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

fix(ms-ai-architect): Foundry URL-navnerom-migrering (ai-foundry → foundry/foundry-classic, 141 filer)

Browse source 
Task #5 del 1/3 (URL-migrering). Verifiseringen motbeviste STATE.md-premisset om ren prefix-swap: rebrand er per-URL, ikke mekanisk. En blind sed ai-foundry→foundry ville lagd 56 nye 404-er (classic-stiene finnes ikke under nytt foundry/-prefiks — bekreftet empirisk).

Metode: resolverte alle 237 unike KB-URLer mot live redirects (curl -L), bygde full-URL→full-URL-mapping fra faktisk url_effective. Bevarer locale-form, query (?view=) og #fragment per lenke.

- 231 navnerom-erstatninger over 141 filer (408 forekomster):
  - 161 → azure/foundry/ (98 ren prefix-swap + 10 sti-reorg + reorg-tilfeller)
  - 69 → azure/foundry-classic/ (eldre hub-spor: assistants, hub-DR, on-your-data; faktisk redirect-mål per operatorvalg)
  - 1 → azure/foundry-local/

- 2 døde lenker (404) fikset til verifiserte mål:
  - agent-service → azure/foundry/agents/overview
  - concepts/evaluation-evaluators/ → azure/foundry/how-to/evaluate-generative-ai-app

- 5 path-/display-referanser (uten https://, i backticks/lenketekst) rettet manuelt.

- 6 slug-baserte ai-foundry-treff urørt (scope-grense): managed-grafana-dashboard, security-baseline, power-platform prompt-builder, architecture baseline-chat (sistnevnte slug-rebrand i annet navnerom — mulig fremtidig funn).

- Parkert til task #5 del 2/3: Norway East GPT-5-datasuverenitet-fiks + modellkatalog-utvidelse (5.3/5.4/5.5, gpt-oss, sora-2).

Verifisert: 0 gjenværende azure/ai-foundry/-navnerom i skills/. validate-plugin.sh 219 PASS. test-kb-integrity.sh 117/117 passed.

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 2026-06-18 13:37:06 +02:00
commit dd1036ab8a
141 changed files with 399 additions and 399 deletions
Download patch file Download diff file Expand all files Collapse all files

4
skills/ms-ai-governance/references/monitoring-observability/compliance-monitoring-ai-governance.md
View file

@ -478,13 +478,13 @@ AppMetrics
**Azure Policy & monitoring:**
- [Azure Policy Regulatory Compliance controls for Azure AI Search](https://learn.microsoft.com/en-us/azure/search/security-controls-policy) — Verified 2026-02
- [Control AI model deployment with built-in policies in Microsoft Foundry portal](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/built-in-policy-model-deployment) — Verified 2026-02
- [Control AI model deployment with built-in policies in Microsoft Foundry portal](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/built-in-policy-model-deployment) — Verified 2026-02
- [AI gateway in Azure API Management (Observability and governance)](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities#observability-and-governance) — Verified 2026-02
**Security & observability:**
- [Assess your organization's AI risk with Microsoft Security Dashboard for AI (Preview)](https://learn.microsoft.com/en-us/security/security-for-ai/security-dashboard-for-ai) — Verified 2026-02
- [Governance and security for AI agents across the organization](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/ai-agents/governance-security-across-organization) — Verified 2026-02
- [Monitor Azure OpenAI (Dashboards)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai) — Verified 2026-02
- [Monitor Azure OpenAI (Dashboards)](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai) — Verified 2026-02
### Konfidensnivå per seksjon

4
skills/ms-ai-governance/references/monitoring-observability/cost-monitoring-cost-attribution.md
View file

@ -439,7 +439,7 @@ if ($metrics.Data.Total -eq 0) {
### Kilder (Microsoft Learn)
1. **Plan to manage costs for Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs
https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
*Konfidensgrad: Verified* – Komplett guide for cost management (budgets, alerts, export)
2. **Azure OpenAI in Foundry Models gateway monitoring** *(Verified MCP 2026-04)*
@ -455,7 +455,7 @@ if ($metrics.Data.Total -eq 0) {
*Konfidensgrad: Verified* – Best practices for TPM/RPM monitoring, commitment billing
5. **Plan and manage costs for Azure AI Foundry**
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/manage-costs
https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
*Konfidensgrad: Verified* – Marketplace models, fine-tuning costs, HTTP error billing
6. **Azure Cost Management API (Python SDK)**

