docs(architect): weekly KB update — 106 files refreshed (2026-04)

Updates across all 5 skills: ms-ai-advisor, ms-ai-engineering, ms-ai-governance, ms-ai-security, ms-ai-infrastructure. Key changes: - Language Services (Custom Text Classification, Text Analytics, QnA): retirement warning 2029-03-31, migration guides to Foundry/GPT-4o - Agentic Retrieval: 50M free reasoning tokens/month (Public Preview) - Computer Use: Claude Sonnet 4.5 (preview) + OpenAI CUA models - Agent Registry: Risks column (M365 E7), user-shared/org-published types - Declarative agents: schema v1.5 → v1.6, Store validation requirements - MLflow 3: 13 built-in LLM judges, production monitoring, Genie Code - AG-UI HITL: ApprovalRequiredAIFunction (C#) + @tool(approval_mode) (Python) - Entra ID Ignite 2025: Agent ID Admin/Developer RBAC roles, Conditional Access - Security Copilot: 400 SCU/month per 1000 M365 E5 licenses, auto-provisioned - Fast Transcription API: phrase lists, 14-language multi-lingual transcription - Azure Monitor Workbooks: Bicep support, RBAC specifics - Power Platform Copilot: data residency (Norway/Europe → EU DB, Bing → USA) - RAG security-rbac: 4-approach table (GA + 3 preview access control methods) - IaC MLOps: Well-Architected OE:05 principles, Bicep/Terraform patterns - Translator: image file batch translation Preview (JPEG/PNG/BMP/WebP) All 106 files: Last updated 2026-04 | Verified: MCP 2026-04 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 09:13:24 +02:00 · 2026-04-10 09:13:24 +02:00 · ff6a50d14f
commit ff6a50d14f
parent dda86449fa
104 changed files with 1986 additions and 520 deletions
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/adaptive-cards-copilot-responses.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/adaptive-cards-copilot-responses.md
@ -1,6 +1,6 @@
 # Adaptive Cards for Rich Copilot Responses

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -272,10 +272,11 @@ Backend mottar POST med verb + data, returnerer oppdatert card.
 **Problem (Verified):** Adaptive Cards tillater multiple submits. Ved consecutive cards kan bruker submitte på feil card.

 **Løsning:**
-1. **Unique IDs:** Hver submit action må ha unik `id`
-2. **Unique data payloads:** Include identifiers i submit data
-3. **Event handling logic:** Valider hvilket card som submittet
-4. **Logging:** Debug sequence av submissions
+1. **`actionSubmitId` i data payload:** Inkluder unik identifikator i submit action data (f.eks. `"actionSubmitId": "booking_confirm_card_v3_confirm"`) for å skille mellom cards
+2. **Unique IDs:** Hver submit action må ha unik `id`
+3. **Event handling logic:** Valider `actionSubmitId` fra response for å identifisere korrekt card
+4. **Web Chat UX:** Deaktiver submit-knapper etter første klikk for å hindre stale submissions
+5. **Logging:** Debug sequence av submissions

 ---

@ -319,18 +320,31 @@ Backend mottar POST med verb + data, returnerer oppdatert card.

 **Use case:** Send Adaptive Card til Teams-bruker fra inactive conversation (f.eks. approval request, notification).

-**Action:** `Post adaptive card and wait for a response`
+**Actions tilgjengelig:**
+- `Post message in a chat or channel` — send enkel tekst- eller card-melding
+- `Post adaptive card in a chat or channel` — send card uten å vente på svar
+- `Post adaptive card and wait for a response` — send card og vent på brukerens valg

 **Config:**
- Post as: `Microsoft Copilot Studio (Preview)`
- Post in: `Chat with bot`
+- Post as: `Microsoft Copilot Studio agent`
+- Post in: `Chat with agent`
 - Recipient: User email/ID
- Bot: Copilot Studio agent
+- Agent: Copilot Studio agent
+
+**Proaktive meldinger til grupper:**
+- Send til teammates via Teams connector → Get a team → List group members
+- Send til sikkerhetsgruppe via Microsoft Entra ID connector → Get group members
+- Parallell utsending: Bruk Concurrency control i Apply to each (hensyn til throttling-grenser)

 **Response handling:** `submitActionId` fra dynamic content = user's choice (title of Action.Submit).

 **Template limitation (Verified):** Power Automate støtter ikke Adaptive Cards templating feature.

+**Viktige begrensninger:**
+- Mottaker må ha installert agenten i Teams
+- Proaktive meldinger vises ikke i conversation transcripts eller analytics
+- Meldinger må være i samme environment som Power Automate flow
+
 ### Teams

 **Schema support:** 1.5 (ikke `Action.Execute`)
@ -486,6 +500,7 @@ Backend mottar POST med verb + data, returnerer oppdatert card.
 - Label vs placeholder accessibility: [Input Validation - Labels](https://learn.microsoft.com/en-us/adaptive-cards/authoring-cards/input-validation#labels)
 - Action.Execute preview: [Allow inline editing of Adaptive Card responses](https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/adaptive-card-edits)
 - Power Automate proactive cards: [Send proactive Microsoft Teams messages](https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-proactive-message#send-a-proactive-adaptive-card)
+- actionSubmitId for consecutive cards: [Submit button behavior](https://learn.microsoft.com/en-us/microsoft-copilot-studio/authoring-ask-with-adaptive-card#use-a-submit-identifier-in-actionsubmit-data)
 - Validation guidelines for agents: [Validation guidelines for agents - Adaptive Card response](https://learn.microsoft.com/en-us/microsoftteams/platform/concepts/deploy-and-publish/appsource/prepare/review-copilot-validation-guidelines#adaptive-card-response)

 **Verified (MCP code samples):**
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-analytics-and-usage-insights.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-analytics-and-usage-insights.md
@ -78,6 +78,8 @@ For compliance og security auditing:
 - Filtering by user, date, action type, workload
 - AIApp og Copilot workload-filtre

+**Merk:** Microsoft Purview audit logs inneholder faktiske prompts brukere sender til Copilot. For offentlig sektor er dette særlig sensitivt — implementer access controls for hvem som kan lese audit logs.
+
 **Søk:**
 ```plaintext
 Purview portal > Solutions > Audit > Workloads: AIApp + Copilot
@ -91,12 +93,16 @@ Purview portal > Solutions > Audit > Workloads: AIApp + Copilot
 - Capacity management (billing oversight)
 - Tenant-wide agent visibility

-**Copilot Studio Analytics:**
+**Copilot Studio Analytics (oppdatert 2026):**
 - Agent performance (respons-effektivitet)
- User satisfaction ratings
+- User satisfaction ratings (thumbs up/down med kommentarer, GA aug 2025)
 - Session metrics (completion rate, abandonment)
 - Topic effectiveness
- Trace data (troubleshooting)
+- Trace data (troubleshooting) — unified activity og transcript-visning
+- **Agent evaluations (GA mar 2026):** Valider agentytelse med tilpassbare testsett, inkl. multi-turn conversation tests
+- **Question themes (GA mar 2026):** Grupper relaterte brukerspørsmål i temaer for dypere innsikt
+- **ROI analytics:** Spor tids- og kostnadsbesparinger for autonome agenter (GA jul 2025)
+- **Download filtered questions/reactions** til CSV for videre analyse

 ## Arkitekturmønstre

@ -453,7 +459,7 @@ Get-MgBetaReportMicrosoft365CopilotUserCountSummary `

 ## Kilder og verifisering

-**Microsoft Learn (Verified – MCP research 2026-02):**
+**Microsoft Learn (Verified – MCP research 2026-04):**
 - [Microsoft 365 Copilot reporting options for admins](https://learn.microsoft.com/en-us/copilot/microsoft-365/microsoft-365-copilot-reports-for-admins)
 - [Microsoft 365 Copilot usage report](https://learn.microsoft.com/en-us/microsoft-365/admin/activity-reports/microsoft-365-copilot-usage)
 - [Microsoft 365 Copilot readiness report](https://learn.microsoft.com/en-us/microsoft-365/admin/activity-reports/microsoft-365-copilot-readiness)
@ -472,7 +478,7 @@ Get-MgBetaReportMicrosoft365CopilotUserCountSummary `
 - ROI methodology: [How we measure the value of AI at work](https://www.microsoft.com/worklab/how-we-measure-the-value-of-ai-at-work)

 **Confidence-nivå per seksjon:**
- **Kjernekomponenter:** Verified (100% – direkte fra Microsoft Learn 2026-02)
+- **Kjernekomponenter:** Verified (100% – direkte fra Microsoft Learn 2026-04)
 - **Arkitekturmønstre:** Baseline (80% – best practices basert på Microsoft-anbefalinger)
 - **Beslutningsveiledning:** Verified (95% – bekreftet av MCP-dokumentasjon)
 - **Integrasjon med Microsoft-stakken:** Verified (100% – API-dokumentasjon og dataflyt-diagrammer)
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-api-rate-limiting-resilience.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-api-rate-limiting-resilience.md
@ -1,6 +1,6 @@
 # API Rate Limiting and Resilience Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -17,7 +17,7 @@ Denne referansen dekker:
 - **Plattformspesifikke kvotegrenser** (Azure OpenAI, Copilot Studio)
 - **Implementeringsmønstre** med kodeeksempler

-**Confidence:** Verified (Microsoft Learn MCP, januar 2026)
+**Confidence:** Verified (Microsoft Learn MCP, januar 2026) | Re-verified: MCP 2026-04

 ---

@ -50,8 +50,9 @@ En naiv "retry on error"-tilnærming kan sende 3x mer trafikk enn nødvendig (ek

 **Løsning:**
 1. **Bruk durable messaging** (Azure Service Bus, Event Hubs, Queue Storage) som buffer
-2. **Dequeue i kontrollert tempo** (f.eks. 20 requests hver 200ms i stedet for 100/sekund)
-3. **Distributed lease management** for multiple prosesser (Azure Blob lease eller Zookeeper/Redis)
+2. **Dequeue i kontrollert tempo** (f.eks. 20 requests hvert 200ms i stedet for 100/sekund) — sender et jevnere dataflyt og forhindrer bottlenecks ved bursts
+3. **Distributed lease management** for multiple prosesser (Azure Blob lease eller Zookeeper/Redis/etcd/Consul)
+4. **Logisk partisjonering:** Deler kapasiteten i partisjoner (f.eks. 20 partisjoner à 25 req/s for 500 req/s totalt) — prosesser konkurrerer om eksklusive blob-leases per partisjon

 **Fordeler:**
 - Redusert trafikk og færre feil
@ -60,6 +61,10 @@ En naiv "retry on error"-tilnærming kan sende 3x mer trafikk enn nødvendig (ek

 **Verified:** [Rate Limiting pattern - Azure Architecture Center](https://learn.microsoft.com/en-us/azure/architecture/patterns/rate-limiting-pattern)

+**Eksempel (Cosmos DB med 20 000 RU/s kapasitet, 10 000 records à 10 RU):**
+- Naiv retry: 30 000 requests sendt (10K + 8K + 6K + 4K + 2K) med 20 000 feil
+- Med rate limiting: 10 000 requests, ingen throttling-feil, forutsigbar gjennomstrømningstid
+
 ### 3. Circuit Breaker Pattern (Beskyttelse mot varige feil)

 **Formål:** Forhindre at applikasjonen spammer en service som er nede eller ikke responderer, ved å "åpne kretsen" etter N feilede forsøk.
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-connectors-design-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-connectors-design-patterns.md
@ -1,6 +1,6 @@
 # Copilot Connectors - Implementation Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** GA (Synced Connectors) / Early Access Preview (Federated Connectors)
 **Category:** Copilot Extensibility & Integration

@ -237,15 +237,21 @@ Bruk Power Platform custom connectors til å utvide Copilot Studio-agenter med I
 **Fordeler:**
 - Lavkode-utvikling (visual designer)
 - Støtter både read og write operations
- 500+ forhåndsbygde connectors tilgjengelig
+- 500+ forhåndsbygde connectors tilgjengelig (standard og premium)
 - Kan bruke Power Automate flows som actions
- Maker-provided credentials (SSO for agenter)
+- **Maker-provided credentials**: Maker kan konfigurere connector med egne credentials — brukere behøver ikke autentisere seg individuelt

 **Ulempler:**
- Kun for Copilot Studio (ikke M365 Copilot)
- Krever Power Platform-lisens
+- Kun for Copilot Studio (ikke M365 Copilot direkte)
+- Krever Power Platform-lisens (standard connectors inkludert, premium connectors krever plan)
 - Ikke fullt integrert med M365 Search
 - Lavere semantic search-kvalitet enn Graph connectors
+- **SSO-begrensning (Verified):** SSO støttes IKKE for connectors når agenten bruker custom Active Directory-autentisering og er deployert til Microsoft Teams — brukere må autentisere manuelt
+
+**Connector-typer:**
+- **Standard connectors**: Inkludert i alle Copilot Studio-planer (f.eks. SharePoint, Office 365)
+- **Premium connectors**: Krever spesifikk Copilot Studio-plan (f.eks. Salesforce, ServiceNow)
+- **Custom connectors**: Bygd fra egne OpenAPI-spesifikasjoner

 **Implementering:**

@ -357,6 +363,8 @@ Er data statisk eller semi-statisk?

 ⚠️ **Latency i federated connectors:** Hvis kildesystemet har >500ms responstid, vil Copilot oppleves treg.

+⚠️ **Bing Custom Search i Copilot Studio:** Bing Custom Search kan brukes som knowledge source i Copilot Studio, men er IKKE tilgjengelig i generativ modus (generative answers node). For Bing Custom Search: bruk klassisk modus med eksplisitt generative answers-node i et topic.
+
 ⚠️ **ACL-kompleksitet:** Hvis kildesystemet har finkornet ACL (document-level, paragraph-level), kan det være vanskelig å modellere i Graph connector.

 ⚠️ **Item quota-kostnad:** 1 million items koster ~$5000/år (varierer). Plan for volumet.
@ -579,4 +587,4 @@ Ingen item quota (ingen indeksering), men:

 ---

-*Denne referansen er skrevet basert på Microsoft Learn-dokumentasjon per februar 2026. Federated connectors er i preview og kan endre seg før GA.*
+*Denne referansen er oppdatert basert på Microsoft Learn-dokumentasjon per april 2026. Federated connectors er i preview og kan endre seg før GA. Maker-provided credentials og SSO-begrensninger verifisert MCP 2026-04-10.*
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-extensibility-security-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-extensibility-security-patterns.md
@ -1,6 +1,6 @@
 # Security Patterns for Copilot Extensions

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -23,6 +23,8 @@ Microsoft tilbyr flere autentiseringsmodeller og sikkerhetskontroller for extens

 **Viktighetsgrad:** KRITISK. Feilkonfigurerte extensions kan lekke sensitiv data, gi uautorisert tilgang eller bli utnyttet i prompt injection-angrep.

+**Re-verified:** Microsoft Security Copilot plugin API og autentiseringsmodeller verifisert via MCP 2026-04.
+
 ---

 ## Kjernekomponenter
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-orchestration-multi-agent.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-orchestration-multi-agent.md
@ -1,6 +1,6 @@
 # Multi-Agent Orchestration in Copilot

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** Generally Available (GA)
 **Category:** Copilot Extensibility & Integration

@ -37,6 +37,11 @@ Når generative orchestration er aktivert, bruker agenten store språkmodeller t
 - Navn på agent/topic/tool
 - Input/output parametere og deres beskrivelser

+**Avanserte kontrollmuligheter (generativ modus):**
+- **Avbryte plan**: Bruk **"End all topics"**-node i et topic for å kansellere gjenværende steg i orchestratorens plan
+- **Samtalehistorikk**: Agenter bruker nylig samtalehistorikk som kontekst. For å nullstille: bruk **"Clear variable values"**-node med alternativet "Conversation history for the current session"
+- **Topic-triggere**: `AI response generated` (agenten genererer svar) og `Plan complete` (alle planlagte steg utført) gir finkornet kontroll
+
 ### Agent-komponenter (Microsoft Agent Framework)

 For pro-code utvikling tilbyr Agent Framework:
@ -204,8 +209,20 @@ var result = await workflow.RunAsync("Write an article about AI safety");

 - Agenter bygget i Copilot Studio kan publiseres som **declarative agents** i M365 Copilot
 - M365 Copilot bruker sin egen orchestrator, men agent kan ha egne instructions, knowledge og actions
- Governance håndteres via **Microsoft 365 admin center** (enable/disable/assign/block agents)
+- Governance håndteres via **Microsoft 365 admin center** (enable/disable/assign/block agents) under **Agents**-seksjonen i Copilot Control System
 - Agent pinning: Microsoft-pinned, admin-pinned, user-pinned
+- **AI Admin**-rollen gir dedikert, lavprivilegert administratortilgang for agent-styring (anbefalt fremfor Global Admin)
+
+**Agent-typer som kan administreres (Verified):**
+- **Publisert av org**: Predefinerte instruksjoner og actions — må gjennom admin approval
+- **Delt av bruker**: Opprettet via Copilot Studio eller Agent Builder
+- **Microsoft-agenter**: Innebygd i M365-tjenester (Researcher, Analyst etc.)
+- **Eksterne partner-agenter**: Fra ISV-er
+- **Frontier agents** (eksperimentelle):
+  - **App Builder agent**: Kan bygge Power Apps via Copilot
+  - **Workflows agent**: Lager flows i Copilot — lagres i default environment
+
+**Microsoft Agent 365** er den nye kontrollplanen for alle AI-agenter (uavhengig av hvor de er bygd), tilgjengelig via M365 admin center.

 **Nøkkel-policy:**
 - Agents arver M365 Copilots security, privacy og compliance
@ -413,27 +430,27 @@ Triage: "Jeg ser du har spørsmål om barnetrygd.

 1. **Multi-agent patterns:**
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/multi-agent-patterns
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 2. **Generative orchestration:**
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/advanced-generative-actions
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 3. **Agents for M365 Copilot:**
   https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/agents-overview
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 4. **Agent Framework Handoff:**
   https://learn.microsoft.com/en-us/agent-framework/user-guide/workflows/orchestrations/handoff
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 5. **Agent governance (M365 admin):**
   https://learn.microsoft.com/en-us/microsoft-365/admin/manage/manage-copilot-agents-integrated-apps
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 6. **Agent security & compliance:**
   https://learn.microsoft.com/en-us/copilot/microsoft-365/agent-essentials/agent-essentials-overview
-   (Verified: 2026-02)
+   (Verified: 2026-04)

 ### Konfidensnivå per seksjon

--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-localization-globalization.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-localization-globalization.md
@ -1,6 +1,6 @@
 # Localization and Globalization in Copilot

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -78,13 +78,13 @@ Best practice: Bytt språk rett etter en **Question** node for å sikre konsiste

 Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gjennom samtalen.

-**Implementasjonsmønster:**
+**Implementasjonsmønster (Verified 2026-04):**
 1. Opprett topic med trigger "A message is received"
-2. Legg til prompt-node med instruksjon: "Determine which language this message is written in"
-3. Send `Activity.Text` (incoming message) som input
-4. Output: JSON med property `language`
-5. Legg til Condition node som sjekker `DetectedLanguage.structuredOutput.language`
-6. For hver branch: Sett `System.User.Language` til detektert språk
+2. Legg til prompt-node: instructions = "Determine which language this message is written in: " + Add content → Text (Name: "Message")
+3. Sett Output format til JSON → Test → Save
+4. Konfigurer Prompt node: Input = `Activity.Text`, Output = ny variabel `DetectedLanguage`
+5. Legg til Condition node basert på `DetectedLanguage.structuredOutput.language`
+6. For hver branch: Sett `User.Language` (system variable) til detektert språk

 **Viktige hensyn:**
 - **Kostnad**: Språkdeteksjon bruker AI prompts og genererer usage costs
@ -108,7 +108,8 @@ Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gje

 **Limitasjoner:**
 - **Adaptive Cards**: Mixed-type strings (statisk tekst + variabler) inkluderes IKKE i localization files
- **Workaround**: Bruk "Set text variable" node (via code editor) for å lagre hele strengen med variabler, referer kun til variabel i Adaptive Card
+- **Workaround (Verified 2026-04):** Bruk "Set variable value" node → åpne code editor → endre `kind: SetVariable` til `kind: SetTextVariable` → legg inn full streng med variabler → referer kun til variabelen i Adaptive Card
+- Etter lagring kan localization-filen lastes ned og vil inkludere den mixed-type strengen som en `setVariable`-action

 **Confidence marker:** Verified (MCP microsoft-learn, 2026-02)

@ -135,7 +136,7 @@ Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gje
 **Microsoft 365 Copilot** har utvidet språkstøtte utover Copilot Studio. Per august 2025 ble 6 nye språk lagt til: Albanian, Filipino, Icelandic, Malay, Maltese, Serbian (Cyrillic).

 **Agent Builder i Microsoft 365 Copilot:**
- **Authoring canvas languages**: 26 språk (inkludert norsk bokmål nb-NO)
+- **Authoring canvas languages**: 25 språk (inkludert norsk bokmål nb-NO) per Copilot Studio language support dokumentasjon
 - **Describe tab**: Støtter alle språk som Microsoft 365 Copilot støtter

 **Voice agents:**
@ -378,9 +379,9 @@ Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gje
 2. **Sekundærspråk**: Nynorsk (nn-NO), samisk (kun hvis påkrevd)
 3. **Engelsk**: For internasjonale brukere (en-US eller en-GB)

-**Copilot Studio-støtte for norsk:**
- **Bokmål (nb-NO)**: Fully supported (authoring + conversation)
- **Nynorsk (nn-NO)**: Sjekk language support-dokumentasjon (kan være preview)
+**Copilot Studio-støtte for norsk (Verified 2026-04):**
+- **Bokmål (nb-NO)**: Fully supported i alle features — authoring canvas, generative answers, orchestration, og voice
+- **Nynorsk (nn-NO)**: Ikke oppført i language support-dokumentasjonen → vurder Azure Translator proxy
 - **Samisk**: Ikke native støtte → vurder Azure Translator proxy

 **Confidence marker:** Baseline + Verified (language list)
@ -578,10 +579,10 @@ Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gje

 ### Microsoft Learn (Verified via MCP 2026-02)

-1. **Configure and create multilingual agents**
+1. **Configure and create multilingual agents** (Re-verified MCP 2026-04)
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/multilingual
   - Primær kilde for Copilot Studio multilingual configuration
-   - Dekker: add languages, localization files, dynamic language switching, testing
+   - Dekker: add languages, localization files, dynamic language switching, testing, adaptive card localization workaround

 2. **Regional settings including supported locales and formats**
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/data-localization
@ -594,10 +595,10 @@ Agent kan detektere brukerens språk i hver melding og bytte språk dynamisk gje
   - Auto-detect spoken language
   - Best practices for localization

-4. **Language support**
+4. **Language support** (Re-verified MCP 2026-04)
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/authoring-language-support
-   - Full liste over støttede språk per feature
-   - Authoring canvas vs. conversational experience
+   - Full liste over støttede språk per feature (authoring canvas, generative answers, voice)
+   - Norsk bokmål (nb-NO) er GA i alle features

 5. **Make Your Employee Self-Service Agent Multilingual**
   https://learn.microsoft.com/en-us/copilot/microsoft-365/employee-self-service/employee-self-service-multilingual
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-nlp-configuration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-nlp-configuration.md
@ -330,11 +330,14 @@ const results = await client.analyze("KeyPhraseExtraction", documents);
 ### Språkkrav og GDPR-compliance

 **Norsk språkstøtte:**
- **Generative Orchestration**: Støtter norsk (nb-NO) ✅
+- **Generative Orchestration**: Støtter norsk (nb-NO) ✅ — automatisk generert innhold oversettes dynamisk; agenten kan bytte språk per samtaletur (dynamic language switching, GA jun 2025)
 - **Built-in NLU**: Støtter norsk (nb-NO) ✅
- **NLU+**: Støtter norsk (nb-NO) ✅
+- **NLU+**: Støtter norsk (nb-NO) ✅ (avansert NLU-tilpasning tilgjengelig fra jul 2025)
 - **Azure CLU**: Støtter norsk (nb-NO) ✅

+**Dynamisk språkbytte (Generative Orchestration):**
+Agenter kan konfigureres til å detektere brukerens språk og respondere på samme språk i sanntid. Bruk `User.Language`-systemvariabelen kombinert med prompt-basert språkdeteksjon. Krever generative orchestration aktivert.
+
 **Data residency:**
 - NLU-treningsdata lagres i Microsoft Dataverse (EU-region kan velges)
 - Azure CLU: Velg Azure Norway East/West for data residency
@ -507,7 +510,7 @@ Før du foreslår NLU-konfigurasjon, sjekk:

 ### MCP-kilder (microsoft-learn)

-Følgende Microsoft Learn-dokumentasjon ble brukt (februar 2026):
+Følgende Microsoft Learn-dokumentasjon ble brukt (april 2026):

 1. **Design effective language understanding**
   - URL: https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/language-understanding
@ -531,7 +534,7 @@ Følgende Microsoft Learn-dokumentasjon ble brukt (februar 2026):

 6. **Configure and create multilingual agents**
   - URL: https://learn.microsoft.com/en-us/microsoft-copilot-studio/multilingual
-   - Dekker: System.User.Language, auto-detect language, localization best practices
+   - Dekker: System.User.Language, auto-detect language, localization best practices, dynamic language switching (generative orchestration), secondary language management

 7. **Code samples**
   - microsoft_code_sample_search: Entity extraction, trigger phrases, YAML topic definitions
@ -559,8 +562,8 @@ Alle "Verified"-markeringer er basert på:
 ### Siste oppdatering

 - **Dokument opprettet**: 2026-02-04
- **MCP-data hentet**: 2026-02-04
- **Microsoft Learn-versjon**: Februar 2026
+- **MCP-data hentet**: 2026-04-10
+- **Microsoft Learn-versjon**: April 2026
 - **Copilot Studio-versjon**: GA (Generally Available)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-topics-and-entities.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/copilot-studio-topics-and-entities.md
@ -115,6 +115,8 @@ Agent gjenkjenner automatisk:

 Agent hopper over allerede besvarte spørsmål.

+**Merk (oppdatert 2026):** Proactive slot filling er aktivert som standard. Deaktiver per node via **Skip question → Ask every time** i Question-noden Properties. Agenten lytter aktivt og husker informasjon gjennom hele samtalen.
+
 **Arkitekturvalg:**

 | Funksjon | Beskrivelse | Kontroll |
@ -226,13 +228,15 @@ await context.sendActivities([

 ### Azure Bot Service Channels

-Topics kan publiseres til eksterne kanaler (SMS, Facebook, Slack) via Azure Bot Service integration:
+Topics kan publiseres til eksterne kanaler (SMS, Facebook, Slack, WhatsApp) via Azure Bot Service integration (GA):

 1. **DirectLineClient** starter Copilot Studio-samtale via DirectLine API
 2. **OnMessageActivityAsync** handler i bot-relay sender brukermelding til Copilot Studio
 3. **Watermark** tracker turntaking i samtalen
 4. **Token refresh** kreves hver 30. minutt (håndteres i relay-logikk)

+**WhatsApp (GA jul 2025):** Copilot Studio støtter nå direkte publisering til WhatsApp-nummer — ingen mellomlagring via Azure Bot Service nødvendig.
+
 ---

 ## Offentlig sektor (Norge)
@ -352,7 +356,7 @@ User → Copilot Studio Agent (Topic)

 ### Primærkilder (Verified)

-Alle referanser er hentet fra offisiell Microsoft Learn-dokumentasjon via MCP (`microsoft-learn` server), januar 2026:
+Alle referanser er hentet fra offisiell Microsoft Learn-dokumentasjon via MCP (`microsoft-learn` server), april 2026:

 1. **Create and edit topics**
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/authoring-create-edit-topics
@ -426,7 +430,7 @@ Følgende informasjon er basert på modellens treningsdata (januar 2025) og bekr
 | Offentlig sektor (Norge) | **Baseline** | Modell-ekstrapolasjon basert på general GDPR/compliance-kunnskap |
 | Kostnad og lisensiering | **Baseline** | Modellkunnskap (januar 2025), kan ha endret seg i 2026 |

-**Sist verifisert:** 2026-02-04 (via MCP `microsoft-learn` server)
+**Sist verifisert:** 2026-04-10 (via MCP `microsoft-learn` server)

 ---

--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/declarative-agents-fundamentals.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/declarative-agents-fundamentals.md
@ -1,6 +1,6 @@
 # Declarative Agents - Design and Implementation

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -55,12 +55,12 @@ En declarative agent pakkes som en Microsoft 365-app med følgende obligatoriske

 ### Declarative Agent Manifest

-Minimumseksempel på declarative agent manifest (schema v1.5):
+Minimumseksempel på declarative agent manifest (schema v1.6):

