseML-klassen hører til Spark-notebook-oppskriften i Fabric Data Science mot den utgående Anomaly Detector-tjenesten, ikke Eventhouse-mekanismen.",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 385,
"claim": "Microsoft Fabric Real-Time Intelligence støtter anomaly detection via Python-plugin i Eventhouse med SimpleDetectAnomalies fra synapse.ml.services.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/anomaly-detection-ai-systems.md#21",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/app/application-insights-faq",
"evidence_quote": "Application Insights is billed through the Log Analytics workspace into which its log data ingested. The default Pay-as-you-go Log Analytics pricing tier includes 5 GB per month of free data allowance per billing account.",
"reason": "5 GB gratis per måned stemmer, men rammen er feil: fribeløpet ligger i Pay-as-you-go-tieren i Log Analytics, ikke i en «Basic-tier» (Basic Logs er en tabellplan, ikke en tier som gir 5 GB gratis).",
"file": "skills/ms-ai-governance/references/monitoring-observability/anomaly-detection-ai-systems.md",
"line": 505,
"claim": "Application Insights er inkludert i Basic-tier, gratis opp til 5 GB per måned.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 26,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#1",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/purview/compliance-manager-assessments#assessments-for-ai-regulations",
"evidence_quote": "The AI regulations listed below align with compliance requirements such as monitoring AI interactions and preventing data loss in AI applications: - EU Artificial Intelligence Act - ISO/IEC 23894:2023 - ISO/IEC 42001:2023 - NIST AI Risk Management Framework (RMF) 1.0",
"reason": "Den kanoniske enumereringen av AI-maler lister ISO/IEC 23894:2023 og ISO/IEC 42001:2023 - ISO/IEC 23053:2022 er fraværende, så den påståtte malen finnes ikke (AI Act og NIST AI RMF stemmer).",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 41,
"claim": "Microsoft Purview Compliance Manager har AI-spesifikke assessment-templates: AI Act | ISO/IEC 23053:2022 | NIST AI RMF.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/purview/compliance-manager-assessments#assessments-for-ai-regulations",
"evidence_quote": "Compliance Manager provides four premium regulatory templates to help your organization assess, implement, and strengthen its compliance against AI regulations. ... - EU Artificial Intelligence Act - ISO/IEC 23894:2023 - ISO/IEC 42001:2023 - NIST AI Risk Management Framework (RMF) 1.0",
"reason": "360+-tallet er grunnet (over 360 regulatory templates), men den load-bearende AI-listen er feil: de AI-spesifikke malene er AI Act, ISO/IEC 23894:2023, ISO/IEC 42001:2023 og NIST AI RMF 1.0 - GDPR AI-tillegg finnes ikke, og CCPA/HIPAA står under Premium templates, ikke Premium AI templates.",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 45,
"claim": "Compliance Manager har 360+ ferdigbygde regulatory templates, inkludert AI-spesifikke: EU AI Act | GDPR AI-tillegg | CCPA | HIPAA.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#6",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/security/security-for-ai/security-dashboard-for-ai",
"evidence_quote": "Identity and access risk | Data security risk | Cloud security risk | Misconfigurations and attack paths | Agents with sensitive interactions",
"reason": "Dashbordets faktiske sider er Overview, AI inventory og AI risk (med risikokategoriene over) - Threat Detection, Access Control og Compliance Status står ikke som seksjoner noe sted på den kanoniske siden, og inventar-siden heter AI inventory, ikke AI Agent Inventory.",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 81,
"claim": "Security Dashboard for AI har seksjonene AI Agent Inventory | Threat Detection | Data Security | Access Control | Compliance Status.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#24",
"judge_verdict": "source_silent",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/how-to/create-projects",
"evidence_quote": "",
"reason": "Første del er grunnet (Select a Location or use the default. The location is the region where the project resources are hosted), men ingen offisiell Learn-side sier at prosjektet ikke kan flyttes til en annen region senere - create-projects dokumenterer ingen flytte-operasjon, og eneste treff på påstanden er et community-svar i Microsoft Q&A, ikke dokumentasjon.",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 355,
"claim": "I Microsoft Foundry velges region ved opprettelse av prosjektet, og prosjektet kan ikke flyttes til en annen region senere.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#25",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/privacy/eudb/eu-data-boundary-transfers-for-optional-capabilities",
"evidence_quote": "When the customer selects any \"Global\" deployment type (for example, Global Standard), prompts and completions sent to and output by that deployment may be processed, for inferencing or fine-tuning, in any Azure AI Foundry Models region globally, including outside the EU for an Azure AI Foundry Models resource created in a region within the EU.",
"reason": "Kilden motsier garantien direkte: med Global-deploymenttyper kan prompts og completions prosesseres utenfor EU, og EU Data Boundary-oversikten sier selv at forpliktelsen er subject to limited circumstances where Customer Data ... will continue to be transferred outside the EU Data Boundary.",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 356,
"claim": "Azure OpenAI med EU Data Boundary garanterer at prompts og responses ikke forlater EU.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/compliance-monitoring-ai-governance.md#26",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/purview/compliance-manager-regulations",
"evidence_quote": "The Microsoft Data Protection Baseline regulatory template is available for organizations at all subscription levels to use. The regulations designated as premium require purchase of a license to use them.",
"reason": "Lisensmodellen er en annen enn claimet: premium-maler (inkludert Premium AI templates) krever kjøpt lisens uavhengig av E5, ikke at E5 gir 360+ maler; i tillegg er ISO/IEC 23053 ikke blant AI-malene (kanonisk liste: ISO/IEC 23894:2023 og ISO/IEC 42001:2023).",
"file": "skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md",
"line": 388,
"claim": "Compliance Manager-lisensiering: Microsoft 365 E3 gir kun basic assessments (Microsoft baseline) uten AI-spesifikke templates | Microsoft 365 E5 gir 360+ regulatory templates, custom templates og automatiserte assessments inkl. AI Act, ISO/IEC 23053 og NIST AI RMF | Purview Compliance standalone gir full Compliance Manager + DLP + eDiscovery med DSPM for AI, AI audit logs og retention for AI-apper.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 20,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/fine-tuning-deploy",
"evidence_quote": "After you deploy a customized model, if at any time the deployment remains inactive for more than 15 days, the deployment is deleted. ... The deletion of an inactive deployment doesn't delete or affect the underlying customized model.",
"reason": "15-dagers automatisk sletting gjelder utelukkende distribusjoner av tilpassede (finjusterte) modeller — påstanden utvider regelen til Azure OpenAI-deployments generelt, og den bærende avgrensningen er dermed feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 56,
"claim": "Azure OpenAI-deployments som har vært inaktive i 15 dager slettes automatisk, mens den underliggende modellen bevares.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#15",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/power-bi/connect-data/refresh-data",
"evidence_quote": "you can configure up to eight daily time slots if your semantic model is on shared capacity, or 48 time slots on Power BI Premium",
"reason": "Planlagt/automatisk oppdatering krever ikke Premium — delt kapasitet gir opptil åtte daglige oppdateringer (Premium hever kun taket til 48), og Cost Management-dokumentasjonen stiller ingen Premium-betingelse for eksportert kostnadsdata eller deling.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 305,
"claim": "Power BI Premium kreves for å aktivere automatisk oppdatering (automatic refresh) og deling med stakeholders av eksportert kostnadsdata.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#16",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/monitor-openai-reference",
"evidence_quote": "Generated Completion Tokens Number of tokens generated (output) from an OpenAI model. Applies to PTU, PTU-managed and Pay-as-you-go deployments. | GeneratedTokens",
"reason": "Den kanoniske metrikk-katalogen for Microsoft.CognitiveServices/accounts inneholder ingen metrikk TokensGenerated; utgangstokens heter GeneratedTokens (og OutputTokens under Models - Usage), så det bærende strengnavnet er feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 320,
"claim": "Azure OpenAI-deployments eksponerer metrikken TokensGenerated, som kan hentes med Get-AzMetric.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#17",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs",
"evidence_quote": "",
"reason": "Verken den siterte siden eller eksportdokumentasjonen oppgir regioner for lagring av kostnadsdata — de sier kun at data eksporteres til en lagringskonto du velger, så Norway East/Norway West kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 338,
"claim": "Cost data kan lagres i de norske Azure-regionene Norway East og Norway West.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing",
"evidence_quote": "Provisioned deployments (Regional, Data Zone, and Global) are charged at an hourly rate ($/PTU/hr) based on the number of PTUs deployed. ... you're billed hourly based on the number of Provisioned Throughput Units (PTUs) you deploy, rather than the number of tokens consumed.",
"reason": "PTU faktureres per time på antall distribuerte PTU-er (med valgfri reservasjon som rabattmekanisme), ikke som fast månedlig kostnad målt i TPM/RPM — den månedlige Commitment-modellen er stengt for nye kunder, så den bærende prismodell-beskrivelsen er utdatert.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 392,
"claim": "Azure OpenAI tilbyr to prismodeller: PTU (Provisioned Throughput Units — fast månedlig kostnad med garantert throughput målt i TPM/RPM) | Pay-as-you-go (betaling kun for faktisk forbruk).",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/cost-monitoring-cost-attribution.md#20",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/api-management/plan-manage-costs",
"evidence_quote": "For example, a unit of the Basic tier has an estimated maximum throughput of approximately 1,000 requests per second. ... For example, two units of the Standard tier provide an estimated throughput of approximately 2,000 requests per second.",
"reason": "Basic 1 000 req/s stemmer, men siden angir ca. 1 000 req/s per Standard-enhet (to enheter gir ca. 2 000), ikke 2 500; Consumption skaleres automatisk uten publisert req/s-tall, og Premium-tallet finnes ikke på Learn — én bærende verdi er dermed motsagt.",
"file": "skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md",
"line": 415,
"claim": "Maksimal throughput per Azure API Management-tier: Consumption 1000 req/sek | Basic 1000 req/sek | Standard 2500 req/sek | Premium 4000 req/sek.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/custom-dashboards-ai-operations.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry-classic/how-to/monitor-applications",
"evidence_quote": "These views bring key metrics - token consumption, latency, exceptions, response quality - into a single pane that provides transparency to teams.",
"reason": "Foundrys workbook sporer token consumption/latency/exceptions/response quality, mens claimens «total conversations», «tool usage» og «topic analytics» er Copilot Studio Dashboard-metrikker — flere bærende deler er tilskrevet feil produkt.",
"file": "skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md",
"line": 46,
"claim": "Microsoft Foundrys out-of-box workbook sporer: Generative AI metrics (total conversations | latency | exceptions) | Tool usage (hvilke extensions og tools brukes mest) | Topic analytics (hvilke conversation topics dominerer) | Operational health (success rates | error patterns | response times).",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/custom-dashboards-ai-operations.md#12",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/power-bi/connect-data/desktop-data-sources",
"evidence_quote": "The Azure category provides the following data connections: Azure SQL Database, Azure Synapse Analytics SQL, Azure Analysis Services database, Azure Database for PostgreSQL, Azure Blob Storage, Azure Table Storage, Azure Cosmos DB v1, Azure Data Explorer (Kusto), Azure Data Lake Storage Gen2, Azure HDInsight (HDFS), Azure HDInsight Spark, HDInsight Interactive Query, Microsoft Cost Management, Azure Resource Graph, Azure HDInsight on AKS Trino (Beta), Azure Cosmos DB v2, Azure Databricks, Azure Synapse Analytics workspace (Beta)",
"reason": "Den kanoniske konnektorlisten for Get Data → Azure i Power BI Desktop inneholder ingen «Azure Monitor Logs»-konnektor; den siterte siden dokumenterer i stedet eksport som M-query eller nytt Dataset.",
"file": "skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md",
"line": 194,
"claim": "Power BI Desktop har en Azure Monitor Logs-konnektor tilgjengelig via Get Data → Azure → Azure Monitor Logs.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 25,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/data-residency-audit-monitoring.md#2",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/purview/audit-solutions-overview",
"evidence_quote": "The default retention period for Audit (Standard) changed from 90 days to 180 days. Audit (Standard) logs generated before October 17, 2023, are retained for 90 days. Audit (Standard) logs generated on or after October 17, 2023, follow the new default retention of 180 days.",
"reason": "Claimet treffer kun den historiske raden (før 17. oktober 2023); gjeldende default for Audit (Standard) er 180 dager, ikke 90 — den lastbærende delen er utdatert selv om Premium-delen om retention policies stemmer.",
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"line": 38,
"claim": "Microsoft Purview Audit Standard har 90 dagers retention som default, mens Premium gir konfigurerbare retention policies.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/data-residency-audit-monitoring.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/purview/audit-solutions-overview",
"evidence_quote": "The following table compares the key capabilities available in Audit (Standard) and Audit (Premium). ... Up to 1-year audit log retention | 10-year audit log retention | Audit log retention policies | Intelligent insights",
"reason": "Den kanoniske sammenligningstabellen som ville enumerert forskjellene mellom nivåene inneholder ingen compliance-sertifiseringer i det hele tatt — verken ISO 27001/SOC for Standard eller FedRAMP/«GDPR-optimalisert» som Premium-tillegg; sertifiseringer gjelder tjenesten, ikke SKU-nivået.",
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"line": 41,
"claim": "Microsoft Purview Audit Standard dekker ISO 27001 | SOC 1/2/3, mens Premium i tillegg dekker FedRAMP | GDPR-optimalisert.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/data-residency-audit-monitoring.md#15",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/office365/servicedescriptions/microsoft-365-service-descriptions/microsoft-365-tenantlevel-services-licensing-guidance/microsoft-purview-service-description",
"evidence_quote": "Which licenses provide the rights for a user to benefit from the service? Microsoft 365 E5/A5/G5/E3/A3/G3, Microsoft 365 Business Premium, SharePoint Online Plan 2, OneDrive for Business (Plan 2), Exchange Online Plan 2; Office 365 E5/A5/G5/E3/A3/G3; Microsoft Purview Suite/EDU/GOV/FLW",
"reason": "Lisenskravet i claimet er for høyt: den kanoniske lisenstabellen gir DLP-rettigheter også med E3/A3/G3 (og Business Premium), og DLP-aktiviteter logges i unified audit log som er Audit (Standard) — det finnes ingen E5/G5-terskel slik claimet påstår.",
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"line": 196,
"claim": "Microsoft Purview DLP med audit krever E5/G5-lisensiering eller Purview standalone.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/data-residency-audit-monitoring.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/purview/audit-copilot",
"evidence_quote": "Pay-as-you-go billing doesn't apply to Microsoft applications. All Microsoft applications, including Microsoft Copilots like Microsoft Security Copilot, Copilot in Microsoft Fabric, and custom applications built using Microsoft Copilot Studio and Microsoft Foundry are included in Audit Standard.",
"reason": "Nivået er feil: Copilot Studio-interaksjoner logges under Audit (Standard), ikke Premium, og «alle» holder ikke — Purview-siden for Copilot Studio krever pay-as-you-go for agenter publisert til ikke-Microsoft-kanaler.",
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"line": 274,
"claim": "Purview Audit Premium logger alle agent-interaksjoner i Copilot Studio.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/data-residency-audit-monitoring.md#22",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/azure/azure-monitor/logs/logs-table-overview",
"evidence_quote": "Interactive retention | The period during which data is available for queries, alerts, and other Azure Monitor features. Interactive retention ranges from 4 to 730 days for Analytics tables, and is fixed at 30 days for Basic and Auxiliary tables. Long-term retention | A low-cost extension that keeps data in your workspace",
"reason": "Rammeverket er erstattet: gjeldende modell har to retention-stadier (Interactive 4–730 dager for Analytics, fast 30 dager for Basic/Auxiliary, og Long-term retention opptil 12 år) — ikke «Interactive 0-31 dager | Basic 31 dager til 2 år | Archive 2+ år», og Basic er et table plan, ikke et retention-nivå.",
"file": "skills/ms-ai-governance/references/monitoring-observability/data-residency-audit-monitoring.md",
"line": 414,
"claim": "Azure Monitor Log Analytics har retention-nivåene Interactive 0-31 dager (default) | Basic 31 dager til 2 år | Archive 2+ år.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 18,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/distributed-tracing-ai-pipelines.md#2",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/foundry/observability/concepts/trace-agent-concept",
"evidence_quote": "Child Span | invoke_agent | agent_to_agent_interaction | Traces communication between agents.",
"reason": "De kanoniske span-navnene på Learn er execute_task, invoke_agent, execute_tool, create_agent og agent_to_agent_interaction — uten gen_ai.-prefiks; ingen Learn-side navngir gen_ai.model.completion, gen_ai.tool.execution eller gen_ai.agent.invoke, så de påståtte strengene (som ER selve assertionen) er feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md",
"line": 55,
"claim": "OpenTelemetrys semantiske konvensjoner for generativ AI definerer standard AI-span: gen_ai.model.completion | gen_ai.tool.execution | gen_ai.agent.invoke | gen_ai.agent_planning | gen_ai.agent_to_agent_interaction.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/distributed-tracing-ai-pipelines.md#3",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/microsoft-agent-365/developer/observability-attribute-reference",
"evidence_quote": "gen_ai.usage.input_tokens | CH | O | -- | Input token count, string-encoded.",
"reason": "Learns kanoniske gen_ai-attributtabell oppgir gen_ai.usage.input_tokens, gen_ai.usage.output_tokens, gen_ai.response.finish_reasons (flertall) og gen_ai.provider.name — påstandens gen_ai.usage.prompt_tokens, gen_ai.usage.completion_tokens, gen_ai.response.finish_reason og gen_ai.system er superserte navn; kun gen_ai.request.model stemmer.",
"file": "skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md",
"line": 62,
"claim": "Standard gen_ai-attributter er: gen_ai.system | gen_ai.request.model | gen_ai.usage.prompt_tokens | gen_ai.usage.completion_tokens | gen_ai.response.finish_reason.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/distributed-tracing-ai-pipelines.md#11",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/develop/langchain-models",
"evidence_quote": "",
"reason": "Den siterte siden omtaler ikke LangChain-konfigurasjon i det hele tatt, og ingen Learn-side oppgir api_version 2024-08-01-preview for AzureChatOpenAI; Learns kanoniske LangChain-side dokumenterer AZURE_OPENAI_API_VERSION med eksempelverdiene v1 eller preview, men enumererer ikke AzureChatOpenAIs api_version, så verdien kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md",
"line": 198,
"claim": "AzureChatOpenAI konfigureres med api_version 2024-08-01-preview i LangChain-integrasjonen mot Azure OpenAI.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/distributed-tracing-ai-pipelines.md#17",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/azure-monitor/app/opentelemetry-sampling",
"evidence_quote": "The Application Insights OpenTelemetry distros include a default sampler. The specific sampler and its rate depend on the language and distro version.",
"reason": "Den bærende delpåstanden om at distroen ikke sampler som standard og at samplerne må konfigureres eksplisitt er motsagt: Learn oppgir rate-limited sampling som default for Python (fra 1.8.6), Node.js (fra 1.16.0) og Java (fra 3.4.0), og ApplicationInsightsSampler som default for ASP.NET Core/.NET.",
"file": "skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md",
"line": 478,
"claim": "Azure Monitor OpenTelemetry-distroen sampler ikke som standard; den støtter fixed-rate og rate-limited samplere som må konfigureres eksplisitt, og trace-basert sampling for logger er default-på først når sampling er aktivert — adaptive sampling gjelder kun den klassiske Application Insights SDK-en.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 25,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/endpoint-health-and-capacity-planning.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/quota",
"evidence_quote": "Quota is allocated in terms of units of capacity, which have corresponding amounts of RPM & TPM: | Older chat models | 1 Unit | 6 RPM | 1,000 TPM |",
"reason": "Tier-oppregningen (Free Tier / Tier 0 og Tier 1–6) er nøyaktig grunnet i quotas-limits (Seven tiers ... Free Tier and Tiers 1 through 6), men den løftebærende negasjonen «ikke via 1 Unit Capacity» motsies: gjeldende quota-side allokerer fortsatt kvote i units of capacity og advarer om feilallokering ved programmatisk deployment.",
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"line": 55,
"claim": "Kvote for Azure OpenAI tildeles via Quota Tiers — Free Tier (Tier 0) | Tier 1 | Tier 2 | Tier 3 | Tier 4 | Tier 5 | Tier 6 — ikke via «1 Unit Capacity».",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/endpoint-health-and-capacity-planning.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/quota",
"evidence_quote": "| Model | Capacity | Requests Per Minute (RPM) | Tokens Per Minute (TPM) | ... | Older chat models | 1 Unit | 6 RPM | 1,000 TPM | ... | o1 & o1-preview | 1 Unit | 1 RPM | 6,000 TPM | ... | o3 | 1 Unit | 1 RPM | 1,000 TPM | ... | o3-mini | 1 Unit | 1 RPM | 10,000 TPM |",
"reason": "Alle fire forholdstallene står i kilden som «1 Unit» Capacity-rater, ikke som Tier 1/GlobalStandard-verdier; i Tier 1-tabellen på quotas-limits finnes verken eldre chat-modeller, o1-preview eller o1-mini under GlobalStandard, og ingen GlobalStandard-rad der har forholdet 6 RPM per 1 000 TPM — den stadfestede scope-angivelsen er dermed feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"line": 59,
"claim": "For Tier 1 og GlobalStandard er RPM/TPM-forholdet modellspesifikt: eldre chat-modeller 6 RPM / 1,000 TPM | o1 og o1-preview 1 RPM / 6,000 TPM | o3 1 RPM / 1,000 TPM | o3-mini og o1-mini 1 RPM / 10,000 TPM.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/endpoint-health-and-capacity-planning.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput",
"evidence_quote": "Provisioned deployments support two billing modes: hourly billing for flexible, short-term usage, and Azure Reservations for sustained production workloads at a discounted rate. ... All provisioned deployment types are billed at an hourly rate ($/PTU/hr) based on the number of PTUs deployed ... In exchange for a 1-month or 1-year commitment, you receive a discounted effective $/PTU/hr rate.",
"reason": "Varighetene 1 måned/1 år er riktige, men de gjelder frivillige Azure Reservations; PTU faktureres som standard per time uten commitment, så den løftebærende delen «krever commitment» motsies av kilden.",
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"line": 199,
"claim": "PTU (Provisioned Throughput) krever commitment på 1 måned eller 1 år.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/endpoint-health-and-capacity-planning.md#18",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/deployment-types",
"evidence_quote": "Data residency for all deployment types: Data stored at rest remains in the designated Azure geography. However, inferencing data is processed as follows: Global types: May be processed in any Azure region; DataZone types: The service processes data only within the Microsoft-specified data zone (US, EU, or Asia Pacific (APAC)); Standard/Regional types: Processed in the deployment region",
"reason": "Påstanden om at databehandling for Azure OpenAI skjer i EU er ubetinget, mens kilden gjør prosesseringssted avhengig av deployment-type — for Global-typer kan data behandles i hvilken som helst Azure-region, altså utenfor EU.",
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"line": 454,
"claim": "Databehandling for Azure OpenAI skjer i EU, selv om kontrollplanet er globalt.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/endpoint-health-and-capacity-planning.md#19",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/logs/quick-create-workspace",
"evidence_quote": "You need Microsoft.OperationalInsights/workspaces/write permissions to the resource group where you want to create the Log Analytics workspace, as provided by the Log Analytics Contributor built-in role, for example.",
"reason": "Kilden krever ikke Owner eller Contributor for å opprette Log Analytics workspace — den smalere rollen Log Analytics Contributor er tilstrekkelig (Microsoft dokumenterer eksplisitt at dette er narrower than a full Contributor role), så den løftebærende rollepåstanden er feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md",
"line": 477,
"claim": "Azure Monitor er inkludert i Azure-abonnementet uten separat lisens, og oppsett av Log Analytics workspace krever Owner- eller Contributor-rolle.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/log-analytics-kql-ai-queries.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/log-analytics-kql-ai-queries.md#9",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry-classic/openai/monitor-openai-reference",
"evidence_quote": "| Input token volume per request | Processed Prompt Tokens | `ProcessedPromptTokens` |",
"reason": "TokenTransaction og TotalTokens finnes i metrikklisten, men PromptTokens og CompletionTokens gjør det ikke - de heter ProcessedPromptTokens og GeneratedTokens (alternativt InputTokens/OutputTokens under Models - Usage); metrikknavnene ER påstanden, så R7s load-bearing carve-out gjelder og to av fire navn er feil.",
"file": "skills/ms-ai-governance/references/monitoring-observability/log-analytics-kql-ai-queries.md",
"line": 294,
"claim": "Azure OpenAI-metrikker i AzureMetrics omfatter TokenTransaction | TotalTokens | PromptTokens | CompletionTokens.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/log-analytics-kql-ai-queries.md#15",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/search/search-monitor-queries",
"evidence_quote": "| where Query_s != \"?api-version=2026-04-01&search=*\"",
"reason": "Den kanoniske siden bruker ?api-version=2026-04-01&search=* i nøyaktig samme query-streng-eksempel (og datareferansen viser api-version=2026-04-01), mens REST-versjonslisten oppgir 2026-04-01 som latest stable og 2025-09-01 som en eldre stabil versjon - påstanden peker på en superseded rad.",
"file": "skills/ms-ai-governance/references/monitoring-observability/log-analytics-kql-ai-queries.md",
"line": 617,
"claim": "Azure AI Search bruker api-version 2025-09-01 i query-strenger (?api-version=2025-09-01&search=*).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 23,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/model-performance-drift-detection.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/concept-model-monitoring?view=azureml-api-2",
"evidence_quote": "Model performance: Classification (preview) | Tracks the objective performance of a model's output in production by comparing it to collected ground truth data. | Accuracy, Precision, and Recall",
"reason": "Kilden merker både Model performance: Classification og Model performance: Regression som (preview) (og Feature attribution drift som (preview)), så den løftebærende GA-delen av påstanden er motsagt selv om data drift, prediction drift og data quality ikke er preview-merket.",
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"line": 4,
"claim": "Model performance monitoring og drift detection i Azure Machine Learning er GA (generelt tilgjengelig).",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/model-performance-drift-detection.md#20",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/observability",
"evidence_quote": "",
"reason": "Den siterte observability-siden sier ingenting om regionvalg for Azure ML, og fallback-søk fant ingen learn.microsoft.com-side som opplister regiontilgjengelighet for Azure ML produksjonsdata eller monitoring jobs (den kanoniske listen ligger på azure.microsoft.com), så påstanden kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"line": 281,
"claim": "Azure-regioner innenfor EU/EØS som kan velges for produksjonsdata og monitoring jobs inkluderer Norway East | Sweden Central | France Central.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/model-performance-drift-detection.md#21",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/concepts/observability",
"evidence_quote": "",
"reason": "Verken den siterte siden eller fallback-søk gir en learn.microsoft.com-side som oppgir lisensierings- eller kjøpsformer for Azure Machine Learning; dette er prisinformasjon som ligger utenfor Learn.",
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"line": 323,
"claim": "Azure Machine Learning lisensieres via Enterprise Agreement eller Pay-As-You-Go.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/model-performance-drift-detection.md#22",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-regions-limits-virtual-network",
