67729152fd
docs(ms-ai-architect): KB-refresh LOW 33/52 — apim-authentication-oauth-managed-identity: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:38 +02:00
564f473409
docs(ms-ai-architect): KB-refresh LOW 32/52 — versioning-ai-api-endpoints: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:38 +02:00
b098936291
docs(ms-ai-architect): KB-refresh LOW 31/52 — request-response-transformation-ai: la til unified model API (Preview) facade-notis
2026-06-24 12:15:38 +02:00
b600d84adb
docs(ms-ai-architect): KB-refresh LOW 30/52 — multi-region-ai-gateway-design: multi-region kun Premium (classic) (Premium v2 ikke), score-threshold 0.9→0.15
2026-06-24 12:15:38 +02:00
e1b42609d5
docs(ms-ai-architect): KB-refresh LOW 29/52 — apim-vs-direct-access-comparison: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:38 +02:00
e2354ad1e6
docs(ms-ai-architect): KB-refresh LOW 28/52 — apim-azure-front-door-ai: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:38 +02:00
e819152d18
docs(ms-ai-architect): KB-refresh LOW 27/52 — backend-pool-management: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:37 +02:00
451f1e6a2e
docs(ms-ai-architect): KB-refresh LOW 26/52 — security-hardening-ai-gateway: llm-content-safety syntaks (text-blocklist-ids→blocklists, shield-prompt, element-rekkefølge)
2026-06-24 12:15:37 +02:00
a05d238eba
docs(ms-ai-architect): KB-refresh LOW 25/52 — developer-portal-ai-apis: Developer Portal nå i alle v2-tiers (Basic v2 inkludert), kun Consumption mangler
2026-06-24 12:15:37 +02:00
81a85d64b3
docs(ms-ai-architect): KB-refresh LOW 24/52 — caching-strategies-apim-ai: TRYGT (kjerneinnhold verifisert — semantisk caching nå alle tiers, header-bump)
2026-06-24 12:15:37 +02:00
2a77e7f606
docs(ms-ai-architect): KB-refresh LOW 23/52 — logging-analytics-ai-traffic: KQL ModelDeploymentName→DeploymentName, subscription/bruker-spørringer join mot ApiManagementGatewayLogs på CorrelationId
2026-06-24 12:15:37 +02:00
4cf479ce63
docs(ms-ai-architect): KB-refresh LOW 22/52 — streaming-support-apim: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 12:15:37 +02:00
4b4fd24702
docs(ms-ai-architect): KB-refresh LOW 21/52 — genai-gateway-policies: token-quota-period sek→Daily, KQL ModelDeployment→DeploymentName, llm-token-limit Consumption Nei, semantic-cache tier-matrise korrigert
2026-06-24 12:15:37 +02:00
10818d1120
docs(ms-ai-architect): KB-refresh LOW 20/52 — zero-etl-fabric-patterns: Oracle+SAP mirroring Preview til GA, SAP HANA roadmap oppdatert
2026-06-24 11:59:29 +02:00
705f62bb9a
docs(ms-ai-architect): KB-refresh LOW 19/52 — synthetic-data-generation: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:29 +02:00
00bfc2da09
docs(ms-ai-architect): KB-refresh LOW 18/52 — schema-evolution-management: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:29 +02:00
614baff99b
docs(ms-ai-architect): KB-refresh LOW 17/52 — real-time-streaming-ai: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:29 +02:00
59f1993ab9
docs(ms-ai-architect): KB-refresh LOW 16/52 — onelake-data-strategy: OneLake Security GA kjerne-engines, Shortcut Transformations GA (CSV/Parquet/JSON), URL-fix
2026-06-24 11:59:28 +02:00
1f81500e99
docs(ms-ai-architect): KB-refresh LOW 15/52 — master-data-management-ai: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:28 +02:00
a90c446a21
docs(ms-ai-architect): KB-refresh LOW 14/52 — lakehouse-architecture-design: liquid clustering Preview til GA
2026-06-24 11:59:28 +02:00
3758f5b97e
docs(ms-ai-architect): KB-refresh LOW 13/52 — feature-stores-engineering: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:28 +02:00
a94b63e5ae
docs(ms-ai-architect): KB-refresh LOW 12/52 — fabric-lakehouse-architecture: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:28 +02:00