 ```json
 {
-  "$schema": "https://developer.microsoft.com/json-schemas/copilot/declarative-agent/v1.5/schema.json",
-  "version": "v1.5",
+  "$schema": "https://developer.microsoft.com/json-schemas/copilot/declarative-agent/v1.6/schema.json",
+  "version": "v1.6",
  "name": "IT Support Assistant",
  "description": "Hjelper ansatte med IT-problemer basert på intern dokumentasjon",
  "instructions": "Du er en IT-support-spesialist. Hjelp brukere med tekniske problemer ved å søke i SharePoint-dokumentasjonen først. Hold en profesjonell og hjelpsom tone.",
@ -195,6 +195,13 @@ Declarative agents bruker en konfigurasjonsdrevet tilnærming i stedet for custo

 *Inkluderer Microsoft service overhead — design for ~66% av grensen.

+**Verified:** ISV store submission krav (Microsoft 365 validation guidelines):
+- Minst 3 prompt starters (conversation_starters) — Must fix
+- App manifest versjon 1.13 eller nyere — Must fix
+- Navn (`name`) MÅ være identisk i manifest.json, declarativeAgent.json og plugin.json — Must fix
+- Responstid ≤9 sekunder (99 percentil) — Must fix
+- Alle serverkall med HTTPS + TLS 1.2+ — Must fix
+
 **Baseline:** Disse begrensningene gjør declarative agents uegnet for:
 - Full-document processing (store PDF-er, lange rapporter)
 - Large dataset analysis
@ -524,4 +531,4 @@ Bruk når: Declarative agent trenger multi-step workflow (workaround for sekvens
 - ROI-beregninger (bransjestandarder)
 - Offentlig sektor-anbefalinger (basert på generell kunnskap om norsk forvaltning)

-**Sist verifisert:** 2026-02-04
+**Sist verifisert:** 2026-04-10
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/declarative-agents-grounding-strategies.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/declarative-agents-grounding-strategies.md
@ -1,6 +1,6 @@
 # Grounding Strategies for Declarative Agents

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -20,18 +20,22 @@ Denne guiden dekker arkitekturmønstre for grounding, beslutningskriterier for v

 ### Tilgjengelige Knowledge Sources

-| Knowledge Source | Beskrivelse | Lisenskrav | Scoping-støtte |
-|-----------------|-------------|------------|----------------|
-| **SharePoint** | Filer, mapper, sites i SharePoint Online | Microsoft 365 Copilot-lisens | Ja (site/folder/file) |
+| Knowledge Source | Beskrivelse | Lisenskrav | Scoping (generativ modus) |
+|-----------------|-------------|------------|---------------------------|
+| **SharePoint** | Filer, mapper, sites i SharePoint Online | Microsoft 365 Copilot-lisens | 25 URLer (klassisk: 4) |
 | **OneDrive** | Brukerens OneDrive-innhold | Microsoft 365 Copilot-lisens | Ja (via manifest) |
-| **Copilot Connectors** | Eksterne systemer (ServiceNow, Salesforce, etc.) via Microsoft Graph | Microsoft 365 Copilot-lisens | Ja (attributt-basert) |
-| **Teams Messages** | Chat-historikk, meeting transcripts, kanal-meldinger | Microsoft 365 Copilot-lisens | Ja (opptil 5 chats) |
-| **Teams Meetings** | Meeting metadata, transkripsjon, meeting chats | Microsoft 365 Copilot-lisens | Ja (opptil 5 meetings) |
+| **Copilot Connectors** | Eksterne systemer (ServiceNow, Salesforce, etc.) via Microsoft Graph | Microsoft 365 Copilot-lisens | Ubegrenset (klassisk: 2) |
+| **Teams Messages** | Chat-historikk, meeting transcripts, kanal-meldinger | Microsoft 365 Copilot-lisens | Opptil 5 chats |
+| **Teams Meetings** | Meeting metadata, transkripsjon, meeting chats | Microsoft 365 Copilot-lisens | Opptil 5 meetings |
 | **Outlook Email** | Brukerens mailbox (full eller delt) | Microsoft 365 Copilot-lisens | Ja (folder-basert) |
 | **People** | Org chart, profiler, skills, samarbeidshistorikk | Microsoft 365 Copilot-lisens | Nei |
 | **Embedded Files** | Opplastede filer (lagres i SharePoint Embedded) | Microsoft 365 Copilot-lisens eller metered usage | Nei |
-| **Web Search** | Bing-indeksert offentlig innhold | Ingen lisenskrav | Ja (opptil 4 URLer) |
-| **Dataverse** | Dynamics 365 / Power Apps-tabeller | Microsoft 365 Copilot-lisens eller metered usage | Ja (tabell-basert) |
+| **Web Search** | Bing-indeksert offentlig innhold | Ingen lisenskrav | Alle offentlige sider (klassisk: 4 URLer) |
+| **Dataverse** | Dynamics 365 / Power Apps-tabeller | Microsoft 365 Copilot-lisens eller metered usage | Ubegrenset (klassisk: 2 sources, 15 tabeller) |
+
+**Viktig om generativ modus (Verified):** Copilot Studio med generativ orchestration støtter IKKE Bing Custom Search eller Azure OpenAI som knowledge sources i generative answers node. Disse må eksplisitt legges til i en generative answers-node i et topic (klassisk data-alternativ).'
+
+

 ### Manifest-syntax for Knowledge Sources

@ -257,11 +261,15 @@ Denne guiden dekker arkitekturmønstre for grounding, beslutningskriterier for v
 ### SharePoint + Semantic Index (Anbefalt for GA-produksjon)

 Hvis tenant har **Microsoft 365 Copilot-lisens**, aktiver **Tenant graph grounding with semantic search** for:
- Støtte for filer opptil **200 MB** (standard: 512 MB for PDF/PPTX/DOCX)
+- Støtte for filer opptil **200 MB** i generell bruk (PDF/PPTX/DOCX støtter opptil 512 MB)
 - Bedre retrieval-kvalitet (bruker Microsoft Graph semantic index)
 - Raskere søk i store SharePoint-sites
+- Krever at agent bruker **Authenticate with Microsoft** (ikke andre auth-metoder)
+- Aktivert som standard for nye agenter med generativ orchestration

-**Trade-off:** Noe høyere latency for enkelte queries.
+**Trade-off:** Noe høyere latency for enkelte queries. Kan slås av per agent hvis kvaliteten er lavere enn forventet.
+
+**Innholdsstyring (Official sources):** Kunnskapskilder kan merkes som "official source" — agenten indikerer dette i svar. Merk: Per april 2026 er official sources-funksjonen ikke kompatibel med generativ orchestration (krever klassisk modus).

 ### Copilot Connectors vs Power Platform Connectors

@ -446,6 +454,6 @@ Tenant graph grounding krever **minst én Microsoft 365 Copilot-lisens** i tenan
 | Kostnad og lisensiering | **Verified** | MCP: knowledge-sources (license requirements table) |
 | Tenant Graph Grounding | **Verified** | MCP: knowledge-copilot-studio#tenant-graph-grounding |

-**Sist verifisert:** 2026-02-04
-**MCP-kall:** 6 (3 search, 2 fetch, 1 code sample search)
+**Sist verifisert:** 2026-04-10
+**MCP-kall:** 7 (3 search, 3 fetch, 1 code sample search)
 **Unike kilder:** 9 Microsoft Learn-dokumenter
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/m365-copilot-plugins-ecosystem.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/m365-copilot-plugins-ecosystem.md
@ -1,6 +1,6 @@
 # M365 Copilot Plugins - Ecosystem and Distribution

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -230,19 +230,33 @@ App Manifest (manifest.json)
 |----------|-------------|
 | **App permission policies** | Definer hvilke plugins som er tillatt per bruker-gruppe |
 | **App setup policies** | Pin plugins til Teams-appen for spesifikke brukere |
-| **App centric management** | (Fra april 2025) Forenklet org-wide app-management |
+| **App centric management** | GA (fra 2025) — forenklet org-wide app-management |
 | **Custom app upload** | Sideload plugins til organisasjonens app catalog |

 ### 3. Microsoft Partner Center (Microsoft 365 and Copilot Program)

 **Rolle:** Distribusjon til Microsoft Commercial Marketplace

-**Sertifiseringskrav:**
+**Sertifiseringskrav (viktige "Must fix"-krav):**
 - [Microsoft Commercial Marketplace certification policies](https://learn.microsoft.com/legal/marketplace/certification-policies)
 - [Microsoft 365 store validation guidelines for agents](https://learn.microsoft.com/microsoftteams/platform/concepts/deploy-and-publish/appsource/prepare/review-copilot-validation-guidelines)
 - [Responsible AI validation checks](https://learn.microsoft.com/microsoft-365-copilot/extensibility/rai-validation)
 - (Valgfri) [Microsoft 365 App Compliance Program certification](https://learn.microsoft.com/microsoft-365-app-certification/docs/certification)

+**Tekniske minstekrav (Must fix — ISV store submission):**
+
+| Krav | Verdi |
+|------|-------|
+| **Manifest-versjon** | 1.13 eller nyere |
+| **Responstid** | ≤9 sek (99%), ≤5 sek (75%), ≤2 sek (50%) |
+| **Tilgjengelighet** | 99.9% uptime |
+| **TLS** | 1.2 eller høyere (alle serverkall) |
+| **Prompt starters** | Minst 3 (declarative og custom engine agents) |
+| **Navn-konsistens** | `name` i manifest.json, declarativeAgent.json og plugin.json MÅ være identiske |
+| **Screenshot** | Minst 1 relatert til M365 Copilot-funksjonalitet |
+| **Action disclosure** | Bruker MÅ bekrefte konsekvente operasjoner (Create/Update/Delete) |
+| **MCP-servere** | `enable_dynamic_discovery` og `enable_dynamic_client_registration` MÅ settes til false |
+
 **Distribusjonsflyt:**
 1. ISV registrerer seg i Partner Center
 2. Laster opp app package (.zip med manifest + icons)
@ -432,4 +446,4 @@ Hvis plugin brukes til å fatte avgjørelser som påvirker individers rettighete
 - ✅ **Verified:** 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:** Januar 2026 (reflektert i MCP-kall 2026-02-04)
+**Siste oppdatering av Microsoft-dokumentasjon:** April 2026 (reflektert i MCP-kall 2026-04-10)
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/mcp-protocol-copilot-studio.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/mcp-protocol-copilot-studio.md
@ -1,6 +1,6 @@
 # Model Context Protocol (MCP) in Copilot Studio

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Generally Available (GA)
 **Category:** Copilot Extensibility & Integration

@ -161,10 +161,12 @@ Svar: "Du har 247 accounts."
 **Implementasjonsalternativer:**
 | Plattform | Språk | Bruksområde |
 |-----------|-------|-------------|
-| **Azure App Service** | Node.js, Python, .NET | Enterprise-skala hosting |
+| **Azure App Service** | Node.js, Python, Java, .NET | Enterprise-skala hosting; eksponerer eksisterende REST API-er som MCP tools |
 | **Azure Container Apps** | Docker | Managed identity-integrasjon |
 | **MCP SDK** | TypeScript, Python | Rask prototyping |

+**Azure App Service som MCP-server:** App Service har innebygd støtte for Microsoft Entra ID og managed identities for produksjonsklare MCP-servere. Eksisterende REST API-er kan eksponeres som AI-tilgjengelige tools uten å omskrive koden. Tutorials tilgjengelig for .NET, Java, Node.js og Python.
+
 **Konfidensmarkering:** Verified (Azure App Service MCP-dokumentasjon)

 ---
@ -422,7 +424,7 @@ Trenger du "write once, run anywhere" for flere agenter?
 **Microsoft Learn-dokumentasjon (Verified):**
 1. [Extend your agent with Model Context Protocol](https://learn.microsoft.com/en-us/microsoft-copilot-studio/agent-extend-action-mcp) — hovedartikkel om MCP i Copilot Studio
 2. [Connect your agent to an existing MCP server](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-existing-server-to-agent) — onboarding wizard og autentisering
-3. [Add tools and resources from MCP server](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-components-to-agent) — tool-konfigurasjon
+3. [Add tools and resources from MCP server](https://learn.microsoft.com/en-us/microsoft-copilot-studio/mcp-add-components-to-agent) — tool-konfigurasjon og selektiv tool-aktivering via "Allow all"-toggle
 4. [Connect to Dataverse with MCP](https://learn.microsoft.com/en-us/power-apps/maker/data-platform/data-platform-mcp-copilot-studio) — Dataverse MCP Server
 5. [Build plugins from MCP server for M365 Copilot](https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/build-mcp-plugins) — M365-integrasjon
 6. [App Service as MCP servers](https://learn.microsoft.com/en-us/azure/app-service/scenario-ai-model-context-protocol-server) — Azure hosting
@ -444,5 +446,5 @@ Trenger du "write once, run anywhere" for flere agenter?

 ---

-**Sist oppdatert:** 2026-02-04
-**Neste review:** 2026-05 (ved nye MCP-features i Copilot Studio)
+**Sist oppdatert:** 2026-04-10
+**Neste review:** 2026-07 (ved nye MCP-features i Copilot Studio)
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/power-automate-copilot-integration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/power-automate-copilot-integration.md
@ -1,6 +1,6 @@
 # Power Automate and Copilot Studio Integration

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -31,8 +31,9 @@ Agent flows er flows skapt og forvaltet direkte i Copilot Studio. De tilbyr en s
 | **Opprettelse** | Natural language (via Copilot) eller visuell designer |
 | **Triggers** | Instant (manuell), schedule-basert, eller event-drevet |
 | **Hovedtrigger** | "Run a flow from Copilot" — gjør flow tilgjengelig som tool i agenter |
-| **Actions** | AI-kapabiliteter (LLM), Human-in-the-loop, Built-in tools, Connectors (700+) |
-| **Fakturering** | Copilot Studio capacity per action (ikke Power Automate) |
+| **Actions** | AI-kapabiliteter (LLM, document processing, natural language reply), Human-in-the-loop, Built-in tools, Connectors (700+) |
+| **Fakturering** | Copilot Studio capacity per action (ikke Power Automate). Test i embedded chat er GRATIS. |
+| **Kapasitetsgrense** | Når prepaid Copilot Studio-kapasitet er oppbrukt, blokkeres nye flow-kjøringer (running flows fullfører normalt) |
 | **Solution-support** | Ja — inkluderer drafts, versioning, export/import |

 **Nøkkelfordeler:**
@ -43,7 +44,8 @@ Agent flows er flows skapt og forvaltet direkte i Copilot Studio. De tilbyr en s
 **Capacity-beregning:**
 - Flow fra topic: 1 **Classic answer** + agent flow actions
 - Flow fra generativ orkestrering: 1 **Autonomous action** + agent flow actions
- Test i embedded chat: kun agent flow actions (ikke meldinger)
+- Test i embedded chat (fra flow designer eller agentens test chat): **INGEN** capacity-forbruk
+- Microsoft 365 Copilot-lisensierte brukere og test-kjøringer påvirkes ikke av kapasitetsgrenser

 ### 2. Power Automate Cloud Flows

@ -536,7 +538,7 @@ Scenario: 100 brukere, 1000 flow runs/måned via Copilot Studio agent

 **Microsoft Learn dokumentasjon (Verified 2026-02):**

-1. **Agent flows overview**
+1. **Agent flows overview** (Re-verified MCP 2026-04)
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/flows-overview

 2. **Call an agent flow**
@ -568,4 +570,4 @@ Scenario: 100 brukere, 1000 flow runs/måned via Copilot Studio agent
 - Topic-based flow calling pattern
 - Approval workflow with Power Automate

-**Confidence level:** Verified — all information sourced from official Microsoft Learn documentation via microsoft-learn MCP server (2026-02).
+**Confidence level:** Verified — all information sourced from official Microsoft Learn documentation via microsoft-learn MCP server (2026-02, re-verified 2026-04).
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/sharepoint-copilot-agents.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/copilot-extensibility/sharepoint-copilot-agents.md
@ -1,6 +1,6 @@
 # SharePoint and OneDrive Copilot Agents

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04-10
 **Status:** GA
 **Category:** Copilot Extensibility & Integration

@ -33,7 +33,7 @@ SharePoint Copilot Agents bruker samme AI-fundamentet som Microsoft 365 Copilot
 | Modell | Beskrivelse | Tilgang |
 |--------|-------------|---------|
 | **Microsoft 365 Copilot license** | Full tilgang til SharePoint Copilot Agents + Microsoft 365 Copilot i alle apper. | Alle agenter er inkludert uten ekstra kostnad. |
-| **Pay-as-you-go billing** | Azure-basert betaling per query for brukere uten Copilot-lisens. | Krever Azure-ressurs og billing policy. |
+| **Pay-as-you-go billing** | Azure-basert betaling per query for brukere uten Copilot-lisens. | Krever Azure-ressurs og billing policy tilknyttet en sikkerhetsgruppe — kun brukere i gruppen får tilgang. |
 | **Trial promotion (6 måneder)** | 10 000 queries/måned gratis for unlicensed users. | Automatisk når pay-as-you-go er aktivert. |

 **Praktisk eksempel:**
@ -169,8 +169,9 @@ SharePoint Copilot Agents respekterer **eksisterende SharePoint-permissions og s
 ### SharePoint + Copilot Chat (M365 Copilot)

 - Agenter opprettet i SharePoint kan brukes i **Copilot Chat** hvis brukeren har M365 Copilot-lisens.
- Tenant admins kan **blokkere** spesifikke agenter fra Copilot Chat via **Copilot Control System** i M365 admin center.
- **Limitation**: Blocking påvirker kun Copilot Chat, ikke OneDrive/SharePoint/Teams (per feb 2026).
+- Tenant admins og AI-admins kan **blokkere** spesifikke agenter fra Copilot Chat via **Copilot Control System** i M365 admin center (under **Agents**-seksjonen).
+- **Limitation (Verified):** Blocking via admin center påvirker kun Copilot Chat — det gjelder IKKE for OneDrive, SharePoint eller Teams.
+- AI Admin er en ny, dedikert rolle for agent-administrasjon (less privileged enn Global Admin).

 ### SharePoint + OneDrive

@ -326,9 +327,9 @@ SharePoint Copilot Agents respekterer **eksisterende SharePoint-permissions og s

 ### Microsoft Learn-kilder (Verified)

-1. [Get started with agents in SharePoint](https://learn.microsoft.com/en-us/sharepoint/get-started-sharepoint-agents) — **Verified** (feb 2026)
-2. [Manage access to agents in SharePoint](https://learn.microsoft.com/en-us/sharepoint/manage-access-agents-in-sharepoint) — **Verified** (feb 2026)
-3. [Microsoft 365 Copilot agents admin guide](https://learn.microsoft.com/en-us/copilot/microsoft-365/agent-essentials/m365-agents-admin-guide) — **Verified** (feb 2026)
+1. [Get started with agents in SharePoint](https://learn.microsoft.com/en-us/sharepoint/get-started-sharepoint-agents) — **Verified** (apr 2026)
+2. [Manage access to agents in SharePoint](https://learn.microsoft.com/en-us/sharepoint/manage-access-agents-in-sharepoint) — **Verified** (apr 2026)
+3. [Microsoft 365 Copilot agents admin guide](https://learn.microsoft.com/en-us/copilot/microsoft-365/agent-essentials/m365-agents-admin-guide) — **Verified** (apr 2026)
 4. [Declarative agents for Microsoft 365 Copilot](https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/overview-declarative-agent) — **Verified** (feb 2026)
 5. [Publish agents for Microsoft 365 Copilot](https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/publish) — **Verified** (feb 2026)
 6. [Agent Builder in Microsoft 365 Copilot](https://learn.microsoft.com/en-us/microsoft-365-copilot/extensibility/agent-builder) — **Verified** (feb 2026)
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/copilot-studio.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/copilot-studio.md
@ -46,6 +46,22 @@ Agenter som kjører i bakgrunnen uten brukerinput:
 - Dataverse table updates
 - Dynamics 365 business events

+### Computer Use (Preview)
+
+**Status:** Preview (US-region, jan 2026+)
+
+Copilot Studio støtter nå Computer-Using Agents (CUA) — AI som kan interagere med Windows-applikasjoner og nettsider via virtuell mus og tastatur:
+
+- **Beskriv oppgaven med naturlig språk** — agenten utfører oppgaven automatisk
+- **Støttede modeller:** OpenAI Computer-Using Agent og Anthropic Claude Sonnet 4.5 (beta, feb 2026)
+- **Bruksscenarier:** Automatisk datainntasting, fakturabehandling, dataekstraksjon fra apper uten API
+- **Fakturering:** 5 Copilot Credits per steg i agentens kjøring
+- **Krav:** Generative orchestration aktivert; dedicated Windows-maskin (isolert)
+- **Sikkerhet:** Anbefalt bruk av dedikerte maskiner med minst mulig tilganger (principle of least privilege)
+
+**Use case:** Automatiser arbeidsoppgaver i legacy-applikasjoner uten REST API.
+
+
 ### 3. Declarative Agents for M365 Copilot
 Agenter som utvider Microsoft 365 Copilot:
 - Tilpasset kunnskap og skills
@ -557,6 +573,20 @@ Copilot Studio kan bruke **Bring Your Own Model** fra Azure AI Foundry for custo

 ---

+
+
+### Nyheter mars/april 2026
+
+| Feature | Status | Detaljer |
+|---------|--------|----------|
+| **Work IQ tools** | Preview | Koble M365 Copilot og agenter til Work IQ for sanntids arbeidsinnsikt (filer, e-post, møter, chatter) |
+| **Agent evaluations** | GA | Valider agentytelse med tilpassbare testsett |
+| **Multi-turn conversation tests** | GA | Test agenter mot realistiske dialogflyter |
+| **ChatGPT-5** | GA (globalt) | Tilgjengelig i produksjonsagenter (unntatt GCC) |
+| **Claude Sonnet/Opus modeller** | GA | Claude Sonnet 4.5, 4.6 og Opus globalt tilgjengelig for agenter |
+| **Bing Custom Search** | GA | Legg til scopet websøk som kunnskapskilde |
+| **Post-call action topics** | GA | Trigger backend-handlinger automatisk etter voice-samtale |
+
 ## For Cosmo: Beslutningsveiledning

 ### Når anbefale Copilot Studio
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/m365-copilot.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/m365-copilot.md
@ -24,10 +24,10 @@ Microsoft 365 Copilot er en AI-drevet produktivitetsassistent som integrerer sto
 |-----------------|-------------|-----------|
 | **Microsoft 365 Copilot** | AI-assistent i M365-apper, grounded i organisasjonsdata | Enterprise-brukere med lisens |
 | **Microsoft 365 Copilot Chat** | Gratis web-grounded chat inkludert i M365 | Alle med M365-abonnement |
-| **Copilot Studio** | Low-code plattform for å bygge agenter | Makers og utviklere |
+| **Copilot Studio** | Low-code plattform for å bygge agenter med generativ orchestration og multi-agent støtte (GA) | Makers og utviklere |
 | **Windows Copilot** | OS-integrert assistent | Forbrukere og bedrifter |
 | **GitHub Copilot** | Kode-assistent for utviklere | Utviklere |
-| **Security Copilot** | Sikkerhetsprofesjonelle verktøy (inkludert i M365 E5 fra nov 2025) | SOC-teams |
+| **Security Copilot** | Sikkerhetsprofesjonelle verktøy (inkludert i M365 E5 fra nov 2025; standalone og M365-integrert) | SOC-teams |

 **Viktig:** M365 Copilot ≠ Copilot Chat. Chat er gratis og web-grounded, M365 Copilot krever lisens og gir tilgang til organisasjonsdata.

--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/power-platform.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/platforms/power-platform.md
@ -345,6 +345,10 @@ Copilot Credits er den unified valutaen for all AI-funksjonalitet i Power Platfo
 | Agent action | 5 credits |
 | Tenant graph grounding | 10 credits |
 | Agent flow actions (per 100) | 13 credits |
+| AI tools (basic, per 10 resp) | 1 credit |
+| AI tools (standard, per 10 resp) | 15 credits |
+| AI tools (premium, per 10 resp) | 100 credits |
+| Content processing (per side) | 8 credits |

 ### Kjøpsalternativer

@ -413,11 +417,14 @@ Power Platform Admin Center som unified governance hub for agenter:
 3. **Managed operations** — Overvåking, alerting, lifecycle management
 4. **Managed availability** — Enterprise-grade pålitelighet

-**Governance-funksjoner:**
+**Governance-funksjoner (Wave 2, okt 2025–mars 2026):**
 - Environment groups og policyer
 - Advanced Connector Policies (ACP)
 - Tenant-wide inventory med agent-oversikt
 - Automatisering via admin connector, PowerShell, API
+- Enterprise scale administration med bulk-governance-verktøy
+- Granulær lisensinnsikt og kapasitetsovervåking
+- Proaktive security-kontroller for AI-agenter

 ### AI Builder Policies

@ -593,7 +600,7 @@ Adapted from Microsoft Learn documentation ([CC BY 4.0](https://creativecommons.
 - [Enhance AI-powered experiences with Dataverse search](https://learn.microsoft.com/power-platform/release-plan/2025wave1/data-platform/enhance-ai-powered-experiences-dataverse-search)
 - [Power Platform governance and administration 2025 Wave 1](https://learn.microsoft.com/power-platform/release-plan/2025wave1/power-platform-governance-administration/)
 - [Power Platform governance and administration 2025 Wave 2](https://learn.microsoft.com/power-platform/release-plan/2025wave2/power-platform-governance-administration/)
- [Billing rates and management — Copilot Credits](https://learn.microsoft.com/microsoft-copilot-studio/requirements-messages-management)
+- [Billing rates and management — Copilot Credits](https://learn.microsoft.com/microsoft-copilot-studio/requirements-messages-management) — Oppdatert april 2026: AI tools faktureres per 10 responses (basic=1, standard=15, premium=100 credits); agent flow enforcement gjelder per-miljø med 125%-terskel
 - [AI Builder licensing](https://learn.microsoft.com/en-us/ai-builder/administer-licensing)
 - Power Platform release plans 2025 Wave 1 and Wave 2

--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/error-handling-and-fallback-prompting.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/error-handling-and-fallback-prompting.md
@ -1,6 +1,6 @@
 # Error Handling and Fallback Prompting Strategies

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Prompt Engineering & LLM Optimization

@ -374,10 +374,20 @@ APIM kan enforces content safety checks automatisk:
 </policies>
 ```

+**Policy-attributter (Verified MCP 2026-04):**
+- `backend-id`: Azure AI Content Safety backend i APIM
+- `shield-prompt`: Sjekk for brukerangrep/adversarial prompts (true/false)
+- `enforce-on-completions`: Aktiver content safety på responser i tillegg til requests
+- `window-size`: Tegn per vindu for evaluering (maks 10 000 tegn, konfigurerbart for responser)
+- `output-type`: FourSeverityLevels (0,2,4,6) eller EightSeverityLevels (0-7)
+- Threshold 0 = mest restriktivt, 7 = minst restriktivt. Threshold 4 blokkerer nivå 4-7, tillater 0-3.
+- Støtter også `blocklists` for tilpassede ord/uttrykk
+
 **Fordeler:**
- Sentralisert content safety enforcement
- Automatisk blokkering av requester som matcher attack patterns
+- Sentralisert content safety enforcement på API-lag
+- Automatisk blokkering (HTTP 403) av requester som matcher attack patterns
 - Ingen endringer nødvendig i applikasjonskode
+- Fungerer for streaming responses (buffer-basert sliding window)

 ### Azure Monitor + Action Groups for Automated Healing

@ -680,7 +690,7 @@ User Request
 2. [Architecture strategies for self-preservation](https://learn.microsoft.com/en-us/azure/well-architected/reliability/self-preservation) – Azure Well-Architected Framework reliability-mønstre
 3. [Azure OpenAI Priority-Based Load Balancer (GitHub)](https://github.com/Azure-Samples/openai-aca-lb) – Referanseimplementasjon av smart load balancing
 4. [Troubleshooting Azure OpenAI On Your Data](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/on-your-data-best-practices) – Best practices for debugging og error handling
-5. [llm-content-safety policy (APIM)](https://learn.microsoft.com/en-us/azure/api-management/llm-content-safety-policy) – Content safety enforcement i API Management
+5. [llm-content-safety policy (APIM)](https://learn.microsoft.com/en-us/azure/api-management/llm-content-safety-policy) (Re-verified MCP 2026-04) – Content safety enforcement i API Management. Policy-attributter: backend-id, shield-prompt, enforce-on-completions, window-size, output-type, threshold (0-7), blocklists.

 **Sekundærkilder:**
 6. [Azure OpenAI FAQ](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/faq) – Vanlige feilsituasjoner og workarounds
@ -690,7 +700,7 @@ User Request
 **Verifisert:** Alle tekniske detaljer er hentet fra offisielle Microsoft-kilder (learn.microsoft.com, GitHub samples). Kodeeksempler er basert på offisielle SDK-dokumentasjon (januar 2026).

 **Confidence markers:**
- **Høy confidence:** HTTP error codes, SDK retry defaults, `Retry-After` header, content safety policies
+- **Høy confidence:** HTTP error codes, SDK retry defaults, `Retry-After` header, content safety policies (re-verified MCP 2026-04)
 - **Medium confidence:** Kostnadsestimater (prisene kan variere), spesifikke PTU-priser for norske kunder
 - **Lav confidence:** N/A – alle anbefalinger er basert på etablerte mønstre

--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/few-shot-learning-techniques.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/few-shot-learning-techniques.md
@ -1,6 +1,6 @@
 # Few-Shot and Zero-Shot Learning Techniques

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Prompt Engineering & LLM Optimization

@ -10,7 +10,7 @@

 Few-shot og zero-shot learning er grunnleggende teknikker i prompt engineering som endrer hvordan språkmodeller tilpasser seg nye oppgaver uten permanent modelltrening. Zero-shot learning utfører oppgaver basert kun på instruksjoner, mens few-shot learning bruker eksempler (input-output par) for å "prime" modellen til ønsket oppførsel. Begge teknikkene opererer via in-context learning — modellen endres ikke permanent, men eksemplene påvirker kun gjeldende inference. Disse metodene er sentrale for Azure OpenAI Service, Copilot Studio og Microsoft Agent Framework.

-**Verifikasjonsgrad:** Verified (MCP microsoft-learn, januar 2026)
+**Verifikasjonsgrad:** Verified (MCP microsoft-learn, januar 2026, re-verified april 2026)

 ---

@ -40,6 +40,10 @@ messages = [
 - Modellen "gjetter" ønsket format
 - Mindre pålitelig for domene-spesifikke oppgaver

+**To primære bruksområder for zero-shot (Verified .NET AI docs, MCP 2026-04):**
+1. **Fine-tunede LLM-er**: Fungerer godt med modeller som allerede er trent på instruksjonsdatasett
+2. **Etablere performance baselines**: Simuler reell brukeratferd → evaluer accuracy/precision → eksperimenter deretter med few-shot
+
 ### One-Shot Learning

 **Definisjon:** Én eksempel-par (input + output) i promptet.
@ -92,6 +96,15 @@ response = client.chat.completions.create(
 - Eksemplene "konditionerer" modellen for gjeldende inference
 - Demonstrerer edge cases og ønsket tone

+**To primære bruksområder for few-shot (Verified .NET AI docs, MCP 2026-04):**
+1. **Tuning av LLM**: Legger til kunnskap og kan forbedre performance. Produserer flere tokens enn zero-shot — kan bli kostbart.
+2. **Fikse performance-problemer**: Bruk zero-shot for baseline → eksperimenter med few-shot basert på svake punkter → iterer
+
+**Caveats (Verified .NET AI docs):**
+- Fungerer dårlig for komplekse resonneringsoppgaver — legg til instruksjoner for å motvirke dette
+- Lange few-shot prompts øker latency og kostnad; det er en grense for prompt-lengde
+- Med mange eksempler kan modellen lære falske mønstre (f.eks. "sentiment er dobbelt så ofte positivt som negativt")
+
 ---

 ## Arkitekturmønstre
@ -504,9 +517,9 @@ User Query
   - https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt
   - Seksjon: Few-shot learning with chat completion

-3. **Zero-shot and few-shot learning** (.NET)
+3. **Zero-shot and few-shot learning** (.NET AI conceptual) (Re-verified MCP 2026-04)
   - https://learn.microsoft.com/en-us/dotnet/ai/conceptual/zero-shot-learning
-   - Primære use cases, performance baselines
+   - Primære use cases, performance baselines, caveats (false patterns, token limits, reasoning gaps)

 4. **Chat Markup Language ChatML**
   - https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chat-markup-language
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/multimodal-prompt-design.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/multimodal-prompt-design.md
@ -1,6 +1,6 @@
 # Multimodal Prompt Design with Images and Text

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Prompt Engineering & LLM Optimization

@ -187,12 +187,20 @@ messages = [
 | Verbalization | Semantisk dybde, LLM-sitérbare beskrivelser | LLM-kall per bilde, høyere latency | Diagrammer, flowcharts, infografikk |
 | Direct embeddings | Rask, ingen LLM-kall ved indexing | Ingen forklaring av relasjoner | Visual similarity, produktsøk |

-**Azure AI Search multimodal pipeline:**
-1. Document extraction (Document Extraction / Layout / Content Understanding skill)
-2. Text chunking (Text Split skill)
-3. Image verbalization (GenAI Prompt skill + LLM)
-4. Embedding (Azure OpenAI / Foundry / Azure Vision)
-5. Knowledge store (for image storage og retrieval)
+**Azure AI Search multimodal pipeline (Verified MCP 2026-04):**
+1. **Content extraction** — velg mellom:
+   - Document Extraction skill: rask prototyping, PDF-støtte
+   - Document Layout skill: presise sidetall, bounding boxes, RAG-optimalisert
+   - Azure Content Understanding skill: avansert — cross-page tabeller, semantisk chunking, DOCX/XLSX/PPTX
+2. **Text chunking:** Text Split skill
+3. **Image verbalization:** GenAI Prompt skill + LLM (phi-4, gpt-4o, gpt-5) → naturlig-språklig beskrivelse
+4. **Embedding:** Azure OpenAI / Microsoft Foundry / Azure Vision multimodal embeddings
+5. **Knowledge store:** Lagrer bilder for retrieval; image-lokasjon lagres i indeks for sitert visning
+
+**To retrieval-stier:**
+- Verbalized content → hybrid queries (text + vector). Gir semantisk dybde og LLM-siterbare beskrivelser.
+- Direct multimodal embeddings (Azure Vision) → image-to-vector queries. Effektiv visual similarity uten LLM-kall ved indexing.
+- Mange løsninger kombinerer begge: forklaringsrike visuals verbaliseres, foto/produktbilder embeddes direkte.

 ## Beslutningsveiledning

@ -445,8 +453,12 @@ Multimodal scenario?
 ├─ Volum > 10k bilder/dag
 │  └─ Azure AI Search multimodal pipeline + Azure Vision embeddings
 │
-└─ Trengs søk over historiske bilder?
-   └─ Azure AI Search multimodal RAG (verbalization eller direct embeddings)
+├─ Trengs søk over historiske bilder?
+│  └─ Azure AI Search multimodal RAG (verbalization eller direct embeddings)
+│
+└─ RAG over PDF/Office-dokumenter med embedded diagrammer?
+   ├─ Forklaringsrike visuals: Document Layout skill + GenAI Prompt verbalization
+   └─ Visual similarity: Azure Content Understanding + Azure Vision embeddings
 ```

 ### Red Flags
@ -532,7 +544,7 @@ AzureDiagnostics
 **Microsoft Learn dokumentasjon (verifisert 2026-02):**
 - [Use vision-enabled chat models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/gpt-with-vision) — Offisiell how-to guide for GPT-4o/GPT-4 Turbo with Vision
 - [Image prompt engineering techniques](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/gpt-4-v-prompt-engineering) — Best practices for multimodal prompting
- [Multimodal search in Azure AI Search](https://learn.microsoft.com/en-us/azure/search/multimodal-search-overview) — RAG-arkitektur med image verbalization og direct embeddings
+- [Multimodal search in Azure AI Search](https://learn.microsoft.com/en-us/azure/search/multimodal-search-overview) (Re-verified MCP 2026-04) — RAG-arkitektur; extraction skill-sammenligning (Document Extraction vs Layout vs Content Understanding); verbalization vs direct embeddings; hybrid query-alternativ
 - [Azure OpenAI models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models) — Modelloversikt og token-kostnader
 - [Quickstart: Multimodal search in Azure portal](https://learn.microsoft.com/en-us/azure/search/search-get-started-portal-image-search) — Wizard-basert oppsett
 - [Get started with multimodal vision chat apps](https://learn.microsoft.com/en-us/azure/developer/ai/get-started-app-chat-vision) — End-to-end sample app med Base64 encoding
@ -547,5 +559,5 @@ AzureDiagnostics
 - ⚠️ **Medium confidence:** Kostberegninger i NOK (basert på jan 2026 pricing, kan variere)
 - ⚠️ **Medium confidence:** Offentlig sektor use cases (inferert fra generelle patterns, ikke Microsoft-spesifikt)

-**Sist verifisert:** 2026-02-04
-**Neste review:** 2026-04 (eller ved nye GPT-modeller)
+**Sist verifisert:** 2026-04-10
+**Neste review:** 2026-07 (eller ved nye GPT-modeller/AI Search features)
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/real-time-reasoning-performance.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/real-time-reasoning-performance.md
@ -1,6 +1,6 @@
 # Real-Time Reasoning and Performance Optimization

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Realtime API: Public Preview)
 **Category:** Prompt Engineering & LLM Optimization

@ -307,6 +307,25 @@ Deployment C: Chatbot (variabel prompt, medium output)
  - **Non-streaming:** End-to-end Request Time
  - **Streaming:** Time to Response (TTFT), Average Token Generation Rate

+### Azure Speech Service (TTS Latency)
+
+**Teknikker for å redusere speech synthesis latency (Verified MCP 2026-04):**
+
+| Teknikk | Effekt |
+|---------|--------|
+| **Streaming (AudioDataStream)** | Start avspilling ved første audio-chunk; ikke vent på komplett audio |
+| **Pre-connect** | Åpne WebSocket-forbindelsen proaktivt mens bruker snakker; kall `SpeakTextAsync` når svar er klart |
+| **Gjenbruk SpeechSynthesizer** | Unngå ny TCP/SSL/HTTP-handshake per request; bruk object pool |
+| **Komprimert lyd** | MP3 (48kbps) vs PCM (384kbps) — 87% lavere nettverkspayload for mobil/ustabile nettverk |
+| **Text streaming (WebSocket v2)** | Send GPT-output til TTS chunk for chunk via `wss://{region}.tts.speech.microsoft.com/cognitiveservices/websocket/v2`. Ideelt for real-time AI-dialoger. |
+
+**Latency-metrikker fra Speech SDK:**
+- `first byte client latency` — fra syntese starter til første audio-chunk mottas (inkl. nettverks-RTT)
+- `finish client latency` — fra syntese starter til all lyd er mottatt
+- `first byte service latency` — behandlingstid på Azure TTS-siden
+
+**Anbefaling:** For sanntids AI-dialoger (GPT + TTS), kombiner Realtime API (audio in/out) med Speech SDK text streaming for hybrid norsk/engelsk-løsninger.
+
 ### Copilot Studio

 **Relevans:** Copilot Studio kan integrere Azure OpenAI custom models via Power Platform connectors.
@ -477,9 +496,9 @@ Deployment C: Chatbot (variabel prompt, medium output)
   [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/realtime-audio-quickstart](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/realtime-audio-quickstart)
   Hentet: januar 2026. Kode-eksempler for Python, JavaScript, deployment steps.

-4. **Lower speech synthesis latency using Speech SDK**
+4. **Lower speech synthesis latency using Speech SDK** (Re-verified MCP 2026-04)
   [https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/how-to-lower-speech-synthesis-latency)
-   Hentet: januar 2026. Dekker text streaming for TTS (komplementær til Realtime API).
+   Hentet: januar 2026, re-verified april 2026. Dekker: first byte latency vs finish latency, streaming via AudioDataStream, pre-connect og SpeechSynthesizer-gjenbruk (object pool), komprimert lyd (MP3 48kbps vs PCM 384kbps), text streaming via WebSocket v2 (wss endpoint) for real-time GPT-output vocalization.

 **Verification steps:**

@ -487,6 +506,7 @@ Deployment C: Chatbot (variabel prompt, medium output)
 2. ✅ **Realtime API models:** Bekreftet at `gpt-4o-mini-realtime-preview` og `gpt-4o-realtime-preview` er tilgjengelige i East US 2 / Sweden Central.
 3. ✅ **VAD modes:** Bekreftet at `server_vad`, `semantic_vad`, og `none` er supported turn detection types.
 4. ✅ **Latency metrics:** Bekreftet at Time to Response (TTFT) og Average Token Generation Rate er recommended metrics for streaming.
+5. ✅ **Speech latency:** first byte client latency og AudioDataStream-streaming bekreftet. Text streaming via WebSocket v2 bekreftet for C#, Python.
 5. ⚠️ **Pricing:** Audio token pricing ikke eksplisitt i dokumentasjon per januar 2026. Brukt representative estimates basert på historisk OpenAI pricing structure.

 **Confidence level:** Høy (✅) for tekniske detaljer, Middels (⚠️) for pricing og production-readiness av Realtime API (public preview).
--- a/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/role-playing-and-persona-techniques.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-advisor/references/prompt-engineering/role-playing-and-persona-techniques.md
@ -1,6 +1,6 @@
 # Role-Playing and Persona-Based Prompting

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Prompt Engineering & LLM Optimization

@ -359,17 +359,22 @@ You are a friendly technical support specialist for [Product].
 5. ✅ Give **a way out** – "If unable, respond with 'not found'"
 6. ✅ Test and refine – Iterer basert på faktisk bruk

-**Prompt Node for Dynamic Personas:**
+**Prompt Node for Dynamic Personas (nlu-prompt-node, Verified 2026-04):**

-Bruk prompt nodes i topics for å endre persona mid-flow:
+Bruk prompt nodes i topics for å endre persona mid-flow. Legges til via "Add a tool" → "New prompt" i topic:

 ```yaml
-Node Type: Prompt
-Persona Override:
-  "For this specific question, act as a billing specialist.
-   Provide detailed information about payment terms and invoice procedures."
+Node Type: Prompt (Add a tool > New prompt)
+Best practices:
+  - Be specific: Klare instruksjoner gir forutsigbare svar
+  - Use examples: Illustrer forventet oppførsel
+  - Keep it brief: Lange instruksjoner → latency og timeouts
+  - Give a way out: "respond with not found if answer isn't present"
+  - Temperature: Kontroller kreativitet/determinisme per prompt
 ```

+Prompts kan også legges til på agent-nivå (Tools tab) eller som node i agent flows (AI capabilities → Run a prompt).
+
 ### Microsoft 365 Copilot (Enterprise)

 **Grounding prompts:**
@ -670,8 +675,8 @@ If uncertain, explain limitations.
 3. [Prompt engineering techniques - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering)
   *Bredere prompt-veiledning inkludert few-shot og token efficiency*

-4. [Use prompts in Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-prompt-node)
-   *Best practices for Copilot Studio prompt instructions*
+4. [Use prompts in Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/nlu-prompt-node) (Re-verified MCP 2026-04)
+   *Prompt editor features: natural language creation, template library, model selection (Azure OpenAI/Foundry), temperature, knowledge retrieval, code interpreter. Prompt-nivå: agent-tool, topic-node, agent flow-node.*

 5. [Azure OpenAI On Your Data - Best practices](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data)
   *System message bruk i RAG-scenarier*
@ -689,5 +694,5 @@ If uncertain, explain limitations.
 - ✅ **Documented best practices:** Authoring techniques tabeller
 - ⚠️ **Implementation-dependent:** Nøyaktig token cost varierer med model version

-**Siste oppdatering:** 2026-02-04
-**Neste review:** 2026-05 (når nye prompt engineering features annonseres på Build 2026)
+**Siste oppdatering:** 2026-04-10
+**Neste review:** 2026-07
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-365-governance-and-deployment.md
@ -22,12 +22,13 @@ Agent Registry er det sentrale administrasjonspunktet for alle agenter i organis

 | Komponent | Beskrivelse | Tilgang |
 |-----------|-------------|---------|
-| **Agent Inventory** | Full oversikt over Microsoft-bygde, partner-bygde og interne agenter | AI Admin, Global Admin, Global Reader (view-only) |
-| **Agent Details** | Metadata (capabilities, data sources, actions, sensitivity labels) | Per agent-basis |
+| **Agent Inventory** | Full oversikt over Microsoft-bygde, partner-bygde, user-shared og org-published agenter | AI Admin, Global Admin, Global Reader (view-only) |
+| **Agent Details** | Metadata (capabilities, data sources, actions, sensitivity labels, permissions-tab) | Per agent-basis |
 | **Security & Compliance** | Oversikt over sikkerhetsrisiko (Entra alerts), compliance gaps (Purview) | Integrert med Defender/Purview |
-| **Ownerless Agent Management** | Identifisering av agenter uten aktiv eier (f.eks. etter at bruker er slettet) | Real-time oppdatering |
+| **Ownerless Agent Management** | Identifisering av agenter uten aktiv eier. Dashboard viser total count, one-click filter, og real-time updates ved brukersletting. *(Verified MCP 2026-04)* | Real-time oppdatering |
+| **Risks Column** | Aggregerte high-severity risks fra Entra, Defender og Purview per agent. Kun tilgjengelig med **Microsoft 365 E7-lisens**. *(Verified MCP 2026-04)* | AI Admin, Global Reader |

-**Verified (Microsoft Learn, 2026-02)**
+**Verified (Microsoft Learn, 2026-04)**

 ### Agent Lifecycle Actions

@ -38,7 +39,7 @@ Administratorer har 11 lifecycle management actions tilgjengelig i Admin Center:
 | **Publish** | Gjør agent tilgjengelig for installasjon (krever AI Admin approval) | Kontrollert utrulling til spesifikke grupper |
 | **Activate** | Tillater brukere å installere agenten og opprette instanser | Selvbetjent agent-onboarding |
 | **Deploy** | Automatisk installasjon for brukere (ready-to-use) | Zero-touch deployment |
-| **Pin** | Fremhev agent i Copilot-interface (opptil 3 administrator-pinned agents) | Prioritering av business-kritiske agenter |
+| **Pin** | Fremhev agent i Copilot-interface (opptil 3 administrator-pinned agents per tenant; kun deployed agents kan pinnes; Researcher/Analyst kan ikke scopes — bruk Block for disse) *(Verified MCP 2026-04)* | Prioritering av business-kritiske agenter |
 | **Block** | Sperr tilgang for hele organisasjonen | Akutt sikkerhetsrespons |
 | **Remove** | Fjern fra tenant inventory (kan gjenopprettes fra store) | Midlertidig deaktivering |
 | **Delete** | Permanent sletting (inkludert SharePoint Embedded containers) | Irreversibel cleanup (24t propagation) |
@ -353,7 +354,7 @@ New-MgIdentityGovernanceLifecycleWorkflow -BodyParameter $params
 ## Kilder og verifisering

 ### Microsoft Learn (Verified, 2026-02)
- [Agent Registry i Microsoft 365 Admin Center](https://learn.microsoft.com/en-us/microsoft-365/admin/manage/agent-registry) – **Confidence: Verified**
+- [Agent Registry i Microsoft 365 Admin Center](https://learn.microsoft.com/en-us/microsoft-365/admin/manage/agent-registry) – **Confidence: Verified (2026-04)** — Oppdatert: Risks column (M365 E7), ownerless agent management, Researcher with Computer Use admin configuration, sensitivity labels for embedded files, GraphAPI for Agent Registry (preview)
 - [Microsoft 365 Copilot Agents Deployment Blueprint](https://learn.microsoft.com/en-us/copilot/microsoft-365/agent-essentials/m365-agents-blueprint) – **Confidence: Verified**
 - [Copilot Control System Management Controls](https://learn.microsoft.com/en-us/copilot/microsoft-365/copilot-control-system/management-controls) – **Confidence: Verified**
 - [Microsoft Entra Agent ID and Agent Identity Platform](https://learn.microsoft.com/en-us/microsoft-agent-365/admin/capabilities-entra) – **Confidence: Verified**
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-evaluation-testing-frameworks.md
@ -1,6 +1,6 @@
 # Agent Evaluation and Testing Frameworks

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Azure AI Evaluation SDK), Preview (Agent-specific evaluators)
 **Category:** Agent Orchestration & Automation

@ -276,6 +276,33 @@ evaluator = TaskAdherenceEvaluator(
 - **KQL queries:** Flexible querying av evaluation metrics over tid
 - **Alerts:** Sett opp alerts hvis pass rate dropper under threshold

+### MLflow 3 (Databricks / Cross-platform)
+
+MLflow 3 tilbyr komprehensiv GenAI-evaluering for agenter paa tvers av plattformer:
+
+| Feature | Beskrivelse |
+|---------|-------------|
+| **Built-in LLM judges** | Innebygde dommere for kvalitetsmetrikker (relevance, groundedness, safety, etc.) |
+| **Custom scorers** | Definer egne kvalitetsmetrikker med Python-funksjoner |
+| **Eval harness** | Test GenAI-app mot eval-datasett under utvikling; sammenlign appversjoner |
+| **Conversation evaluation** | Vurder multi-turn samtalekvaltiet (completeness, user frustration, dialogue coherence) |
+| **Conversation simulation** | Generer syntetiske multi-turn samtaler for testing |
+| **Production monitoring** | Kjoer scorers og judges paa produksjons-traces automatisk (Beta) |
+| **Review App** | Samle ekspertfeedback og bygg eval-datasett |
+
+MLflow Tracing gir real-time trace logging gjennom hele livssyklusen. Samme judges og scorers kan brukes i baade development og produksjon — konsistent evaluering.
+
+```python
+# MLflow 3 evaluation eksempel
+import mlflow
+
+results = mlflow.genai.evaluate(
+    data=eval_dataset,
+    predict_fn=my_agent,
+    scorers=[mlflow.genai.scorers.groundedness(), mlflow.genai.scorers.safety()]
+)
+```
+
 ### Prompt Flow

 - **Evaluation flows:** Custom evaluation logic som Prompt Flow (deprecated approach — bruk Azure AI Evaluation SDK i stedet)
@ -488,7 +515,7 @@ evaluator = TaskAdherenceEvaluator(

 9. **Evaluate and monitor AI agents (MLflow 3 on Databricks)**
   https://learn.microsoft.com/en-us/azure/databricks/mlflow3/genai/eval-monitor/
-   *Confidence: Verified* — MLflow-based evaluation for cross-platform agents
+   *Confidence: Verified* — MLflow 3 GenAI evaluation: built-in LLM judges og scorers, eval-harness for development, production monitoring (Beta), conversation evaluation (multi-turn), conversation simulation, Review App for human feedback, Genie Code for observability; integrert med MLflow Tracing paa tvers av development/test/produksjon; oppdatert 2026-04

 10. **Run automated tests for agent quality and reliability (Copilot Studio)**
    https://learn.microsoft.com/en-us/power-platform/release-plan/2025wave1/microsoft-copilot-studio/run-automated-tests-agent-quality-reliability
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-memory-and-context-management.md
@ -1,6 +1,6 @@
 # Agent Memory and Context Management Strategies

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Managed Memory in Foundry Agent Service: Preview)
 **Category:** Agent Orchestration & Automation

@ -189,9 +189,12 @@ var agent = new ChatClientAgent(
 ```

 **Azure Copilot BYOS (Bring Your Own Storage):**
- Organisations-kontrollert Cosmos DB instance
- Audit trail av alle samtaler
- Managed identity-basert tilgang
+- Organisasjonen velger og administrerer sin egen Azure Cosmos DB-instans
+- Full audit trail av alle Azure Copilot-samtaler (user prompts + Copilot responses) for alle tenant-brukere
+- System-assigned managed identity med `Cosmos DB Built-in Data Contributor`-rollen for sikker lese-/skrivetilgang
+- Aktiveres via Azure Copilot admin center → Conversation storage
+- **OBS:** Hvis BYOS aktiveres, mister brukere tilgang til samtaler lagret av Microsoft foer aktivering. Bytte av Cosmos DB-instans gir tilsvarende tap av tilgang til tidligere instans.
+- **OBS:** BYOS deaktiverer for oeyeblikket migration agent-kapabiliteter i Azure Copilot

 **Fordeler:**
 - Full data control og compliance
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-a2a-protocol.md
@ -1,6 +1,6 @@
 # Agent2Agent (A2A) Protocol — Åpen Standard for Agent-Interoperabilitet

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Preview (Microsoft-implementasjoner) / GA (protokollspesifikasjon v0.3)
 **Category:** Agent Orchestration & Automation

@ -210,6 +210,8 @@ A2A og MCP (Model Context Protocol) løser forskjellige problemer og er kompleme
 | **Transparens** | Intern logikk er ugjennomsiktig for kallende agent | Orkestrator ser og kontrollerer all verktøybruk |
 | **Beste for** | Agenter eid av forskjellige team/org, kompleks delegering | Enkelt, kontrollert tilgang til APIer og data |

+**A2A-melding inkluderer rik metadata:** Hver A2A-melding inneholder et unikt `contextId`, `messageId`, locale-info, full chat-historikk (ikke bare siste melding), og content parts (tekst, tool calls, etc.). Downstream agenter kan bruke denne metadata til routing, kontekst og kontinuitet.
+
 **Typisk kombinert bruk:**

 ```
@ -263,12 +265,24 @@ with AIProjectClient(endpoint=endpoint, credential=DefaultAzureCredential()) as

 Copilot Studio kan konsumere A2A-agenter direkte:

-1. Gå til **Agents** → **Add an agent** → **Connect to an external agent** → velg **Agent2Agent**
-2. Angi endepunkt-URL (ikke URL for agent card, men kommunikasjonsendepunktet)
-3. Copilot Studio henter automatisk navn og beskrivelse fra `/.well-known/agent.json`
-4. Velg autentiseringsmetode
+1. Gå til **Agents**-siden → **Add an agent** → **Connect to an external agent** → velg **Agent2Agent**
+2. Angi endepunkt-URL (kommunikasjonsendepunktet, IKKE URL for agent card)
+3. Copilot Studio henter automatisk navn og beskrivelse fra `/.well-known/agent.json` (standard well-known-URL). Hvis automatisk populering feiler, angi navn og beskrivelse manuelt
+4. Velg autentiseringsmetode: **None**, **API key**, eller **OAuth 2.0**
+5. Velg eller opprett connection, deretter **Add and configure**

-**Viktig:** Copilot Studio er ansvarlig for å vurdere datadeling, sikkerhet og compliance for tilkoblede eksterne agenter.
+**A2A vs HTTP connector — valg av integrasjonstype:**
+
+| Behov | Anbefalt |
+|-------|----------|
+| Agenter som er bygget på eksterne rammeverk | A2A |
+| Agenter hostet utenfor Copilot Studio | A2A |
+| Multi-turn interaksjoner med domenespesifikk resonnering | A2A |
+| Enkle API-kall eller HTTP-tjenester | Custom connectors |
+| MCP-verktøy og ressurser | MCP-servere |
+| Microsoft 365 Agents SDK-agenter | Activity Protocol |
+
+**Viktig:** Tilkobling til A2A-agenter utenfor Copilot Studio gir brukeransvar for datadeling, sikkerhet, compliance og kvalitetssikring.

 ### Semantic Kernel

@ -614,11 +628,11 @@ app.MapA2A(agent, "/a2a/my-agent", agentCard: new()

 3. **Copilot Studio — Connect A2A Agent**
   - https://learn.microsoft.com/microsoft-copilot-studio/add-agent-agent-to-agent
-   - Confidence: **Verified** (offisiell guide, februar 2026)
+   - Confidence: **Verified** (offisiell guide, oppdatert 2026-04: oppsettstrinn, autentiseringsalternativer, A2A vs HTTP connector-tabell)

 4. **Multi-agent Patterns — MCP vs A2A**
   - https://learn.microsoft.com/microsoft-copilot-studio/guidance/architecture/multi-agent-patterns
-   - Confidence: **Verified** (Copilot Studio arkitekturguide, februar 2026)
+   - Confidence: **Verified** (Copilot Studio arkitekturguide, oppdatert 2026-04: MCP vs A2A capability-matrise, hybrid workflow-anbefalinger, Agent 365 control plane)

 5. **Azure API Management — A2A Agent API**
   - https://learn.microsoft.com/azure/api-management/agent-to-agent-api
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/agent-to-agent-communication.md
@ -1,6 +1,6 @@
 # Agent-to-Agent Communication Protocols

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Agent Orchestration & Automation

@ -237,8 +237,14 @@ eventBus.Subscribe<AgentCompletedEvent>(async evt =>

 | Topologi | Beskrivelse | Use Case |
 |----------|-------------|----------|
-| **Broker Topology** | Agenter broadcaster events, andre agenter reagerer eller ignorerer | Dynamiske workflows, ingen sentral koordinering |
-| **Mediator Topology** | En mediator styrer event flow og state | Komplekse workflows med error handling og state management |
+| **Broker Topology** | Agenter broadcaster events, andre agenter reagerer eller ignorerer. Hoey dekobling, men mangler innebygd error handling og distributed transaction-stoette | Dynamiske workflows, ingen sentral koordinering |
+| **Mediator Topology** | En mediator styrer event flow og state, dispatcher commands til dedikerte kanaler. Bedre feilhaandtering og datakonsistens, men oekt kobling og potensielt bottleneck | Komplekse workflows med error handling og state management |
+
+**Event-driven utfordringer ved agent-kommunikasjon:**
+- **Eventual consistency:** Data paa tvers av agenter er ikke umiddelbart konsistent. Design for dette bevisst.
+- **Ordering:** Ved skalering kan events motttas i feil rekkefoelge. Bruk partisjonsnoekler og idempotent processing.
+- **Observability:** Inkluder correlation ID i alle events fra start — retrofit er vanskelig.
+- **Schema evolution:** Definer versjonsstrategi tidlig. Design consumers til aa haandtere ukjente event-versjoner.

 **Når brukes dette:**
 - Lang-levende workflows (timer/dager)
@ -538,7 +544,7 @@ Trenger dere agent discovery?

 4. **Event-Driven Architecture (Azure)**
   - https://learn.microsoft.com/en-us/azure/architecture/guide/architecture-styles/event-driven
-   - Confidence: **Verified** (Azure Architecture Center, 2024)
+   - Confidence: **Verified** (Azure Architecture Center, oppdatert 2026-04: broker vs mediator topology, eventual consistency, ordering, observability, schema evolution)

 5. **Azure Service Bus Integration**
   - https://learn.microsoft.com/en-us/dotnet/architecture/microservices/multi-container-microservice-net-applications/integration-event-based-microservice-communications
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/computer-using-agents-cua.md
@ -1,6 +1,6 @@
 # Computer-Using Agents (CUA)

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Preview (sep 2025 — Foundry Agent Service; mai 2025 — Copilot Studio)
 **Category:** Agent Orchestration & Automation

@ -109,12 +109,15 @@ Copilot Studio tilbyr CUA som et lavkode **Computer Use Tool** — ingen koding

 ### Oppsett

-1. Gå til **Tools** i agenten → **Add tool** → **Computer use**
-2. Velg modell: OpenAI Computer-Using Agent eller Anthropic Claude Sonnet 4.5
-3. Skriv instruksjoner på naturlig norsk/engelsk
+1. Gå til **Tools** i agenten → **Add tool** → **New tool** → **Computer use**
+2. Velg modell: **OpenAI Computer-Using Agent** eller **Anthropic Claude Sonnet 4.5** (preview, pågående regionutrulling — krever at administrator har aktivert external models)
+3. Skriv instruksjoner på naturlig norsk/engelsk (se "Best practices for instructions" under)
 4. Konfigurer **Machine** (hvor CUA kjøres):
-   - **Hosted browser** (Windows 365 for Agents) — rask start, kun web, ikke anbefalt for produksjon
-   - **Dedikert Windows-maskin** — gir full desktop-tilgang, anbefalt for produksjon
+   - Velg målmaskin fra listen, eller opprett ny via Power Automate Portal
+   - **Hosted browser**: rask start, kun web — ikke anbefalt for produksjon
+   - **Dedikert Windows-maskin**: gir full desktop-tilgang, anbefalt for produksjon
+
+**Merk:** Tilgangskontroll (access control) hindrer kun at modellen *utfører handlinger* på ikke-autoriserte nettsider/apper — ikke at de åpnes. Eksempel: Bing kan åpnes fra Edge-søkebaren selv om kun microsoft.com er på allowlisten, men interaksjon med Bing vil feile.

 ### Credentials og tilgangskontroll

@ -122,12 +125,13 @@ Copilot Studio tilbyr CUA som et lavkode **Computer Use Tool** — ingen koding
 |---------------|-------------|
 | **Maker-provided credentials** | Agenten bruker makerens innloggingsinfo (for autonome agenter) |
 | **End user credentials** | Brukeren logger inn selv (for konversasjonelle agenter) |
+| **Intern Power Platform-lagring** | Kryptert intern lagring — ingen forhåndskonfigurasjon nødvendig |
 | **Azure Key Vault** | Passord lagres i Key Vault — anbefalt for produksjonsmiljøer |
 | **Access control** | Begrens hvilke nettsider/applikasjoner CUA kan operere på |

 ### Lisensiering (Copilot Studio, preview)

-Faktureres som Agent action: **5 Copilot Credits per steg**.
+Faktureres som Agent action: **5 Copilot Credits per steg** (hvert steg kan inneholde én eller flere lavnivå-handlinger som klikk, skriving eller navigering).

