open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 4 Activity

docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer)

Browse source 
Verifisert mot offisiell MS-doc (juni 2026): «Microsoft Foundry» er det
gjeldende produkt-/portalnavnet; «Foundry (classic)» = gamle «Azure AI Foundry»
(/azure/foundry/ vs /azure/foundry-classic/). Premiss bekreftet før sveip.

Multi-regel, IKKE naiv s/Azure AI Foundry/Microsoft Foundry/ — MS dropper
«Azure AI» (legger IKKE til «Microsoft») for to produktvarianter:
- «Azure AI Foundry Agent[ Service|s]» → «Foundry Agent Service/Agents» (MS-form)
- «Azure AI Foundry Models» → «Foundry Models» (i «Azure OpenAI in Foundry Models»)
- «Azure AI Foundry SDK» → «Microsoft Foundry SDK» (operatør-valg)
- «Azure AI Foundry portal/project» + generisk → «Microsoft Foundry»
- Pre-eksisterende «Microsoft Foundry Models» (4) normalisert → «Foundry Models»

Bevart: «Azure OpenAI», «Azure AI Inference SDK», «Azure AI Search»,
«Azure AI Services», kode-IDer. Historisk ref «(tidligere Azure AI Foundry)»
i model-catalog-2026.md beskyttet via lookbehind. URL /azure/ai-foundry/→
/azure/foundry/ kun i owasp-llm-top10 (KB-ref); docs/-filer deferred.

Scope: skills (inkl. 3 SKILL.md) + commands + agents + README + CLAUDE.
Ekskludert: docs/ (interne), playground/+tests/ fixtures (testdata),
CHANGELOG.md (historisk logg), STATE.md (gitignored).

3 SKILL.md endret (advisor/engineering/security) → judge-cache teknisk
invalidert for disse, men scorer uendret: advisor 91, eng/gov/infra/sec 96
(alle ≥90). validate 239/0. 0 «Azure AI Foundry» igjen (utenom bevart ref).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-06-23 21:00:27 +02:00
commit 03d596e4ec
233 changed files with 810 additions and 810 deletions
Download patch file Download diff file Expand all files Collapse all files

8
skills/ms-ai-governance/references/responsible-ai/fairness-testing-measurement.md
View file

@ -221,7 +221,7 @@ def fairness_scorer(inputs, outputs, context):
)
```
### Pattern 4: Azure AI Foundry — Hate and Unfairness Evaluator
### Pattern 4: Microsoft Foundry — Hate and Unfairness Evaluator
**Verified** (Azure AI Evaluation SDK, 2026-02): For Azure OpenAI og generative modeller.
@ -313,9 +313,9 @@ Er dette en high-stakes decision? (lån, jobb, helse)
5. **Generer scorecard** → eksporter PDF med fairness target values
6. **Deployment gate** → beslutning basert på fairness thresholds
### Azure AI Foundry
### Microsoft Foundry
**Verified** (Azure AI Foundry documentation, 2026-02):
**Verified** (Microsoft Foundry documentation, 2026-02):
| Capability | Beskrivelse | Status |
|------------|-------------|--------|
@ -396,7 +396,7 @@ Er dette en high-stakes decision? (lån, jobb, helse)
- Compute: ~2000-3000 NOK/år
- Storage (dashboard artifacts): ~100 NOK/år
### Azure AI Foundry — Content Safety Evaluators
### Microsoft Foundry — Content Safety Evaluators
| Evaluator | Pricing Model | Estimat |
|-----------|---------------|---------|