docs(architect): weekly KB update — 106 files refreshed (2026-04)
Updates across all 5 skills: ms-ai-advisor, ms-ai-engineering, ms-ai-governance, ms-ai-security, ms-ai-infrastructure. Key changes: - Language Services (Custom Text Classification, Text Analytics, QnA): retirement warning 2029-03-31, migration guides to Foundry/GPT-4o - Agentic Retrieval: 50M free reasoning tokens/month (Public Preview) - Computer Use: Claude Sonnet 4.5 (preview) + OpenAI CUA models - Agent Registry: Risks column (M365 E7), user-shared/org-published types - Declarative agents: schema v1.5 → v1.6, Store validation requirements - MLflow 3: 13 built-in LLM judges, production monitoring, Genie Code - AG-UI HITL: ApprovalRequiredAIFunction (C#) + @tool(approval_mode) (Python) - Entra ID Ignite 2025: Agent ID Admin/Developer RBAC roles, Conditional Access - Security Copilot: 400 SCU/month per 1000 M365 E5 licenses, auto-provisioned - Fast Transcription API: phrase lists, 14-language multi-lingual transcription - Azure Monitor Workbooks: Bicep support, RBAC specifics - Power Platform Copilot: data residency (Norway/Europe → EU DB, Bing → USA) - RAG security-rbac: 4-approach table (GA + 3 preview access control methods) - IaC MLOps: Well-Architected OE:05 principles, Bicep/Terraform patterns - Translator: image file batch translation Preview (JPEG/PNG/BMP/WebP) All 106 files: Last updated 2026-04 | Verified: MCP 2026-04 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
parent
dda86449fa
commit
ff6a50d14f
104 changed files with 1986 additions and 520 deletions
|
|
@ -412,13 +412,37 @@ def main(req: func.HttpRequest) -> func.HttpResponse:
|
|||
return func.HttpResponse("Alert received, no failover needed", status_code=200)
|
||||
```
|
||||
|
||||
|
||||
|
||||
## Application Insights for AI-agenter i BCDR-kontekst *(Verified MCP 2026-04)*
|
||||
|
||||
Azure Monitor Application Insights tilbyr nå dedikert støtte for AI-agenter via **Agent details view**, som er kritisk for failover-deteksjon i agent-baserte AI-systemer.
|
||||
|
||||
### Agent details view — BCDR-relevans
|
||||
|
||||
| Funksjon | BCDR-bruk |
|
||||
|----------|-----------|
|
||||
| **Unified agent view** | Monitorer agenter fra Foundry, Copilot Studio og tredjeparts i én visning |
|
||||
| **End-to-end transaction details** | Spor samtaler (prompts, systemInstructions, tool usage) ved incident-analyse |
|
||||
| **Live metrics** | Sanntids health under failover-scenarier |
|
||||
| **Availability tests** | Automatisk helsesjekk av agent-endepunkter |
|
||||
|
||||
### Instrumenteringsveiledning per agent-plattform
|
||||
|
||||
- **Azure AI Foundry-agenter:** Koble Application Insights til Foundry-prosjektet for automatisk tracing
|
||||
- **Copilot Studio-agenter:** Konfigurer built-in telemetri-eksport til App Insights
|
||||
- **Microsoft Agent Framework (self-hosted):** Bruk Azure Monitor OpenTelemetry Distro
|
||||
- **LangChain/LangGraph og OpenAI Agents SDK:** Bruk Azure AI OpenTelemetry Tracer
|
||||
|
||||
**Anbefaling:** Gi hver agent et unikt navn for å skille dem i Agent details view. Bruk samme App Insights-ressurs for agenter som er del av et større system.
|
||||
|
||||
## Referanser
|
||||
|
||||
- [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai) — OpenAI monitoring og alerting
|
||||
- [Monitor Azure AI Search](https://learn.microsoft.com/en-us/azure/search/monitor-azure-cognitive-search) — AI Search monitoring
|
||||
- [Azure Monitor alerts overview](https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview) — Alert-rammeverk
|
||||
- [Azure Monitor alerts overview](https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview) — Alert-rammeverk *(Verified MCP 2026-04)* — Stateful vs. stateless alerts, Simple Log Search Alerts (preview) for per-row evaluering, Query-based metric alerts for Prometheus/OTel (public preview). Alert processing rules for suppression ved planlagt vedlikehold. Opptil 5 action groups per alert rule.
|
||||
- [Health modeling and observability of mission-critical workloads](https://learn.microsoft.com/en-us/azure/well-architected/mission-critical/mission-critical-health-modeling) — Health modeling
|
||||
- [Application Insights overview](https://learn.microsoft.com/en-us/azure/azure-monitor/app/app-insights-overview) — APM for applikasjoner
|
||||
- [Application Insights overview](https://learn.microsoft.com/en-us/azure/azure-monitor/app/app-insights-overview) — APM for applikasjoner *(Verified MCP 2026-04)* — Nå OpenTelemetry-basert (OTel) som primær instrumentering. Nye features: **Agent details view** for AI-agenter fra Foundry, Copilot Studio og tredjeparts agenter. Støtter: Azure AI Foundry (via Foundry SDK tracing), Copilot Studio (built-in telemetri → App Insights), Microsoft Agent Framework (self-hosted), LangChain/LangGraph og OpenAI Agents SDK. Batch og continuous evaluations for produksjonstraffic. Live Metrics for sanntids observabilitet under failover-scenarier.
|
||||
- [Azure Service Health](https://learn.microsoft.com/en-us/azure/service-health/overview) — Azure-tjenestestatus
|
||||
|
||||
## For Cosmo
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue