open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 4 Activity

chore(ms-ai-architect): refresh KB high-bucket — 49 files [skip-docs]

Browse source 
KB-currency refresh (high priority, 2026-06-19) via /architect:kb-update.
49 high-prioritets governance/security/monitoring-filer re-verifisert mot
Microsoft Learn (MCP) — delegert til 8 parallelle Opus-subagenter gruppert
etter delt kilde, verifisert i hovedkontekst (diff-review + tester).

Hovedendringer (faktuelle korreksjoner + currency):
- MITRE ATLAS-IDer korrigert (supply-chain): AML.T0050 -> AML.T0018.000
  (Poison AI Model); AML.T0020 = Poison Training Data; T1195 Supply Chain
  Compromise. Gamle IDer var utdaterte (verifisert mot MCSB v2 AI-1).
- OTel-sampling presisert (distributed-tracing): adaptive sampling = klassisk
  App Insights SDK; OTel-distroen sampler IKKE by default (fixed-rate/
  rate-limited maa konfigureres); Functions parent-based sampling er default.
- MCSB v2 AI-kontroller AI-1 -> AI-7 (risk-taxonomy three-pillar, scoring-
  framework, rubrics, red-team, adversarial); Defender for Cloud AI threat
  protection + AI-SPM (GA).
- AI gateway (APIM) multi-provider: Anthropic Messages API v2-tiers, Google
  Vertex, unified model API (preview), MCP/A2A, Foundry-integrasjon; eksakte
  policy-navn (llm-emit-token-metric maks 5 dims, llm-semantic-cache-*,
  score-threshold = avstand, MS-eks. 0.15).
- Purview Enterprise AI apps inkl. Anthropic Claude (Enterprise) + ChatGPT
  Enterprise; Security Dashboard for AI (Agent 365-inventar, MCP-servere,
  tredjepartsmodeller; Security Reader minimumsrolle).
- Entra Agent ID: CA-lisenskrav (Entra ID P1/P2 + Agent 365), CA-scoping per
  tilgangsmoenster (on-behalf-of/app-only/agent-as-user), CA-grenser,
  connector-permissions som API-permissions.
- Copilot DLP: Block SITs in web search (GA, Performing Web Searches) + Block
  external email (preview) som prompt injection-vern.
- Azure AI Language PII: tre feature-typer, GA-API 2026-05-01; NOIdentityNumber
  bekreftet dedikert kategori for norske foedselsnummer.
- Foundry Tools-rename forsterket paa tvers; alle 49 Last updated -> 2026-06-19.

Discovery: 500 kandidater (alle Databricks-stoey) -> kun registry-kandidater,
ingen nye skills/-filer -> 389-telling uendret. validate 239 PASS,
kb-integrity 115/115 (262 orphan-warnings uendret), gitleaks clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-19 11:09:54 +02:00
commit 25bcb74d9a
49 changed files with 304 additions and 235 deletions
Download patch file Download diff file Expand all files Collapse all files

4
skills/ms-ai-governance/references/monitoring-observability/alerting-strategies-escalation.md
View file

@ -1,6 +1,6 @@
# Alerting Strategies and Escalation Policies for AI Incidents
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -549,7 +549,7 @@ Cost = 0.10 USD (rule) + (8640 × 0.20 USD) = 1728.10 USD/month
1. **Action Groups Overview**
https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/action-groups
*Confidence: High — Official documentation retrieved 2026-02, covers notification types, managed identity, rate limits.*
*Confidence: High — Official documentation retrieved 2026-06-19, covers notification types, managed identity (preview, role IDs bekreftet), rate limits (SMS/voice/push/email), webhook retry-intervaller (5/20/5/40/5s + 15-min cooldown), Event Hub cross-tenant til API 2023-09-01-preview. Kilden bekrefter eksisterende innhold.*
2. **Best Practices for Azure Monitor Alerts**
https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/best-practices-alerts

37
skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md
View file

@ -1,6 +1,6 @@
# Compliance Monitoring and AI Governance Dashboards
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -64,18 +64,20 @@ Unified view av AI-security posture på tvers av Microsoft Entra, Defender, Purv
| Seksjon | Metrikker | Alerts |
|---------|-----------|--------|
| **AI Agent Inventory** | Totalt antall agents, managed vs. unmanaged, shadow AI | Nye uregistrerte agents oppdaget |
| **AI Agent Inventory** | Totalt antall agents (registrert i Microsoft Agent 365), modeller, MCP-servere og tredjeparts AI-apper (Gemini, ChatGPT); managed vs. unmanaged, shadow AI | Nye uregistrerte agents oppdaget |
| **Threat Detection** | Jailbreak-forsøk, prompt injection, abuse patterns | High-severity AI-threats (real-time) |
| **Data Security** | Sensitive data i prompts/responses, oversharing risks | PII-lekkasje via AI-interaksjoner |
| **Access Control** | Conditional access policies, privileged access reviews | Over-privileged AI agent identities |
| **Compliance Status** | % av agents med required policies, policy drift | Non-compliant agents etter 24t grace period |
**Supported products:**
- **Microsoft Entra**: Agent identity platform, conditional access for AI apps
- **Microsoft Defender for Cloud**: AI workload discovery, posture management, threat protection
- **Microsoft Purview**: Data classification, DLP for AI prompts, insider risk detection
- **Microsoft Entra**: Agent identity platform (Agent Registry), conditional access for AI apps
- **Microsoft Defender**: AI model/MCP/app-discovery, posture management, AI threat protection (real-time blokkering for støttede agenter)
- **Microsoft Purview**: Data classification, DLP for AI prompts, insider risk detection (DSPM for AI)
- **Security Copilot**: Prompt-basert exploration av AI-risikoer
> Minimumsrolle for full innsikt: **Security Reader** (Microsoft Entra). Agent-inventar dekker agenter registrert i Microsoft Agent 365; modeller/MCP-servere/øvrige AI-apper oppdages av Defender.
---
## Arkitekturmønstre
@ -248,11 +250,14 @@ async with DefaultAzureCredential() as credential, \
### Azure API Management (AI Gateway)
**Modell-/endepunktdekning:** OpenAI Chat Completions/Responses, **Anthropic Messages API** (støttet i API Management v2-tiers), **Google Vertex AI**, modeller i Microsoft Foundry og Amazon Bedrock, samt remote **MCP-servere** og **A2A agent-APIer**. En **unified model API (preview)** eksponerer flere backends gjennom ett OpenAI-kompatibelt endepunkt med felles governance-policyer. AI gateway kan nå integreres direkte i **Microsoft Foundry (preview)**.
**Governance capabilities:**
- **Token consumption metrics**: Emit til Application Insights med custom dimensions (user ID, cost center, API ID)
- **Quota enforcement**: Rate limits per user/tenant
- **Logging**: Prompts, completions, token usage → Azure Monitor Logs
- **Policy enforcement**: Input validation, content filtering, max token caps
- **Token consumption metrics**: Emit til Application Insights med custom dimensions (user ID, cost center, API ID) via `llm-emit-token-metric` (maks 5 custom dimensions inbound)
- **Quota enforcement**: Rate limits / token-kvoter per consumer (`llm-token-limit`)
- **Semantic caching**: `llm-semantic-cache-store` / `llm-semantic-cache-lookup` mot Azure Managed Redis (RediSearch); `score-threshold` er et distanse-mål (lavere = strengere, MS-eksempel 0,15)
- **Logging**: Prompts, completions, token usage → Azure Monitor Logs + innebygd dashboard
- **Policy enforcement**: Input validation, content safety (`llm-content-safety`), max token caps
**Sample policy:**
```xml
@ -270,8 +275,14 @@ async with DefaultAzureCredential() as credential, \
- **Audit logs**: Unified audit log for AI interactions (prompts, responses, referenced files, sensitivity labels)
- **Communication Compliance**: Policy violations i AI-generert innhold (harassment, sensitive info sharing)
- **eDiscovery**: Søk og slett AI interaction data (GDPR "right to be forgotten")
- **Insider Risk Management**: `Risky AI usage`-policy fanger prompt injection-forsøk og tilgang til beskyttet materiale
- **Retention policies**: Automatisk retain/delete prompts og responses per compliance requirements