2
skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md
View file

@ -483,7 +483,7 @@ Når kunden spør om dashboards for AI operations:
### Microsoft Learn
- [Azure Workbooks overview](https://learn.microsoft.com/en-us/azure/azure-monitor/visualize/workbooks-overview)
- [Create an Azure AI Foundry dashboard](https://learn.microsoft.com/en-us/azure/managed-grafana/azure-ai-foundry-dashboard)
- [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai)
- [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai)
- [Workbooks programmatic management](https://learn.microsoft.com/en-us/azure/azure-monitor/visualize/workbooks-automate) *(Verified MCP 2026-04)* — ARM/Bicep deployment, RBAC (Monitoring Contributor for redigering, Monitoring Reader for visning), `microsoft.insights/workbooks/write` for custom roles
- [Power BI + Azure Monitor](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/log-powerbi)

8
skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md
View file

@ -587,19 +587,19 @@ az role assignment create \
### Microsoft Learn (Verified via MCP)
1. **Monitor Azure OpenAI:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai
*Confidence: Verified* — Komplett guide til diagnostics, metrics, alerts, og KQL-queries
2. **Manage Azure OpenAI quota:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/quota
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota
*Confidence: Verified* — TPM/RPM-allokering, quota requests, 429-feilhåndtering
3. **Azure OpenAI quotas and limits:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits
https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
*Confidence: Verified* — Rate limits per modell, Usage tiers, regional constraints
4. **Dynamic quota (Preview):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/dynamic-quota
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota
*Confidence: Verified* — Opportunistic burst-kapasitet for Standard deployments
5. **Supported metrics for Microsoft.CognitiveServices/accounts:**

4
skills/ms-ai-governance/references/monitoring-observability/log-analytics-kql-ai-queries.md
View file

@ -723,7 +723,7 @@ AzureDiagnostics
- **KQL Quick Reference:** [learn.microsoft.com/kusto/query/kql-quick-reference](https://learn.microsoft.com/en-us/kusto/query/kql-quick-reference)
- **Azure Monitor KQL Samples:** [learn.microsoft.com/azure/azure-monitor/logs/queries](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/queries)
- **Azure OpenAI Monitoring:** [learn.microsoft.com/azure/ai-foundry/openai/how-to/monitor-openai](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai)
- **Azure OpenAI Monitoring:** [learn.microsoft.com/azure/foundry-classic/openai/how-to/monitor-openai](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai)
- **Optimize Log Queries:** [learn.microsoft.com/azure/azure-monitor/logs/query-optimization](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/query-optimization)
## Nøkkelinnsikter
@ -743,7 +743,7 @@ AzureDiagnostics
## Referanser
- Microsoft Learn: [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai)
- Microsoft Learn: [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai)
- Microsoft Learn: [Get started with log queries in Azure Monitor](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/get-started-queries)
- Microsoft Learn: [Optimize log queries in Azure Monitor](https://learn.microsoft.com/en-us/azure/azure-monitor/logs/query-optimization) *(Verified MCP 2026-04)*
- Microsoft Learn: [Configure diagnostic logging for Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-monitor-enable-logging)

4
skills/ms-ai-governance/references/monitoring-observability/model-performance-drift-detection.md
View file

@ -377,8 +377,8 @@ Model monitoring er inkludert i Azure Machine Learning workspace, men du betaler
- [Azure Machine Learning model monitoring (concept)](https://learn.microsoft.com/en-us/azure/machine-learning/concept-model-monitoring?view=azureml-api-2) — **Verified** (fetched 2026-02)
- [Monitor performance of models deployed to production](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-monitor-model-performance?view=azureml-api-2) — **Verified** (fetched 2026-02)
- [Data drift monitoring (legacy, retiring)](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-monitor-datasets?view=azureml-api-1) — **Verified** (fetched 2026-02, kontext: migrering til Model Monitor)
- [Evaluate generative AI models (Azure AI Foundry)](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/evaluate-generative-ai-app?view=foundry-classic) — **Verified** (fetched 2026-02)
- [Observability in generative AI (Azure AI Foundry)](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability?view=foundry-classic) — **Verified** (fetched 2026-02)
- [Evaluate generative AI models (Azure AI Foundry)](https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app?view=foundry-classic) — **Verified** (fetched 2026-02)
- [Observability in generative AI (Azure AI Foundry)](https://learn.microsoft.com/en-us/azure/foundry/concepts/observability?view=foundry-classic) — **Verified** (fetched 2026-02)
- [Test and evaluate AI workloads on Azure](https://learn.microsoft.com/en-us/azure/well-architected/ai/test) — **Verified** (fetched 2026-02)
### Baseline (Model knowledge)

2
skills/ms-ai-governance/references/monitoring-observability/real-time-streaming-monitoring.md
View file

@ -525,7 +525,7 @@ Real-Time Dashboard er IKKE erstatning for data warehouse. Bruk for operational
**Confidence:** Verified (Feb 2026) - Real-time architecture patterns
7. **Observability in generative AI**
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability
https://learn.microsoft.com/en-us/azure/foundry/concepts/observability
**Confidence:** Verified (Feb 2026) - AI Foundry monitoring integration
8. **Implement advanced monitoring for Azure OpenAI in Foundry Models through a gateway**

12
skills/ms-ai-governance/references/monitoring-observability/response-quality-metrics-rag.md
View file

@ -591,14 +591,14 @@ PTU equivalent: ~300 PTUs @ $6/PTU = $1800/måned
### Microsoft Learn (Verified via MCP)
1. [Observability in generative AI - What are evaluators?](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability#what-are-evaluators) — RAG evaluators (Retrieval, Groundedness, Relevance, Response Completeness)
2. [Retrieval-Augmented Generation (RAG) evaluators](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/rag-evaluators) — Detaljert dokumentasjon for alle RAG-evaluatorer, input/output formats
1. [Observability in generative AI - What are evaluators?](https://learn.microsoft.com/en-us/azure/foundry/concepts/observability#what-are-evaluators) — RAG evaluators (Retrieval, Groundedness, Relevance, Response Completeness)
2. [Retrieval-Augmented Generation (RAG) evaluators](https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/rag-evaluators) — Detaljert dokumentasjon for alle RAG-evaluatorer, input/output formats
3. [Large language model end-to-end evaluation](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-llm-evaluation-phase) — Groundedness, completeness, utilization, relevance, correctness metrics
4. [Evaluate generative AI models and applications](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/evaluate-generative-ai-app) — Foundry portal evaluation workflow, testing criteria configuration
5. [Submit a batch run and evaluate a flow](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/flow-bulk-test-evaluation) — Built-in evaluation methods (QnA Groundedness, Relevance, Coherence)
4. [Evaluate generative AI models and applications](https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app) — Foundry portal evaluation workflow, testing criteria configuration
5. [Submit a batch run and evaluate a flow](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/flow-bulk-test-evaluation) — Built-in evaluation methods (QnA Groundedness, Relevance, Coherence)
6. [Evaluation of RAG performance basics](https://learn.microsoft.com/en-us/fabric/data-science/tutorial-evaluate-rag-performance) — AI-assisted metrics (groundedness, relevance, similarity), top-N retrieval rate
7. [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai) — Azure Monitor integration, KQL queries, diagnostic settings
8. [Use Risks & Safety monitoring](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/risks-safety-monitor) — Content filtering metrics, severity distribution
7. [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai) — Azure Monitor integration, KQL queries, diagnostic settings
8. [Use Risks & Safety monitoring](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor) — Content filtering metrics, severity distribution
9. [Azure AI Evaluation SDK - Python samples](https://github.com/Azure-Samples/azureai-samples/blob/main/scenarios/evaluate/) — Code examples for groundedness, relevance evaluators
### Code samples (Verified via MCP)