7ecd854a2f
docs(ms-ai-architect): KB-refresh LOW 11/52 — etl-vs-elt-ai: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:28 +02:00
7712147b4b
docs(ms-ai-architect): KB-refresh LOW 10/52 — delta-lake-parquet-optimization: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:27 +02:00
04c5c31b32
docs(ms-ai-architect): KB-refresh LOW 9/52 — data-versioning-lineage: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:27 +02:00
8b3a5947f8
docs(ms-ai-architect): KB-refresh LOW 8/52 — data-sampling-labeling: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:27 +02:00
2bb12de705
docs(ms-ai-architect): KB-refresh LOW 7/52 — data-quality-ai-frameworks: MLV-syntaks ON MISMATCH (ikke WITH ACTION), funksjoner/UDF stottes i constraints, DLT to Lakeflow SDP rebrand
2026-06-24 11:59:27 +02:00
4bd1b1d625
docs(ms-ai-architect): KB-refresh LOW 6/52 — data-pipeline-orchestration: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:27 +02:00
56357eeb19
docs(ms-ai-architect): KB-refresh LOW 5/52 — data-mesh-patterns: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:27 +02:00
f527ed2a4b
docs(ms-ai-architect): KB-refresh LOW 4/52 — data-factory-ai-pipelines: TRYGT (170+ konnektorer + ML SDK v1-datoer verifisert, header-bump)
2026-06-24 11:59:26 +02:00
a6a005d498
docs(ms-ai-architect): KB-refresh LOW 3/52 — data-cataloging-discovery: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:26 +02:00
37f128c66c
docs(ms-ai-architect): KB-refresh LOW 2/52 — data-anonymization-privacy: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:26 +02:00
cd6d0d98c2
docs(ms-ai-architect): KB-refresh LOW 1/52 — cross-cloud-data-integration: TRYGT (innhold verifisert gjeldende, header-bump)
2026-06-24 11:59:26 +02:00
257561de7a
docs(ms-ai-architect): KB-refresh MEDIUM 32/33 — speaker-recognition: Limited Access-status (kun Microsoft-managed customers)
2026-06-24 11:38:26 +02:00
0c633bd9b4
docs(ms-ai-architect): KB-refresh MEDIUM 31/33 — model-versioning: MLflow stages legacy i UC (aliases/tags/deployment jobs) + MLflow 3-endringer
2026-06-24 11:38:26 +02:00
34dae8603b
docs(ms-ai-architect): KB-refresh MEDIUM 30/33 — feedback-loops: header-bump (TRYGT: MLflow 3 scorers + Azure ML monitoring uendret)
2026-06-24 11:38:26 +02:00
8739f8e8e5
docs(ms-ai-architect): KB-refresh MEDIUM 29/33 — agent-memory: procedural memory (3. type) + TTL/CRUD + Norway East-region (VNet ikke støttet)
2026-06-24 11:38:26 +02:00
7a42701f2c
docs(ms-ai-architect): KB-refresh MEDIUM 28/33 — agent-evaluation: nye agent-evaluatorer (Task Completion/Tool Selection m.fl.) + FoundryEvals + 4.1-mini judge
2026-06-24 11:38:25 +02:00
92f0aea4d5
docs(ms-ai-architect): KB-refresh MEDIUM 27/33 — streaming-rag: header-bump (TRYGT: background streaming + SSE-konfig uendret)
2026-06-24 11:38:25 +02:00
9907725a4e
docs(ms-ai-architect): KB-refresh MEDIUM 26/33 — self-reflective-rag: header-bump (TRYGT: Foundry RAG-evaluatorer + SK agent-RAG uendret)
2026-06-24 11:38:25 +02:00
3494bc90f6
docs(ms-ai-architect): KB-refresh MEDIUM 25/33 — rag-hallucination: groundedness API mitigating/correctionText + GA-til-preview-nyanse
2026-06-24 11:38:25 +02:00
1c2980837b
docs(ms-ai-architect): KB-refresh MEDIUM 24/33 — rag-evaluation: header-bump (TRYGT: RAG-evaluatorer + Prompt Flow-retirement + token-budsjett uendret)
2026-06-24 11:38:25 +02:00
17ab402752
docs(ms-ai-architect): KB-refresh MEDIUM 23/33 — late-chunking: header-bump (TRYGT: text-embedding-3 8191 tokens/dimensjoner uendret)
2026-06-24 11:38:25 +02:00
477c808744
docs(ms-ai-architect): KB-refresh HIGH 11/11 — agent-autonomy: Task Adherence (preview) lagt til risk-kategorier
2026-06-24 10:44:37 +02:00
e78fb2f698
docs(ms-ai-architect): KB-refresh RBAC-rolle-renavn — Azure AI User→Foundry User (1 fil)
...
