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
0eb30fa853
commit
6645e93205
104 changed files with 1986 additions and 520 deletions
|
|
@ -1,6 +1,6 @@
|
|||
# Multi-Agent Orchestration in Copilot
|
||||
|
||||
**Last updated:** 2026-02
|
||||
**Last updated:** 2026-04 | Verified: MCP 2026-04-10
|
||||
**Status:** Generally Available (GA)
|
||||
**Category:** Copilot Extensibility & Integration
|
||||
|
||||
|
|
@ -37,6 +37,11 @@ Når generative orchestration er aktivert, bruker agenten store språkmodeller t
|
|||
- Navn på agent/topic/tool
|
||||
- Input/output parametere og deres beskrivelser
|
||||
|
||||
**Avanserte kontrollmuligheter (generativ modus):**
|
||||
- **Avbryte plan**: Bruk **"End all topics"**-node i et topic for å kansellere gjenværende steg i orchestratorens plan
|
||||
- **Samtalehistorikk**: Agenter bruker nylig samtalehistorikk som kontekst. For å nullstille: bruk **"Clear variable values"**-node med alternativet "Conversation history for the current session"
|
||||
- **Topic-triggere**: `AI response generated` (agenten genererer svar) og `Plan complete` (alle planlagte steg utført) gir finkornet kontroll
|
||||
|
||||
### Agent-komponenter (Microsoft Agent Framework)
|
||||
|
||||
For pro-code utvikling tilbyr Agent Framework:
|
||||
|
|
@ -204,8 +209,20 @@ var result = await workflow.RunAsync("Write an article about AI safety");
|
|||
|
||||
- Agenter bygget i Copilot Studio kan publiseres som **declarative agents** i M365 Copilot
|
||||
- M365 Copilot bruker sin egen orchestrator, men agent kan ha egne instructions, knowledge og actions
|
||||
- Governance håndteres via **Microsoft 365 admin center** (enable/disable/assign/block agents)
|
||||
- Governance håndteres via **Microsoft 365 admin center** (enable/disable/assign/block agents) under **Agents**-seksjonen i Copilot Control System
|
||||
- Agent pinning: Microsoft-pinned, admin-pinned, user-pinned
|
||||
- **AI Admin**-rollen gir dedikert, lavprivilegert administratortilgang for agent-styring (anbefalt fremfor Global Admin)
|
||||
|
||||
**Agent-typer som kan administreres (Verified):**
|
||||
- **Publisert av org**: Predefinerte instruksjoner og actions — må gjennom admin approval
|
||||
- **Delt av bruker**: Opprettet via Copilot Studio eller Agent Builder
|
||||
- **Microsoft-agenter**: Innebygd i M365-tjenester (Researcher, Analyst etc.)
|
||||
- **Eksterne partner-agenter**: Fra ISV-er
|
||||
- **Frontier agents** (eksperimentelle):
|
||||
- **App Builder agent**: Kan bygge Power Apps via Copilot
|
||||
- **Workflows agent**: Lager flows i Copilot — lagres i default environment
|
||||
|
||||
**Microsoft Agent 365** er den nye kontrollplanen for alle AI-agenter (uavhengig av hvor de er bygd), tilgjengelig via M365 admin center.
|
||||
|
||||
**Nøkkel-policy:**
|
||||
- Agents arver M365 Copilots security, privacy og compliance
|
||||
|
|
@ -413,27 +430,27 @@ Triage: "Jeg ser du har spørsmål om barnetrygd.
|
|||
|
||||
1. **Multi-agent patterns:**
|
||||
https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/multi-agent-patterns
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
2. **Generative orchestration:**
|
||||
https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-generative-actions
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
3. **Agents for M365 Copilot:**
|
||||
https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/agents-overview
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
4. **Agent Framework Handoff:**
|
||||
https://learn.microsoft.com/en-us/agent-framework/user-guide/workflows/orchestrations/handoff
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
5. **Agent governance (M365 admin):**
|
||||
https://learn.microsoft.com/en-us/microsoft-365/admin/manage/manage-copilot-agents-integrated-apps
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
6. **Agent security & compliance:**
|
||||
https://learn.microsoft.com/en-us/copilot/microsoft-365/agent-essentials/agent-essentials-overview
|
||||
(Verified: 2026-02)
|
||||
(Verified: 2026-04)
|
||||
|
||||
### Konfidensnivå per seksjon
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue