fix(ms-ai-architect): ✅ Verified → ✅ Documented (tillit-hygiene)

Markøren over-påsto ekstern verifisering; faktisk semantikk (per legend i m365-copilot-plugins-ecosystem.md) er «hentet fra MS Learn via MCP» = Documented. Smal scope (operatør-besluttet A): de 101 ✅ Verified-konfidens-cellene i 13 filer + 5 kolonne-overskrifter (ptu, agent-memory) + skill-gen-taksonomien (Verified/Baseline/Assumed → Documented/Baseline/Assumed) + licensing-seksjonstittel. La de 137 plain «Verified»-cellene i 31 kilde-attribusjons-tabeller stå — de peker på en faktisk kilde i nabokolonnen (proveniens bevart). Suite 509/509.
2026-06-26 12:31:45 +02:00 · 2026-06-26 12:31:45 +02:00 · 83fd9b58d3
commit 83fd9b58d3
parent 5cff871c99
15 changed files with 110 additions and 110 deletions
--- a/scripts/skill-gen/generate-skills.sh
+++ b/scripts/skill-gen/generate-skills.sh
@ -243,7 +243,7 @@ Denne filen tilhører kategorien **${category_name}**.

 9. **Kilder og verifisering**
   - Microsoft Learn-referanser
-   - Konfidensnivå (Verified / Baseline / Assumed)
+   - Konfidensnivå (Documented / Baseline / Assumed)

 ## Regler

--- a/scripts/skill-gen/prompt-template.md
+++ b/scripts/skill-gen/prompt-template.md
@ -82,7 +82,7 @@ Filen MÅ følge dette eksakte formatet:
 9. **Kilder og verifisering**
   - Referanser til Microsoft Learn-artikler
   - Sist verifisert dato
-   - Konfidensnivå per seksjon (Verified / Baseline / Assumed)
+   - Konfidensnivå per seksjon (Documented / Baseline / Assumed)

 ## Regler

--- a/skills/ms-ai-advisor/references/architecture/licensing-matrix.md
+++ b/skills/ms-ai-advisor/references/architecture/licensing-matrix.md
@ -567,9 +567,9 @@ Tilgjengelig som selvstendig add-on (~$15/bruker/måned, *community-kilde*); anb

 ---

-## 10. Verified vs Assumed Information
+## 10. Documented vs Assumed Information

-### ✅ Verified (fra microsoft-learn MCP)
+### ✅ Documented (fra microsoft-learn MCP)

 - M365 Copilot add-on pris: $30/user/month
 - AI Builder seeded credits fjernes 1. nov 2026
--- a/skills/ms-ai-advisor/references/copilot-extensibility/m365-copilot-plugins-ecosystem.md
+++ b/skills/ms-ai-advisor/references/copilot-extensibility/m365-copilot-plugins-ecosystem.md
@ -429,21 +429,21 @@ Hvis plugin brukes til å fatte avgjørelser som påvirker individers rettighete

 | Seksjon | Kilde | Konfidensnivå |
 |---------|-------|---------------|
-| **Ecosystem Overview** | [Copilot extensibility in the Microsoft 365 ecosystem](https://learn.microsoft.com/microsoft-365-copilot/extensibility/ecosystem) | ✅ Verified (MCP) |
-| **App Package Structure** | [Agents are apps for Microsoft 365](https://learn.microsoft.com/microsoft-365-copilot/extensibility/agents-are-apps) | ✅ Verified (MCP) |
-| **Distribution Methods** | [Publish agents for Microsoft 365 Copilot](https://learn.microsoft.com/microsoft-365-copilot/extensibility/publish) | ✅ Verified (MCP) |
-| **Manifest Schema** | [Microsoft 365 app manifest schema reference](https://learn.microsoft.com/microsoft-365/extensibility/schema) — seneste GA: v1.28 (mai 2026); v1.29 dokumentert (juni 2026) | ✅ Verified (MCP 2026-06) |
-| **Plugin Types** | [Adopt, extend and build Copilot experiences](https://learn.microsoft.com/copilot/roadmap/overview) | ✅ Verified (MCP) |
-| **Teams Admin Center** | [Manage apps in Teams admin center](https://learn.microsoft.com/microsoftteams/manage-apps) | ✅ Verified (MCP) |
-| **Partner Center** | [Microsoft 365 and Copilot program](https://learn.microsoft.com/partner-center/marketplace/why-publish) | ✅ Verified (MCP) |
+| **Ecosystem Overview** | [Copilot extensibility in the Microsoft 365 ecosystem](https://learn.microsoft.com/microsoft-365-copilot/extensibility/ecosystem) | ✅ Documented (MCP) |
+| **App Package Structure** | [Agents are apps for Microsoft 365](https://learn.microsoft.com/microsoft-365-copilot/extensibility/agents-are-apps) | ✅ Documented (MCP) |
+| **Distribution Methods** | [Publish agents for Microsoft 365 Copilot](https://learn.microsoft.com/microsoft-365-copilot/extensibility/publish) | ✅ Documented (MCP) |
+| **Manifest Schema** | [Microsoft 365 app manifest schema reference](https://learn.microsoft.com/microsoft-365/extensibility/schema) — seneste GA: v1.28 (mai 2026); v1.29 dokumentert (juni 2026) | ✅ Documented (MCP 2026-06) |
+| **Plugin Types** | [Adopt, extend and build Copilot experiences](https://learn.microsoft.com/copilot/roadmap/overview) | ✅ Documented (MCP) |
+| **Teams Admin Center** | [Manage apps in Teams admin center](https://learn.microsoft.com/microsoftteams/manage-apps) | ✅ Documented (MCP) |
+| **Partner Center** | [Microsoft 365 and Copilot program](https://learn.microsoft.com/partner-center/marketplace/why-publish) | ✅ Documented (MCP) |
 | **GDPR Compliance** | EU GDPR Articles 5, 32 | ⚠️ Baseline (legal text) |
 | **Schrems II** | CJEU Case C-311/18 | ⚠️ Baseline (legal text) |
 | **AI Act** | EU AI Act Articles 52, Annex III | ⚠️ Baseline (legal text) |
 | **Forvaltningsloven** | Forvaltningsloven §§ 11a-11c (Norge) | ⚠️ Baseline (legal text) |
-| **Licensing** | [Microsoft 365 Copilot developer licenses](https://learn.microsoft.com/microsoft-365-copilot/extensibility/prerequisites) | ✅ Verified (MCP) |
+| **Licensing** | [Microsoft 365 Copilot developer licenses](https://learn.microsoft.com/microsoft-365-copilot/extensibility/prerequisites) | ✅ Documented (MCP) |

 **Konfidensnivå-definisjon:**
- ✅ **Verified:** Hentet direkte fra Microsoft Learn via MCP (oppdatert per januar 2026)
+- ✅ **Documented:** Hentet direkte fra Microsoft Learn via MCP (oppdatert per januar 2026)
 - ⚠️ **Baseline:** Basert på modellkunnskap (legal/regulatory tekster, ikke Microsoft-dokumentasjon)

 **Siste oppdatering av Microsoft-dokumentasjon:** Juni 2026 (reflektert i MCP-kall 2026-06-19) — Manifest v1.28 seneste GA, v1.29 dokumentert
--- a/skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md
+++ b/skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md
@ -20,7 +20,7 @@ Hovedutfordringen er å håndtere to typer minne: **short-term memory** (session

 ### Memory-typer i Microsoft AI-stakken

-| Memory-type | Varighet | Bruksområde | Implementering | Verified |
+| Memory-type | Varighet | Bruksområde | Implementering | Documented |
 |-------------|----------|-------------|----------------|----------|
 | **Short-term (Session)** | Inneværende samtale | Opprettholde immediate context | ChatHistory, AgentThread | ✅ |
 | **Working Memory** | Inneværende session | Kritiske beslutninger/krav | WhiteboardProvider (SK) | ✅ |
@ -30,7 +30,7 @@ Hovedutfordringen er å håndtere to typer minne: **short-term memory** (session

 ### Minnearkitekturer per plattform

-| Plattform | Kortvarig minne | Langvarig minne | Persistence-layer | Verified |
+| Plattform | Kortvarig minne | Langvarig minne | Persistence-layer | Documented |
 |-----------|----------------|-----------------|-------------------|----------|
 | **Semantic Kernel Agents** | ChatHistoryAgentThread | Mem0Provider, Vector Stores | Egen/ekstern (Cosmos DB, Redis, etc.) | ✅ |
 | **Foundry Agent Service** | Session context (managed) | Managed Memory Store (preview) | Azure-managed (AI Search, embeddings) | ✅ |
@ -42,7 +42,7 @@ Hovedutfordringen er å håndtere to typer minne: **short-term memory** (session

 **Legacy Memory Stores (deprecated — bruk Vector Store abstractions):**

-| Provider | Type | Verified |
+| Provider | Type | Documented |
 |----------|------|----------|
 | InMemoryMemoryStore | Prototyping, testing | ✅ |
 | Azure AI Search | Production vector storage | ✅ |
@ -462,45 +462,45 @@ Gir data lineage tracking og governance-enforcement.

 1. **Semantic Kernel Agent Memory**
   https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-memory
-   Confidence: ✅ Verified (Mem0Provider, WhiteboardProvider documentation)
+   Confidence: ✅ Documented (Mem0Provider, WhiteboardProvider documentation)

 2. **Foundry Agent Service Memory (preview)**
   https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/what-is-memory?view=foundry
-   Confidence: ✅ Verified (Managed Memory Store, extraction/consolidation/retrieval phases)
+   Confidence: ✅ Documented (Managed Memory Store, extraction/consolidation/retrieval phases)

 3. **Agent Framework Chat History Providers**
   https://learn.microsoft.com/en-us/agent-framework/integrations/overview
-   Confidence: ✅ Verified (CosmosChatHistoryProvider, Memory AI Context Providers)
+   Confidence: ✅ Documented (CosmosChatHistoryProvider, Memory AI Context Providers)

 4. **Azure Copilot BYOS (Bring Your Own Storage)**
   https://learn.microsoft.com/en-us/azure/copilot/bring-your-own-storage
-   Confidence: ✅ Verified (Cosmos DB conversation history, managed identity)
+   Confidence: ✅ Documented (Cosmos DB conversation history, managed identity)

 5. **Semantic Kernel Vector Stores**
   https://learn.microsoft.com/en-us/semantic-kernel/concepts/vector-store-connectors/memory-stores
-   Confidence: ✅ Verified (Legacy IMemoryStore deprecated, Vector Store abstractions GA)
+   Confidence: ✅ Documented (Legacy IMemoryStore deprecated, Vector Store abstractions GA)

 6. **Multi-turn Conversations with Agents**
   https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/multi-turn-conversation
-   Confidence: ✅ Verified (AgentSession for state management)
+   Confidence: ✅ Documented (AgentSession for state management)

 7. **Foundry Agent Service Context Layer**
   https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/ai-agents/build-secure-process
-   Confidence: ✅ Verified (Hierarchical memory: knowledge, long-term, short-term)
+   Confidence: ✅ Documented (Hierarchical memory: knowledge, long-term, short-term)

 8. **Azure OpenAI Web App Chat History (Cosmos DB)**
   https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/use-web-app
-   Confidence: ✅ Verified (Cosmos DB enablement for chat history)
+   Confidence: ✅ Documented (Cosmos DB enablement for chat history)

 ### Konfidensnivå per seksjon

 | Seksjon | Konfidens | Kilde |
 |---------|-----------|-------|
-| Memory-typer | ✅ Verified | Microsoft Learn docs (Foundry, SK, Agent Framework) |
-| Arkitekturmønstre | ✅ Verified | Code samples fra microsoft-learn MCP |
-| Foundry Managed Memory | ✅ Verified | Microsoft Foundry Memory docs (preview disclaimer inkludert) |
-| Cosmos DB Chat History | ✅ Verified | Agent Framework integrations, Azure Copilot BYOS |
-| Vector Store deprecation | ✅ Verified | Semantic Kernel Memory Stores migration guide |
+| Memory-typer | ✅ Documented | Microsoft Learn docs (Foundry, SK, Agent Framework) |
+| Arkitekturmønstre | ✅ Documented | Code samples fra microsoft-learn MCP |
+| Foundry Managed Memory | ✅ Documented | Microsoft Foundry Memory docs (preview disclaimer inkludert) |
+| Cosmos DB Chat History | ✅ Documented | Agent Framework integrations, Azure Copilot BYOS |
+| Vector Store deprecation | ✅ Documented | Semantic Kernel Memory Stores migration guide |
 | Offentlig sektor compliance | 🟡 Baseline | GDPR/AI Act krav (established), Foundry Memory region-support TBD |
 | Pricing | 🟡 Baseline | General Azure pricing (Cosmos DB, AI Search verified), Foundry Memory preview (TBD) |

--- a/skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md
+++ b/skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md
@ -692,7 +692,7 @@ AzureDiagnostics

 ## Kilder og verifisering

-**Verification status:** ✅ Verified via Microsoft Learn MCP (2026-02)
+**Verification status:** ✅ Documented via Microsoft Learn MCP (2026-02)

 **Primary sources (fetched):**

--- a/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md
+++ b/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md
@ -365,13 +365,13 @@ Azure AI Vision er en **Azure resource** som faktureres direkte via Azure-abonne
 8. [Azure Image Analysis client library for Python](https://learn.microsoft.com/en-us/python/api/overview/azure/ai-vision-imageanalysis-readme) - Visual features, gender-neutral captions

 **Konfidensnivå per seksjon:**
- **Introduksjon:** ✅ Verified (Florence integration, GA status)
- **Kjernekomponenter:** ✅ Verified (visual features, Florence-modell)
+- **Introduksjon:** ✅ Documented (Florence integration, GA status)
+- **Kjernekomponenter:** ✅ Documented (visual features, Florence-modell)
 - **Arkitekturmønstre:** ⚠️ Baseline (arkitekturprinsipper er ikke eksplisitt dokumentert i Microsoft Learn, men basert på Azure best practices)
 - **Beslutningsveiledning:** ⚠️ Baseline (sammenligningstabell basert på modellkunnskap + Microsoft pricing)
- **Integrasjon med Microsoft-stakken:** ✅ Verified (Azure AI Search ImageAnalysisSkill, SDK-eksempler)
+- **Integrasjon med Microsoft-stakken:** ✅ Documented (Azure AI Search ImageAnalysisSkill, SDK-eksempler)
 - **Offentlig sektor:** ⚠️ Baseline (GDPR/EU AI Act er juridisk tolkning, ikke Microsoft-dokumentasjon)
- **Kostnad og lisensiering:** ✅ Verified (prismodell er fra Azure Pricing Calculator, konvertert til NOK)
+- **Kostnad og lisensiering:** ✅ Documented (prismodell er fra Azure Pricing Calculator, konvertert til NOK)
 - **For arkitekten:** ⚠️ Baseline (rådgivningsspørsmål er erfaringsbaserte, ikke offisiell dokumentasjon)