4
skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md
View file

@ -385,8 +385,8 @@ Ingen ekstra lisenser kreves for audit logging — funksjonen er inkludert i Azu
| Kilde | URL | Konfidensnivå |
|-------|-----|---------------|
| **Enable diagnostic logging for Azure AI services** | https://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging | ✅ Verified |
| **Monitor Azure OpenAI** | https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai | ✅ Verified |
| **Azure security baseline for Azure OpenAI** | https://learn.microsoft.com/en-us/security/benchmark/azure/baselines/azure-openai-security-baseline | ✅ Verified — **OBS:** Basert på MCSB v1.0 (kan inneholde utdatert veiledning). Produktet refereres nå som "Foundry Tools" i baseline-dokumentet. Siste veiledning: [Azure OpenAI docs](https://learn.microsoft.com/en-us/azure/ai-foundry/). *(Verified MCP 2026-04)* |
| **Monitor Azure OpenAI** | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai | ✅ Verified |
| **Azure security baseline for Azure OpenAI** | https://learn.microsoft.com/en-us/security/benchmark/azure/baselines/azure-openai-security-baseline | ✅ Verified — **OBS:** Basert på MCSB v1.0 (kan inneholde utdatert veiledning). Produktet refereres nå som "Foundry Tools" i baseline-dokumentet. Siste veiledning: [Azure OpenAI docs](https://learn.microsoft.com/en-us/azure/foundry/). *(Verified MCP 2026-04)* |
| **Azure security baseline for Microsoft Foundry** | https://learn.microsoft.com/en-us/security/benchmark/azure/baselines/azure-ai-foundry-security-baseline | ✅ Verified — **OBS:** Tjenesten er omdøpt til "Microsoft Foundry" i baseline-dokumentet. Basert på MCSB v1.0. Viktige avvik: Customer Lockbox **ikke støttet** for Foundry, lokal autentisering til data plane **ikke støttet** (positivt for sikkerhet), DLP/sensitive data discovery **ikke støttet** nativt. *(Verified MCP 2026-04)* |
| **Microsoft cloud security benchmark: Logging and threat detection** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-logging-threat-detection | ✅ Verified |
| **Artificial Intelligence Security (AI-6: Establish monitoring and detection)** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security | ✅ Verified |

6
skills/ms-ai-governance/references/monitoring-observability/sla-monitoring-ai-services.md
View file

@ -351,11 +351,11 @@ Metric Alert
### Microsoft Learn (Verified via MCP)
1. **Monitor Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai
*Confidence: Verified* — Detaljert guide til Azure Monitor-integrasjon for OpenAI.
2. **Azure OpenAI monitoring data reference**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/monitor-openai-reference
https://learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference
*Confidence: Verified* — Fullstendig liste over metrics (inkl. `ModelAvailabilityRate`).
3. **Monitoring and diagnostics guidance**
@ -363,7 +363,7 @@ Metric Alert
*Confidence: Verified* — SLA monitoring best practices (generell Azure-arkitektur). Dekker: tilgjengelighetssporing, ytelsesovervåkning, SLA-etterlevelse, sikkerhet/personvern, regulatorisk audit, trend-deteksjon. Brukes i AI-kontekst for å sikre end-to-end synlighet i distribuerte AI-systemer. *(Verified MCP 2026-04)*
4. **Azure OpenAI FAQ - SLA**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/faq#what-are-the-slas-service-level-agreements-in-azure-openai
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq#what-are-the-slas-service-level-agreements-in-azure-openai
*Confidence: Verified* — Bekreftelse av 99.9% Availability SLA + Latency SLA for PTU.
5. **Supported metrics for Microsoft.CognitiveServices/accounts**

8
skills/ms-ai-governance/references/monitoring-observability/token-usage-tracking-attribution.md
View file

@ -568,11 +568,11 @@ Owner: <email>
## Kilder (Microsoft Learn)
1. [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai) — Official monitoring guide
1. [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai) — Official monitoring guide
2. [Implement advanced monitoring for Azure OpenAI in Foundry Models through a gateway](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-monitoring) *(Verified MCP 2026-04)* — Gateway patterns for usage tracking. Ny brukscase dokumentert: audit av model inputs/outputs for threat detection og data exfiltration detection. Merk: gateway monitoring kan bli single point of failure — vurder redundans.
3. [Plan to manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs) — Cost management strategies
4. [Token usage estimation for Azure OpenAI On Your Data](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data) — RAG-specific token calculations
5. [Understanding costs associated with PTU](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) — PTU billing model
3. [Plan to manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs) — Cost management strategies
4. [Token usage estimation for Azure OpenAI On Your Data](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data) — RAG-specific token calculations
5. [Understanding costs associated with PTU](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing) — PTU billing model
6. [Application design for AI workloads](https://learn.microsoft.com/en-us/azure/well-architected/ai/application-design#consider-nonfunctional-requirements) — Cost and chargeback scenarios
7. [Architecture strategies for cost data](https://learn.microsoft.com/en-us/azure/well-architected/cost-optimization/collect-review-cost-data#generate-cost-reports) — Chargeback vs. showback

12
skills/ms-ai-governance/references/norwegian-public-sector-governance/copyright-ai-training-data-norway.md
View file

@ -142,7 +142,7 @@ Kunden må ha implementert alle mitigations (tiltak) som kreves i Azure OpenAI-d
For å opprettholde CCC-dekning må kunder implementere følgende universelle mitigations:
**1. Metaprompt (effektiv fra 1. desember 2023):**
Kundens løsning må inkludere en metaprompt som instruerer modellen til å forhindre opphavsrettsbrudd i output. Eksempel på anbefalt metaprompt finnes i Microsoft Learn: "To Avoid Copyright Infringements" i [System message framework and template recommendations for Large Language Models (LLMs)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/system-message).
Kundens løsning må inkludere en metaprompt som instruerer modellen til å forhindre opphavsrettsbrudd i output. Eksempel på anbefalt metaprompt finnes i Microsoft Learn: "To Avoid Copyright Infringements" i [System message framework and template recommendations for Large Language Models (LLMs)](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message).
**2. Testing and Evaluation Report (effektiv fra 1. desember 2023):**
Kundens løsning må ha vært gjenstand for evalueringer (f.eks. guided red teaming, systematisk måling, eller annen ekvivalent tilnærming) ved hjelp av tester designet for å oppdage output av tredjepartsinnhold. Betydelig løpende reproduksjon av tredjepartsinnhold oppdaget gjennom evaluering må adresseres. Rapporten over resultater og tiltak må oppbevares av kunden og gjøres tilgjengelig for Microsoft i tilfelle krav.
@ -243,11 +243,11 @@ Når du veileder norsk offentlig sektor om AI og opphavsrett, vurder disse spør
- [Commission launches consultation on protocols for reserving rights from text and data mining under the AI Act and the GPAI Code of Practice](https://digital-strategy.ec.europa.eu/en/consultations/commission-launches-consultation-protocols-reserving-rights-text-and-data-mining-under-ai-act-and)
### Microsoft Learn-kilder
- [Customer Copyright Commitment Required Mitigations | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/customer-copyright-commitment?view=foundry-classic)
- [Data, privacy, and security for Azure Direct Models in Microsoft Foundry | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy?view=foundry-classic)
- [Transparency note for Azure OpenAI | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note?view=foundry-classic)
- [Azure OpenAI frequently asked questions | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/faq?view=foundry-classic)
- [System message framework and template recommendations for LLMs | Microsoft Learn](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/system-message)
- [Customer Copyright Commitment Required Mitigations | Microsoft Learn](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/customer-copyright-commitment?view=foundry-classic)
- [Data, privacy, and security for Azure Direct Models in Microsoft Foundry | Microsoft Learn](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy?view=foundry-classic)
- [Transparency note for Azure OpenAI | Microsoft Learn](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note?view=foundry-classic)
- [Azure OpenAI frequently asked questions | Microsoft Learn](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq?view=foundry-classic)
- [System message framework and template recommendations for LLMs | Microsoft Learn](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message)
---

2
skills/ms-ai-governance/references/responsible-ai/ai-impact-assessment-framework.md
View file

@ -616,7 +616,7 @@ Purview SDK-integrasjon gir:
- Status: Azure ML GA feature
6. **Azure AI Foundry Evaluation**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/evaluation-github-action
- URL: https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action
- Status: Azure AI Foundry GA
7. **Microsoft Purview AI Risk Management**

2
skills/ms-ai-governance/references/responsible-ai/ai-risk-taxonomy-classification.md
View file

@ -420,7 +420,7 @@ Anbefal denne kombinasjonen:
- Innhold: Cross-product risk monitoring, AI inventory
5. **Default Guidelines & controls policies (Azure AI Foundry)**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/default-safety-policies
- URL: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies
- Hentet: 2026-02-04
- Innhold: Content filtering categories, severity levels, default thresholds

2
skills/ms-ai-governance/references/responsible-ai/algorithmic-accountability-auditability.md
View file

@ -516,7 +516,7 @@ registered_model = ml_client.models.create_or_update(model)
(Assign unique identities, maintain agent inventory, centralize logging, track and allocate costs)
5. **Trace and observe AI agents in Microsoft Foundry**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/trace-agents-sdk?view=foundry-classic
https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-agents-sdk?view=foundry-classic
(OpenTelemetry tracing, Application Insights integration, Azure Monitor exporter)
6. **Microsoft Purview data security and compliance protections for generative AI apps**

2
skills/ms-ai-governance/references/responsible-ai/bias-detection-mitigation-strategies.md
View file

@ -937,7 +937,7 @@ Risikokategori (EU AI Act)?
Verifisert: 2026-02-03 | Status: GA | Confidence: ✅ High
6. **Content filter severity levels**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-severity-levels
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-severity-levels
Verifisert: 2026-02-03 | Status: GA | Confidence: ✅ High
7. **Monitor fairness and bias (Databricks)**

12
skills/ms-ai-governance/references/responsible-ai/content-safety-implementation.md
View file

@ -280,7 +280,7 @@ Azure AI Content Safety har PII-detection for completions:
| **Record-keeping** | Retain logs i 6+ år (Azure Log Analytics long-term retention) |
**Transparency Note:**
Microsoft publiserer [Transparency Note for Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/content-safety/transparency-note) som dekker:
Microsoft publiserer [Transparency Note for Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/content-safety/transparency-note) som dekker:
- System capabilities and limitations
- Training data og known biases
- Best practices for deployment
@ -464,22 +464,22 @@ Scenario: 1 million samtaler/måned, gjennomsnitt 2 meldinger per samtale = 2M t
1. [What is Azure AI Content Safety?](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview)
*Confidence: High* — Oversikt over features, pricing tiers, region availability, service limits
2. [Content filtering overview (Azure OpenAI)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter)
2. [Content filtering overview (Azure OpenAI)](https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/content-filter)
*Confidence: High* — Filter categories, severity levels, scenario details for API response behavior
3. [Harm categories in Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/harm-categories)
*Confidence: High* — Detaljert beskrivelse av severity levels 0-7 per kategori (hate, sexual, violence, self-harm)
4. [Data, privacy, and security for Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/content-safety/data-privacy)
4. [Data, privacy, and security for Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/content-safety/data-privacy)
*Confidence: High* — Data residency, encryption at rest, customer controls, GDPR compliance statements
5. [Custom categories (preview)](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/custom-categories)
*Confidence: Medium* — Preview feature, API-detaljer kan endre seg før GA
6. [Transparency note: Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/content-safety/transparency-note)
6. [Transparency note: Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/content-safety/transparency-note)
*Confidence: High* — System capabilities, intended uses, limitations, best practices
7. [Default Guidelines & controls policies (Azure OpenAI)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/default-safety-policies)
7. [Default Guidelines & controls policies (Azure OpenAI)](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies)
*Confidence: High* — Default severity thresholds for text/image models, table of blocked categories
8. [Azure AI Content Safety Quickstart (C# code samples)](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-text?pivots=programming-language-csharp)
@ -488,7 +488,7 @@ Scenario: 1 million samtaler/måned, gjennomsnitt 2 meldinger per samtale = 2M t
9. [Mitigate false results in Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance)
*Confidence: High* — Best practices for severity tuning, custom categories, blocklists
10. [Content Safety in the Microsoft Foundry portal](https://learn.microsoft.com/en-us/azure/ai-foundry/ai-services/content-safety-overview)
10. [Content Safety in the Microsoft Foundry portal](https://learn.microsoft.com/en-us/azure/foundry-classic/ai-services/content-safety-overview)
*Confidence: High* — Beskrivelse av Content Safety Studio features, Try it out workflow
**Baseline (modellkunnskap, ikke verifisert mot ferske kilder):**

10
skills/ms-ai-governance/references/responsible-ai/continuous-improvement-feedback-loops.md
View file