"evidence_quote": "These regions support the following safety evaluators: Hate and unfairness, Sexual, Violent, Self-harm, Indirect attack, Code vulnerabilities, and Ungrounded attributes. | Americas | Europe | Asia Pacific | | East US 2 | France Central | Australia East | | North Central US | Sweden Central | | | | Switzerland West | |",
"reason": "Den kanoniske regionlisten for risk and safety evaluators inneholder East US 2, North Central US, France Central, Sweden Central, Switzerland West og Australia East - UK South står ikke i listen, så den påståtte regionen mangler i den enumererende kilden.",
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"line": 325,
"claim": "Microsoft Foundry safety evaluations er hostet i East US 2 | France Central | UK South | Sweden Central.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/model-performance-drift-detection.md#23",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/azure/machine-learning/how-to-monitor-datasets?view=azureml-api-1",
"evidence_quote": "Data drift (preview) was retired on September 1, 2025. Migrate to Model Monitor for your data drift tasks.",
"reason": "Legacy-stemplingen og migreringen til Model Monitor stemmer, men gjeldende status er at funksjonen allerede ble pensjonert 1. september 2025 - ikke at den er under utfasing - så statusdelen av påstanden er superseded.",
"file": "skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md",
"line": 393,
"claim": "Den eldre dataset-baserte data drift monitoring i Azure ML (azureml-api-1) er legacy og under utfasing, med migrering til Model Monitor.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 22,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/microsoft-cloud/dev/copilot/isv/observability-for-ai",
"evidence_quote": "",
"reason": "Påstanden gjelder referansefilens egen statusmerking (GA per 2026-05); ingen learn.microsoft.com-side uttaler seg om statusen til dette KB-dokumentet, og den siterte ISV-veiledningen bærer verken GA- eller preview-merking.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 4,
"claim": "Referansen for observability for Copilot-extensions er merket med status GA (per 2026-05).",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#3",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/microsoft-cloud/dev/copilot/isv/observability-for-ai",
"evidence_quote": "",
"reason": "Den siterte ISV-observabilitetssiden inneholder ingen fem-lags telemetri-inndeling med verktøytilordning (den strukturerer stoffet i tre livssyklusfaser og metrikk-kategorier), og søk finner ingen annen Learn-side som angir denne taksonomien; enkeltkoblingene er dokumentert hver for seg, men selve fem-lags-framingen står ingen steder.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 39,
"claim": "Telemetri for Copilot-extensions deles i fem lag med tilhørende verktøy: Copilot Studio Agent → Application Insights | Plugin/Connector Runtime → Application Insights SDK | LLM Interaction → Azure OpenAI metrics | User Engagement → Custom events | Security/Compliance → Microsoft Sentinel, Purview.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-bot-framework-composer-capture-telemetry",
"evidence_quote": "Enable logging: If turned on, the system logs details of incoming and outgoing messages and events. Log conversation details: Includes user ID, user name, and message text (for Message activities). Log sensitive Activity properties: If turned on, the logs include the values of certain properties that could be considered sensitive on incoming and outgoing messages and events. Node execution events: Log an event each time a node within a topic is executed.",
"reason": "Settings → Advanced → Connection string stemmer, men den kanoniske siden lister fire valgfrie innstillinger (Enable logging, Log conversation details, Log sensitive Activity properties, Node execution events) — verken «Log activities» eller «Log custom telemetry events» finnes, så to av tre påståtte innstillingsnavn er fraværende.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 50,
"claim": "Application Insights konfigureres i Copilot Studio under Settings → Advanced med en Connection string, og har tre valgfrie innstillinger: Log activities | Log sensitive Activity properties | Log custom telemetry events.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-bot-framework-composer-capture-telemetry",
"evidence_quote": "Log sensitive Activity properties: If turned on, the logs include the values of certain properties that could be considered sensitive on incoming and outgoing messages and events.",
"reason": "Den kanoniske siden enumererer ingen egenskaper for «Log sensitive Activity properties», og tilordner tvert imot user ID, user name og message text til den separate innstillingen «Log conversation details» — påstandens liste userid/name/text/speak står ikke der.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 52,
"claim": "Innstillingen «Log sensitive Activity properties» i Copilot Studio logger egenskapene userid | name | text | speak.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#13",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-logging-copilot-studio",
"evidence_quote": "| Agents | BotCreate | The creation of a new agent in Copilot Studio | ... | Agents | BotUpdateOperation-BotPublish | Publishing of an agent in Copilot Studio | | Agents | BotUpdateOperation-BotShare | Sharing of an agent to other users in Copilot Studio |",
"reason": "Den kanoniske Purview-enumerasjonen navngir hendelsene BotUpdateOperation-BotPublish og BotUpdateOperation-BotShare, ikke BotPublish/BotShare; event-label er en lastebærende streng en leser filtrerer på, så to av tre navn er feil selv om BotCreate og M365-lisenskravet stemmer.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 224,
"claim": "Purview-revisjonslogger dekker Copilot Studio-hendelsene BotCreate | BotPublish | BotShare, og revisjonslogging må aktiveres for Microsoft 365-lisensinnehavere.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#16",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/azure-monitor/app/application-insights-faq",
"evidence_quote": "Raw data retention can be set to 30, 60, 90, 120, 180, 270, 365, 550, or 730 days. Retention beyond 90 days can incur extra charges. ... Data is stored in the region you choose when creating the resource.",
"reason": "Learn dokumenterer at dataplassering bestemmes av regionen du velger ved opprettelse av ressursen, mens Settings → Data retention styrer oppbevaringstid — påstanden tilordner data residency til feil mekanisme.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 253,
"claim": "Data Residency aktiveres i Application Insights under Settings → Data retention.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#19",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/requirements-sessions-management",
"evidence_quote": "This section is for billed sessions in the legacy Power Virtual Agents license, which was available for purchase starting on December 1, 2023. This legacy license is no longer available for purchase starting on January 1, 2024.",
"reason": "Lisensrammen påstanden bygger på er erstattet: Power Virtual Agents-lisensen er merket legacy og ikke kjøpbar etter 1. januar 2024, og dagens modell er Copilot Studio-lisens/Copilot Credits-kapasitet (analyse er dessuten tilgjengelig via Teams-planen i M365-lisenser).",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 304,
"claim": "Innebygd Copilot Studio-analyse krever Power Virtual Agents-lisens eller Copilot Studio-kapasitet.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/observability-for-copilot-extensions.md#21",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/sentinel/sentinel-overview",
"evidence_quote": "Microsoft Sentinel SIEM is available in the Microsoft Defender portal - for customers with or without Defender XDR or an E5 license - offering a unified security operations experience.",
"reason": "Learn sier eksplisitt at Sentinel er tilgjengelig uten E5-lisens (og faktureres på forbruk, ikke som «standalone»-lisens), mens Copilot Studio-veiledningen bare krever «an assigned Microsoft 365 license» — det lastebærende E5-kravet er motsagt.",
"file": "skills/ms-ai-governance/references/monitoring-observability/observability-for-copilot-extensions.md",
"line": 306,
"claim": "Microsoft Sentinel for revisjonslogger krever Microsoft 365 E5 eller Sentinel standalone.",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"batch": "R7.3",
"judged_at": "2026-07-25",
"per_file_verdict": "flagged",
"claim_count": 24,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#14",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/logs/data-ingestion-time",
"evidence_quote": "The average latency to ingest log data is less than 10 seconds.",
"reason": "Azure Monitor oppgir gjennomsnittlig ingestion-latency til under 10 sekunder og prosesstid under 10 sekunder, ikke en iboende latency på 1-5 minutter.",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 92,
"claim": "Application Insights og Log Analytics har en iboende ingestion-latency på 1-5 minutter.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#15",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/real-time-intelligence/dashboard-live-refresh",
"evidence_quote": "",
"reason": "Refresh-innstillingene dokumenterer Refresh rate limit som minste tidsintervall mellom oppdateringer, men verken denne siden eller create-dashboard-siden oppgir noen 10-sekunders minimumsverdi.",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 110,
"claim": "Minimum auto-refresh-intervall for Fabric Real-Time Dashboard er 10 sekunder.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#19",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/admin/region-availability",
"evidence_quote": "Europe | Norway West | ✅ | ❌ | Power BI only region",
"reason": "Norway East har alle Fabric-workloads, men Norway West er en Power BI only-region uten Fabric-workloads, så Fabric-kapasitet med eventhouse kan ikke velges der; én bærende del av påstanden er feil (R8).",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 340,
"claim": "Fabric-kapasitet med eventhouse kan velges i Norway East/West for datasuverenitet.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#20",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/azure-monitor/app/connection-strings",
