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

docs(ms-ai-architect): KB-refresh HIGH 11/11 — agent-autonomy: Task Adherence (preview) lagt til risk-kategorier

Browse source
This commit is contained in:
Kjell Tore Guttormsen 2026-06-24 10:44:37 +02:00
commit 477c808744
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
skills/ms-ai-engineering/references/agent-orchestration/agent-autonomy-and-control-governance.md
View file

@ -1,6 +1,6 @@
# Agent Autonomy and Control - Governance Framework
**Last updated:** 2026-05
**Last updated:** 2026-06-24 | Verified: MCP 2026-06-24
**Status:** GA
**Category:** Agent Orchestration & Automation
@ -47,7 +47,7 @@ Guardrails opererer ved fire intervention points i agent execution lifecycle:
- User prompt attacks, Indirect attacks
- Protected material (code + text)
- Personally identifiable information (PII)
- Groundedness, Spotlighting (preview)
- Groundedness, Spotlighting (preview), Task Adherence (preview)
**Actions:**
- `Annotate` — Logg risikodeteksjon uten å blokkere (kun modeller)