 **Antall unike kilder:** 8 Microsoft Learn-artikler
--- a/skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md
+++ b/skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md
@ -465,11 +465,11 @@ Ved bruk i offentlig saksbehandling:

 | Seksjon | Konfidensnivå | Kilde |
 |---------|---------------|-------|
-| **Introduksjon** | ✅ Verified | Microsoft Learn (MCP fetch) |
-| **Kjernekomponenter** | ✅ Verified | Microsoft Learn + Code Samples (MCP) |
+| **Introduksjon** | ✅ Documented | Microsoft Learn (MCP fetch) |
+| **Kjernekomponenter** | ✅ Documented | Microsoft Learn + Code Samples (MCP) |
 | **Arkitekturmønstre** | ⚠️ Baseline | Utledet fra use cases i Microsoft Learn + modellkunnskap |
 | **Beslutningsveiledning** | ⚠️ Baseline | Best practices fra Microsoft Learn + modellkunnskap |
-| **Integrasjon** | ✅ Verified | Microsoft Learn (Foundry, Azure AI Search integration) |
+| **Integrasjon** | ✅ Documented | Microsoft Learn (Foundry, Azure AI Search integration) |
 | **Offentlig sektor** | ⚠️ Baseline | GDPR/AI Act-kunnskap + Azure compliance docs (ikke MCP-verifisert) |
 | **Kostnad** | ⚠️ Baseline | Prismodell fra Azure Pricing Calculator (per 2024 data, ikke 2026-verifisert) |
 | **For arkitekten** | ⚠️ Baseline | Best practices syntetisert fra Microsoft Learn + erfaring |
--- a/skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md
+++ b/skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md
@ -387,24 +387,24 @@ Language Services bruker **pay-per-call** modell (per text record).

 | Kategori | URL | Konfidensnivå |
 |----------|-----|---------------|
-| **Sentiment Analysis Overview** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/overview | ✅ Verified (2026-02) |
-| **Sentiment Analysis How-To** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/call-api | ✅ Verified (2026-02) |
-| **Key Phrase Extraction How-To** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/call-api | ✅ Verified (2026-02) |
-| **NER Entity Categories** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/named-entity-categories | ✅ Verified (2026-02) |
-| **Fabric Text Analytics** | https://learn.microsoft.com/en-us/fabric/data-science/ai-services/how-to-use-text-analytics | ✅ Verified (2026-02) |
-| **Key Phrase Language Support** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support | ✅ Verified (2026-02) |
-| **Sentiment Language Support** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/language-support | ✅ Verified (2026-02) |
-| **Custom Text Classification** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/overview | ✅ Verified (2026-02) |
+| **Sentiment Analysis Overview** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/overview | ✅ Documented (2026-02) |
+| **Sentiment Analysis How-To** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/how-to/call-api | ✅ Documented (2026-02) |
+| **Key Phrase Extraction How-To** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/how-to/call-api | ✅ Documented (2026-02) |
+| **NER Entity Categories** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/named-entity-recognition/concepts/named-entity-categories | ✅ Documented (2026-02) |
+| **Fabric Text Analytics** | https://learn.microsoft.com/en-us/fabric/data-science/ai-services/how-to-use-text-analytics | ✅ Documented (2026-02) |
+| **Key Phrase Language Support** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/key-phrase-extraction/language-support | ✅ Documented (2026-02) |
+| **Sentiment Language Support** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/sentiment-opinion-mining/language-support | ✅ Documented (2026-02) |
+| **Custom Text Classification** | https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-text-classification/overview | ✅ Documented (2026-02) |

 ### Konfidensnivå per seksjon

 | Seksjon | Konfidens | Kilde |
 |---------|-----------|-------|
-| Introduksjon | ✅ Verified | Microsoft Learn docs (MCP-fetched) |
-| Kjernekomponenter | ✅ Verified | REST API examples + model outputs fra docs |
-| Arkitekturmønstre | ✅ Verified | Fabric tutorial + Synapse docs + SDK samples |
+| Introduksjon | ✅ Documented | Microsoft Learn docs (MCP-fetched) |
+| Kjernekomponenter | ✅ Documented | REST API examples + model outputs fra docs |
+| Arkitekturmønstre | ✅ Documented | Fabric tutorial + Synapse docs + SDK samples |
 | Beslutningsveiledning | ⚠️ Baseline | Best practices (modellkunnskap), ikke eksplisitt dokumentert |
-| Integrasjon med MS-stakken | ✅ Verified | Power BI tutorial + SynapseML docs + Foundry quickstarts |
+| Integrasjon med MS-stakken | ✅ Documented | Power BI tutorial + SynapseML docs + Foundry quickstarts |
 | Offentlig sektor (Norge) | ⚠️ Baseline | GDPR-analyse (modellkunnskap) + Azure datacenter geografi |
 | Kostnad og lisensiering | ⚠️ Baseline | Generell Azure pricing structure (ikke eksakte NOK-priser hentet) |
 | For arkitekten (Cosmo) | ⚠️ Baseline | Arkitekturerfaringer (modellkunnskap), ikke dokumentert av Microsoft |
--- a/skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md
+++ b/skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md
@ -491,16 +491,16 @@ Billable characters: `Hello, world!` = 13 tegn (ikke `<speak>` eller `<voice>`)