@ -48,7 +48,7 @@ Microsoft implementerer feedback loops gjennom hele AI-livssyklusen – fra utvi
- Error logs og exception traces
- User feedback (thumbs up/down, ratings)
**Confidence:** Verified – [MLflow Tracing](https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/tracing/), [Azure Monitor](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability)
**Confidence:** Verified – [MLflow Tracing](https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/tracing/), [Azure Monitor](https://learn.microsoft.com/en-us/azure/foundry/concepts/observability)
### 2. Automated Quality Monitoring
@ -69,7 +69,7 @@ Microsoft bruker automated scorers (LLM judges) for kontinuerlig kvalitetsvurder
- Automated alerts ved threshold violations
- Integration med Azure AI Foundry evaluation tools
**Confidence:** Verified – [Generation Quality Monitoring](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/monitor-quality-safety?view=foundry-classic)
**Confidence:** Verified – [Generation Quality Monitoring](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-quality-safety?view=foundry-classic)
### 3. Human Feedback Integration
@ -258,7 +258,7 @@ model_monitor = MonitorSchedule(
)
```
**Confidence:** Verified – [Azure AI Foundry Monitoring](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/monitor-quality-safety?view=foundry-classic)
**Confidence:** Verified – [Azure AI Foundry Monitoring](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-quality-safety?view=foundry-classic)
### MLflow on Azure Databricks
@ -531,7 +531,7 @@ Models, prompts, eval datasets, scorers – full reproducibility er non-negotiab
- Key content: 10-step feedback loop, human-aligned metrics, production monitoring
2. **Azure AI Foundry Production Monitoring**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/monitor-quality-safety?view=foundry-classic
- URL: https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-quality-safety?view=foundry-classic
- Key content: Continuous evaluation, scorers, threshold configuration
3. **AI Builder Feedback Loop**
@ -571,7 +571,7 @@ Models, prompts, eval datasets, scorers – full reproducibility er non-negotiab
- Key content: Feedback mechanisms, bias monitoring, iterative updates
12. **Azure AI Foundry Observability Concepts**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/observability
- URL: https://learn.microsoft.com/en-us/azure/foundry/concepts/observability
- Key content: Tracing, monitoring features, model performance tracking
**Code samples (Verified):**

2
skills/ms-ai-governance/references/responsible-ai/gdpr-compliance-ai-systems.md
View file

@ -537,7 +537,7 @@ Norge implementerer GDPR gjennom personopplysningsloven. Datatilsynet er tilsyns
*How to handle access, rectify, erase, restrict, portability, object requests*
6. **Data, privacy, and security for Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy
*No training on customer data, no sharing with OpenAI, encryption, CMK support*
7. **Manage personal data in Azure Monitor Logs**

2
skills/ms-ai-governance/references/responsible-ai/human-in-the-loop-oversight.md
View file

@ -790,7 +790,7 @@ For offentlig sektor i Norge:
3. [Power Automate - Multistage and AI approvals](https://learn.microsoft.com/en-us/microsoft-copilot-studio/flows-advanced-approvals) — Power Platform approvals
4. [FAQ for AI Approvals](https://learn.microsoft.com/en-us/microsoft-copilot-studio/faqs-ai-approvals) — Best practices og limitations
5. [Copilot Studio - Topic escalation analysis](https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/deflection-topic-escalation-analysis) — Escalation patterns
6. [Azure AI Agent Service - Transparency Note](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/agents/transparency-note) — Real-time oversight guidance
6. [Azure AI Agent Service - Transparency Note](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/transparency-note) — Real-time oversight guidance
7. [Durable Agent Features - HITL workflows](https://learn.microsoft.com/en-us/agent-framework/user-guide/agents/agent-types/durable-agent/features) — Durable Functions patterns
8. [Responsible AI in Azure workloads](https://learn.microsoft.com/en-us/azure/well-architected/ai/responsible-ai) — Escape hatches og human-in-the-loop checkpoints
9. [Catalog Enrichment Agent - Responsible AI FAQ](https://learn.microsoft.com/en-us/industry/retail/catalog-enrichment-agent/faqs-catalog-enrichment-agent) — Human-in-the-loop implementation example

2
skills/ms-ai-governance/references/responsible-ai/model-explainability-interpretability.md
View file

@ -530,7 +530,7 @@ SLUTT: Dokumenter valg i ADR, implementer, valider med stakeholders
*Confidence: Verified* - Alternative XAI-teknikk for .NET-utviklere
7. **Azure OpenAI Transparency Note - Limitations**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note?view=foundry-classic#limitations