Microsoft har omdøpt Foundry RBAC-rollene (visningsnavn) — rolle-IDer og
kjernepermisjoner UENDRET. Verifisert mot offisiell MS-doc (juni 2026,
konsistent «Important»-note på tvers av kilder):
- Azure AI User → Foundry User
- Azure AI Owner → Foundry Owner
- Azure AI Account Owner → Foundry Account Owner
- Azure AI Project Manager → Foundry Project Manager
Kun ÉN genuin bruks-forekomst i korpuset (RBAC-krav for publisert
Agent Application-endepunkt). Renavnet med parentes «(tidligere Azure AI
User — rolle-ID og kjernepermisjoner uendret)» ved nevningen, konsistent
med at gamle navn fortsatt vises under utrullingen.
BEVART: azure-ai-foundry-cost-governance.md:109 dokumenterer hele
renavn-mappingen som forklarende ref (tema b) — ikke rørt.
Ref-fil-edit (ikke SKILL.md) → judge-cache gyldig. Deterministisk re-score:
advisor 91, eng/gov/infra/sec 96 (alle ≥90, uendret). validate 239/0.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:23:09 +02:00
03d596e4ec
docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer)
...
Verifisert mot offisiell MS-doc (juni 2026): «Microsoft Foundry» er det
gjeldende produkt-/portalnavnet; «Foundry (classic)» = gamle «Azure AI Foundry»
(/azure/foundry/ vs /azure/foundry-classic/). Premiss bekreftet før sveip.
Multi-regel, IKKE naiv s/Azure AI Foundry/Microsoft Foundry/ — MS dropper
«Azure AI» (legger IKKE til «Microsoft») for to produktvarianter:
- «Azure AI Foundry Agent[ Service|s]» → «Foundry Agent Service/Agents» (MS-form)
- «Azure AI Foundry Models» → «Foundry Models» (i «Azure OpenAI in Foundry Models»)
- «Azure AI Foundry SDK» → «Microsoft Foundry SDK» (operatør-valg)
- «Azure AI Foundry portal/project» + generisk → «Microsoft Foundry»
- Pre-eksisterende «Microsoft Foundry Models» (4) normalisert → «Foundry Models»
Bevart: «Azure OpenAI», «Azure AI Inference SDK», «Azure AI Search»,
«Azure AI Services», kode-IDer. Historisk ref «(tidligere Azure AI Foundry)»
i model-catalog-2026.md beskyttet via lookbehind. URL /azure/ai-foundry/→
/azure/foundry/ kun i owasp-llm-top10 (KB-ref); docs/-filer deferred.
Scope: skills (inkl. 3 SKILL.md) + commands + agents + README + CLAUDE.
Ekskludert: docs/ (interne), playground/+tests/ fixtures (testdata),
CHANGELOG.md (historisk logg), STATE.md (gitignored).
3 SKILL.md endret (advisor/engineering/security) → judge-cache teknisk
invalidert for disse, men scorer uendret: advisor 91, eng/gov/infra/sec 96
(alle ≥90). validate 239/0. 0 «Azure AI Foundry» igjen (utenom bevart ref).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:00:27 +02:00
dab3f1d044
chore(ms-ai-architect): Sesjon 6 bootstrap - **Source:**-header på 3 entydige ref-filer
...
De 3 ref-filene som siteres av nøyaktig 1 URL med rent topisk treff får sin **Source:**-autoritetsheader (entydig, ingen gjetning): late-chunking-patterns→embeddings-tutorial, ai-red-team-operations-practical→ai-red-team/training, batch-api-usage-optimization→batch-blob-storage. authority_source-dekning 0→0,22%; lag-5 regel 3 nå virksom for disse filene.
Bevisst utelatt: ai-act-annex-iii-checklist.md — dens autoritet er EU-forordningen (deklarert **Hjemmel:** Regulation (EU) 2024/1689), ikke den tangentielle Purview-URLen den siterer. Å sette Purview som autoritet ville vært en gjetning som får regel 3 til å bomme (verifiseringsplikt).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-19 22:58:10 +02:00
070141f06b
chore(ms-ai-architect): refresh KB medium-bucket — 74 files [skip-docs]
...
KB-currency refresh (medium priority, 2026-06-19) via /architect:kb-update.
74 medium-prioritets filer re-verifisert mot Microsoft Learn (MCP) — delegert
til 15 parallelle Opus-subagenter (3 bølger) gruppert etter delt kilde, med
disjunkte fil-sett. Verifisert i hovedkontekst (scope-sjekk + diff-review av
de faktatunge gruppene + tester).