**App-dekning (Purview-kategorier):**
- **Copilot experiences and agents**: Microsoft 365 Copilot (+ Cowork), Security Copilot, Copilot in Fabric, Copilot Studio, Microsoft Facilitator, Teams Channel Agent
- **Enterprise AI apps**: Microsoft Foundry, Entra-registrerte AI-apper, **Anthropic Claude (Enterprise)**, **ChatGPT Enterprise**
- **Other AI apps** (oppdaget via browser, Defender for Cloud Apps): ChatGPT, Google Gemini, Microsoft Copilot (consumer), DeepSeek
**Collection policies:**
- `DSPM for AI - Detect sensitive info shared with AI via network`
- `DSPM for AI - Capture interactions for enterprise AI apps`
@ -459,7 +470,7 @@ AppMetrics
---
*(Verified MCP 2026-04)*
*(Verified MCP 2026-06-19)*
## Kilder og verifisering
@ -472,17 +483,17 @@ AppMetrics
- [Govern AI apps and data for regulatory compliance](https://learn.microsoft.com/en-us/security/security-for-ai/govern) — Verified 2026-02
**Microsoft Purview for AI:**
- [Microsoft Purview data security and compliance protections for generative AI apps](https://learn.microsoft.com/en-us/purview/ai-microsoft-purview) — Verified 2026-02
- [Microsoft Purview data security and compliance protections for generative AI apps](https://learn.microsoft.com/en-us/purview/ai-microsoft-purview) — Verified 2026-06-19 (Enterprise AI apps inkluderer nå Anthropic Claude Enterprise + ChatGPT Enterprise)
- [Use Microsoft Purview to manage data security & compliance for Microsoft Foundry](https://learn.microsoft.com/en-us/purview/ai-azure-foundry) — Verified 2026-02
- [Assessments for AI regulations](https://learn.microsoft.com/en-us/purview/compliance-manager-assessments#assessments-for-ai-regulations) — Verified 2026-02
**Azure Policy & monitoring:**
- [Azure Policy Regulatory Compliance controls for Azure AI Search](https://learn.microsoft.com/en-us/azure/search/security-controls-policy) — Verified 2026-02
- [Control AI model deployment with built-in policies in Microsoft Foundry portal](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/built-in-policy-model-deployment) — Verified 2026-02
- [AI gateway in Azure API Management (Observability and governance)](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities#observability-and-governance) — Verified 2026-02
- [AI gateway in Azure API Management (Observability and governance)](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities#observability-and-governance) — Verified 2026-06-19 (Anthropic Messages API v2-tiers, Google Vertex AI, unified model API preview, MCP/A2A, AI gateway i Foundry preview)
**Security & observability:**
- [Assess your organization's AI risk with Microsoft Security Dashboard for AI (Preview)](https://learn.microsoft.com/en-us/security/security-for-ai/security-dashboard-for-ai) — Verified 2026-02
- [Assess your organization's AI risk with Microsoft Security Dashboard for AI](https://learn.microsoft.com/en-us/security/security-for-ai/security-dashboard-for-ai) — Verified 2026-06-19 (Agent 365-inventar, MCP-servere, tredjepartsmodeller; Security Reader minimumsrolle)
- [Governance and security for AI agents across the organization](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/ai-agents/governance-security-across-organization) — Verified 2026-02
- [Monitor Azure OpenAI (Dashboards)](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai) — Verified 2026-02

6
skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md
View file

@ -1,7 +1,7 @@
# Custom Dashboards for AI Operations
**Kategori:** Monitoring & Observability
**Sist oppdatert:** 2026-05 | Verified: MCP 2026-05
**Sist oppdatert:** 2026-06-19 | Verified: MCP 2026-06-19
**Brukes av:** Cosmo Skyberg, Microsoft AI Solution Architect
---
@ -215,7 +215,7 @@ AzureDiagnostics
- Benchmark mot SLA
**Scheduling:**
- Sett opp scheduled refresh (8x per dag for free, hourly for Pro)
- Scheduled refresh, deling, dataflows og incremental refresh krever Power BI Pro eller Premium (gratis-tier dekker kun lokal rapport-/dashboardbygging). Incremental refresh forutsetter et **datetime**-felt i resultatsettet.