 Eksempel — utfylling av timeregistreringsskjema (4 steg = 20 Copilot Credits):
 1. Åpne nettleser og naviger til URL
@ -481,7 +485,7 @@ Kostnader basert på:

 2. **Automate web and desktop apps with computer use — Copilot Studio**
   - https://learn.microsoft.com/microsoft-copilot-studio/computer-use
-   - Confidence: **Verified** (offisiell Copilot Studio preview-dokumentasjon, 2025)
+   - Confidence: **Verified** (offisiell Copilot Studio preview-dokumentasjon, oppdatert 2026-04: støttede modeller, credentials, access control-semantikk)

 3. **Configure where computer use runs**
   - https://learn.microsoft.com/microsoft-copilot-studio/configure-where-computer-use-runs
@ -497,7 +501,7 @@ Kostnader basert på:

 6. **FAQ for the computer use tool**
   - https://learn.microsoft.com/microsoft-copilot-studio/faqs-computer-use
-   - Confidence: **Verified** (offisiell FAQ, inkl. 80%/35% suksessrater)
+   - Confidence: **Verified** (offisiell FAQ, inkl. 80%/35% suksessrater, human supervision-detaljer, oppdatert 2026-04)

 7. **Computer Use Release Plan (2025 Wave 1)**
   - https://learn.microsoft.com/power-platform/release-plan/2025wave1/microsoft-copilot-studio/automate-web-desktop-apps-computer-use
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/foundry-workflows-visual-orchestration.md
@ -1,6 +1,6 @@
 # Foundry Workflows — Visuell Multi-Agent Orkestrering

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Public Preview (announced MS Ignite november 2025)
 **Category:** Agent Orchestration & Automation

@ -133,6 +133,8 @@ Human-in-the-loop er et førsteklasses konsept i Foundry Workflows. Workflowen *
  falsePath: return_for_revision
 ```

+**Agent Framework HITL (pro-code):** Bruk `RequestPort` (C#) eller `ctx.request_info()` (Python) for HITL i egendefinerte workflows. For agent orchestrations (sequential, concurrent, group chat): bruk `ToolApprovalRequestContent` — agenten kan markere tools som approval-required, workflow pauser og emitter `RequestInfoEvent`. Checkpoints bevarer pending requests ved gjenopptak.
+
 ### Detaljer: Loop-noden (For each)

 ```yaml
@ -598,7 +600,7 @@ Foundry Workflows' visuelle designer gir offentlig sektor-organisasjoner en unik

 5. **Declarative Workflows — Overview (Agent Framework)**
   - https://learn.microsoft.com/agent-framework/workflows/declarative
-   - Confidence: **Verified** (YAML patterns, looping, HITL, error handling)
+   - Confidence: **Verified** (YAML action types tabell: Variable Management, Control Flow, Agent/Tool Invocation, HITL, Conversation — C# og Python; oppdatert 2026-04)

 6. **Human-in-the-Loop Workflows**
   - https://learn.microsoft.com/agent-framework/workflows/human-in-the-loop
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/multi-agent-orchestration-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/multi-agent-orchestration-patterns.md
@ -1,6 +1,6 @@
 # Multi-Agent Orchestration Patterns and Topologies

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Agent Orchestration & Automation

@ -429,11 +429,24 @@ await Task.WhenAll(taskA, taskB); // Checkpoint ensures no replay
 - Anbefales for inter-platform orchestration

 **Multi-Agent Pattern Recommendations (Microsoft Copilot Studio):**
-1. Prefer platform-native orchestration for internal flows
-2. Use MCP for tool/data access (M365 services)
-3. Use A2A for cross-platform messaging
-4. Integrate mature agents via MCP or A2A
-5. Enforce policy/auditing via Agent 365 control plane
+1. Prefer platform-native orchestration for internal flows with subagents
+2. Use MCP for tool and data access (M365 services) — enterprise-grade security, authentication, auditing
+3. Use A2A for cross-platform agent-to-agent messaging — design for capability discovery and task contracts
+4. Integrate mature or abstracted agents via MCP or A2A for reuse and end-to-end traceability
+5. Enforce policy and auditing at control-plane layer with Agent 365
+6. Use least-privileged scope when calling MCP-hosted tools
+7. Design for parallelism, limit inter-agent context to strictly necessary, use short-term memory
+8. Include users in workflow — require human approvals for high-impact cross-agent actions
+
+**MCP vs A2A — nar bruke hva (oppdatert fra Copilot Studio multi-agent-patterns):**
+
+| Kapabilitet | MCP | A2A |
+|-------------|-----|-----|
+| Multimodalitet | Krever at MCP host stoetter det | Annonserer stoettede medietyper |
+| Multi-turn interaksjoner | Valgfri elicitation. Kontekst hos host | contextId haandterer kontekst paa tvers av agenter |
+| Orkestrering | Host orkestrerer hvilke tools som kalles | Invokert agent bruker sin egen chain-of-thought |
+| Forhandling | Krever klientoppdatering | Dynamisk forhandling, robust mot serviceoppdateringer |
+| Beste for | Full kontroll over resonnering, kontrollerte scenarios | Opake agenter, cross-org, ekstern agent |

 ### Semantic Kernel + Agent Framework

@ -638,7 +651,7 @@ scope.RecordOutputMessages(new[] { output });

 1. **AI agent orchestration patterns** (Azure Architecture Center)
   https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns
-   *Confidence: Verified* — Definitive guide til alle 5 patterns
+   *Confidence: Verified* — Definitive guide til alle 5 patterns, spektrum av kompleksitet (direct model call → single agent → multi-agent), oppdatert 2026-04

 2. **Microsoft Agent Framework Workflows Orchestrations**
   https://learn.microsoft.com/en-us/agent-framework/user-guide/workflows/orchestrations/overview
@ -658,7 +671,7 @@ scope.RecordOutputMessages(new[] { output });

 6. **Multi-agent patterns (Copilot Studio)**
   https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/architecture/multi-agent-patterns
-   *Confidence: Verified* — A2A protocol, MCP integration
+   *Confidence: Verified* — A2A protocol, MCP integration, capability matrise, hybrid workflow diagram, oppdatert 2026-04

 7. **Build agent platforms on Azure** (Microsoft for Startups)
   https://learn.microsoft.com/en-us/microsoft-for-startups/build/build-agent
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/semantic-kernel-agents-implementation.md
@ -1,6 +1,6 @@
 # Semantic Kernel and Microsoft Agent Framework - Implementation Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Agent Orchestration: Experimental)
 **Category:** Agent Orchestration & Automation

@ -235,6 +235,12 @@ Trenger du OpenAI Assistants API features (code interpreter, retrieval)?

 ### Velg Orchestration Pattern

+**Foer du velger multi-agent pattern:** Evaluer om scenariet faktisk krever det. Hvert kompleksitetsnivaa introduserer koordinerings-overhead, latens og kostnad. Bruk laveste kompleksitetsnivaa som tilfredsstillende loser problemet:
+
+1. **Direct model call** — klassifisering, oppsummering, oversettelse (ingen agent)
+2. **Single agent med tools** — varierte spoerringsmaal innen ett domene (ofte riktig default)
+3. **Multi-agent orchestration** — cross-domain, ulike sikkerhetsbegrensninger, eller oppgaver som drar nytte av parallell spesialisering
+
 | Scenario | Anbefalt Pattern | Hvorfor |
 |----------|------------------|---------|
 | Uavhengige subtasks | Concurrent | Parallell utførelse, redusert total tid |
@ -459,7 +465,7 @@ Kernel agentKernel = sharedKernel.Clone();  // Rebruk AI service connections
 5. [Microsoft Agent Framework Overview](https://learn.microsoft.com/en-us/agent-framework/overview/agent-framework-overview) — Confidence: Verified (2026-02)
 6. [Magentic Orchestration Pattern](https://learn.microsoft.com/en-us/agent-framework/user-guide/workflows/orchestrations/magentic) — Confidence: Verified (2026-02)
 7. [Microsoft 365 Agents SDK - Semantic Kernel Integration](https://learn.microsoft.com/en-us/microsoft-365/agents-sdk/using-semantic-kernel-agent-framework) — Confidence: Verified (2026-02)
-8. [AI Agent Orchestration Patterns (Azure Architecture)](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns) — Confidence: Verified (2026-02)
+8. [AI Agent Orchestration Patterns (Azure Architecture)](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns) — Confidence: Verified (oppdatert 2026-04: start med riktig kompleksitetsnivaa — direct model call, single agent med tools, multi-agent; guidance om naar multi-agent er hensiktsmessig)

 ### Kodeeksempler (Verified via MCP Code Search)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/agent-orchestration/tool-use-and-function-calling-patterns.md
@ -1,6 +1,6 @@
 # Tool Use and Function Calling - Advanced Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Agent Orchestration & Automation

@ -207,19 +207,35 @@ var result = await mainAgent.RunAsync("Hvordan er været i Oslo?");

 **Implementering (AG-UI + Agent Framework):**

-```python
-# AG-UI middleware for approval
-def approval_middleware(tool_call):
-    if tool_call.name in ["delete_record", "send_email"]:
-        user_response = input(f"Approve {tool_call.name}? (yes/no): ")
-        return user_response.lower() == "yes"
-    return True  # Auto-approve andre funksjoner
+AG-UI backend tool rendering stoetter HITL via to mekanismer:

-# Agent med approval-workflow
-agent = ChatAgent(chat_client=client, tools=[delete_record, send_email])
-# Koble approval_middleware til agent runtime
+**C# - ApprovalRequiredAIFunction:**
+```csharp
+// Tool som krever human approval
+var approvalTool = ApprovalRequiredAIFunction.Create(DeleteRecord);
+
+// Workflow emitter RequestInfoEvent med ToolApprovalRequestContent
+await foreach (var evt in workflow.WatchStreamAsync()) {
+    if (evt is RequestInfoEvent req && req.Data is ToolApprovalRequestContent tc) {
+        bool approved = await AskUserApproval(tc.ToolName);
+        await handle.SendResponseAsync(req.Request.CreateResponse(approved));
+    }
+}
 ```

+**Python - @tool med approval_mode:**
+```python
+@tool(approval_mode="always_require")
+def delete_record(record_id: str) -> str:
+    # Sletter en post - krever alltid menneskelig godkjenning
+    return db.delete(record_id)
+
+# Workflow pauser og emitter function_approval_request event
+# Klient-loop maa haandtere og respondere
+```
+
+**Backend tool events streames til klient i sanntid:** TOOL_CALL_START, TOOL_CALL_ARGS, TOOL_CALL_END, TOOL_CALL_RESULT.
+
 ---

 ## Beslutningsveiledning
@ -412,7 +428,7 @@ def update_citizen_record(ssn: str, field: str, value: str) -> str:
 1. [Azure OpenAI Function Calling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/function-calling) — **Verified 2026-02**
 2. [Semantic Kernel Agent Functions](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-functions) — **Verified 2026-02**
 3. [Agent Framework - Agent as Function Tool](https://learn.microsoft.com/en-us/agent-framework/tutorials/agents/agent-as-function-tool) — **Verified 2026-02**
-4. [AG-UI Backend Tool Rendering](https://learn.microsoft.com/en-us/agent-framework/integrations/ag-ui/backend-tool-rendering) — **Verified 2026-02**
+4. [AG-UI Backend Tool Rendering](https://learn.microsoft.com/en-us/agent-framework/integrations/ag-ui/backend-tool-rendering) — **Verified 2026-04** (backend tool streaming, ApprovalRequiredAIFunction C#, @tool(approval_mode) Python, TOOL_CALL_* events)
 5. [Azure OpenAI Assistants Function Calling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/assistant-functions) — **Verified 2026-02**
 6. [Structured Outputs](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/structured-outputs) — **Verified 2026-02**

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-api-best-practices.md
@ -1,6 +1,6 @@
 # Azure AI Services - API Design and Best Practices

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-enterprise-architecture.md
@ -1,5 +1,5 @@
 # Azure AI Services - Enterprise Architecture Patterns
-**Last updated:** 2026-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Azure AI Services (Foundry Tools)

@ -16,7 +16,7 @@ Azure AI Services (tidligere Cognitive Services) krever robuste enterprise-arkit
 - Network isolation og security perimeter
 - Kvotestyring og throttling-håndtering

-**Scope:** Dette dokumentet fokuserer på arkitekturmønstre for Azure OpenAI (del av Foundry Models), Azure AI Search, og støttetjenester som Azure API Management og Azure Front Door. Mønstrene gjelder både Foundry-baserte løsninger og standalone AI Services.
+**Scope:** Dette dokumentet fokuserer på arkitekturmønstre for Azure OpenAI (del av Foundry Models, tidligere "OpenAI in Azure" — nå konsolidert under Foundry Tools), Azure AI Search, og støttetjenester som Azure API Management og Azure Front Door. Mønstrene gjelder både Foundry-baserte løsninger og standalone AI Services.

 ---

@ -549,7 +549,7 @@ TOTAL: ~46 700 NOK/måned (høyere cost, men forutsigbar)
 3. [Baseline Foundry Chat Architecture (Foundry Agent Service + Microsoft Agent Framework)](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/architecture/baseline-microsoft-foundry-chat) — Verified (MCP 2026-04)
 4. [Azure API Management - AI Gateway Capabilities](https://learn.microsoft.com/en-us/azure/api-management/genai-gateway-capabilities)
 5. [Reliability in Azure AI Search](https://learn.microsoft.com/en-us/azure/reliability/reliability-ai-search)
-6. [Multi-Backend Gateway Guide](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend)
+6. [Multi-Backend Gateway Guide](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Verified MCP 2026-04: Dokumentet bekrefter fire gateway-topologier (single instance/multiple deployments, multi-instance same region/subscription, multi-instance multi-region). Tagger nå eksplisitt "Foundry Tools" og "Azure OpenAI in Foundry Models".
 7. [Load Balancing Options - Azure Architecture](https://learn.microsoft.com/en-us/azure/architecture/guide/technology-choices/load-balancing-overview)

 **GitHub Samples (Microsoft-verified):**
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-monitoring-logging.md
@ -1,6 +1,6 @@
 # Azure AI Services - Monitoring, Logging and Diagnostics

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-networking-security.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-networking-security.md
@ -1,7 +1,10 @@
 # Azure AI Services - Networking, Security and Private Endpoints

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
+
+> **Navngivning 2026-04:** Microsoft har omdøpt "Azure Cognitive Services" til **"Azure AI Foundry Tools"** (eller kortform "Foundry Tools") i dokumentasjonen. API-endepunkter, RBAC-roller og ARM-ressurstyper beholder "CognitiveServices" i identifikatoren. Alle nye dokumentasjonsreferanser bruker "Foundry Tools".
+
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/ai-services-vs-foundry-tools-selection.md
@ -1,6 +1,6 @@
 # Azure AI Services vs Foundry Tools - Platform Selection Guide

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-image-analysis.md
@ -1,6 +1,6 @@
 # Azure AI Vision - Image Analysis and Tagging

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Generally Available)
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/azure-ai-vision-ocr-processing.md
@ -1,7 +1,10 @@
 # Azure AI Vision - OCR and Document Processing

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
+
+> **Oppdatering 2026-04:** For OCR kombinert med semantisk analyse, bruk **Azure AI Content Understanding** (GA). Azure AI Vision OCR (Read API) er fortsatt det beste valget for ren tekst-ekstraksjon, men Content Understanding gir overlegent resultat for dokumenter der layout, tabeller og kontekstuell forståelse er viktig.
+
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/content-understanding-multimodal-analysis.md
@ -1,6 +1,6 @@
 # Content Understanding - Multimodal Analysis and Video Intelligence

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Preview (GA for core features, Limited Access for face description)
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/document-intelligence-prebuilt-models.md
@ -1,7 +1,10 @@
 # Document Intelligence - Prebuilt Models for Forms and Invoices

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
+
+> **Oppdatering 2026-04:** Azure AI Content Understanding er nå **fullt GA** og er anbefalt startpunkt for de fleste IDP-scenarier. Content Understanding dekker og utvider Document Intelligence-funksjonalitet med multimodal analyse. Velg Document Intelligence for spesifikke prebuilt-skjemaer (regnskap, ID-dokumenter, kvitteringer) der disse gir direkte verdi uten tilpasning. For generell dokumentanalyse og semantisk chunking — start med Content Understanding.
+
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-custom-text-classification.md
@ -1,7 +1,9 @@
 # Language Services - Custom Text Classification and NER

-**Last updated:** 2026-02
-**Status:** GA
+**Last updated:** 2026-04 | Verified: MCP 2026-04
+**Status:** GA — avvikles 31. mars 2029
+
+> **ADVARSEL — TJENESTE AVVIKLES:** Custom Text Classification og Custom Named Entity Recognition (NER) avvikles **31. mars 2029**. Migrer til Azure AI Foundry-modeller (prompt-basert klassifisering og NER med GPT-4o eller GPT-4.1). Se [migrasjonsveiledning](https://learn.microsoft.com/azure/ai-services/language-service/custom-text-classification/how-to/migrate-azure-openai) for detaljer.
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-question-answering.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-question-answering.md
@ -1,7 +1,9 @@
 # Language Services - Question Answering and Knowledge Mining

-**Last updated:** 2026-02
-**Status:** GA
+**Last updated:** 2026-04 | Verified: MCP 2026-04
+**Status:** GA — avvikles 31. mars 2029
+
+> **ADVARSEL — TJENESTE AVVIKLES:** Custom Question Answering (CQA) avvikles **31. mars 2029**. Migrer til Azure AI Foundry-baserte løsninger: Agentic Retrieval, Azure AI Search + GPT-4o RAG-pipeline, eller AI Foundry Knowledge Retrieval. Se [migrasjonsveiledning](https://learn.microsoft.com/azure/ai-services/language-service/question-answering/how-to/migrate-qnamaker-to-question-answering) for detaljer.
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/language-services-text-analytics.md
@ -1,7 +1,9 @@
 # Language Services - Text Analytics for Sentiment and Key Phrases

-**Last updated:** 2026-02
-**Status:** GA
+**Last updated:** 2026-04 | Verified: MCP 2026-04
+**Status:** GA (deler avvikles 2029-03-31)
+
+> **ADVARSEL — TJENESTER AVVIKLES (2029-03-31):** Sentiment Analysis, Opinion Mining og Custom Text Classification avvikles 31. mars 2029. Migrer til Azure AI Foundry-modeller. PII Detection, Key Phrase Extraction og Language Detection er ikke berørt.
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/speech-services-speech-to-text.md
@ -1,6 +1,6 @@
 # Speech Services - Speech-to-Text and Real-time Transcription

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/speech-services-text-to-speech.md
@ -1,7 +1,10 @@
 # Speech Services - Text-to-Speech and Neural Voices

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
+
+> **Status 2026-04:** Azure Neural TTS og Custom Neural Voice er begge bekreftet GA og aktivt vedlikeholdt. `nb-NO-PernilleNeural` og `nb-NO-FinnNeural` er de primære norske stemmene. Custom Neural Voice Pro tilbyr ytterligere tilpasning for enterprise-bruk.
+
 **Category:** Azure AI Services (Foundry Tools)

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/azure-ai-services/translator-document-translation.md
@ -1,6 +1,6 @@
 # Translator Service - Document Translation and Multi-language Support

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (General Availability) + Preview features
 **Category:** Azure AI Services (Foundry Tools)

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/data-engineering/microsoft-purview-governance.md
@ -231,9 +231,11 @@ Purview Data Owner Policies muliggjør sentralisert tilgangsstyring:

 ### Governance Domains og OKR-er

+Governance Domains er nå den sentrale organiseringsenhet for glossary terms i Unified Catalog. Workflow: opprett term (Draft) → rediger → publiser. Glossary terms kan flyttes mellom domains (begge domains krever Data Steward-rolle). Termer kan linkes til data products og critical data elements på tvers av domains. *(Verified MCP 2026-04)*
+
 ```
 Governance Domain: "AI og Maskinlæring"
-├── Glossary Terms
+├── Glossary Terms (Data Steward-rolle påkrevd)
 │   ├── "Treningsdata" -- Definisjon og bruksregler
 │   ├── "Feature Store" -- Standard for feature-lagring
 │   └── "Ground Truth" -- Krav til merkede datasett
@ -243,7 +245,7 @@ Governance Domain: "AI og Maskinlæring"
 ├── OKRs
 │   ├── "90% av AI-datasett klassifisert innen Q2"
 │   └── "100% lineage-dekning for ML-pipelines"
-└── Data Products
+└── Data Products (kan linkes til glossary terms)
    ├── "Customer 360 Feature Set"
    └── "Trafikkdata for ML"
 ```
@ -344,7 +346,7 @@ Microsoft Purview gir nå governance-dekning for Fabric Copilots og agenter —
 - [How to get lineage from Microsoft Fabric items into Microsoft Purview](https://learn.microsoft.com/en-us/purview/data-map-lineage-fabric) -- Lineage fra Fabric
 - [Data lineage in classic Data Catalog](https://learn.microsoft.com/en-us/purview/data-gov-classic-lineage) -- Lineage-konsepter
 - [Learn about sensitivity labels in Data Map](https://learn.microsoft.com/en-us/purview/data-map-sensitivity-labels) -- Sensitivitetsmerking
- [Create and manage glossary terms](https://learn.microsoft.com/en-us/purview/unified-catalog-glossary-terms-create-manage) -- Business glossary
+- [Create and manage glossary terms](https://learn.microsoft.com/en-us/purview/unified-catalog-glossary-terms-create-manage) -- Business glossary *(Verified MCP 2026-04)* — Ny funksjonalitet: bulk edit opptil 50 terms, flytt terms mellom governance domains, custom attributes med filter, Data Steward-rolle påkrevd for opprettelse. Terms opprettes i Draft state, må publiseres for å bli synlige. Governance domain MÅ publiseres FØR terms publiseres.
 - [Glossary terms in Unified Catalog](https://learn.microsoft.com/en-us/purview/unified-catalog-glossary-terms) -- Aktive glossary-termer
 - [Learn about Microsoft Purview Unified Catalog](https://learn.microsoft.com/en-us/purview/unified-catalog) -- Oversikt over Unified Catalog
 - [Set up data quality for Fabric Lakehouse data](https://learn.microsoft.com/en-us/purview/unified-catalog-data-quality-fabric-lakehouse) -- Datakvalitet for Fabric
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/ab-testing-llm-applications.md
@ -1,11 +1,14 @@
 # A/B Testing and Experimentation for AI Models

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 A/B-testing og eksperimentering er kritiske teknikker for å validere og optimalisere AI-modeller i produksjon. I motsetning til tradisjonell programvareutvikling, hvor funksjonalitet er binær (fungerer/fungerer ikke), er AI-modeller probabilistiske — ytelsen deres varierer med data, kontekst og bruksmønster. A/B-testing gjør det mulig å sammenligne modelversjoner, fine-tuning-strategier, prompt-varianter eller RAG-konfigurasjoner under reelle forhold, med ekte brukere og reell trafikk.
@ -438,3 +441,35 @@ Krever:
 - Shadow deployment patterns

 **Antall unike kilder:** 7 (Microsoft Learn) + 3 (baseline concepts) = **10 kilder**
+
+
+### A/B Testing with Azure ML Managed Online Endpoints + MLflow 3 (2026)
+
+**Traffic splitting via managed online endpoints**:
+```bash
+# Deploy challenger model with 10% traffic
+az ml online-deployment create --name challenger --endpoint my-endpoint
+az ml online-endpoint update --name my-endpoint --traffic control=90 challenger=10
+
+# Monitor with MLflow 3 scorers — same metrics for both variants
+# Use RelevanceToQuery, Correctness, custom business scorers
+```
+
+**MLflow 3 A/B evaluation pattern**:
+- Use `mlflow.genai.evaluate()` on traces from each variant
+- Compare scorers: `Correctness`, `RelevanceToQuery`, `ToolCallEfficiency`
+- Statistical significance: MLflow tracks Cohen's Kappa against human baseline
+- Aliases in Prompt Registry: `@control` and `@challenger` for prompt A/B testing
+
+**Azure ML safe rollout progression**:
+1. **Shadow testing**: Mirror X% of traffic to new model (no user impact)
+2. **Canary**: Route 10% live traffic, monitor bake time (hours/days)
+3. **Progressive**: 10% → 50% → 100% with health gate at each step
+4. **Rollback trigger**: Automatic halt on health signal degradation
+
+**Evaluation metrics for LLM A/B tests**:
+- Quality: Groundedness, Relevance, Correctness (MLflow judges)
+- Latency: P50, P90, P99 response times
+- Cost: Token usage per request
+- Business: Task completion rate, user satisfaction
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/azure-ml-pipelines-orchestration.md
@ -1,11 +1,14 @@
 # Azure ML Pipelines - Orchestration and Automation

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Azure Machine Learning pipelines representerer et komplett orkestreringsrammeverk for machine learning-arbeidsflyter. En pipeline automatiserer en komplett ML-oppgave ved å dele den inn i flere håndterbare steg (components), hvor hvert steg kan utvikles, optimaliseres, konfigureres og automatiseres uavhengig. Azure ML håndterer dependencies mellom steg automatisk, og legger til rette for parallellisering, caching og gjenbruk.
@ -18,6 +21,61 @@ Fra et kostnads- og effektivitetsperspektiv gir pipelines betydelige fordeler: d

 ### Pipeline Components (v2)

+
+### Azure ML Pipelines — Python SDK v2 (Tutorial 2026)
+
+**Key benefits**: Standardized MLOps, scalable team collaboration, training efficiency, cost reduction.
+
+**Pipeline creation pattern** (SDK v2):
+```python
+from azure.ai.ml import MLClient, dsl, Input, Output, command
+from azure.identity import DefaultAzureCredential
+
+ml_client = MLClient(DefaultAzureCredential(), subscription_id, resource_group, workspace)
+
+# 1. Create reusable components
+data_prep_component = command(
+    name="data_prep",
+    inputs={"data": Input(type="uri_folder"), "test_train_ratio": Input(type="number")},
+    outputs={"train_data": Output(type="uri_folder"), "test_data": Output(type="uri_folder")},
+    code="./components/data_prep",
+    command="python data_prep.py --data ${{inputs.data}} ...",
+    environment=f"{env.name}:{env.version}",
+)
+# Register for reuse
+ml_client.create_or_update(data_prep_component.component)
+
+# 2. Define pipeline with @dsl.pipeline decorator
+@dsl.pipeline(compute="serverless", description="E2E training pipeline")
+def training_pipeline(data_input, test_train_ratio, learning_rate, model_name):
+    prep_job = data_prep_component(data=data_input, test_train_ratio=test_train_ratio)
+    train_job = train_component(
+        train_data=prep_job.outputs.train_data,
+        test_data=prep_job.outputs.test_data,
+        learning_rate=learning_rate,
+        registered_model_name=model_name,
+    )
+
+# 3. Submit pipeline
+pipeline_job = ml_client.jobs.create_or_update(
+    training_pipeline(data_input=..., ...),
+    experiment_name="e2e_pipeline"
+)
+```
+
+**Component lifecycle**:
+1. Write YAML spec or create programmatically (`CommandComponent`)
+2. Register with name+version in workspace or registry
+3. Load and compose into pipeline
+4. Submit via `ml_client.jobs.create_or_update()`
+
+**Compute options**: `serverless` (recommended), named compute cluster, or per-step compute override.
+**Environment**: Curated environments (`azureml://registries/azureml/environments/sklearn-1.5/labels/latest`) or custom conda/Docker.
+**Output types**: `uri_folder` (data), `mlflow_model` (model), `uri_file` (file).
+
+**MLflow integration**: Use `mlflow.start_run()` in scripts for automatic experiment tracking (metrics, parameters, models).
+
+
 | Komponent-type | Beskrivelse | Bruksområde |
 |----------------|-------------|-------------|
 | **Command component** | Kjører et shell-script eller Python-script | Data prep, training, scoring, evaluation |
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/ci-cd-for-ml-models.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/ci-cd-for-ml-models.md
@ -1,6 +1,7 @@
 # CI/CD Pipelines for Machine Learning Models

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

@ -288,6 +289,34 @@ Disse signalene indikerer at din ML CI/CD ikke er production-ready:

 ### GitHub Actions Integration

+
+### GitHub Actions with Azure Machine Learning (2026 Update)
+The recommended authentication approach is **OpenID Connect (OIDC) with federated credentials** — eliminates long-lived secrets.
+
+**Workflow structure** (`/.github/workflows/`):
+```yaml
+permissions:
+  id-token: write
+jobs:
+  build:
+    steps:
+    - uses: azure/login@v2
+      with:
+        client-id: ${{ secrets.AZURE_CLIENT_ID }}
+        tenant-id: ${{ secrets.AZURE_TENANT_ID }}
+        subscription-id: ${{ secrets.AZURE_SUBSCRIPTION_ID }}
+    - run: az ml job create --file pipeline.yml
+```
+
+**MLOps v2 GitHub setup** (recommended end-to-end):
+1. Fork `Azure/mlops-v2-gha-demo` template repo
+2. Set GitHub secrets: `ARM_CLIENT_ID`, `ARM_CLIENT_SECRET`, `ARM_SUBSCRIPTION_ID`, `ARM_TENANT_ID`
+3. Deploy infrastructure via `tf-gha-deploy-infra.yml` workflow
+4. Run `deploy-model-training-pipeline` and `deploy-online-endpoint-pipeline` workflows
+
+**Pipeline stages**: Prepare Data → Train Model → Evaluate Model → Register Model → Deploy Endpoint
+
+
 **Setup:**
 - Opprett `.github/workflows/` directory i repo
 - Konfigurer GitHub Secrets for Azure credentials (eller OIDC)
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/data-drift-monitoring-detection.md
@ -1,11 +1,14 @@
 # Data Drift Monitoring and Detection

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Data drift er endringer i statistisk fordeling av modellinput-data over tid som kan føre til forringet modellprestasjon. For machine learning-modeller er kontinuerlig overvåking av data drift avgjørende for å opprettholde produksjonskvalitet. Azure Machine Learning tilbyr innebygd drift detection som sammenligner produksjonsdata mot baseline-datasett (typisk treningsdata eller nylig produksjonsdata) og beregner statistiske avstandsmål.
@ -363,3 +366,31 @@ Hvis kunden bruker legacy `DataDriftDetector` (azureml-datadrift SDK):

 **MCP Calls:** 5 (3 × microsoft_docs_search, 1 × microsoft_docs_fetch, 1 × microsoft_code_sample_search)
 **Unique Sources:** 12 Microsoft Learn URLs
+
+
+### Azure ML Model Monitoring — Data Drift Detection (2026)
+
+**Model monitoring signals** (out-of-box for online endpoints):
+
+| Signal | What it detects |
+|--------|----------------|
+| **Data quality** | Null values, out-of-range values, type mismatches in input features |
+| **Data drift** | Statistical distribution change: training data vs production data |
+| **Prediction drift** | Distribution shift in model output predictions |
+| **Feature attribution drift** | Changes in which features drive predictions |
+| **Custom signals** | User-defined metrics via Python scripts |
+
+**Setup options**:
+- **Out-of-box**: Automatically configured for Azure ML online endpoints (no configuration required)
+- **Advanced**: Custom monitoring for models deployed outside Azure ML (batch endpoints, external)
+- **Azure Event Grid integration**: Route monitoring alerts for automated response
+
+**Statistical methods used**:
+- Jensen-Shannon divergence for categorical features
+- Wasserstein distance (Earth Mover's Distance) for numerical features
+- Population Stability Index (PSI) for feature stability
+
+**Reference dataset**: Training dataset used as baseline; monitoring compares production distribution against it.
+
+**Alerting**: Configure thresholds per signal; integrate with Azure Monitor alerts and Action Groups.
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/feedback-loops-continuous-improvement.md
@ -4,6 +4,8 @@
 **Dato:** 2026-02-04
 **Confidence:** HIGH (basert på offisiell Microsoft-dokumentasjon)

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Feedback loops og kontinuerlig forbedring er kritiske komponenter i moderne AI-operasjoner. I motsetning til tradisjonell programvare, hvor funksjonalitet er deterministisk, kan AI-modeller vise kvalitetsdrift eller uventet oppførsel når de møter reelle data. Et velfungerende feedback-system sikrer at modeller forblir nøyaktige, relevante og trygge gjennom hele sin livssyklus.
@ -738,3 +740,32 @@ Dette dokumentet dekker hele feedback loop-syklusen for både classical ML og Ge
 5. **Kostnad:** Threshold-based retraining kan spare 50-70% compute vs daily retraining

 Bruk arkitekturmønstrene til å visualisere løsningen for kunden. Påpek at MLflow Tracing + Agent Evaluation gir "free" observability (built-in i Databricks).
+
+
+### MLflow 3 Evaluation & Feedback Loop (2026)
+
+MLflow 3 introduces a unified evaluation-monitoring lifecycle for GenAI feedback loops:
+
+**Iterative workflow**:
+1. **Trace** production requests (MLflow Tracing — end-to-end observability)
+2. **Evaluate** against scorers during development (`mlflow.genai.evaluate()`)
+3. **Monitor** production with same scorers (consistent quality measurement)
+4. **Gather human feedback** via Review App (expert annotations)
+5. **Improve** prompts/models based on evaluation datasets
+
+**Azure ML Model Monitoring signals**:
+- Data quality: null values, out-of-range, type mismatch
+- Data drift: statistical distribution changes between training and production data
+- Prediction drift: distribution shift in model outputs
+- Feature attribution drift: changes in feature importance
+- Custom signals: user-defined metrics via custom scripts
+
+**Monitoring setup**:
+```python
+# Set up out-of-box monitoring for Azure ML online endpoints
+# Monitors data drift, prediction drift automatically
+# Integrates with Azure Event Grid for alerting
+```
+
+**Continuous improvement cycle**: Production traces → MLflow evaluation datasets → Scorer alignment → Prompt/model update → A/B test → Production rollout
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/genaiops-llm-specific-practices.md
@ -1,6 +1,7 @@
 # GenAIOps - LLM-Specific MLOps Practices

 **Dato:** 2026-02-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Kategori:** MLOps & GenAIOps
 **Konfidensgrad:** Høy (basert på 18 MCP-kilder fra Microsoft Learn)

@ -10,252 +11,16 @@

 GenAIOps (Generative AI Operations), også kalt LLMOps, beskriver operasjonelle praksiser og strategier for håndtering av store språkmodeller (LLMs) i produksjon. Mens tradisjonell MLOps fokuserer på å trene og deploye diskriminative modeller, handler GenAIOps om å **velge, tilpasse, orkestrere og overvåke** eksisterende foundation models.

-### Forskjell mellom MLOps og GenAIOps

-| Dimensjon | Tradisjonell MLOps | GenAIOps (LLMOps) |
-|-----------|-------------------|-------------------|
-| **Primært fokus** | Trene nye modeller fra scratch | Konsumere og fine-tune eksisterende foundation models |
-| **Artefakter** | Trainede modeller (pkl, ONNX) | Prompts, orchestrators, agents, chains, grounding data |
-| **Evaluering** | Accuracy, precision, recall (deterministiske) | Groundedness, relevance, coherence, fluency (LLM-as-judge) |
-| **Infrastruktur** | Modell-serving endepunkter | Orchestrators, vector stores, API gateways, LLM endpoints |
-| **Deployment** | Modellversjonering | Modell + prompt + grounding data + orchestrator |
-| **Monitoring** | Model drift, data drift | Data drift + prompt effectiveness + content safety + token usage |

-**Konfidensgrad:** 95% — Microsoft dokumentasjon definerer eksplisitt disse forskjellene.
+### MLflow 3 Tracing — GenAI Observability
+MLflow Tracing provides end-to-end observability for GenAI applications:
+- Records inputs, outputs, intermediate steps, and metadata
+- Supports complex agent-based systems and multi-turn conversations
+- Integrates with Genie Code for natural language trace analysis
+- Enables: debugging, performance monitoring, cost optimization, auditability
+- Production monitoring reuses same scorers as development evaluation (consistent lifecycle)

---
-
-## Kjernekomponenter
-
-### 1. Prompt Engineering og Prompt Registry
-
-**Hva:** Strukturert håndtering av system- og user prompts som versjonerte artefakter.
-
-**Hvorfor:** Prompts er den primære "koden" i GenAI-løsninger. Endringer i prompts påvirker output like mye som kodeendringer.
-
-**Hvordan (Azure):**
- **MLflow Prompt Registry** (Databricks): Versjonert prompt-håndtering med aliaser (f.eks. `production`, `staging`)
- **Azure AI Foundry Prompt Flow**: Visuell prompt designer med versjonering og CI/CD-integrasjon
- **Semantic Kernel Prompt Functions**: Prompts som code-artefakter i `.txt`-filer med Handlebars-syntax
-
-```python
-# MLflow Prompt Registry eksempel
-import mlflow
-
-prompt = mlflow.genai.register_prompt(
-    name="mycatalog.myschema.customer_support",
-    template="You are a helpful assistant. Answer this question: {{question}}",
-    commit_message="Initial customer support prompt"
-)
-
-mlflow.genai.set_prompt_alias(
-    name="mycatalog.myschema.customer_support",
-    alias="production",
-    version=1
-)
-
-# I applikasjon
-prompt = mlflow.genai.load_prompt(
-    name_or_uri="prompts:/mycatalog.myschema.customer_support@production"
-)
-response = llm.invoke(prompt.format(question="How do I reset my password?"))
-```
-
-**Konfidensgrad:** 90% — Prompt Registry er dokumentert, men adoption rates varierer.
-
-### 2. Orchestration Layer
-
-**Hva:** Systemet som håndterer logikk, kaller datakilder/agenter, genererer prompts og kaller LLM-modeller.
-
-**Hvorfor:** Generative AI-løsninger er ikke bare modellen — de er komplekse workflows som krever orkestrering.
-
-**Microsoft-alternativer:**
- **Azure AI Foundry Agent Service**: Low-code agent-orkestrering
- **Microsoft Agent Framework SDK (Semantic Kernel)**: Code-first orkestrering med C#/Python
- **Prompt Flow**: Visuell workflow-designer for LLM-chains
- **LangChain/LlamaIndex**: Open source (støttes av Azure ML)
-
-**Deployment:**
- Azure App Service (containerized orchestrator)
- Azure Container Apps (serverless orchestrator)
- Azure Kubernetes Service (high-scale orchestrator)
- Azure Machine Learning Managed Online Endpoints
-
-**Konfidensgrad:** 85% — Mange deployment-alternativer, best practice varierer med use case.
-
-### 3. Vector Stores og Grounding Data
-
-**Hva:** Datalagringsløsninger for RAG (Retrieval-Augmented Generation) som støtter vektor-søk.
-
-**Azure-alternativer:**
- **Azure AI Search**: Hybrid search (full-text + vector + semantic)
- **Azure Cosmos DB for MongoDB vCore**: Vector search capabilities
- **Azure Database for PostgreSQL (pgvector)**: Open source vector extension
- **Databricks Vector Search**: Delta table-basert, auto-syncing
-
-**DataOps-utvidelser for GenAIOps:**
- **Chunking pipelines**: Split dokumenter i semantisk meningsfulle chunks (Azure Machine Learning pipelines)
- **Embedding generation**: Batch-generering av embeddings (Azure OpenAI text-embedding-ada-002 / text-embedding-3-small)
- **Index maintenance**: Incremental updates vs. full rebuilds (compliance: right-to-be-forgotten)
- **Data freshness**: Real-time vs. batch refresh (business requirements)
-
-**Konfidensgrad:** 90% — Dokumentert arkitektur, men chunking-strategier er eksperimentelle.
-
-### 4. Evaluation Framework
-
-**Hva:** LLM-spesifikke evalueringsmetrikker og human-in-the-loop feedback.
-
-**Azure AI Foundry Evaluation SDK:**
-```python
-from azure.ai.evaluation import evaluate, RelevanceEvaluator, CoherenceEvaluator
-
-model_config = {
-    "azure_endpoint": os.environ.get("AZURE_OPENAI_ENDPOINT"),
-    "api_key": os.environ.get("AZURE_OPENAI_KEY"),
-    "azure_deployment": os.environ.get("AZURE_OPENAI_DEPLOYMENT"),
-}
-
-result = evaluate(
-    data="test_data.jsonl",
-    evaluators={
-        "relevance": RelevanceEvaluator(model_config=model_config),
-        "coherence": CoherenceEvaluator(model_config=model_config),
-    },
-    evaluator_config={
-        "relevance": {
-            "column_mapping": {
-                "query": "${data.query}",
-                "ground_truth": "${data.ground_truth}",
-                "response": "${outputs.response}"
-            }
-        }
-    },
-    azure_ai_project=azure_ai_project,
-    output_path="./evaluation_results.json"
-)
-```
-
-**Evaluerings-dimensjoner:**
-| Use case | Metrikker |
-|----------|-----------|
-| **RAG** | Groundedness, relevance, coherence, fluency |
-| **Summarization** | ROUGE, BLEU, BERTScore, METEOR |
-| **Translation** | BLEU |
-| **Classification** | Precision, recall, accuracy, F1 |
-| **Content Safety** | Hate/violence/sexual/self-harm scores (Azure AI Content Safety) |
-
-**Human Feedback Loop:**
- **Mosaic AI Agent Framework Review App** (Databricks): UI for human reviewers
- **Application Insights**: Thumbs up/down fra sluttbrukere
- **Custom feedback APIs**: Integrasjon i enterprise workflows
-
-**Konfidensgrad:** 95% — Built-in evaluators er godt dokumentert.
-
-### 5. CI/CD for GenAIOps
-
-**GenAIOps Prompt Flow Template** (Microsoft-anbefalt):
- **Repository**: [microsoft/genaiops-promptflow-template](https://github.com/microsoft/genaiops-promptflow-template)
- **CI/CD**: GitHub Actions eller Azure DevOps Pipelines
- **Lifecycle**: Feature branch → PR → Dev → Staging → Production
-
-**Pipeline-faser:**
-1. **PR Pipeline** (CI):
-   - Flow validation
-   - Unit testing av custom Python code
-   - Variant experimentation
-   - Evaluation runs mot test data
-2. **Dev Pipeline** (CI + CD):
-   - Batch testing
-   - Model/prompt registration (conditional)
-   - Human-in-the-loop approval gate
-   - Deployment til dev/staging endpoints
-3. **Production Pipeline** (CD):
-   - Blue-green deployment
-   - A/B testing (traffic splitting)
-   - Canary deployment
-   - Rollback capabilities
-
-**Azure DevOps-integrasjon:**
-```yaml
-# Eksempel: Prompt Flow evaluation i Azure Pipelines
- task: AzureCLI@2
-  displayName: 'Run Prompt Flow Evaluation'
-  inputs:
-    azureSubscription: 'AzureML-ServiceConnection'
-    scriptType: 'bash'
-    scriptLocation: 'inlineScript'
-    inlineScript: |
-      az ml job create --file evaluation-job.yaml \
-        --workspace-name $(ML_WORKSPACE) \
-        --resource-group $(RESOURCE_GROUP)
-```
-
-**Konfidensgrad:** 85% — Template er aktiv (2025), men requires customization.
-
-### 6. Monitoring og Observability
-
-**LLM-spesifikke overvåkningsdimensjoner:**
-
-| Dimensjon | Hva overvåkes | Azure-verktøy |
-|-----------|---------------|---------------|
-| **Operational** | Latency, token usage, 429 errors, endpoint availability | Azure Monitor, Application Insights |
-| **Quality** | Groundedness, relevance, coherence, fluency (sampled) | Azure Machine Learning Model Monitoring (Generation Quality Signal) |
-| **Safety** | Harmful content detection (hate, violence, sexual, self-harm) | Azure AI Content Safety (real-time filtering) |
-| **Cost** | Token consumption per user/session, quota utilization | Azure Cost Management, API Management gateway logs |
-| **Data drift** | Changes in user query patterns, grounding data staleness | Azure ML Data Drift monitors |
-| **Feedback** | User ratings (thumbs up/down), session abandonment rate | Custom telemetry (Application Insights) |
-
-**MLflow Tracing for GenAI:**
-```python
-import mlflow
-
-# Automatisk tracing av OpenAI calls
-mlflow.openai.autolog()
-
-# Custom trace decorators
-@mlflow.trace
-def my_rag_app(query: str):
-    context = retrieve_from_vector_store(query)
-    prompt = format_prompt(query, context)
-    response = llm.invoke(prompt)
-    return response
-```
-
-**Azure AI Foundry Monitoring (SDK v2):**
-```python
-from azure.ai.ml.entities import (
-    MonitorSchedule, GenerationSafetyQualitySignal,
-    GenerationTokenStatisticsSignal
-)
-
-# Quality monitoring
-gsq_signal = GenerationSafetyQualitySignal(
-    connection_id=aoai_connection_id,
-    metric_thresholds={
-        "groundedness": {"aggregated_groundedness_pass_rate": 0.7},
-        "relevance": {"aggregated_relevance_pass_rate": 0.7},
-    },
-    production_data=[production_data],
-    sampling_rate=1.0
-)
-
-# Token monitoring
-token_signal = GenerationTokenStatisticsSignal()
-
-monitor = MonitorSchedule(
-    name="genai-monitor",
-    trigger=CronTrigger(expression="15 10 * * *"),
-    create_monitor=MonitorDefinition(
-        monitoring_signals={"quality": gsq_signal, "tokens": token_signal}
-    )
-)
-```
-
-**Konfidensgrad:** 90% — Monitoring capabilities er dokumentert, men sampling rates må justeres for cost.
-
---
-
-## Arkitekturmønstre

 ### 1. Fine-Tuning Pattern

--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/inferencing-optimization-caching.md
@ -4,6 +4,8 @@
 **Dato:** 2026-02-04
 **Forfattet av:** Cosmo Skyberg, Senior Microsoft AI Solution Architect

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Inferencing optimization og caching representerer kritiske teknikker for å maksimere ytelse og minimere kostnader når AI-modeller skal serve prediksjoner i produksjon. Mens model training handler om å oppnå høy accuracy, handler inferencing om å levere disse prediksjonene raskt, pålitelig og kostnadseffektivt til brukere og systemer.
@ -1011,3 +1013,36 @@ Diagnostikk:
 - Monitor **cache hit rate** og **autoscaling metrics** kontinuerlig

 **Confidence nivå: HIGH** — Denne referansen er basert på 12 MCP-kall til offisiell Microsoft-dokumentasjon og kodeeksempler.
+
+
+### ONNX Inferencing Optimization for Computer Vision (Azure ML AutoML 2026)
+
+ONNX (Open Neural Network Exchange) enables cross-framework interoperability and inference optimization:
+
+**Supported AutoML computer vision tasks**:
+- Image classification (binary and multi-class)
+- Object detection
+- Instance segmentation
+
+**ONNX inference workflow**:
+1. Download ONNX model files from AutoML training run
+2. Understand model inputs/outputs (image format requirements)
+3. Preprocess data to required input format
+4. Run inference with ONNX Runtime Python API (`onnxruntime`)
+5. Post-process predictions (bounding boxes for detection, masks for segmentation)
+
+**Python ONNX Runtime**:
+```python
+import onnxruntime as rt
+sess = rt.InferenceSession("model.onnx")
+# Works across languages: Python, C++, C#, Java, JavaScript
+```
+
+**Cross-platform benefits**:
+- Deploy on any platform without framework dependencies
+- Reduced inference latency vs Python framework
+- Edge deployment: Azure IoT Edge, on-premises
+- Language flexibility post-export
+
+**SDK**: `azure-ai-ml v2 (current)` — use AutoML image tasks to generate ONNX models automatically
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/infrastructure-as-code-mlops.md
@ -4,6 +4,8 @@
 **Kategori:** MLOps & GenAIOps
 **Forfatter:** Cosmo Skyberg, Senior Microsoft AI Solution Architect

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Infrastructure as Code (IaC) er en fundamental MLOps-praksis der infrastruktur defineres og deployes gjennom kode fremfor manuelle konfigurasjoner. Dette er kritisk viktig for AI/ML-prosjekter fordi det sikrer reproducerbarhet, konsistens og versjonskontroll av hele ML-miljøet — fra development til production.
@ -539,6 +541,42 @@ resource mlWorkspace 'Microsoft.MachineLearningServices/workspaces@2024-01-01-pr

 ### IaC-verktøy kostnader

+
+### IaC Design for MLOps — Azure Well-Architected (OE:05) 2026
+
+**Core principle** (Well-Architected OE:05): Standardized IaC approach with declarative syntax, consistent styles, appropriate modularization, quality assurance.
+
+**Declarative over imperative** (recommended):
+- Bicep / ARM templates: Azure-native, JSON/DSL declarative
+- Terraform: Industry-standard, multi-cloud declarative
+- Avoid: imperative scripts for infrastructure state management
+
+**Azure-native tools**:
+```bash
+# Bicep — deploy Azure ML workspace
+az deployment group create --template-file ml-workspace.bicep
+
+# Terraform — integrated into GitHub Actions / Azure Pipelines
+terraform init && terraform apply
+```
+
+**Layered IaC pipeline approach for MLOps**:
+- **Low-touch** (networking, VNet, ACR): Rarely changes, stable baseline
+- **Medium-touch** (compute clusters, storage, AKS): Occasional changes
+- **High-touch** (model endpoints, deployments): Continuous delivery
+
+**IaC best practices**:
+- Treat IaC artifacts the same as application code (version control, PR reviews, testing)
+- Use parameters/variables for multi-environment support (dev/test/prod)
+- Collocate IaC with application code for synchronized deployments
+- Scan IaC repos for secrets (Microsoft Defender for Cloud: IaC vulnerability scanning)
+- Immutable infrastructure preferred for business-critical workloads
+
+**AI opportunity** (2026): AI tools (GitHub Copilot) can review IaC templates, identify misconfigurations, suggest security improvements, and generate templates from natural language.
+
+**MLOps v2 infrastructure**: `tf-gha-deploy-infra.yml` workflow in `Azure/mlops-v2-gha-demo` deploys full Azure ML infrastructure via Terraform + GitHub Actions.
+
+
 | Verktøy | Lisens | Kostnad |
 |---------|--------|---------|
 | **Bicep** | Open source (MIT) | Gratis |
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/llm-evaluation-production.md
@ -6,6 +6,8 @@

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 LLM-evaluering i produksjonsmiljø er fundamentalt forskjellig fra tradisjonell ML-evaluering. Mens klassiske ML-modeller evalueres med deterministiske metrikker på statiske test-sett, krever generative AI-applikasjoner kontinuerlig evaluering av åpne, ikke-deterministiske output i dynamiske produksjonsscenarioer.
@ -558,6 +560,38 @@ project = AIProjectClient.from_connection_string(

 ### MLflow 3 + Databricks Unity Catalog

+
+### MLflow 3 LLM Evaluation Framework (2026)
+
+MLflow 3 (SDK `mlflow[databricks]>=3.1`) introduces a unified evaluation model:
+
+**Core architecture**: Traces → Scorers → Feedback
+- Traces from `mlflow.genai.evaluate()` or production monitoring service
+- Scorers parse traces, assess quality, return `Feedback` objects
+- Same scorers used in development AND production (consistent lifecycle)
+
+**Built-in LLM judges** (research-validated):
+
+| Judge | Needs Ground Truth | Evaluates |
+|-------|-------------------|-----------|
+| `RelevanceToQuery` | No | Response relevance to user request |
+| `RetrievalGroundedness` | No | Hallucination detection |
+| `Safety` | No | Harmful/toxic content |
+| `Correctness` | Yes | Accuracy vs ground truth |
+| `Completeness` | Yes | All questions addressed |
+| `ToolCallCorrectness` | Yes | Tool calls and arguments |
+| `ToolCallEfficiency` | No | Redundant tool usage |
+| `Guidelines` | No | Custom natural-language rules |
+
+**Multi-turn judges** (conversation-level): `ConversationCompleteness`, `UserFrustration`, `KnowledgeRetention`, `ConversationalSafety`
+
+**Production monitoring**: Automatically runs scorers on production traces; uses Databricks-hosted LLM judges (EU workspaces: EU-hosted models). No prompts stored with Azure OpenAI (Abuse Monitoring opt-out).
+
+**Custom judges**: Full control over evaluation criteria, scores (numerical/categorical/boolean), human feedback alignment via `align_judges()`.
+
+**Key note**: MLflow 3 replaced Agent Evaluation SDK — migrate with `mlflow.genai.*` functions.
+
+
 **Enterprise governance for AI:**