 | Kilde | Confidence | URL |
 |-------|------------|-----|
-| What is Text-to-Speech? | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech |
-| Customize voice and sound with SSML | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice |
-| How to synthesize speech from text | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis |
-| Text-to-Speech FAQ | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts |
-| Transparency note for TTS | ✅ Verified | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/speech-service/text-to-speech/transparency-note |
-| Language support | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts |
-| Speech service pricing | ✅ Verified | https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/ |
-| Batch synthesis API | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis |
-| Custom neural voice | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice |
-| Personal voice | ✅ Verified | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview |
+| What is Text-to-Speech? | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech |
+| Customize voice and sound with SSML | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup-voice |
+| How to synthesize speech from text | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-speech-synthesis |
+| Text-to-Speech FAQ | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts |
+| Transparency note for TTS | ✅ Documented | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/speech-service/text-to-speech/transparency-note |
+| Language support | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts |
+| Speech service pricing | ✅ Documented | https://azure.microsoft.com/pricing/details/cognitive-services/speech-services/ |
+| Batch synthesis API | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/batch-synthesis |
+| Custom neural voice | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/custom-neural-voice |
+| Personal voice | ✅ Documented | https://learn.microsoft.com/en-us/azure/ai-services/speech-service/personal-voice-overview |

 ### Code Samples (Verified via MCP)

@ -512,13 +512,13 @@ Billable characters: `Hello, world!` = 13 tegn (ikke `<speak>` eller `<voice>`)

 | Seksjon | Confidence | Basert på |
 |---------|------------|-----------|
-| Introduksjon | ✅ Verified | MCP docs_search + docs_fetch |
-| Kjernekomponenter | ✅ Verified | MCP docs + code samples |
+| Introduksjon | ✅ Documented | MCP docs_search + docs_fetch |
+| Kjernekomponenter | ✅ Documented | MCP docs + code samples |
 | Arkitekturmønstre | ⚠️ Baseline + Verified | Patterns fra docs + erfaring |
 | Beslutningsveiledning | ⚠️ Baseline | Best practices (ikke eksplisitt i docs) |
-| Integrasjon Microsoft-stakken | ✅ Verified (delvis) | Dokumentert for noen, baseline for andre |
+| Integrasjon Microsoft-stakken | ✅ Documented (delvis) | Dokumentert for noen, baseline for andre |
 | Offentlig sektor (Norge) | ⚠️ Baseline | GDPR/AI Act-vurdering ikke i MS docs |
-| Kostnad og lisensiering | ✅ Verified | Pricing docs + examples |
+| Kostnad og lisensiering | ✅ Documented | Pricing docs + examples |
 | For arkitekten | ⚠️ Baseline | Praktisk erfaring, ikke dokumentert i MCP |

 **Totalt antall MCP-kall:** 7 (4 × docs_search, 3 × docs_fetch, 1 × code_sample_search)
--- a/skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md
+++ b/skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md
@ -277,20 +277,20 @@ GraphRAG introduserer spesifikke personvernrisiki i offentlig sektor:

 | Seksjon | URL | Konfidensnivå |
 |---------|-----|---------------|
-| CosmosAIGraph arkitektur | https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/cosmos-ai-graph | ✅ Verified (2026-06-19) |
-| Graph semantics i KQL | https://learn.microsoft.com/en-us/kusto/query/graph-semantics-overview | ✅ Verified (2026-02) |
-| Entity Recognition skill (v3) | https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-entity-recognition-v3 | ✅ Verified (2026-02) |
-| Azure AI Search transparency note | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note | ✅ Verified (2026-02) |
-| RAG solution design guide | https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide | ✅ Verified (2026-02) |
-| Labeled Property Graphs (LPG) | https://learn.microsoft.com/en-us/fabric/graph/graph-data-models | ✅ Verified (2026-06-19) |
+| CosmosAIGraph arkitektur | https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/cosmos-ai-graph | ✅ Documented (2026-06-19) |
+| Graph semantics i KQL | https://learn.microsoft.com/en-us/kusto/query/graph-semantics-overview | ✅ Documented (2026-02) |
+| Entity Recognition skill (v3) | https://learn.microsoft.com/en-us/azure/search/cognitive-search-skill-entity-recognition-v3 | ✅ Documented (2026-02) |
+| Azure AI Search transparency note | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note | ✅ Documented (2026-02) |
+| RAG solution design guide | https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-solution-design-and-evaluation-guide | ✅ Documented (2026-02) |
+| Labeled Property Graphs (LPG) | https://learn.microsoft.com/en-us/fabric/graph/graph-data-models | ✅ Documented (2026-06-19) |

 ### Konfidens per seksjon

- **Introduksjon**: ✅ Verified (direkte fra Cosmos DB docs)
- **Kjernekomponenter**: ✅ Verified (Azure AI Search + Cosmos DB capabilities)
+- **Introduksjon**: ✅ Documented (direkte fra Cosmos DB docs)
+- **Kjernekomponenter**: ✅ Documented (Azure AI Search + Cosmos DB capabilities)
 - **Arkitekturmønstre**: ⚠️ Baseline (inferert fra best practices, ikke eksplisitt dokumentert)
 - **Beslutningsveiledning**: ⚠️ Baseline (syntetisert fra multiple sources)
- **Microsoft-integrasjon**: ✅ Verified (official API docs)
+- **Microsoft-integrasjon**: ✅ Documented (official API docs)
 - **Offentlig sektor**: ⚠️ Baseline (GDPR-prinsipper applisert på GraphRAG-kontekst)
 - **Kostnad**: ⚠️ Baseline (Cosmos DB pricing, estimater fra modell-kunnskap)

--- a/skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md
+++ b/skills/ms-ai-governance/references/monitoring-observability/security-and-audit-logging-ai.md
@ -384,24 +384,24 @@ 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/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 |
-| **Azure Policy Regulatory Compliance controls** | https://learn.microsoft.com/en-us/azure/governance/policy/samples/azure-security-benchmark | ✅ Verified |
-| **Best practices for data and AI governance (Databricks)** | https://learn.microsoft.com/en-us/azure/databricks/lakehouse-architecture/data-governance/best-practices | ✅ Verified — Unity Catalog er nå sentral governance for BÅDE data og AI assets (modeller, features, lineage ned til kolonne-nivå). Tre governance-modeller: sentralisert, distribuert (federated), hybrid. Audit-logging på to nivåer (workspace + account) + verbose audit logs per query/kommando. AI-genererte kommentarer støttes (krever human review). *(Verified MCP 2026-06-19)* |
+| **Enable diagnostic logging for Azure AI services** | https://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging | ✅ Documented |
+| **Monitor Azure OpenAI** | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai | ✅ Documented |
+| **Azure security baseline for Azure OpenAI** | https://learn.microsoft.com/en-us/security/benchmark/azure/baselines/azure-openai-security-baseline | ✅ Documented — **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 | ✅ Documented — **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 | ✅ Documented |
+| **Artificial Intelligence Security (AI-6: Establish monitoring and detection)** | https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security | ✅ Documented |
+| **Azure Policy Regulatory Compliance controls** | https://learn.microsoft.com/en-us/azure/governance/policy/samples/azure-security-benchmark | ✅ Documented |
+| **Best practices for data and AI governance (Databricks)** | https://learn.microsoft.com/en-us/azure/databricks/lakehouse-architecture/data-governance/best-practices | ✅ Documented — Unity Catalog er nå sentral governance for BÅDE data og AI assets (modeller, features, lineage ned til kolonne-nivå). Tre governance-modeller: sentralisert, distribuert (federated), hybrid. Audit-logging på to nivåer (workspace + account) + verbose audit logs per query/kommando. AI-genererte kommentarer støttes (krever human review). *(Verified MCP 2026-06-19)* |

 ### Konfidensgradering per seksjon

 | Seksjon | Konfidensnivå | Merknad |
 |---------|---------------|---------|
-| **Introduksjon** | ✅ Verified | Basert på offisielle Microsoft docs + compliance-rammeverk |
-| **Kjernekomponenter** | ✅ Verified | Loggkategorier og schema hentet fra Azure Monitor-dokumentasjon |
-| **Arkitekturmønstre** | ✅ Verified | Pattern 1-3 er anbefalt praksis fra Microsoft security baselines |
-| **Beslutningsveiledning** | ✅ Verified | KQL-queries testet mot Azure Monitor-dokumentasjon |
-| **Integrasjon** | ✅ Verified | Native integrasjoner dokumentert i Microsoft Learn |
+| **Introduksjon** | ✅ Documented | Basert på offisielle Microsoft docs + compliance-rammeverk |
+| **Kjernekomponenter** | ✅ Documented | Loggkategorier og schema hentet fra Azure Monitor-dokumentasjon |
+| **Arkitekturmønstre** | ✅ Documented | Pattern 1-3 er anbefalt praksis fra Microsoft security baselines |
+| **Beslutningsveiledning** | ✅ Documented | KQL-queries testet mot Azure Monitor-dokumentasjon |
+| **Integrasjon** | ✅ Documented | Native integrasjoner dokumentert i Microsoft Learn |
 | **Offentlig sektor** | ⚠️ Baseline | Rettsgrunnlag er korrekt, implementasjonsdetaljer er tolkninger |
 | **Kostnad** | ⚠️ Baseline | Priser fra Azure Pricing Calculator (februar 2026), kan variere |

--- a/skills/ms-ai-security/references/ai-security-engineering/output-validation-grounding-verification.md
+++ b/skills/ms-ai-security/references/ai-security-engineering/output-validation-grounding-verification.md
@ -670,9 +670,9 @@ def cached_groundedness_check(key):

 | Seksjon | Kilde | Konfidens |
 |---------|-------|-----------|
-| Groundedness Detection API | Microsoft Learn (MCP-verified) | ✅ Verified |
-| Citation Verification | Microsoft Learn (MCP-verified) | ✅ Verified |
-| Evaluation Frameworks | Microsoft Learn (MCP-verified) | ✅ Verified |
+| Groundedness Detection API | Microsoft Learn (MCP-verified) | ✅ Documented |
+| Citation Verification | Microsoft Learn (MCP-verified) | ✅ Documented |
+| Evaluation Frameworks | Microsoft Learn (MCP-verified) | ✅ Documented |
 | Arkitekturmønstre | Baseline (modellkunnskap) + MCP-grunnlag | 🟡 Baseline |
 | Offentlig sektor Norge | Baseline (modellkunnskap) + kjent lovverk | 🟡 Baseline |
 | Kostnadsestimater | Baseline (modellkunnskap av prismodeller) | 🟡 Baseline |
--- a/skills/ms-ai-security/references/cost-optimization/ai-builder-credits-transition.md
+++ b/skills/ms-ai-security/references/cost-optimization/ai-builder-credits-transition.md
@ -651,27 +651,27 @@ Azure-fakturering
 1. **Licensing and AI Builder credits**
   https://learn.microsoft.com/en-us/ai-builder/credit-management
   Lastet: 2026-02-04
-   Status: ✅ Verified (fetched via MCP)
+   Status: ✅ Documented (fetched via MCP)

 2. **End of AI Builder credits**
   https://learn.microsoft.com/en-us/ai-builder/endofaibcredits
   Lastet: 2026-02-04
-   Status: ✅ Verified (fetched via MCP)
+   Status: ✅ Documented (fetched via MCP)

 3. **Overview of licensing**
   https://learn.microsoft.com/en-us/ai-builder/administer-licensing
   Lastet: 2026-02-04
-   Status: ✅ Verified (fetched via MCP)
+   Status: ✅ Documented (fetched via MCP)

 4. **Power Platform licensing FAQs**
   https://learn.microsoft.com/en-us/power-platform/admin/powerapps-flow-licensing-faq
   Lastet: 2026-02-04
-   Status: ✅ Verified (fetched via MCP)
+   Status: ✅ Documented (fetched via MCP)

 5. **AI Builder consumption report**
   https://learn.microsoft.com/en-us/ai-builder/administer-consumption-report
   Lastet: 2026-02-04
-   Status: ✅ Verified (fetched via MCP)
+   Status: ✅ Documented (fetched via MCP)

 ### Microsoft Power Platform Licensing Guide (Baseline)

@ -696,12 +696,12 @@ Azure-fakturering

 | Seksjon | Konfidensnivå | Begrunnelse |
 |---------|---------------|-------------|
-| **Kjernekomponenter** | ✅ Verified | Direkte fra Microsoft Learn MCP-kilder |
+| **Kjernekomponenter** | ✅ Documented | Direkte fra Microsoft Learn MCP-kilder |
 | **Arkitekturmønstre** | 🔵 Baseline + Verified | Mønstre er arkitektanbefalinger (baseline), underliggende fakta er verified |
 | **Beslutningsveiledning** | 🔵 Baseline + Verified | Beslutningstabell er arkitektanalyse (baseline), prisdata er verified |
-| **Integrasjon med Microsoft-stakken** | ✅ Verified | Direkte fra Microsoft Learn MCP-kilder |
+| **Integrasjon med Microsoft-stakken** | ✅ Documented | Direkte fra Microsoft Learn MCP-kilder |
 | **Offentlig sektor (Norge)** | 🔵 Baseline | Norsk offentlig sektor-kontekst er ikke dokumentert i Microsoft Learn |
-| **Kostnad og lisensiering** | ✅ Verified + Baseline | Rate table er verified, TCO-analyser er baseline (kalkuleringer) |
+| **Kostnad og lisensiering** | ✅ Documented + Baseline | Rate table er verified, TCO-analyser er baseline (kalkuleringer) |
 | **For arkitekten** | 🔵 Baseline | Arkitektveiledning er erfaring-basert (ikke Microsoft-dokumentert) |

 ---
--- a/skills/ms-ai-security/references/cost-optimization/ptu-vs-paygo-economics.md
+++ b/skills/ms-ai-security/references/cost-optimization/ptu-vs-paygo-economics.md
@ -21,25 +21,25 @@ En hybrid tilnærming, der man kombinerer PTU for stabil baseline-traffic og Pay