"evidence_quote": "Customized endpoints (sovereign or hybrid cloud environments): Endpoint settings allow sending data to a specific Azure Government region.",
"reason": "Endepunktet live.applicationinsights.azure.com hører riktig nok til public cloud, men samme side lister applicationinsights.us som gyldig suffiks og live som prefiks for Live Metrics, altså er Live Metrics tilgjengelig i Azure Government; andre bærende del er feil (R8).",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 345,
"claim": "Live Metrics-endepunktet live.applicationinsights.azure.com hostes i Azure public cloud, og Live Metrics er ikke tilgjengelig i Azure Government.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#21",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/overview",
"evidence_quote": "Managed identities can be used at no extra cost.",
"reason": "Forutsetningene for Entra-autentisering i Application Insights er managed identity eller service principal pluss Monitoring Metrics Publisher-rollen, uten noe lisenskrav, og managed identities koster ingenting ekstra; SKU-delen om Entra ID P1/P2 er derfor feil selv om september 2025-kravet stemmer (R8).",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 381,
"claim": "Entra ID-autentisering for Live Metrics er inkludert i Entra ID P1/P2 og er påkrevd fra september 2025.",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#22",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/real-time-intelligence/real-time-dashboards-overview",
"evidence_quote": "",
"reason": "Verken dashboard-oversikten, lisenssiden eller RTI-forbrukssidene sier at Real-Time Dashboard er inkludert i kapasiteten uten ekstra kostnad; forbruk måles i CU per operasjon, så påstanden kan verken bekreftes eller motbevises.",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 391,
"claim": "Real-Time Dashboard er inkludert i Fabric-kapasiteten uten ekstra kostnad.",
"disposition": "unsourced"
},
{
"id": "ms-ai-governance/monitoring-observability/real-time-streaming-monitoring.md#23",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/en-us/fabric/real-time-intelligence/data-activator/activator-capacity-usage",
"evidence_quote": "Similar to other workloads in Fabric, Activator billing is based on the consumption of resources. Fabric uses Capacity Units (CU) to measure and bill for resource usage.",
"reason": "Activator faktureres som CU-forbruk på Fabric-kapasiteten med publiserte satser (rule uptime per hour 0.02222, event ingestion, event computations, storage), ikke som egen SKU per reflex med uannonsert preview-prising; både rammeverket og TBA-statusen er erstattet (R3).",
"file": "skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md",
"line": 394,
"claim": "Data Activator faktureres som egen SKU per reflex/trigger, med preview-prising ikke annonsert (TBA).",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 10,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/monitoring-observability/security-and-audit-logging-ai.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/navigate-from-classic",
"evidence_quote": "Resource type | Azure OpenAI + Hub | Foundry Resource | Single AIServices kind with child projects. ... AI services | Azure AI Services | Foundry Tools",
"reason": "Defender AI threat protection/AI-SPM does support Azure OpenAI, but the load-bearing rename is contradicted: Foundry Resource (AIServices kind) was classically 'Azure OpenAI + Hub' and Foundry Tools is a distinct current term (classically 'Azure AI Services') - Foundry resource is not the new name for a previous Foundry Tools.",
"file": "skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md",
"line": 40,
"claim": "Microsoft Defender for Cloud AI threat protection + AI-SPM: støtter Azure OpenAI; konfigureres separat for Foundry-ressurser; «Foundry resource» (kind=AIServices) er nytt navn på tidligere «Foundry Tools»",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 9,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#5",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/speech-service/language-support#supported-languages",
"evidence_quote": "nb-NO Norwegian Bokmaal (Norway) supported",
"reason": "The canonical Speech-to-text locales enumeration lists nb-NO (Bokmaal) but contains no nn-NO (Nynorsk) row anywhere (nor in Custom speech or TTS tables); the claim asserts Azure AI Speech supports nynorsk (nn-NO), so one load-bearing part is absent from the enumeration (R2/R8).",
"file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md",
"line": 235,
"claim": "Azure AI Speech norsk språkstøtte: bokmål (nb-NO), nynorsk (nn-NO), Custom Speech for dialektvarianter; funksjoner: real-time transcription, speaker diarization, profanity filter/content moderation, batch-transkripsjon",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-moderator/content-moderator",
"evidence_quote": "PII detection | Basic PII detection in text | Use Azure AI Language PII detection",
"reason": "Image Analysis captions, OCR, Face, and adult/racy/gory content moderation are all Vision features, but PII detection is an Azure AI Language capability, not an Azure AI Vision one (Vision overview enumerates only Face, Image Analysis, OCR); one stated load-bearing part is misattributed (R8).",
"file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md",
"line": 248,
"claim": "Azure AI Vision-kapabiliteter: Image Analysis API (beskrivende bildetekster), OCR, Face API (attributtgjenkjenning); innebygd content moderation og PII detection",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/power-apps/maker/canvas-apps/accessible-apps",
"evidence_quote": "The following screen readers have been verified to work with Power Apps: JAWS... Narrator... NVDA...",
"reason": "Screen readers (Narrator/JAWS/NVDA) and keyboard-only navigation are confirmed, but high-contrast mode is absent from the canonical Power Apps canvas accessibility enumeration (which covers layout/color contrast ratios, keyboard, screen readers, controls, multimedia) and from the accessibility-limitations page; one stated load-bearing part is unsupported by the enumerating page (R8/R2).",
"file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/accessibility-requirements-wcag-norway.md",
"line": 276,
"claim": "Power Apps støtter skjermlesere (Narrator, JAWS, NVDA), tastaturnavigasjon uten mus og høykontrast-modus",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-governance/references/norwegian-public-sector-governance/budget-and-accounting-ai-costs.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "pass",
"claim_count": 6,
"verified": "2026-07-18",
"verified_by": "judge-v3.1",
"flags": []
},
{
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/whats-new",
"evidence_quote": "Protected material detection for code (preview)",
"reason": "The claim marks Protected Material Code as GA, but What's new and the current quickstart both title it '(preview)' with no GA announcement (the Aug 2024 GA covered only Prompt Shields and Protected Material for text), so one load-bearing status in the bundle is wrong while the other statuses match.",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 37,
"claim": "Content Safety feature statuses: Analyze Text GA | Analyze Image GA | Prompt Shields GA | Groundedness Detection Preview | Protected Material Text GA | Protected Material Code GA | Custom Categories (Standard) Preview | Custom Categories (Rapid) Preview | Blocklists GA",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview",
"evidence_quote": "Maximum length for grounding sources: 55,000 characters (per API call). Maximum text and query length: 7,500 characters.",
"reason": "The claim states 'Groundedness query+sources max 55K chars', but the live page gives 55,000 characters to grounding sources only and caps text/query separately at 7,500 characters, so that load-bearing limit is misstated even though the other limits (Analyze Text 10K, image 4MB JPEG/PNG/GIF/BMP/TIFF/WEBP, Prompt Shields 10K, PM-Text min 110) match.",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 37,
"claim": "Content Safety input limits: Analyze Text max 10K chars | Analyze Image JPEG/PNG/GIF/BMP/TIFF/WEBP max 4MB | Prompt Shields text max 10K chars | Groundedness query+sources max 55K chars | Protected Material Text min 110 chars",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#6",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/knowledge-copilot-studio",
"evidence_quote": "The moderation levels range from **Lowest** to **Highest**. The lowest level generates the most answers, but they might contain harmful content. The highest level of content moderation generates fewer answers, and applies a stricter filter to restrict harmful content. The default moderation level is **High**.",
"reason": "The claim says moderation 'uses Azure OpenAI deployment settings' and that custom blocklists can be enabled in Agent Settings, but the live docs show content moderation is configured inside Copilot Studio itself (agent-, topic-, and prompt-level Lowest-Highest levels) and the Agent settings enumeration has a Moderation level dropdown with no custom-blocklist option, so two load-bearing parts are wrong (only the no-per-category-severity part holds).",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 239,
"claim": "Copilot Studio cannot (per feb 2026) configure severity levels per category - uses Azure OpenAI deployment settings; custom blocklists can be enabled in Agent Settings",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#7",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/ai-builder/prebuilt-azure-openai",
"evidence_quote": "This feature is deprecated and isn't visible anymore.",
"reason": "AI Builder's Text generation model is deprecated and replaced by prompt builder, where per the prompts FAQ 'Makers can configure the content moderation level for harmful content only' - so the claim's frame (no configuration options, implicit Medium+High default) describes a replaced world and its 'no configuration' part is contradicted for the current mechanism.",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 243,
"claim": "AI Builder Text generation uses Azure OpenAI with content filtering enabled by default and no configuration options (default Medium+High block)",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#8",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-365/copilot/harmful-content-protection-copilot-chat",
"evidence_quote": "For these special use cases, your organization's Microsoft 365 Apps administrator can enable a specific group of users to adjust harmful content protection settings in their Copilot Chat experiences.",
"reason": "The claim's load-bearing 'not customer-configurable' is contradicted by the live page: admins can policy-enable users to toggle harmful content protection off in Copilot Chat (and the privacy doc says Microsoft 'offers certain content filtering controls for admins and users'), even though severity-level sliders indeed do not exist.",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 259,
"claim": "Microsoft 365 Copilot has its own content filtering policies that are not customer-configurable (severity levels cannot be adjusted; Microsoft-managed)",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#9",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview",
"evidence_quote": "To use the Content Safety APIs, you must create your Azure AI Content Safety resource in a supported region. Currently, the Content Safety features are available in the following Azure regions with different API versions:",
"reason": "The canonical region-availability table on the cited page lists West Europe but contains no Norway East row for any Content Safety API, and no Learn page found states Content Safety availability in Norway East (even via Azure OpenAI), so the Norway East part fails the enumeration check; the in-region/no-US-transfer part alone is supported by the data-privacy page.",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 275,
"claim": "Azure AI Content Safety available in West Europe and Norway East (via Azure OpenAI); models run in EU (no data transfer to USA)",
"disposition": "outdated"
},
{
"id": "ms-ai-governance/responsible-ai/content-safety-implementation.md#10",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/language-service/personally-identifiable-information/concepts/entity-categories",
"evidence_quote": "To retrieve this entity type, specify **NOIdentityNumber** in the **piiCategories** request parameter. If detected, the entity appears in the **PII** response payload.",
"reason": "The PII filter page links this entity-categories list as 'the complete list of supported personal data entity types' and lists 'National ID numbers (50+ countries)' including a dedicated Norway Identity Number (NOIdentityNumber) type, contradicting the claim's load-bearing assertion that the Norwegian national ID format is not officially supported (the detection-in-completions and block/redacted_text parts do hold).",
"file": "skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md",
"line": 270,
"claim": "Azure AI Content Safety has PII detection for completions (names, addresses; Norwegian national ID format not officially supported), configurable to block or mask PII in LLM output",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 12,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#1",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/entra/fundamentals/whats-new-archive",
"evidence_quote": "General Availability - Protect enterprise GenAI applications with Prompt Injection Protection",
"reason": "The Content Safety Prompt Shields GA part holds, but the Entra whats-new archive (November 2025) announces General Availability of the AI Gateway prompt protection capability (now named Prompt Injection Protection), contradicting the claim's Preview status.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 6,
"claim": "Two separate products: Azure AI Content Safety Prompt Shields is GA; AI Gateway Prompt Shield via Global Secure Access is Preview",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/overview",
"evidence_quote": "Prompt Shields API: Maximum prompt length: 10K characters. Up to five documents with a total of 10K characters.",
"reason": "Prompt limit 10K and max 5 documents hold, but the claim's 'each document max 10 000 chars' contradicts the source, which caps all documents at 10K characters combined, not per document.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 139,
"claim": "Prompt Shields input limits: userPrompt max 10 000 chars | documents array max 5 documents per request | each document max 10 000 chars",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#4",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/entra/global-secure-access/how-to-ai-prompt-injection-protection",
"evidence_quote": "Prompt Injection Protection is preconfigured with custom extractors for the following models: ChatGPT, Claude, Cohere, Deepseek, Gemini, Grok, Meta AI, Mistral, Perplexity, Pi, and Qwen.",
"reason": "The canonical enumeration does not include 'Microsoft Copilot' and lists 'Meta AI' rather than 'Meta Llama' (and now also includes Deepseek, Gemini, Perplexity), so the claim's stated extractor list disagrees with the current page.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 180,
"claim": "AI Gateway Prompt Shield has pre-configured extractors for: Microsoft Copilot, OpenAI ChatGPT, Anthropic Claude, Meta Llama, xAI Grok, Mistral, Cohere, Inflection Pi, Alibaba Qwen, plus custom JSON-based LLMs (custom URL + JSON path)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#5",
"judge_verdict": "not_grounded",
"rule": "R1",
"evidence_url": "https://learn.microsoft.com/entra/global-secure-access/how-to-ai-prompt-injection-protection",
"evidence_quote": "Prompt Injection Protection supports prompts up to 64,000 characters. Anything longer is truncated.",
"reason": "Text-only and JSON-only limitations still hold, but the claimed 10 000-char ceiling is superseded — the live page states 64,000 characters, and Gemini (the claim's example of an unsupported app) is now a preconfigured extractor.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 193,
"claim": "AI Gateway Prompt Shield limitations: text prompts only (no files); JSON-based GenAI apps only (not URL-encoded, e.g. Gemini); max 10 000 chars per prompt (longer prompts truncated)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#11",
"judge_verdict": "not_grounded",
"rule": "R7",
"evidence_url": "https://learn.microsoft.com/azure/ai-services/content-safety/quickstart-groundedness",
"evidence_quote": "The current version is: api-version=2024-09-15-preview. Example: <endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview",
"reason": "The endpoint path matches, but the load-bearing api-version string is wrong — the canonical quickstart states 2024-09-15-preview as the current version, not 2024-09-01.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 309,
"claim": "Groundedness endpoint: POST {endpoint}/contentsafety/text:detectGroundedness?api-version=2024-09-01",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/ai-prompt-shield-network.md#12",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/entra/fundamentals/whats-new-archive",
"evidence_quote": "General Availability - Protect enterprise GenAI applications with Prompt Injection Protection",
"reason": "The license-inclusion part is supported (the feature's prerequisites require a Microsoft Entra Internet Access license), but the stated '(Preview)' status is contradicted — the November 2025 Entra release notes announce General Availability.",
"file": "skills/ms-ai-security/references/ai-security-engineering/ai-prompt-shield-network.md",
"line": 428,
"claim": "AI Gateway Prompt Shield (Preview) is included in the Microsoft Entra Internet Access license (licensed per user/month)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 13,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/ai-security-engineering/entra-agent-id-zero-trust.md#1",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/entra/fundamentals/whats-new",
"evidence_quote": "The Microsoft Entra Agent ID platform is now generally available.",
"reason": "The claim asserts Public Preview status, but the April 2026 release notes announce general availability and the live product page now states 'Agent ID is available for all Microsoft Entra customers' with no preview disclaimer.",
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"line": 5,
"claim": "Microsoft Entra Agent ID har status Public Preview (utvidet etter Ignite 2025)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/entra-agent-id-zero-trust.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-use-entra-agent-identities",
"evidence_quote": "Starting July 2026, all new agents must have Microsoft Entra Agent IDs, and you can no longer opt out of automatic agent identity creation.",
"reason": "The blueprint name and Blueprint ID 25664c89-cea5-4ab6-b924-a54fd8a19ae0 match, but the load-bearing 'preview, activated per environment in Power Platform Admin Center' framing is superseded - creation is now automatic and mandatory with the per-environment opt-out removed.",
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"line": 20,
"claim": "Copilot Studio (preview, aktiveres per miljø i Power Platform Admin Center) oppretter automatisk Entra Agent ID for hver ny agent, knyttet til Microsoft Copilot Studio agent identity blueprint med Blueprint ID 25664c89-cea5-4ab6-b924-a54fd8a19ae0",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/entra-agent-id-zero-trust.md#10",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-use-entra-agent-identities",
"evidence_quote": "Previously, you could opt out of Entra Agent ID at the environment level. Starting July 2026, all new agents must have Microsoft Entra Agent IDs, and you can no longer opt out of automatic agent identity creation.",
"reason": "The claim describes the opt-out as currently existing with mandatory enforcement coming 'in the future', but the current page states the opt-out is already removed and Agent IDs are mandatory for all new agents as of July 2026.",
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"line": 322,
"claim": "Opt-out fra Entra Agent Identity per miljø i Copilot Studio er midlertidig — Microsoft vil gjøre det obligatorisk for alle nye agenter i fremtiden",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/entra-agent-id-zero-trust.md#11",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/entra/fundamentals/whats-new",
"evidence_quote": "The Microsoft Entra Agent ID platform is now generally available.",