Hovedendringer (faktuelle korreksjoner + currency):
- Azure AI Search semantic ranker: TILGJENGELIG PÅ ALLE TIERS (også Free/Basic
m/ gratis månedlig kvote) — gammel KB sa feilaktig "kun S1+". Korrigert i
tier-tabell, anti-patterns og beslutningstabell (azure-ai-search-setup).
- APIM score-threshold = DISTANSE (lavere = strengere): tuning-tabellen i
rag-caching-optimization hadde retningen baklengs — invertert til korrekt.
- Agentic retrieval GA/preview-nyanse presisert (hovedkontekst-korreksjon mot
agentic-retrieval-how-to-migrate): GA via REST 2026-04-01 returnerer EKSTRAKTIV
grounding (references + activity), IKKE syntetiserte svar. Answer synthesis,
ikke-minimal reasoning effort (LLM query planning) og multi-turn messages
forblir preview (2026-05-01-preview). Subagent hadde overforenklet til "hele
kjernepipelinen GA"; rettet i agentic-rag-patterns + citation-tracking.
- Copilot Studio modell-tabeller (platforms/copilot-studio): fjernet Claude Opus
4.5 + GPT-5.2 (borte fra kilde), lagt til Claude Sonnet 4.6/Opus 4.6 (GA),
Opus 4.7 + Mistral Medium 3.5 (experimental); GPT-5 Reasoning/Auto = preview;
A2A GA (apr 2026).
- Computer Use (CUA): Copilot Studio GA 2026-05-07; 4 modeller m/ tier/status
(OpenAI CUA + Sonnet 4.5 GA, Sonnet 4.6 + Opus 4.6 experimental); 5 credits/
steg standard, 15 premium; US-only region-krav FJERNET i GA-dok; Cloud PC pool
+ Hosted browser + bring-your-own-machine.
- Azure AI Search REST API-versjoner bumpet: 2025-09-01 -> 2026-04-01 (stabil),
2025-11-01-preview -> 2026-05-01-preview (hybrid-search, rag-security-rbac,
chunking).
- Power Automate-integrasjon: trigger "Run a flow from Copilot" -> "When an agent
calls the flow"; App Service innebygd MCP (preview) lagt til.
- M365 Copilot-manifest v1.26 -> v1.28 (GA, mai) / v1.29 dokumentert (juni);
"Tenant graph grounding" -> "Work IQ".
- Speech fast transcription 2t/300MB -> 5t/500MB; multilingual 14 -> 15 locales
(+ pt-BR). Content Understanding reasoning preview -> GA (v1.0, 2025-11-01).
- Security Copilot E5 -> E5+E7. Død Databricks-URL ci-cd/best-practices ->
ci-cd/flows. Prompt Flow retirement (2027-04-20 -> MAF) notert der den
presenteres som go-forward. Gateway-topologi-tabell-feil rettet.
- Alle 74 Last updated -> 2026-06-19.
Discovery ikke kjørt (historisk kun Databricks-støy) -> 389-telling uendret,
ingen resync. 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
2026-06-19 14:02:18 +02:00
25bcb74d9a
chore(ms-ai-architect): refresh KB high-bucket — 49 files [skip-docs]
...
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
2026-06-19 11:09:54 +02:00
41b390b38d
chore(ms-ai-architect): refresh KB critical-bucket — 15 files [skip-docs]
...
KB-currency refresh (critical priority, 2026-06-19) via /architect:kb-update.
15 critical cost/arkitektur-filer re-verifisert mot Microsoft Learn (MCP).
Hovedendringer:
- Azure AI Search Serverless (Preview) prismodell (rag-cost, rag-query,
vector-storage, rag-enterprise-scale)
- Agentic retrieval GA-split (2026-04-01 REST GA, portal preview) + Foundry IQ
- AI gateway multi-provider (Anthropic v2 / Google Vertex), unified model API
(preview), Foundry-integrasjon (enterprise-arch, ai-services-cost,
multi-model, cost-tracking)
- FOCUS-skjema + Cost Mgmt -> ADLS Gen2 -> Fabric -> Power BI pipeline
(cost-management, cost-allocation)
- FinOps hub AI-agent via Azure MCP / Copilot Studio (budget-forecasting)
- OTel trace-based sampling for logs (observability)
- Korreksjoner: semantic-cache score-threshold = AVSTAND (0.15, ikke 0.85
cosine-likhet); llm-emit-token-metric maks 5 custom dimensions;
Foundry RBAC-renames (Owner/Contributor = kun mgmt); Researcher/Analyst er
ikke agenter
- Alle 15 Last updated -> 2026-06-19
High-bucket (49 filer) UTSATT til egen sesjon (operatoer-valg).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
2026-06-19 06:22:48 +02:00