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note?view=foundry-classic#limitations
*Confidence: Verified* - Begrensninger i explainability for fine-tuned og reasoning models
### Ekstern dokumentasjon (Baseline knowledge)

6
skills/ms-ai-governance/references/responsible-ai/red-teaming-ai-models.md
View file

@ -247,7 +247,7 @@ steps:
- Azure tool calls (✅ supported)
- Function tool calls (❌ not supported)
**Comprehensive tools list:** [Azure AI Foundry Tools](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/overview)
**Comprehensive tools list:** [Azure AI Foundry Tools](https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/overview)
### Azure OpenAI Service
@ -492,10 +492,10 @@ jobs:
| Kilde | URL | Verifikasjonsdato |
|-------|-----|-------------------|
| **AI Red Teaming Agent (preview)** | https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/ai-red-teaming-agent | 2026-02-03 |
| **AI Red Teaming Agent (preview)** | https://learn.microsoft.com/en-us/azure/foundry/concepts/ai-red-teaming-agent | 2026-02-03 |
| **Microsoft Security Benchmark: AI-7 Continuous Red Teaming** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security#ai-7-perform-continuous-ai-red-teaming | 2026-02-03 |
| **AI Red Teaming Training Series** | https://learn.microsoft.com/en-us/security/ai-red-team/training | 2026-02-03 |
| **Planning red teaming for LLMs** | https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/red-teaming | 2026-02-03 |
| **Planning red teaming for LLMs** | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/red-teaming | 2026-02-03 |
| **Prompt Shields (Jailbreak detection)** | https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection | 2026-02-03 |
### Open-source verktøy

2
skills/ms-ai-governance/references/responsible-ai/responsible-ai-policy-development.md
View file

@ -227,7 +227,7 @@ Start: New AI initiative or capability?
| **Content Safety** | Harmful content filtering (text, image, multimodal) | [Azure AI Content Safety](https://learn.microsoft.com/azure/ai-services/content-safety/) - konfigurerbare severity thresholds |
| **Evaluation Tools** | Pre-deployment safety, hallucination, bias testing | [Foundry evaluation SDK](https://learn.microsoft.com/azure/ai-studio/) - integreres i CI/CD |
| **Model Registry** | Versioning, approval workflows, provenance tracking | [Azure ML Model Registry](https://learn.microsoft.com/azure/machine-learning/concept-model-management-and-deployment) - RBAC-controlled |
| **Monitoring** | Model drift, performance degradation, quality metrics | [Foundry Agent Service metrics](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/metrics) - alert rules |
| **Monitoring** | Model drift, performance degradation, quality metrics | [Foundry Agent Service metrics](https://learn.microsoft.com/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard) - alert rules |
| **Data Governance** | Data lineage, sensitivity labels, DLP policies | [Microsoft Purview integration](https://learn.microsoft.com/purview/ai-azure-services) |
**Policy Implementation Example (Foundry):**

2
skills/ms-ai-governance/references/responsible-ai/stakeholder-communication-ai-decisions.md
View file

@ -804,7 +804,7 @@ Hvis noen av disse mangler: **IKKE deploy før de er på plass.** AI uten stakeh
- Verifisert: 2026-02
6. **Transparency note for Azure OpenAI**
- https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note?view=foundry-classic
- https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note?view=foundry-classic
- Status: GA
- Verifisert: 2026-02

8
skills/ms-ai-governance/references/responsible-ai/transparency-documentation-standards.md
View file

@ -380,7 +380,7 @@ rai_insights.save("rai_scorecard.pdf")
- Content filter annotations → apps kan forklare hvorfor content ble blocked
**Transparency Note URL:**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note
---
@ -699,15 +699,15 @@ Return on investment: Transparency er billigere enn cleanup. Skal vi prioritere
**Verified sources (MCP: microsoft-learn):**
1. **Transparency note for Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note
(Status: Verified 2026-02 — Latest updates: o3/o4-mini, Deep Research system cards)
2. **Transparency note for Azure AI Search**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/search/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note
(Status: Verified 2026-02 — Recommendations for A/B testing, bias detection)
3. **Transparency note for Document Intelligence**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/document-intelligence/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/document-intelligence/transparency-note
(Status: Verified 2026-02 — Limitations for prebuilt/custom models)
4. **Responsible AI scorecard documentation**