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

fix(ms-ai-architect): Sesjon 7 steg 1+2 - refTall-konsistens + døde ref-paths

Browse source 
Lukker målte eval-FAIL i optimaliseringsfasen (krav 4):

Steg 1 (refTall): engineering agent-orchestration 20→24 (faktisk på disk)
+ total 149→153; governance npsg 29→30; fjerner inkonsistent 24/20-dobbel-
sitering. Verifisert: eval refCountConsistency PASS for alle 5.

Steg 2 (døde ref-paths i governance §4 monitoring-bullets — bare-filnavn,
derfor ufanget av kb-integrity): azure-monitor-ai-services-setup →
azure-monitor-setup-ai-workloads; drift-detection-automated-retraining →
model-performance-drift-detection. Begge fant ekte filer på disk (STATE
flagget kun den ene; den andre er et verifiseringsfunn). Grep: ingen døde igjen.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-19 23:18:25 +02:00
commit 3c097f5fb4
2 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

6
skills/ms-ai-engineering/SKILL.md
View file

@ -111,19 +111,19 @@ For detailed guidance, see `references/api-management/` (19 files).
### Egne referanser
Denne skillen har 149 filer fordelt på 7 domener. Bruk `Read`-verktøyet for å hente spesifikke filer.
Denne skillen har 153 filer fordelt på 7 domener. Bruk `Read`-verktøyet for å hente spesifikke filer.
| Domene | Mappe | Filer | Dekning |
|--------|-------|-------|---------|
| RAG-arkitektur | `references/rag-architecture/` | 28 | Naive/advanced/modular/agentic RAG, Azure AI Search, embeddings, chunking, evaluering |
| Agent-orkestrering | `references/agent-orchestration/` | 20 | Multi-agent patterns, Semantic Kernel, tool use, routing, governance, compliance, Foundry Agent Service GA, A2A, CUA, Foundry Workflows |
| Agent-orkestrering | `references/agent-orchestration/` | 24 | Multi-agent patterns, Semantic Kernel, tool use, routing, governance, compliance, Foundry Agent Service GA, A2A, CUA, Foundry Workflows |
| Azure AI Services | `references/azure-ai-services/` | 20 | Vision, Speech, Language, Document Intelligence, Translator, Content Safety |
| Dataingeniør | `references/data-engineering/` | 22 | Fabric Lakehouse, OneLake, Data Factory, data quality, Purview, Delta Lake |
| MLOps/GenAIOps | `references/mlops-genaiops/` | 22 | CI/CD, model registry, evaluering, drift detection, IaC, GenAIOps pipelines |
| Multimodal AI | `references/multi-modal/` | 18 | GPT-4o vision, Video Indexer, multimodal RAG, speech pipelines, OCR |
| API Management | `references/api-management/` | 19 | APIM AI gateway, rate limiting, circuit breaker, semantic caching, security |
**Totalt: 149 filer**
**Totalt: 153 filer**
### Kryss-referanser til andre skills

6
skills/ms-ai-governance/SKILL.md
View file

@ -187,8 +187,8 @@ Implement drift detection (data drift, concept drift, feature drift, prediction
> **Key references** in `references/monitoring-observability/`:
> - `application-insights-llm-monitoring.md` — Application Insights for LLM
> - `azure-monitor-ai-services-setup.md` — Azure Monitor setup
> - `drift-detection-automated-retraining.md` — Drift detection
> - `azure-monitor-setup-ai-workloads.md` — Azure Monitor setup
> - `model-performance-drift-detection.md` — Drift detection
---
@ -198,7 +198,7 @@ Implement drift detection (data drift, concept drift, feature drift, prediction
| Directory | Files | Coverage |
|-----------|-------|----------|
| `references/norwegian-public-sector-governance/` | 29 | Utredningsinstruksen, Forvaltningsloven, Digdir principles, DPIA methodology, ROS analysis (incl. threat library, scoring rubrics, sector checklists), NSM, EIF, procurement, benefit realization, accessibility, copyright, budgeting |
| `references/norwegian-public-sector-governance/` | 30 | Utredningsinstruksen, Forvaltningsloven, Digdir principles, DPIA methodology, ROS analysis (incl. threat library, scoring rubrics, sector checklists), NSM, EIF, procurement, benefit realization, accessibility, copyright, budgeting |
| `references/responsible-ai/` | 30 | AI Act (compliance guide, Annex III, classification, provider/deployer obligations, FRIA template, conformity assessment, transparency notices, Microsoft tools mapping), GDPR, bias, explainability, HITL, governance, red teaming, content safety, data quality, drift detection, ethics, accountability |
| `references/monitoring-observability/` | 18 | Azure Monitor, Application Insights, token tracking, KQL, dashboards, alerting, distributed tracing, drift detection, compliance monitoring, cost attribution, data residency, anomaly detection, Copilot observability, streaming, RAG quality, audit logging, SLA |