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

docs(ms-ai-architect): KB-refresh MEDIUM 8/33 — regulatory: Guardrails-rebranding (tidl. content filters) + Models sold by Azure-kildetittel

Browse source
This commit is contained in:
Kjell Tore Guttormsen 2026-06-24 11:38:23 +02:00
commit b290ed3ff4
1 changed files with 7 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

14
skills/ms-ai-advisor/references/prompt-engineering/regulatory-and-compliance-prompting.md
View file

@ -1,6 +1,6 @@
# Regulatory and Compliance-Aware Prompting
**Last updated:** 2026-02
**Last updated:** 2026-06-24
**Status:** GA
**Category:** Prompt Engineering & LLM Optimization
@ -108,7 +108,7 @@ Du er en helseinformasjons-assistent. HIPAA-regler gjelder:
**Azure AI Content Safety Integration:**
Microsoft tilbyr innebygde content filters som evaluerer prompts og completions i sanntid:
Microsoft tilbyr innebygde **Guardrails (tidligere «content filters»)** som evaluerer prompts og completions i sanntid. Default-guardrail for modeller er `Microsoft.DefaultV2`. Kategoriene under er fortsatt gyldige:
| Kategori | Beskrivelse | Typisk Threshold (Compliance) |
|----------|-------------|-------------------------------|
@ -859,17 +859,17 @@ Før produksjonsdeploy, gjennomfør en 2-dagers compliance sprint:
### Microsoft Official Documentation
1. **Data, privacy, and security for Azure OpenAI** (februar 2026)
1. **Data, privacy, and security for Models sold by Azure in Microsoft Foundry** (juni 2026)
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy
→ Autoritativ kilde for data processing, abuse monitoring, residency
→ Autoritativ kilde for data processing, abuse monitoring, residency. (Sidetittel endret fra «Azure OpenAI» til «Models sold by Azure».)
2. **Govern AI apps and data for regulatory compliance** (februar 2026)
https://learn.microsoft.com/en-us/security/security-for-ai/govern
→ Compliance Manager, Purview integration, EU AI Act readiness
3. **Azure OpenAI Content Filtering** (februar 2026)
https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/content-filter
→ Content Safety API, thresholds, custom policies
3. **Guardrails and controls (tidligere «Content Filtering»)** (juni 2026)
https://learn.microsoft.com/en-us/azure/foundry/guardrails/guardrails-overview
→ Guardrails/controls, intervensjonspunkter, terskler, `Microsoft.DefaultV2`, custom policies
4. **Azure Data Residency** (februar 2026)
https://azure.microsoft.com/explore/global-infrastructure/data-residency