- Email subscriptions for stakeholders
- Power BI mobile app for on-the-go access
@ -485,7 +485,7 @@ Når kunden spør om dashboards for AI operations:
- [Create an Azure AI Foundry dashboard](https://learn.microsoft.com/en-us/azure/managed-grafana/azure-ai-foundry-dashboard)
- [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai)
- [Workbooks programmatic management](https://learn.microsoft.com/en-us/azure/azure-monitor/visualize/workbooks-automate) *(Verified MCP 2026-04)* — ARM/Bicep deployment, RBAC (Monitoring Contributor for redigering, Monitoring Reader for visning), `microsoft.insights/workbooks/write` for custom roles
- [Power BI + Azure Monitor](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/log-powerbi)
- [Power BI + Azure Monitor](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/log-powerbi) *(Verified MCP 2026-06-19)* — eksport fra Log Analytics som M-query (.txt → Power BI Desktop) eller new Dataset (Power BI-tjenesten); dataflows + incremental refresh; scheduled refresh/deling krever Pro/Premium
### Code Samples
- [Workbook ARM/Bicep template samples](https://learn.microsoft.com/en-us/azure/azure-monitor/visualize/workbooks-samples) — workbook templates bruker apiVersion `2019-10-17-preview` (type: microsoft.insights/workbooktemplates); workbook instances bruker `2018-06-17-preview` (type: Microsoft.Insights/workbooks) *(Verified MCP 2026-04)*

14
skills/ms-ai-governance/references/monitoring-observability/distributed-tracing-ai-pipelines.md
View file

@ -1,7 +1,7 @@
# Distributed Tracing for AI Pipelines
**Kategori:** Monitoring & Observability
**Dato:** 2026-02-05
**Dato:** 2026-06-19
**Status:** ✅ Komplett
## Innledning
@ -150,6 +150,12 @@ def orchestrator(req: func.HttpRequest) -> func.HttpResponse:
return func.HttpResponse("OK", status_code=200)
```
**Viktige forbehold for OpenTelemetry-modus i Functions** *(Verified MCP 2026-06-19)*:
- OTel aktiveres på app-nivå i både `host.json` (`"telemetryMode": "OpenTelemetry"`) og i koden. Når du oppgir både `APPLICATIONINSIGHTS_CONNECTION_STRING` og en OTLP-eksportør (`OTEL_EXPORTER_OTLP_ENDPOINT`/`OTEL_EXPORTER_OTLP_HEADERS`), sendes telemetri til begge endepunktene.
- I OTel-modus støtter Azure-portalen **ikke** log streaming, og `Recent function invocation`-traces vises kun hvis telemetri sendes til Azure Monitor. Logging-konfigurasjon under `logging.applicationInsights` i `host.json` gjelder ikke.
- **Parent-based sampling er standard.** Triggere som HTTP, Service Bus og Event Hubs avhenger av context propagation; request-telemetri genereres ikke når den innkommende requesten/meldingen ikke samples. `OperationId` hentes direkte fra `traceparent` — gjenbruk av samme `traceparent` gir samme `OperationId`.
- Filtre i `host.json` gjelder kun host-prosessens logger; worker-prosessens logger filtreres via språkspesifikke OTel-innstillinger. Go-worker har egen opt-in OTel-middleware (`middleware/otelfunc`).
### 3. LangChain/LangGraph + Azure AI Tracing
**Setup:**
@ -447,10 +453,12 @@ traces
### 5. Sampling for High-Volume Scenarios
**Adaptive sampling (automatisk i Azure Monitor):**
**Adaptive sampling (Application Insights SDK / klassisk):**
- Reduserer volum uten å miste viktige traces
- Prioriterer feil og trege forespørsler
> **Merk:** Azure Monitor OpenTelemetry-distroen sampler **ikke** som standard. Distroen støtter fixed-rate og rate-limited samplere som må konfigureres eksplisitt; trace-basert sampling for logger er default-på først når sampling er aktivert. Adaptive sampling over gjelder den klassiske Application Insights SDK-en, ikke OTel-distroen. *(Verified MCP 2026-06-19)*
**Custom sampling (avansert):**
```python
@ -596,7 +604,7 @@ Adapted from Microsoft Learn documentation ([CC BY 4.0](https://creativecommons.
- [Tracing in Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-studio/how-to/develop/trace-local-sdk)
- [Azure Monitor OpenTelemetry overview](https://learn.microsoft.com/en-us/azure/azure-monitor/app/opentelemetry-overview)
- [Azure Functions OpenTelemetry](https://learn.microsoft.com/en-us/azure/azure-functions/opentelemetry-howto)
- [Azure Functions OpenTelemetry](https://learn.microsoft.com/en-us/azure/azure-functions/opentelemetry-howto) *(Verified MCP 2026-06-19 — parent-based sampling default; OTLP + App Insights dual-export; portal log-streaming/recent-invocation-traces krever Azure Monitor)*
- [Distributed tracing in Application Insights](https://learn.microsoft.com/en-us/azure/azure-monitor/app/distributed-trace-data)
- [Semantic Kernel observability](https://learn.microsoft.com/en-us/semantic-kernel/concepts/enterprise-readiness/observability/)

6
skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md
View file

@ -1,6 +1,6 @@
# Endpoint Health Monitoring and Capacity Planning
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -612,7 +612,7 @@ az role assignment create \
7. **Service limits in Azure AI Search:**
https://learn.microsoft.com/en-us/azure/search/search-limits-quotas-capacity
*Confidence: Verified* — Throttling patterns (relevant for RAG-arkitekturer)
*Confidence: Verified* — Throttling patterns (relevant for RAG-arkitekturer). To prismodeller: Dedicated (SU) + Serverless (Preview, CU/time + per-GB, kun West Central US / Switzerland North / Japan East, ingen SLA). Basic-tier (tjenester opprettet etter 2024-04-03) støtter inntil 3 partisjoner × 3 replikaer (9 SU). *(Verified MCP 2026-06-19)*
8. **Monitor model quality and endpoint health (Databricks):**
https://learn.microsoft.com/en-us/azure/databricks/machine-learning/model-serving/monitor-diagnose-endpoints
@ -645,4 +645,4 @@ az role assignment create \
**Samlet konfidens:** 85% Verified (core features), 15% Baseline (best practices, offentlig sektor-spesifikt)
**Sist verifisert:** 2026-04 (MCP-searches mot Microsoft Learn)
**Sist verifisert:** 2026-06-19 (MCP-fetch mot search-limits-quotas-capacity + Databricks model-serving monitor-diagnose-endpoints — kildene bekrefter eksisterende innhold)

6
skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md
View file

@ -1,6 +1,6 @@
# Real-Time Streaming and Live Monitoring Dashboards
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -522,7 +522,7 @@ Real-Time Dashboard er IKKE erstatning for data warehouse. Bruk for operational
6. **Build real-time monitoring and observable systems for media**
https://learn.microsoft.com/en-us/azure/architecture/example-scenario/monitoring/monitoring-observable-systems-media
**Confidence:** Verified (Feb 2026) - Real-time architecture patterns
**Confidence:** Verified (2026-06-19) - Real-time architecture patterns (Eventstream → eventhouse → Real-Time Intelligence hub; Data Activator subsecond anomaly detection)
7. **Observability in generative AI**
https://learn.microsoft.com/en-us/azure/foundry/concepts/observability