 ### PTU-prismodell

-| Komponent | Beskrivelse | Verified |
+| Komponent | Beskrivelse | Documented |
 |-----------|-------------|----------|
-| **Provisioned Throughput Unit (PTU)** | Generisk enhet for modellprosesseringskapasitet. Ikke modellspesifikk – samme PTU-quota kan brukes på tvers av Azure OpenAI-modeller og Foundry-modeller (DeepSeek, Llama, etc.). | ✅ Verified |
-| **Hourly billing** | Faktureres per time: `$/PTU/hr × antall PTUer`. Proratert ved partial hours (15 min = 1/4 av time-rate). | ✅ Verified |
-| **Azure Reservations** | 1-måned eller 1-år commitments gir betydelige rabatter (ofte 50%+). Reservasjoner kjøpes i Azure Portal, ikke AI Foundry. | ✅ Verified |
-| **Deployment types** | Global Provisioned (multi-region), Data Zone Provisioned (data residency), Regional Provisioned (single-region). Hver type krever separat reservation. | ✅ Verified |
-| **Minimum PTU** | Varierer per modell: GPT-4o (50 PTU regional, 15 PTU global), GPT-4o-mini (25 PTU regional, 15 PTU global), DeepSeek-R1 (100 PTU global, ingen regional). | ✅ Verified |
-| **Throughput per PTU** | For nyere modeller (GPT-4.1+): Separate input/output TPM per PTU. Eksempel: GPT-5 har 4750 input TPM per PTU. Output tokens "koster" mer kapasitet enn input. | ✅ Verified |
-| **Utilization metric** | Azure Monitor: `Provisioned-Managed Utilization V2` måler utnyttelse. Ved 100% returneres HTTP 429. | ✅ Verified |
+| **Provisioned Throughput Unit (PTU)** | Generisk enhet for modellprosesseringskapasitet. Ikke modellspesifikk – samme PTU-quota kan brukes på tvers av Azure OpenAI-modeller og Foundry-modeller (DeepSeek, Llama, etc.). | ✅ Documented |
+| **Hourly billing** | Faktureres per time: `$/PTU/hr × antall PTUer`. Proratert ved partial hours (15 min = 1/4 av time-rate). | ✅ Documented |
+| **Azure Reservations** | 1-måned eller 1-år commitments gir betydelige rabatter (ofte 50%+). Reservasjoner kjøpes i Azure Portal, ikke AI Foundry. | ✅ Documented |
+| **Deployment types** | Global Provisioned (multi-region), Data Zone Provisioned (data residency), Regional Provisioned (single-region). Hver type krever separat reservation. | ✅ Documented |
+| **Minimum PTU** | Varierer per modell: GPT-4o (50 PTU regional, 15 PTU global), GPT-4o-mini (25 PTU regional, 15 PTU global), DeepSeek-R1 (100 PTU global, ingen regional). | ✅ Documented |
+| **Throughput per PTU** | For nyere modeller (GPT-4.1+): Separate input/output TPM per PTU. Eksempel: GPT-5 har 4750 input TPM per PTU. Output tokens "koster" mer kapasitet enn input. | ✅ Documented |
+| **Utilization metric** | Azure Monitor: `Provisioned-Managed Utilization V2` måler utnyttelse. Ved 100% returneres HTTP 429. | ✅ Documented |

 ### PayGo-prismodell

-| Komponent | Beskrivelse | Verified |
+| Komponent | Beskrivelse | Documented |
 |-----------|-------------|----------|
-| **Token-based billing** | Faktureres per 1000 tokens (1K tokens). Input og output har ulike priser (output er dyrere). | ✅ Verified |
-| **Dynamic quota (preview)** | Lar standard-deployments opportunistisk bruke mer quota når tilgjengelig, uten ekstra konfigurasjon. Faktureres fortsatt per token. | ✅ Verified |
-| **TPM-quota** | Tokens Per Minute (TPM) quota definerer maks throughput. Kan økes via quota-request. | ✅ Verified |
-| **Rate limiting** | Custom rate limiting basert på estimert traffic load. Kan gi HTTP 429 før quota nås hvis traffic er ujevnt distribuert. | ✅ Verified |
-| **No minimum commitment** | Ingen forhåndskostnader eller minimum deployment-størrelse. Betaler kun for faktisk forbruk. | ✅ Verified |
+| **Token-based billing** | Faktureres per 1000 tokens (1K tokens). Input og output har ulike priser (output er dyrere). | ✅ Documented |
+| **Dynamic quota (preview)** | Lar standard-deployments opportunistisk bruke mer quota når tilgjengelig, uten ekstra konfigurasjon. Faktureres fortsatt per token. | ✅ Documented |
+| **TPM-quota** | Tokens Per Minute (TPM) quota definerer maks throughput. Kan økes via quota-request. | ✅ Documented |
+| **Rate limiting** | Custom rate limiting basert på estimert traffic load. Kan gi HTTP 429 før quota nås hvis traffic er ujevnt distribuert. | ✅ Documented |
+| **No minimum commitment** | Ingen forhåndskostnader eller minimum deployment-størrelse. Betaler kun for faktisk forbruk. | ✅ Documented |

 ### Breakeven-analyse