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
This commit is contained in:
Kjell Tore Guttormsen 2026-06-19 06:22:48 +02:00
commit 41b390b38d
15 changed files with 69 additions and 30 deletions

View file

@ -1,6 +1,6 @@
# Azure AI Services - Pricing Models and Cost Optimization
**Last updated:** 2026-02
**Last updated:** 2026-06-19
**Status:** GA
**Category:** Azure AI Services (Foundry Tools)
@ -199,6 +199,7 @@ PTU er en kapasitetsbasert prismodell for Azure OpenAI, primært for produksjons
- **Rate limiting:** Forhindre overskridelser
- **Circuit breaker:** Automatisk failover til billigere endepunkt
- **Load balancing:** Distribuer trafikk mellom PTU og pay-as-you-go
- **Multi-provider + Foundry (MCP 2026-06):** AI gateway styrer nå også Anthropic Messages API (v2-tiers) og Google Vertex AI, tilbyr unified model API (preview), og kan integreres direkte i Microsoft Foundry (preview) for sentral token-/kostnadsgovernance på tvers av modeller, agenter og verktøy
**Verified** – Microsoft Learn: Generative AI Gateway Capabilities.