@ -545,4 +545,4 @@ Real-Time Dashboard er IKKE erstatning for data warehouse. Bruk for operational
**MCP calls:** 6 (3 × search, 2 × fetch, 1 × code search)
**Unique sources:** 8 Microsoft Learn URLs
**Last verified:** 2026-04
**Last verified:** 2026-06-19

8
skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md
View file

@ -1,6 +1,6 @@
# Security and Audit Logging for AI Systems
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -23,7 +23,7 @@ For norsk offentlig sektor er audit logging et lovpålagt krav under Forvaltning
| **Azure Monitor Resource Logs** | Detaljert logging av data plane-operasjoner | API calls, modell-inferens, plugin-interaksjoner, token-forbruk |
| **Azure Activity Log** | Control plane-hendelser på abonnementsnivå | Ressursopprettelse, rolleutdelinger, brannmurregler, sletting |
| **Diagnostic Settings** | Rute-konfigurasjon for loggeksport | Log Analytics, Storage Account, Event Hub, SIEM-partnere |
| **Microsoft Defender for AI Services** | Trusseldeteksjon spesifikk for AI | Jailbreak-forsøk, prompt injection, unormale modell-outputs. Støtter Azure OpenAI (via Foundry Tools). Konfigureres separat for Foundry-ressurser. *(Verified MCP 2026-04)* |
| **Microsoft Defender for Cloud — AI threat protection + AI-SPM** | Trusseldeteksjon spesifikk for AI | Jailbreak-forsøk, prompt injection, unormale modell-outputs + AI Security Posture Management. Støtter Azure OpenAI. Konfigureres separat for Foundry-ressurser. («Foundry resource», kind=AIServices, er nytt navn på det som tidligere het «Foundry Tools».) *(Verified MCP 2026-06-19)* |
| **Microsoft Purview** | Dataklassifisering og tilgangssporing | PII-aksess, sensitiv datalogging, dataeiers-revisjon |
| **Azure Policy** | Compliance enforcement | Automatisk pålegging av diagnostiske innstillinger, policy-etterlevelse |
@ -391,7 +391,7 @@ Ingen ekstra lisenser kreves for audit logging — funksjonen er inkludert i Azu
| **Microsoft cloud security benchmark: Logging and threat detection** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-logging-threat-detection | ✅ Verified |
| **Artificial Intelligence Security (AI-6: Establish monitoring and detection)** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security | ✅ Verified |
| **Azure Policy Regulatory Compliance controls** | https://learn.microsoft.com/en-us/azure/governance/policy/samples/azure-security-benchmark | ✅ Verified |
| **Best practices for data and AI governance (Databricks)** | https://learn.microsoft.com/en-us/azure/databricks/lakehouse-architecture/data-governance/best-practices | ✅ Verified — Unity Catalog er nå sentral governance for BÅDE data og AI assets (modeller, features, lineage). Tre governance-modeller: sentralisert, distribuert (federated), hybrid. AI-genererte kommentarer støttes (krever human review). *(Verified MCP 2026-04)* |
| **Best practices for data and AI governance (Databricks)** | https://learn.microsoft.com/en-us/azure/databricks/lakehouse-architecture/data-governance/best-practices | ✅ Verified — Unity Catalog er nå sentral governance for BÅDE data og AI assets (modeller, features, lineage ned til kolonne-nivå). Tre governance-modeller: sentralisert, distribuert (federated), hybrid. Audit-logging på to nivåer (workspace + account) + verbose audit logs per query/kommando. AI-genererte kommentarer støttes (krever human review). *(Verified MCP 2026-06-19)* |
### Konfidensgradering per seksjon
@ -405,4 +405,4 @@ Ingen ekstra lisenser kreves for audit logging — funksjonen er inkludert i Azu
| **Offentlig sektor** | ⚠️ Baseline | Rettsgrunnlag er korrekt, implementasjonsdetaljer er tolkninger |
| **Kostnad** | ⚠️ Baseline | Priser fra Azure Pricing Calculator (februar 2026), kan variere |
### Sist verifisert: 2026-04
### Sist verifisert: 2026-06-19

4
skills/ms-ai-governance/references/monitoring-observability/sla-monitoring-ai-services.md