"reason": "The status table's load-bearing 'Public Preview (Frontier program)' frame is superseded: the Agent ID platform reached GA in April 2026, the live product page lists Agent 365/E5/E7/P1-P2 licensing with no Frontier requirement, and the Entra Agent Registry blades were retired May 1, 2026 in the consolidation into Microsoft Agent 365 - even though the AI Prompt Shield, App Service/Functions, and Teams Developer Portal items individually check out.",
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"line": 439,
"claim": "Statustabell: Entra Agent ID kjerne/Agent Registry/Identity Protection for agenter/Global Secure Access for agenter = Public Preview (Frontier-program); Foundry-integrasjon Public Preview (alle Foundry-brukere); Conditional Access for agenter Public Preview; AI Prompt Shield nytt via Entra Internet Access; App Service/Azure Functions agent identity og Teams Developer Portal agent blueprints nye",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/entra-agent-id-zero-trust.md#12",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/entra/agent-id/identity-professional/microsoft-entra-agent-identities-for-ai-agents",
"evidence_quote": "Extending Microsoft Entra security features to agents requires Microsoft 365 E7 (includes Agent 365 and Microsoft Entra Suite) or Microsoft 365 E5 paired with a Microsoft Agent 365 license.",
"reason": "The Frontier-program + M365 Copilot licensing frame has been replaced: the live page states full Agent ID security functionality requires Agent 365/E5/E7 (or P1/P2 standalone options) with no mention of Frontier enrollment or the Copilot Frontier admin-center toggle, which now applies only to pre-release Agent 365 features.",
"file": "skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md",
"line": 452,
"claim": "Full Entra Agent ID-funksjonalitet krever deltakelse i Microsoft Frontier-programmet og M365 Copilot-lisens (aktiveres via M365 admin center → Copilot → Settings → User access → Copilot Frontier); Foundry-integrert agentidentitet er tilgjengelig for alle Foundry-brukere uten Frontier",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/entra/identity/managed-identities-azure-resources/managed-identity-best-practice-recommendations",
"evidence_quote": "This means that it can take several hours for changes to a managed identity's group or role membership to take effect.",
"reason": "The 24-hour token cache and hours-long propagation parts are confirmed, but the page explicitly treats group AND app-role membership identically (both are claims in the cached token, same several-hours delay, and it recommends user-assigned MI with direct permissions for fast changes), contradicting the load-bearing part that App Roles propagate faster than groups.",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 128,
"claim": "Managed Identity tokens are cached up to 24 hours; group/role membership changes can take hours to propagate; App Roles propagate faster than groups",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#3",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/navigate-from-classic",
"evidence_quote": "Microsoft's AI Platform has evolved from Azure AI Studio -> Azure AI Foundry -> to Microsoft Foundry (current). Similarly, our AI services portfolio evolved with the platform from Azure Cognitive Services -> Azure AI Services -> to Foundry Tools (current).",
"reason": "The avoid-API-keys recommendation, kind=AIServices, and DefaultAzureCredential pattern are grounded, but the naming part 'formerly Foundry Tools' is contradicted: Foundry Tools is the CURRENT name of the AI services portfolio (formerly Azure AI Services), not a former name of the Microsoft Foundry resource (whose lineage is Azure AI Studio -> Azure AI Foundry -> Microsoft Foundry).",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 130,
"claim": "Microsoft now explicitly recommends avoiding API keys for Azure AI Services in production; Microsoft Foundry resource (formerly 'Foundry Tools', kind=AIServices) uses the same DefaultAzureCredential pattern across all AI services",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#4",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/entra/identity/conditional-access/concept-continuous-access-evaluation",
"evidence_quote": "The goal for critical event evaluation is for response to be near real time, but latency of up to 15 minutes might be observed because of event propagation time; however, IP locations policy enforcement is instant.",
"reason": "The 28-hour CAE token lifetime and 1-hour standard token parts are confirmed on the page (and the MI 24-hour cache on the MI best-practices page), but the load-bearing part 'critical events revoke in seconds' is contradicted: the page states near real time with up to 15 minutes latency and 'within minutes after a critical event', not seconds.",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 149,
"claim": "CAE token lifetime: up to 28 hours (vs standard access token 1 hour, Managed Identity refresh token 24 hours); critical events revoke in seconds",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#5",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/entra/identity/conditional-access/concept-continuous-access-evaluation-strict-enforcement",
"evidence_quote": "Standard (Default) | Suitable for all topologies | A short-lived token is issued only if Microsoft Entra ID detects an allowed IP address. Otherwise, access is blocked",
"reason": "The move to Conditional Access session controls is confirmed ('The CAE setting moved to Conditional Access.'), but the option set is wrong: the documented options are Disable (session control) and Strictly enforce location policies, with the default enforcement mode named 'Standard (Default)' - no option named 'Basic' exists on the session-control or strict-enforcement pages.",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 152,
"claim": "From 2025 CAE is configured via Conditional Access policies (Session controls) instead of a separate toggle; options Disabled, Basic (default), Strict",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#6",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/en-us/entra/identity/conditional-access/concept-continuous-access-evaluation",
"evidence_quote": "Continuous access evaluation is also available in Azure Government tenants (GCC High and DOD) for Exchange Online.",
"reason": "Preview status, per-policy activation, and near-realtime blocking are confirmed on the strict-enforcement page, but 'now supports Azure Government clouds' is absent from both canonical pages - the only Government-availability statement covers CAE generally and only for Exchange Online, so the claimed strict-enforcement Government support is not documented.",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 154,
"claim": "Strict Location Enforcement is Preview, activated per Conditional Access policy, blocks tokens used outside approved network locations in near-realtime, and now supports Azure Government clouds",
"disposition": "outdated"
},
{
"id": "ms-ai-security/ai-security-engineering/zero-trust-ai-services.md#9",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/power-platform/admin/vnet-support-overview",
"evidence_quote": "| Dataverse | Dataverse plug-ins | Generally available |",
"reason": "The cited vnet-data-gateway page returns 404; the live Virtual Network support overview states Dataverse (plug-ins) Virtual Network support is Generally available, contradicting the claimed 'Private Preview (Q1 2026)' status.",
"file": "skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md",
"line": 606,
"claim": "Virtual Network Integration for Dataverse is in Private Preview (Q1 2026)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/cost-optimization/azure-ai-foundry-cost-governance.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 9,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/cost-optimization/azure-ai-foundry-cost-governance.md#7",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/how-to/navigate-from-classic",
"evidence_quote": "| Resource type | Azure OpenAI + Hub | Foundry Resource | Single `AIServices` kind with child projects. | | AI services | Azure AI Services | Foundry Tools | Speech, Vision, Language, Content Safety, Content Understanding. |",
"reason": "The kind-AIServices-to-Microsoft-Foundry-resource part and projects-as-folders part are grounded, but the terminology mapping shows 'Foundry Tools' is the CURRENT name for the constituent AI services (formerly Azure AI Services), coexisting with the Foundry resource — not the predecessor name the Foundry resource was renamed from — so one load-bearing lineage part is contradicted.",
"file": "skills/ms-ai-security/references/cost-optimization/azure-ai-foundry-cost-governance.md",
"line": 121,
"claim": "The underlying Azure resource (API kind AIServices) is renamed Microsoft Foundry resource (successor/renaming of 'Foundry Tools'); projects function as folders grouping work under one resource",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/cost-optimization/batch-processing-cost-reduction.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 11,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/cost-optimization/batch-processing-cost-reduction.md#2",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types",
"evidence_quote": "DataZone types: The service processes data only within the Microsoft-specified data zone (US, EU, or Asia Pacific (APAC)). Standard/Regional types: Processed in the deployment region",
"reason": "The two type names Global-Batch and Data Zone Batch are confirmed, but the load-bearing gloss 'regionsbasert' is contradicted: the page's taxonomy explicitly separates data-zone processing (US/EU/APAC zone spanning many regions) from regional processing (single deployment region), so calling Data Zone Batch region-based misstates its data-residency category.",
"file": "skills/ms-ai-security/references/cost-optimization/batch-processing-cost-reduction.md",
"line": 29,
"claim": "To batch deployment-typer: Global-Batch (globalt distribuert) | Data Zone Batch (regionsbasert)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 17,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#1",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic",
"evidence_quote": "- 1,047,576 - 300,000 (standard deployments) - 128,000 (provisioned managed and batch deployments)",
