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

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

Browse source 
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.
This commit is contained in:
Kjell Tore Guttormsen 2026-06-26 12:31:45 +02:00
commit 83fd9b58d3
15 changed files with 110 additions and 110 deletions
Download patch file Download diff file Expand all files Collapse all files

32
skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md
View file

@ -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) |

2
skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md
View file

@ -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):**

8
skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md
View file

@ -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

6
skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md
View file

@ -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 |

24
skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md
View file

@ -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 |

28
skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md
View file

@ -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)

18
skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md
View file

@ -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)