View file

@ -1,6 +1,6 @@
# SLA Monitoring and Availability Tracking for AI Services
**Last updated:** 2026-05
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Monitoring & Observability
@ -360,7 +360,7 @@ Metric Alert
3. **Monitoring and diagnostics guidance**
https://learn.microsoft.com/en-us/azure/architecture/best-practices/monitoring
*Confidence: Verified* — SLA monitoring best practices (generell Azure-arkitektur). Dekker: tilgjengelighetssporing, ytelsesovervåkning, SLA-etterlevelse, sikkerhet/personvern, regulatorisk audit, trend-deteksjon. Brukes i AI-kontekst for å sikre end-to-end synlighet i distribuerte AI-systemer. *(Verified MCP 2026-04)*
*Confidence: Verified* — SLA monitoring best practices (generell Azure-arkitektur). Dekker: tilgjengelighetssporing, ytelsesovervåkning, SLA-etterlevelse, sikkerhet/personvern, regulatorisk audit, trend-deteksjon. Brukes i AI-kontekst for å sikre end-to-end synlighet i distribuerte AI-systemer. *(Verified MCP 2026-06-19 — kilde uendret, bekrefter eksisterende innhold)*
4. **Azure OpenAI FAQ - SLA**
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq#what-are-the-slas-service-level-agreements-in-azure-openai

11
skills/ms-ai-governance/references/monitoring-observability/token-usage-tracking-attribution.md
View file

@ -1,7 +1,7 @@
# Token Usage Tracking and Attribution
**Kategori:** Monitoring & Observability
**Dato:** 2026-04-09
**Dato:** 2026-06-19
**Versjon:** 1.0
## Introduksjon
@ -505,9 +505,14 @@ Owner: <email>
**3. Budgets:**
- Opprett per resource group eller subscription
- Sett alert thresholds (50%, 80%, 100%, 120%)
- Sett alert thresholds (50%, 80%, 100%, 120%). WAF anbefaler som minimum 90% (ideelt forbruk), 100% (mål) og 110% (mindre ideelt) for budget alerts, og 110% for forecast alerts. *(Verified MCP 2026-06-19)*
- Action groups for automated response (webhook, Logic App)
**4. FOCUS-basert eksport og analyse** *(Verified MCP 2026-06-19)*:
- Azure Cost Management beholder kostnadsdata i **13 måneder**. For lengre historikk: planlegg Cost Management-eksport til et Azure Data Lake Storage Gen2-lager (daglig/månedlig) med **FOCUS**-malen (FinOps Open Cost and Usage Specification — leverandøragnostisk, standardisert skjema).
- Skill mellom **actual costs** (som fakturert, 24–72 t ingestion-forsinkelse) og **amortized costs** (commitment-baserte kjøp fordelt jevnt over perioden). Samle inn begge for å avstemme faktura mot effektiv kostnad.
- Avansert rapportering: pipeline **Cost Management exports → ADLS Gen2 → Fabric Lakehouse → Power BI** skalerer til store datasett og muliggjør egendefinert FOCUS-rapportering. For høyvolum-tjenester: bruk ingestion-time transformation i Log Analytics for å redusere loggvolum.
## Best Practices
### 1. Data Store Selection
@ -574,7 +579,7 @@ Owner: <email>
4. [Token usage estimation for Azure OpenAI On Your Data](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data) — RAG-specific token calculations
5. [Understanding costs associated with PTU](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing) — PTU billing model
6. [Application design for AI workloads](https://learn.microsoft.com/en-us/azure/well-architected/ai/application-design#consider-nonfunctional-requirements) — Cost and chargeback scenarios
7. [Architecture strategies for cost data](https://learn.microsoft.com/en-us/azure/well-architected/cost-optimization/collect-review-cost-data#generate-cost-reports) — Chargeback vs. showback
7. [Architecture strategies for cost data](https://learn.microsoft.com/en-us/azure/well-architected/cost-optimization/collect-review-cost-data#generate-cost-reports) — Chargeback vs. showback. *(Verified MCP 2026-06-19 — FOCUS-eksport, actual vs amortized costs, Cost Management 13-mnd retention, Fabric/Power BI-pipeline, budget/forecast alert-terskler)*
## For Cosmo