"reason": "The page states 300,000 for standard deployments and 128,000 for provisioned managed AND batch deployments, while the claim swaps them (128K for standard/provisioned, 300K for batch).",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 56,
"claim": "gpt-4.1 kontekstvindu: 1047576 tokens (full), 128000 tokens (standard og provisioned deployments), 300000 tokens (batch deployments)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#5",
"judge_verdict": "not_grounded",
"rule": "R4",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/reasoning",
"evidence_quote": "Access is no longer restricted for this model.",
"reason": "The live availability table states this for both gpt-5 and gpt-5-codex, so the claimed registration/approval requirement is superseded (the mini/nano/chat 'No access request needed' half still matches, but the load-bearing requirement part is now wrong).",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 83,
"claim": "gpt-5 og gpt-5-codex krever registrering og godkjenning; gpt-5-mini, gpt-5-nano, gpt-5-chat har ingen registreringskrav",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#9",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/prompt-model-settings",
"evidence_quote": "| Claude Sonnet 4.6 | Standard rate | External model from Anthropic. Context allowed up to 200K tokens. | General |",
"reason": "The current model table lists Claude Sonnet 4.6 (Standard) and Claude Opus 4.6 (Premium) instead of the claimed 4.5 versions and contains no o3 row at all, so multiple load-bearing entries in the claimed rate lineup are superseded or absent.",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 203,
"claim": "Copilot Credits-takstnivåer: gpt-4.1-mini Basic | gpt-4.1 Standard | gpt-5-chat (preview) Standard | gpt-5-reasoning (preview) Premium | o3 Premium | Claude Sonnet 4.5 (experimental) Standard | Claude Opus 4.5 (experimental) Premium",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#11",
"judge_verdict": "not_grounded",
"rule": "R2",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/prompt-model-settings",
"evidence_quote": "| Claude Sonnet 4.6 | Standard rate | External model from Anthropic. Context allowed up to 200K tokens. | General | | Claude Opus 4.6 | Premium rate | External model from Anthropic. Context allowed up to 200K tokens. | Deep |",
"reason": "The canonical model enumeration lists Claude Sonnet 4.6 and Claude Opus 4.6 (200K); the claimed Sonnet 4.5/Opus 4.5 are absent, i.e. superseded by 4.6 versions.",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 217,
"claim": "Claude Sonnet 4.5 og Claude Opus 4.5 er tilgjengelig i Copilot Studio (experimental, 200K kontekstvindu)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-region-availability?pivots=standard",
"evidence_quote": "| gpt-5.4 | 2026-03-05 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |",
"reason": "The Data Zone Standard Europe table now shows gpt-5.4, gpt-5.5, and gpt-5.6-sol/terra/luna all available in norwayeast, so the load-bearing 'eneste GPT-5 ... er gpt-5.5' part is superseded, even though the no-Regional/PTU parts (gpt-4.1, o-series, GPT-5 family absent in Norway East) still verify.",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 393,
"claim": "Norway East: kun gpt-4o/gpt-4o-mini tilgjengelig som Norge-resident (Standard/Regional PTU); gpt-4.1, o-serien (o3/o4-mini/o3-mini/o1) og GPT-5-familien finnes ikke som Regional/PTU i Norway East; eneste GPT-5 med EU-residens i Norway East er gpt-5.5 via Data Zone Standard",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#16",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/azure/foundry/openai/how-to/reasoning",
"evidence_quote": "Access is no longer restricted for this model.",
"reason": "The live availability table states this for gpt-5, gpt-5-codex, and gpt-5-pro, contradicting the claimed aka.ms/oai/gpt5access approval requirement and the MCA-E/Default-only restriction for gpt-5-pro; the gpt-5-chat 'Preview (2 versions)' part matches, but the load-bearing access-status parts are superseded.",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 468,
"claim": "GPT-5-tilgjengelighet: gpt-5 GA (begrenset, krever godkjenning aka.ms/oai/gpt5access) | gpt-5-mini GA | gpt-5-nano GA | gpt-5-chat Preview (2 versjoner) | gpt-5-codex GA (begrenset) | gpt-5-pro GA (begrenset, kun MCA-E/Default-abonnementer)",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/gpt5-gpt41-pricing-models.md#17",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/ai-builder/credit-management",
"evidence_quote": "| Power Apps Premium | 500 | Maximum = 1,000,000 AI Builder credits per tenant. | ... | Power Automate Premium | 5,000 | Maximum = 1,000,000 AI Builder credits per tenant. |",
"reason": "The 500-credit figure applies only to Power Apps Premium; other premium Power Platform plans seed 250 to 5,000 AI Builder credits, and the page adds that these seeded credits are removed on November 1, 2026, so the blanket '500 credits/bruker/mnd i premium-planer' is contradicted even though the gpt-4.1-mini Basic default is correct.",
"file": "skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md",
"line": 443,
"claim": "AI Builder: prompt builder credits inkludert i premium Power Platform-planer (500 credits/bruker/mnd); default modell gpt-4.1-mini (Basic rate)",
"disposition": "outdated"
}
]
},
{
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"batch": "R7.1",
"judged_at": "2026-07-18",
"per_file_verdict": "flagged",
"claim_count": 16,
"verified": null,
"verified_by": null,
"flags": [
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#1",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/dotnet/ai/conceptual/understanding-tokens",
"evidence_quote": "",
"reason": "No learn.microsoft.com page states that o200k_base is the default tiktoken encoding for gpt-4o/o1/o3 (the cited source is GitHub, and two targeted searches found only cl100k_base/BPE mentions on Learn), so the claim can be neither confirmed nor refuted from Microsoft Learn.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 53,
"claim": "o200k_base er default tiktoken-encoding for gpt-4o, o1, o3",
"disposition": "unsourced"
},
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#6",
"judge_verdict": "source_silent",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching",
"evidence_quote": "",
"reason": "The page confirms cache reads are discounted on Standard and 'up to 100% discount on input tokens' for Provisioned, but the load-bearing 50% figure for Standard is never stated on any Learn page - it lives on the JS-rendered Azure pricing page, so it can be neither confirmed nor refuted.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 148,
"claim": "Cached tokens: 50% rabatt på Standard deployment; opptil 100% rabatt på Provisioned (inkludert i PTU-pris)",
"disposition": "unsourced"
},
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#8",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "| `text-embedding-ada-002` (version 2) | 8,192 | 1,536 | Sep 2021 | ... | `text-embedding-3-large` | 8,192 | 3,072 | Sep 2021 | | `text-embedding-3-small` | 8,192 | 1,536 | Sep 2021 |",
"reason": "The current canonical models table states max request of 8,192 tokens for ada-002 v2, 3-small, and 3-large (the REST reference likewise says '8192 tokens for all embedding models'), which differs from the claimed 8191.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 263,
"claim": "Token-limit per chunk for embeddings: text-embedding-ada-002 8191 tokens | text-embedding-3-small/large 8191 tokens",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#9",
"judge_verdict": "not_grounded",
"rule": "",
"evidence_url": "https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models#fine-tuning-models",
"evidence_quote": "| `gpt-4o-mini` (2024-07-18) | North Central US Sweden Central | - | Input: 128,000 Output: 16,384 Training example context length: 65,536 | Oct 2023 |",
"reason": "The canonical fine-tuning models table states a training example context length of 65,536 tokens for gpt-4o-mini, contradicting the claimed 64,536 (a figure that appears only in the tutorial and is superseded by the spec table); the 128,000 input limit part does hold.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 327,
"claim": "gpt-4o-mini fine-tuning: training example max 64536 tokens, input limit 128000 tokens",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#14",
"judge_verdict": "not_grounded",
"rule": "R8",
"evidence_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models",
"evidence_quote": "| `gpt-4.1` (2025-04-14) | ... | - 1,047,576 - 300,000 (standard deployments) - 128,000 (provisioned managed and batch deployments) | 32,768 | May 31, 2024 |",
"reason": "The gpt-4.1 context window is 1,047,576 tokens (~1M) on the live models page, not the claimed 128K (128,000 is only the provisioned/batch deployment cap), so one load-bearing part is wrong even though gpt-5/gpt-5-mini 400K, gpt-4o/gpt-4o-mini 128K, and o3-mini 200K all match.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 480,
"claim": "Context windows: gpt-5 400K | gpt-5-mini 400K | gpt-4o 128K | gpt-4o-mini 128K | o3-mini 200K | gpt-4.1 128K",
"disposition": "outdated"
},
{
"id": "ms-ai-security/cost-optimization/token-counting-optimization.md#16",
"judge_verdict": "not_grounded",
"rule": "R3",
"evidence_url": "https://learn.microsoft.com/microsoft-copilot-studio/requirements-messages-management",
"evidence_quote": "| Classic answer | 1 Copilot Credit | No charge | | Generative answer | 2 Copilot Credits | No charge | ... Text and generative AI tools (basic) per 10 response 0.1 Copilot Credit per 1K tokens",
"reason": "Copilot Studio bills Generative Answers at a flat per-event rate (2 Copilot Credits, formerly 2 messages), not token-based Azure OpenAI billing; per-1K-token rates apply only to the separate 'Text and generative AI tools' (AI Builder) meters, so the claim's billing frame is replaced by the current credits model.",
"file": "skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md",
"line": 406,
"claim": "Copilot Studio: token-basert billing for Generative Answers (Azure OpenAI), message-basert billing for standard topics; token counting via AI Builder credits",
"disposition": "outdated"
}
]
}
]
}
Reference in a new issue View git blame Copy permalink