 ```
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-fundamentals-overview.md
@ -1,11 +1,14 @@
 # MLOps Fundamentals - Lifecycle and Principles

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Machine Learning Operations (MLOps) er anvendelse av DevOps-prinsipper på machine learning-prosjekter. Målet er å automatisere og effektivisere hele ML-livssyklusen – fra eksperimentering og trening, via deployment, til overvåking og retrening. MLOps bygger på etablert DevOps-praksis som continuous integration (CI), continuous deployment (CD), version control, og infrastructure as code (IaC), men legger til ML-spesifikke utfordringer som data versioning, model tracking, feature engineering, og drift detection.
@ -292,6 +295,49 @@ jobs:

 ### DevOps-verktøy

+
+### DevOps for Machine Learning — Azure DevOps Integration (2026)
+
+**Azure Pipelines + Azure ML** (how-to-devops-machine-learning):
+
+Automate the ML lifecycle via Azure DevOps pipelines:
+1. Data preparation (ETL)
+2. On-demand scale-out training
+3. Model deployment (public/private web service)
+4. Monitoring (performance, data drift)
+
+**Azure DevOps pipeline YAML pattern**:
+```yaml
+- task: AzureCLI@2
+  inputs:
+    azureSubscription: $(service-connection)
+    inlineScript: |
+      job_name=$(az ml job create --file pipeline.yml -g $(resource-group) -w $(workspace) --query name -o tsv)
+      echo "##vso[task.setvariable variable=JOB_NAME;isOutput=true;]$job_name"
+
+- job: WaitForJobCompletion
+  pool: server  # Server job — no agent costs
+  steps:
+  - task: AzureMLJobWaitTask@1  # From Azure ML extension
+    inputs:
+      serviceConnection: $(service-connection)
+      azureMLJobName: $(azureml_job_name)
+```
+
+**Authentication options**:
+- Azure Resource Manager service connection (recommended with Azure ML extension)
+- Generic service connection (uses InvokeRESTAPI task)
+
+**MLOps maturity model**: Manual → Partial automation → Full CI/CD → Full MLOps with monitoring
+
+**Key automation operations** (Azure DevOps):
+- Infrastructure deployment (Terraform / Bicep)
+- Component registration and versioning
+- Model training on compute clusters
+- Online/batch endpoint deployment
+- Production monitoring alerts
+
+
 | Verktøy | Kostnad | Anbefaling |
 |---------|---------|-----------|
 | **Azure DevOps** | Gratis for 5 brukere + 1800 min/mnd pipeline | Bruk Basic plan for mindre team |
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-security-access-control.md
@ -1,7 +1,8 @@
 # Security and Access Control in MLOps

 **Kategori:** MLOps & GenAIOps
-**Dato:** 2026-02-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
+**Dato:** 2026-04-10
 **Confidence:** HIGH — Basert på offisiell Microsoft Learn dokumentasjon (8 MCP-oppslag, 16 kilder)

 ---
@ -747,3 +748,30 @@ AmlComputeClusterNodeEvent
 - ✅ HIGH confidence: Offisiell dokumentasjon + kodeeksempler fra Microsoft Learn
 - ⚠️ MEDIUM confidence: Utledet fra best practices og architecture patterns
 - ❓ LOW confidence: Ikke aktuelt (alle påstander er verifisert mot offisiell dokumentasjon)
+
+
+### Azure Machine Learning VNet Security (2026 Update)
+
+**Managed Virtual Networks** (recommended approach): Azure ML handles network isolation automatically.
+Use `az ml workspace update` with managed network settings instead of manual VNet configuration.
+
+**Private Endpoint for Workspace**:
+- Connects workspace via private IP addresses within your VNet
+- Requires securing all dependent resources: Storage, Key Vault, Container Registry
+- Private endpoint alone does NOT ensure end-to-end security — all components must be secured
+
+**Storage Account Security**:
+- Private endpoint (recommended): Blob, File, Queue, Table subresources
+- Service endpoint: Must be same VNet and subnet as compute
+- Set `Microsoft.MachineLearningServices/Workspace` as trusted resource type
+
+**Required outbound traffic service tags**:
+- `AzureActiveDirectory` (TCP 443) — authentication
+- `AzureMachineLearning` (TCP 443, 18881, UDP 5831)
+- `Storage.region` (TCP 443) — data access
+- `MicrosoftContainerRegistry.region` (TCP 443) — Docker images
+
+**Secure connectivity options**: Azure VPN Gateway (Point-to-site/Site-to-site), ExpressRoute, Azure Bastion (jump box)
+
+**ACR requirements**: Premium SKU required for private endpoints; ACR must be in same VNet or peered VNet.
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/mlops-teams-collaboration-tools.md
@ -5,6 +5,8 @@
 **Kilde:** Microsoft Learn, Azure Architecture Center
 **Konfidensgradering:** ⭐⭐⭐⭐⭐ (Verifisert mot offisiell Microsoft-dokumentasjon)

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Vellykkede MLOps-implementeringer krever samarbeid mellom flere teamroller med ulike verktøy, arbeidsflyter og ansvar. Denne referansen dekker hvordan ulike personas samarbeider gjennom machine learning-livssyklusen, hvilke verktøy som støtter samarbeid, og hvordan organisasjoner kan strukturere teamarbeid for maksimal effektivitet.
@ -123,6 +125,32 @@ MLOps-miljøer opererer med distinkte roller som hver har spesifikke ansvarsomr
 **Konfidensmarkør:** ⭐⭐⭐⭐⭐ Azure Boards er core DevOps-plattform med native Azure DevOps-integrasjon.

 #### Azure DevOps / GitHub Actions
+
+
+### Azure DevOps — Integrated MLOps Platform (2026)
+
+Azure DevOps provides end-to-end project management for ML teams:
+
+| Service | ML Use Case |
+|---------|-------------|
+| **Azure Boards** | Sprint planning for model iterations, bug tracking, backlog management |
+| **Azure Repos** | Git repositories for model code, notebooks, IaC; branch policies + PR reviews |
+| **Azure Pipelines** | CI/CD for ML (build, test, train, deploy); integrates with Azure ML via `AzureMLJobWaitTask@1` |
+| **Azure Test Plans** | Manual testing of model outputs, test case management |
+| **Azure Artifacts** | Package feeds (NuGet, pip, conda) for ML libraries and shared components |
+
+**Azure DevOps MCP Server**: Natural language queries for project management — `Summarize sprint status`, `List blocked work items`, `Show pipeline success rates` (2026 feature).
+
+**GitHub Actions integration** (alternative to Azure Pipelines):
+- OIDC authentication (recommended, no long-lived secrets)
+- `azure/login@v2` + `az ml job create` pattern
+- MLOps v2 solution accelerator: `Azure/mlops-v2-gha-demo`
+
+**Databricks CI/CD best practices**:
+- Feature branching with short-lived branches
+- Automated notebook testing before merge
+- MLflow experiment tracking integrated into PR workflows
+
 **Formål:** CI/CD automation for ML lifecycle
 **Nøkkelkapabiliteter:**
 - Pipeline-basert workflow automation
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-deployment-strategies-azure.md
@ -5,6 +5,8 @@
 **Målgruppe:** Arkitekter som planlegger ML-modellutplassering i produksjon
 **Konfidensgrad:** ⚡️⚡️⚡️ Høy (basert på Microsoft Learn + offisielle code samples)

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Model deployment strategies handler om hvordan man trygt og effektivt ruller ut nye ML-modeller eller modellversjoner til produksjon uten å forårsake nedetid eller forringet brukeropplevelse. Azure Machine Learning tilbyr flere deployment patterns som støtter **progressive exposure**, **traffic routing**, og **rollback-mekanismer**.
@ -1050,3 +1052,36 @@ Denne kunnskapsreferansen er basert på følgende Microsoft Learn-artikler og co

 **Sist oppdatert:** 2026-02-04
 **Neste review:** 2026-05-04 (eller ved større endringer i Azure ML deployment capabilities)
+
+
+### Safe Rollout / Blue-Green Deployment (Azure Well-Architected 2026)
+
+Azure ML managed online endpoints support blue-green (safe rollout) deployments natively:
+
+```bash
+# Deploy green deployment with 0% traffic initially
+az ml online-deployment create --name green --endpoint my-endpoint --traffic-allocation 0
+
+# Test green deployment in isolation (direct routing)
+az ml online-endpoint invoke --name my-endpoint --deployment-name green
+
+# Mirror 10% of live traffic to green for shadow testing
+# Then progressively shift: 10% → 50% → 100%
+az ml online-endpoint update --name my-endpoint --traffic blue=90 green=10
+```
+
+**Azure Well-Architected SDP principles (OE:11)**:
+- **Progressive exposure**: Canary → Blue-Green → Deployment Stamps
+- **Health models**: Pass health checks before each rollout phase
+- **Bake time**: Hours/days between phases (not minutes) to capture time-zone usage patterns
+- **Failure detection**: Automatic halt + investigation when health signals degrade
+- **Recovery options**: Roll back (revert), roll forward (hotfix), or redeploy last known good
+
+**Azure facilitation**:
+- `Azure Pipelines` + `GitHub Actions` support multi-stage deployments with approval gates
+- `Azure App Configuration` for feature flag management
+- `Azure Load Balancers` for traffic routing and health monitoring
+- Point-in-time restore available for Azure SQL, Cosmos DB, MySQL, PostgreSQL
+
+**Emergency SDP**: Prescriptive protocols for hotfix acceleration — approval stage and bake time reduction — with explicit approval criteria.
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-drift-performance-degradation.md
@ -1,11 +1,14 @@
 # Model Drift and Performance Degradation Detection

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Model drift og performance degradation er kritiske fenomener som oppstår når en maskinlæringsmodells ytelse forverres over tid i produksjon. Dette skjer fordi virkeligheten endrer seg – input-data får andre distribusjoner, forretningslogikk endres, sensorer kalibreres feil, eller brukernes atferd endrer seg. Uten kontinuerlig overvåking kan modeller raskt bli utdaterte og levere feil prediksjoner som undergraver forretningsmål eller skaper compliance-problemer i regulerte sektorer.
@ -633,3 +636,39 @@ Email Alerts + Azure Monitor Dashboard
 ### Sist oppdatert

 **2026-02** – Basert på Microsoft Learn-dokumentasjon (azure-ai-ml SDK v2, API version 2).
+
+
+### Azure ML Model Drift & Performance Degradation Monitoring (2026)
+
+**Model monitoring** provides continuous tracking of production model performance:
+
+**Degradation signals**:
+- **Prediction drift**: Output distribution shifts away from training baseline
+- **Feature attribution drift**: Feature importance changes indicate concept drift
+- **Data quality degradation**: Input data quality issues upstream
+- **Performance metric degradation**: Track against ground truth when labels available
+
+**Monitoring configuration**:
+```python
+# Set up monitoring for deployed models on online endpoints
+# Azure ML handles data collection and signal computation
+# Monitoring jobs run on schedule (default: daily)
+```
+
+**Alert thresholds** (recommended):
+- Data drift coefficient > 0.1: Investigate
+- Data drift coefficient > 0.3: Retrain trigger
+- Prediction drift > 15%: Production alert
+- Unusable nodes > 0: Infrastructure alert (Azure Monitor)
+
+**Continuous learning loop**:
+1. Monitor signals → detect drift early
+2. Critically evaluate inherent model risks
+3. Identify hidden problems before business impact
+4. Trigger retraining or model update workflow
+5. Validate new model before rollout (blue-green/canary)
+
+**Integration**: Azure Event Grid for alerting → Logic Apps / Functions → automated retraining trigger
+
+**For GenAI/LLM**: MLflow 3 production monitoring reuses development scorers (Groundedness, Relevance) on production traces — consistent quality measurement throughout lifecycle.
+
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-evaluation-frameworks.md
@ -1,11 +1,14 @@
 # Model Evaluation Frameworks and Metrics

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Evaluering av AI-modeller, spesielt generative AI-applikasjoner, krever en helt annen tilnærming enn tradisjonell maskinlæring. Mens tradisjonell ML fokuserer på deterministiske metrikker som accuracy og precision, må GenAI-evaluering håndtere multi-turn-samtaler, kontekstuell relevans, sikkerhet og subjektiv kvalitet. Microsoft tilbyr et omfattende rammeverk for modellevaluering gjennom Azure AI Foundry, Azure Machine Learning Prompt Flow og MLflow 3, som dekker hele utviklingsløpet fra modellvalg til produksjonsovervåking.
@ -107,6 +110,42 @@ print(f"Foundry URL: {result.get('studio_url')}")

 ### MLflow 3 Evaluation & Monitoring

+
+### MLflow 3 Evaluation Framework (2026)
+
+MLflow 3 provides the evaluation framework for both traditional ML and GenAI applications on Databricks:
+
+**Scorer types** (unified interface for all evaluation):
+
+| Type | Customization | Use Case |
+|------|--------------|---------|
+| Built-in judges | Minimal | Quick evaluation: `Correctness`, `RetrievalGroundedness`, `Safety` |
+| Guidelines judges | Moderate | Custom natural-language rules (pass/fail) |
+| Custom LLM judges | Full | Domain-specific criteria, detailed scoring |
+| Code-based scorers | Full | Deterministic: exact match, format validation, business logic |
+
+**Key evaluation functions**:
+```python
+import mlflow
+
+# Development evaluation
+results = mlflow.genai.evaluate(
+    data=eval_dataset,
+    scorers=[RelevanceToQuery(), RetrievalGroundedness(), Correctness()]
+)
+
+# Production monitoring — same scorers as development
+# Automatically applied to production traces
+```
+
+**Judge accuracy**: Databricks validates with Cohen's Kappa, accuracy, F1 score against human expert judgment.
+
+**Traditional ML evaluation** (Azure ML):
+- Data quality signals: null rate, out-of-bounds, type errors
+- Statistical drift: Jensen-Shannon divergence, Wasserstein distance
+- Custom metrics via Python scripts in monitoring jobs
+
+
 MLflow 3 integrerer evaluering og production monitoring i én workflow. Samme LLM judges og scorers kan brukes i development, testing og production.

 **Hovedkomponenter:**
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/model-versioning-registry-management.md
@ -1,11 +1,14 @@
 # Model Versioning and Registry Management

 **Last updated:** 2026-02
+**Verified:** MCP 2026-04
 **Status:** GA
 **Category:** MLOps & GenAIOps

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Model versioning og registry management er fundamentale komponenter i MLOps-livssyklusen som sikrer sporbarhet, reproduserbarhet og effektiv styring av maskinlæringsmodeller gjennom hele deres levetid. Azure Machine Learning tilbyr to primære tilnærminger: workspace model registry for team-intern bruk og Azure Machine Learning registry for tverrorganisatorisk deling. Begge støtter MLflow som standardformat, noe som gir portabilitet og integrasjon med et bredt økosystem av verktøy.
@ -31,6 +34,44 @@ Azure Machine Learning skiller seg fra tradisjonelle Git-baserte tilnærminger v

 ### Registry-typer sammenlignet

+
+### Azure Machine Learning Cross-Workspace Registry (2026)
+
+**Azure ML Registry** enables model, component, and environment sharing across workspaces and subscriptions:
+
+**Two primary scenarios**:
+1. **Cross-workspace MLOps**: Train in `dev` → deploy to `test`/`prod` with full lineage (code, data, environment)
+2. **Cross-team sharing**: Publish models/components to central catalog for reuse across teams
+
+**Registry operations** (CLI v2 / Python SDK v2):
+```bash
+# Create model in registry (from local files)
+az ml model create --name nyc-taxi-model --version 1 --type mlflow_model   --path ./artifacts/model/ --registry-name <registry-name>
+
+# Share model from workspace to registry (preserves training lineage)
+az ml model share --name nyc-taxi-model --version 1   --registry-name <registry-name> --share-with-name <new-name> --share-with-version 1
+
+# Deploy model from registry to any workspace
+# (model: azureml://registries/<registry-name>/models/<name>/versions/<v>)
+az ml online-deployment create --file deploy.yml --all-traffic
+```
+
+**Python SDK pattern**:
+```python
+ml_client_registry = MLClient(credential=credential, registry_name="<REGISTRY_NAME>")
+ml_client_workspace = MLClient(credential=credential, workspace_name="<WS_NAME>", ...)
+
+# Create in registry
+ml_client_registry.models.create_or_update(mlflow_model)
+# Deploy from registry to workspace
+ml_client_workspace.online_deployments.begin_create_or_update(deployment)
+```
+
+**Lineage tracking**: Models registered from job outputs link back to training job, code, data, and environment.
+**Access control**: ACR token-based access (workspace compute has `AcrPull` via registry's managed identity).
+**MLflow format**: Required for no-code deployment with built-in scoring server.
+
+
 | Egenskap | Workspace Registry | Azure ML Registry |
 |----------|-------------------|-------------------|
 | **Scope** | Enkelt workspace | Multi-workspace, cross-subscription |
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/monitoring-observability-ml-systems.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/mlops-genaiops/monitoring-observability-ml-systems.md
@ -7,6 +7,8 @@

 ---

+**Verified:** MCP 2026-04
+
 ## Introduksjon

 Monitoring og observability for ML-systemer handler om kontinuerlig overvåkning av modeller i produksjon for å sikre ytelse, kvalitet og pålitelighet. Azure tilbyr et komplett økosystem for ML-overvåkning gjennom Azure Machine Learning Model Monitoring og Azure Monitor, som til sammen gir innsikt i både **modellytelse** (data science-perspektiv) og **operasjonell helse** (infrastruktur-perspektiv).
@ -297,6 +299,45 @@ create_monitor:

 ### Azure Monitor

+
+### Azure Machine Learning Monitoring Architecture (2026)
+
+**Azure Monitor integration**:
+- All metrics in namespace: `Machine Learning Service Workspace`
+- Platform metrics collected automatically, no configuration needed
+- Route resource logs to Log Analytics for querying with KQL
+
+**Key Kusto (KQL) queries**:
+```kusto
+# Failed jobs last 5 days
+AmlComputeJobEvent
+| where TimeGenerated > ago(5d) and EventType == "JobFailed"
+| project TimeGenerated, ClusterId, EventType, ExecutionState, ToolType
+
+# Failed online endpoint requests
+AmlOnlineEndpointTrafficLog
+| where TimeGenerated > ago(1d) and ResponseCode != 200
+| project TimeGenerated, EndpointName, DeploymentName, ResponseCode
+```
+
+**Recommended alert rules**:
+| Alert | Condition | Threshold |
+|-------|-----------|-----------|
+| Model Deploy Failed | Total > 0 | Any failure |
+| Quota Utilization | Average > 90% | High utilization |
+| Unusable Nodes | Total > 0 | Any unusable |
+
+**Application Insights integration**: Live metrics, Transaction search, Failures, Performance analysis.
+Use workspace-based Application Insights (default for new workspaces) + Azure Monitor Private Link for VNet isolation.
+
+**Data storage layers**:
+- Metrics database: Platform metrics (near real-time)
+- Log Analytics: Resource logs + Activity log (queryable with KQL)
+- Azure Storage / Event Hubs: Long-term export
+
+**Cross-workspace monitoring**: Use single Log Analytics workspace for multiple Azure ML workspaces to query across all resources simultaneously.
+
+
 **Application Insights** (📊 For endpoints):
 ```python
 # Enable for online endpoint
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/agentic-rag-patterns.md
@ -1,6 +1,6 @@
 # Agentic RAG Patterns — Agent-styrt retrieval

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Semantic Kernel), Preview (Azure AI Search agentic retrieval)
 **Category:** RAG Architecture & Semantic Search

@ -285,3 +285,24 @@ agent = chat_client.as_agent(
 | AI Agent Design Patterns | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/ai-agent-design-patterns) |
 | Semantic Kernel Agent Orchestration | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/semantic-kernel/frameworks/agent/agent-orchestration/) |
 | Multi-agent performance (34% accuracy) | **Baseline** | Community source (ragaboutit.com) |
+
+
+### Azure AI Search Agentic Retrieval (Public Preview — oppdatert 2026-04)
+
+Azure AI Search agentic retrieval er en managed multi-query pipeline for komplekse spørsmål i chat og copilot-apper:
+
+**Funksjonalitet:**
+- LLM (gpt-4o/4.1/5-serien) bryter ned komplekse queries til fokuserte subqueries
+- Subqueries kjøres **parallelt** med semantisk reranking per query
+- Resultater slås sammen til ett grounding data-sett med query plan og source documents
+- Leser inn chat history for kontekstuell query planning
+
+**Prising:**
+- Free plan: **50 millioner gratis reasoning tokens/mnd** (alle tiers)
+- Standard plan: pay-as-you-go etter fri kvote
+- Avhenger av semantic ranker (premium feature)
+
+**Arkitektur:** Knowledge Base + Knowledge Source(s) + Azure OpenAI LLM + Azure AI Search index
+
+**AI Agent Design Patterns (Azure Architecture Center):**
+Agentic RAG plasseres i et spektrum fra single model call → single agent with tools → multi-agent orchestration. Start med laveste nødvendige kompleksitetsnivå. Mønstre: sequential (pipeline), parallel fanout, supervisor, og autonomous loop. Multi-agent krever koordineringsoverhead og økt latency — bruk kun når single-agent RAG ikke er tilstrekkelig.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/azure-ai-search-setup.md
@ -1,6 +1,6 @@
 # Azure AI Search - Configuration and Deployment

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -34,6 +34,10 @@ For offentlig sektor er Azure AI Search spesielt relevant fordi den støtter dat
 - **Semantic Ranker:** Kun Standard og høyere (S1+)
 - **Private Link:** Standard (S1+), Storage Optimized

+
+
+> **SKU-oppdatering 2026-04:** Search services opprettet etter 3. april 2024 har større partisjoner og høyere vector kvoter på nesten alle tiers. Basic støtter 3 replicas for SLA. Standard (S1-S3) er standard valg. S3 HD er hosting mode for mange små indekser (multitenancy). Storage Optimized (L1/L2) gir lavere pris/TB for sjeldent oppdaterte, store indekser — med høyere query latency. Tier-bytte er nå mulig mellom Basic og Standard (S1/S2/S3) uten å gjenoppbygge indeksen fra scratch i mange tilfeller.
+
 ### Indekseringsstrategier

 Azure AI Search støtter tre indekseringsmodeller:
@ -462,3 +466,15 @@ Azure AI Search prises per **search unit** (SU = 1 partition × 1 replica).
 ---

 **For Cosmo:** Denne referansen brukes når kunden snakker om "RAG-implementasjon", "søkeløsning", "Azure AI Search setup", eller spør om SKU-valg. Kombiner med **RAG Core Patterns** for arkitekturveiledning og **Hybrid Search - Full-Text and Vector Combined** for query-optimalisering.
+
+
+### Hybrid Search (oppdatert 2026-04)
+
+Hybrid search kombinerer full-text search og vector search i én enkelt forespørsel mot en søkeindeks med både tekstlig og vektorisert innhold:
+- Kjører full-text og vector search **parallelt**
+- Merger resultater med **Reciprocal Rank Fusion (RRF)**
+- Støtter filtrering, faceting, sortering, scoring profiles og semantic ranking i én request
+- `maxTextRecallSize` (preview) kontrollerer antall BM25-resultater inn til RRF-ranker (default 1000, max 10000)
+- Benchmark testing viser at hybrid retrieval med semantic ranker gir signifikant bedre søkerelevans enn enkelt-modalitet
+
+**Query-struktur:** `search` for full-text, `vectorQueries` for vector (kan ha flere), valgfri `queryType=semantic` for L2-reranking.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/citation-tracking.md
@ -1,6 +1,6 @@
 # Citation Tracking and Source Attribution

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (classic RAG), Preview (agentic retrieval)
 **Category:** RAG Architecture & Semantic Search

@ -292,3 +292,14 @@ result = groundedness_eval(
 - Norsk lovgivning (Forvaltningsloven, Offentleglova, Arkivloven)
 - Kostnadsoptimerings-anbefalinger
 - Modenhetsnivå-tabellen
+
+
+### Agentic Retrieval — Citation Tracking (oppdatert 2026-04)
+
+Azure AI Search agentic retrieval (preview) returnerer et tre-delt svar som gjør citation tracking robust:
+
+1. **Merged content** — samlet grounding data for LLM
+2. **Source references** — kildereferanser for inspeksjon og citation
+3. **Activity plan** — query execution-detaljer (subqueries, sources, parameters)
+
+Agentic retrieval bruker LLM til å rive ned komplekse queries til subqueries som kjøres parallelt, med semantisk reranking av hvert delresultat. Dette gir bedre grounding data enn klassisk RAG for komplekse spørsmål. Source references med full provenance tracking støtter transparenskrav i norsk offentlig sektor.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/contextual-retrieval.md
@ -1,6 +1,6 @@
 # Contextual Retrieval — Kontekstuell berikelse av chunks

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (custom skill pattern), Preview (agentic retrieval)
 **Category:** RAG Architecture & Semantic Search

@ -282,3 +282,18 @@ Hvis contextual retrieval reduserer irrelevante LLM-kall med 30%:
 | Custom skill interface (Azure AI Search) | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/azure/search/cognitive-search-custom-skill-interface) |
 | Custom skill example (Python) | **Verified** | [learn.microsoft.com](https://learn.microsoft.com/en-us/previous-versions/azure/search/cognitive-search-custom-skill-python) |
 | Retrieval failure benchmarks | **Baseline** | Anthropic research, validert av Microsoft |
+
+
+### Custom Skill Interface (oppdatert 2026-04)
+
+Custom skills integreres i Azure AI Search enrichment pipeline via `#Microsoft.Skills.Custom.WebApiSkill`.
+
+**Interface-krav:**
+- HTTPS endpoint (Azure Functions, containers, eller annen Azure-hosted tjeneste)
+- Aksepterer JSON batch: `{"values": [{"recordId": "...", "data": {...}}, ...]}`
+- Returnerer JSON batch: `{"values": [{"recordId": "...", "data": {...}, "errors": [], "warnings": []}]}`
+- Timeout: default 30s, maks 230s (`PT230S`)
+- Autentisering: API-key i URI/header, eller managed identity med `authResourceId`
+
+**Kontekstuell berikelse via custom skill:**
+Custom skills brukes for contextual retrieval der hver chunk berikes med kontekst fra omliggende tekst (f.eks. "Dette er fra kapittel 3 om sikkerhet..."). Custom skill kaller LLM med original dokument + chunk, og returnerer kontekstualisert chunk for bedre embedding-kvalitet.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/graphrag-knowledge-graphs.md
@ -1,6 +1,6 @@
 # GraphRAG - Knowledge Graphs and Relationship Extraction

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Preview
 **Category:** RAG Architecture & Semantic Search

@ -23,7 +23,7 @@ GraphRAG-systemet består av flere integrerte lag som sammen muliggjør relasjon
 | Komponent | Beskrivelse | Microsoft-teknologi |
 |-----------|-------------|---------------------|
 | **Entity Extraction** | Identifiserer og trekker ut navngitte entiteter (personer, organisasjoner, lokasjoner) fra tekst | Azure AI Language Service (NER v3), GenAI Prompt skill |
-| **Relationship Graphs** | Representerer entiteter som nodes og relasjoner som edges i en graph-struktur | Azure Cosmos DB (graph API), Kusto Query Language (KQL) graph semantics |
+| **Relationship Graphs** | Representerer entiteter som nodes og relasjoner som edges i en graph-struktur | Azure Cosmos DB (graph API), Microsoft Fabric Graph (Labeled Property Graph — LPG model, Public Preview), Kusto Query Language (KQL) graph semantics |
 | **Graph Indexing** | Lagrer og indekserer graph-strukturen for effektiv traversal og søk | Azure Cosmos DB indexing, Azure AI Search (hybrid indexing) |
 | **Traversal Queries** | Søkemekanismer for å navigere graph-strukturen (pattern matching, shortest path, neighborhood search) | KQL `graph-match`, `graph-shortest-paths`, Labeled Property Graphs (LPG) |
 | **Entity Linking** | Forbinder ekstraherte entiteter med eksisterende knowledge bases (f.eks. Wikipedia) for normalisering og anrikning | Azure AI Language Entity Linking skill |
@ -39,6 +39,8 @@ Entity extraction-prosessen transformerer ustrukturert tekst til strukturerte en

 ### Graph Database Modeller

+> **Microsoft Fabric Graph (Preview):** Fabric Graph bruker Labeled Property Graph (LPG)-modellen for rask traversal og analytics. RDF-formatet støttes ikke. LPG egner seg for enterprise analytics og fraud detection der semantisk web-integrasjon ikke er nødvendig.
+
 Microsoft Fabric og Azure støtter **Labeled Property Graphs (LPG)** som standard graph-modell:

 - **Nodes (entiteter)**: Har labels (typer), properties (attributter) og unique IDs
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/hybrid-search-configuration.md
@ -1,6 +1,6 @@
 # Hybrid Search - Full-Text and Vector Combined

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -223,3 +223,27 @@ Bruk `debug: "vector"` eller `debug: "semantic"` i API-kallet for å pakke ut su
 ### Baseline (modellkunnskap)
 - Kostnadsoptimerings-tips basert på generell Azure-erfaring
 - Offentlig sektor-anbefalinger basert på norsk kontekst
+
+
+### Hybrid Search — Konfigurasjon og Tuning (oppdatert 2026-04)
+
+**Anbefalt startpunkt:** Balanced hybrid med `k=30-50`, `top=10-20`, semantic ranking etter relevans-test.
+
+**maxTextRecallSize (preview):** Kontrollerer BM25-bidrag til RRF
+- Default: 1000, Max: 10000
+- Reduser hvis vector dominerer; øk for store indekser der default ikke gir nok dekning
+- `countAndFacetMode: "countRetrievableResults"` scope-r teller til maxTextRecallSize-vinduet
+
+**Ytelsesmønstre:**
+- Recall-first: øk `maxTextRecallSize` gradvis
+- Precision-first: lav `k` og `top`, unngå unødvendig semantic ranker
+
+**Filter-moduser i hybrid:**
+- `preFilter` (default) — filtrerer FØR query, reduserer søkerom for begge subqueries
+- `postFilter` — filtrerer ETTER, men kan gi <50 docs til semantic ranker
+- `strictPostFilter` (preview) — strengeste modus, ikke anbefalt med semantic ranker
+- `filterOverride` (preview) — per-vectorQuery filter, overstyrer globalt filter
+
+**SDK-støtte:** Python (`azure-search-documents`), C# (`Azure.Search.Documents`), Java, JavaScript.
+
+**API-versjoner:** `2025-09-01` (stable), `2025-11-01-preview` (maxTextRecallSize, filterOverride, etc.)
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/metadata-management-filtering.md
@ -1,6 +1,6 @@
 # Metadata Management and Filtered Search

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -523,3 +523,28 @@ $filter=personalDataCategories/any(c: c eq 'Helseopplysninger') and legalBasis n

 **For Cosmo:**
 Metadata management er ofte undervurdert i RAG-prosjekter. Kunder fokuserer på embeddings og vector search, men glemmer at 70% av queries i produksjon inneholder strukturerte filter-kriterier ("bare fra min avdeling", "kun siste år", "høyeste klassifikasjon"). Design metadata-schema tidlig, test med reelle cardinality-tall, og prioritér normalizers og security trimming fra dag 1. I offentlig sektor er compliance non-negotiable — bygg audit trail og retention policies inn fra start.
+
+
+### OData Filter Syntax (oppdatert 2026-04)
+
+Azure AI Search bruker OData `$filter`-syntaks for metadata-filtrering:
+
+**Operatorer:**
+- Sammenligning: `eq`, `ne`, `gt`, `lt`, `ge`, `le`
+- Logisk: `and`, `or`, `not` (høyest presedens: `not` > sammenlignings-ops > `and` > `or`)
+- Samling: `any()`, `all()` for collection-felt
+- Geo-spatial: `geo.distance()`, `geo.intersects()`
+- Full-text i filter: `search.ismatch()`, `search.ismatchscoring()`
+- Effektiv liste-matching: `search.in(field, "val1,val2", ",")`
+
+**Viktig:** `search.in()` teller som én klausul (bedre enn lange OR-kjeder for filter size limits).
+
+**Eksempel — sikkerhetstrimming:**
+```odata
+$filter=search.in(UserGroup, "GroupA,GroupB", ",")
+```
+
+**Hybrid search med filter:**
+- `preFilter` (default) — anvendes FØR query execution, reduserer søkerom
+- `postFilter` — anvendes ETTER, trimmer resultater (bedre med semantic ranker)
+- `filterOverride` (preview) — per-vectorQuery filter som overstyrer globalt filter
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/multi-index-federation.md
@ -1,6 +1,6 @@
 # Multi-Index Federation and Cross-Search

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (single-index), Not supported (native cross-index)
 **Category:** RAG Architecture & Semantic Search

@ -16,6 +16,10 @@ For scenarioer der data logisk tilhører separate indekser (ulike skjemaer, comp

 **Viktig funn:** Microsofts offisielle FAQ sier eksplisitt: *"Can I search across multiple indexes? No. A query is always scoped to a single index."*

+**Multi-region støtte:** Azure AI Search er en single-region service, men du kan oppnå høyere reliability ved å deploye identiske search services i flere regioner. Data synkroniseres via push eller pull (indexer) APIer. Load balancing håndteres av Azure Front Door, Traffic Manager, eller Application Gateway. Data residency: innhold lagres i regionen du velger, uten kryssregional dataflyt uten eksplisitt autorisasjon.
+
+**Multi-vector fields (Preview):** Azure AI Search støtter nå multiple vektorer i ett dokumentfelt via `Collection(Edm.ComplexType)` — opp til 100 vektorer per dokument. Nyttig for multimodal data og lange dokumenter. `perDocumentVectorLimit`-parameteren kontrollerer antall matchende vektorer per dokument i query-resultater.
+
 ## Kjernekomponenter

 ### Hvorfor Azure AI Search ikke støtter cross-index queries
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/multimodal-rag.md
@ -1,6 +1,6 @@
 # Multimodal RAG — Bilder, tabeller og dokumenter i RAG

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Document Intelligence, Content Understanding), Preview (multimodal embeddings)
 **Category:** RAG Architecture & Semantic Search

@ -309,3 +309,17 @@ chartFormat=markdown
 | Multimodal RAG with Vision (ISE DevBlog) | **Verified** | [devblogs.microsoft.com](https://devblogs.microsoft.com/ise/multimodal-rag-with-vision/) |
 | RAG Time Journey 4: Advanced Multimodal Indexing | **Verified** | [techcommunity.microsoft.com](https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/rag-time-journey-4-advanced-multimodal-indexing/4397300) |
 | Azure-Samples/multimodal-rag-code-execution | **Baseline** | [github.com](https://github.com/Azure-Samples/multimodal-rag-code-execution) |
+
+
+### Azure AI Search Multimodal Pipeline (oppdatert 2026-04)
+
+Azure AI Search multimodal pipeline (GA) støtter nå en fullstendig 5-stegs prosess:
+1. **Ekstraksjon** — Document Extraction, Document Layout, eller Content Understanding skill
+2. **Tekst-chunking** — Text Split skill for håndterbare biter
+3. **Bildebeskriving** — GenAI Prompt skill verbaliserer bilder via LLM
+4. **Embedding** — Azure OpenAI, Microsoft Foundry, eller Azure Vision embedding
+5. **Bildestoring** — Knowledge store lagrer ekstraherte bilder for annotation i klientapp
+
+Hybrid queries kombinerer full-text search, vector search, og semantic ranking for å svare på spørsmål der svaret befinner seg i et innebygd diagram i en PDF.
+
+**Querytidsstøtte:** GenAI Prompt skill-baserte pipelines støtter hybrid queries over tekst og verbaliserte bilder. For bilde-til-vektor-queries (søk med bilde som input), bruk Azure Vision multimodal embedding skill med en tilsvarende vectorizer.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-caching-optimization.md
@ -1,6 +1,6 @@
 # RAG Caching and Performance Optimization

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -503,3 +503,23 @@ cache_key = f"user:{user_id}:tenant:{tenant_id}:query_hash:{hash(prompt)}"
 **Totalt antall kilder:** 9 unike Microsoft Learn URLer
 **MCP calls:** 6 (4 docs_search + 2 docs_fetch + 1 code_sample_search)
 **Sist verifisert:** 2026-02-03
+
+
+### Azure Managed Redis — Arkitektur (oppdatert 2026-04)
+
+Azure Managed Redis (basert på Redis Enterprise) er anbefalt for AI-workloads vs. Azure Cache for Redis (community edition):
+
+| Egenskap | Azure Cache for Redis | Azure Managed Redis |
+|---------|----------------------|---------------------|
+| Threading | Single-threaded | Multi-threaded (Redis Enterprise) |
+| Arkitektur | Primary + replica (2 nodes) | Multiple shards per node, distributed primaries |
+| Performance | Begrenset av single thread | Nær-lineær skalering med vCPUs |
+| Clustering | Valgfritt | Alltid aktivert (OSS, Enterprise, eller Non-Clustered policy) |
+| Active geo-replication | Nei | Ja |
+
+**Cluster policies:**
+- **OSS policy** — anbefalt for de fleste. Klienten kobles direkte til shards, laveste latency, best throughput
+- **Enterprise policy** — enkelt endpoint, bakoverkompatibelt, men enkelt-node proxy kan bli bottleneck. Påkrevd for RediSearch
+- **Non-Clustered** — kun ≤25 GB, for migrering fra ikke-shardede miljøer
+
+**Flash Optimized tier:** 20% RAM + 80% NVMe Flash. Optimal for read-heavy workloads med subset av hot keys.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-core-patterns.md
@ -1,6 +1,6 @@
 # RAG Core Patterns and Architecture

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -417,3 +417,25 @@ results = search_client.search(
 ---

 **For Cosmo:** Når kunde spør om RAG, start med "Naive vs Advanced vs Agentic"-beslutningstreet. Identifiser data source, query complexity, og latency-krav først. Hvis offentlig sektor: alltid spør om GDPR/Schrems II/AI Act compliance før du foreslår arkitektur. Hvis customer mangler evaluation strategy: stopp og definer retrieval recall/precision targets før du går videre med implementation.
+
+
+### Hybrid Search — Kjernemønster (oppdatert 2026-04)
+
+Hybrid search er standardmønsteret for RAG i Azure AI Search:
+
+```json
+{
+  "search": "historisk hotell nær restauranter",
+  "vectorQueries": [{"kind": "vector", "vector": [...], "k": 50, "fields": "DescriptionVector"}],
+  "queryType": "semantic",
+  "semanticConfiguration": "my-semantic-config"
+}
+```
+
+**Hvorfor hybrid:**
+- Vector search: finner konseptuelt like dokumenter uten nøyaktige nøkkelord-treff
+- Full-text search: presis matching for produktkoder, navn, datoer
+- RRF merger: normaliserer scores fra BM25 og HNSW/eKNN
+- Semantic ranker (L2): re-ranker opp til 50 resultater med maskinlesningsforståelse
+
+**Best practice:** Sett `k=50` ved bruk av semantic ranker.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-document-preprocessing.md
@ -1,6 +1,6 @@
 # Document Preprocessing and Pipeline Automation

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -776,3 +776,15 @@ Images (JPEG/PNG)?
 **Totalt antall MCP-kilder:** 3 docs_search calls + 2 docs_fetch calls = **5 MCP-kall**
 **Totalt antall unike URLer:** 8 Microsoft Learn-artikler + 4 GitHub-repos = **12 kilder**
 **Konfidensnivå totalt:** 95% Verified (fra MCP), 5% Baseline (norske forhold og priser)
+
+
+### Kognitiv søk — bildeprosessering (oppdatert 2026-04)
+
+Azure AI Search støtter tre tilnærminger til bildeinnhold i RAG:
+1. **Vektorisering** — Azure Vision genererer bildere presentasjoner som søkbare vektorer
+2. **Verbalisering** — GenAI Prompt skill sender bilde til LLM-chat-modell for naturlig tekstbeskrivelse (bedre for RAG-grounding)
+3. **Analyse/OCR** — Image Analysis skill (tags, description) og OCR skill (tekst fra bilder)
+
+`imageAction: generateNormalizedImages` er påkrevd for bildebehandling. Maks 1000 bilder ekstraheres per dokument. Kostnader påløper ved `imageAction != none`.
+
+**Skillset tutorial (oppdatert):** Skillsets bygges med OCR, språkdeteksjon, entity recognition og key phrase extraction i pipeline. Output field mappings mapper enriched document tree til søkeindeksfelt.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-hallucination-mitigation.md
@ -1,6 +1,6 @@
 # RAG Hallucination Mitigation Strategies

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -400,3 +400,22 @@ Hvis AI-systemet gir feil informasjon som fører til skade:

 **Sist verifisert:** 2026-02-03
 **Neste revisjon:** 2026-05 (eller ved oppdatering av Azure AI Content Safety API)
+
+
+### Azure AI Content Safety — Groundedness Detection (oppdatert 2026-04)
+
+**Breaking change:** API-feltnavn er endret:
+- `correction` → `mitigating` (deteksjons-modus)
+- `correctedText` → `correctionText` (output-felt med korrigert tekst)
+
+**Deteksjonsmoduser:**
+- **Non-Reasoning mode** — rask binær deteksjon (grounded/ungrounded), lav latency for produksjon
+- **Reasoning mode** — detaljerte forklaringer på ungrounded segmenter, bruk under utvikling/debugging
+
+**Domenestøtte:** `MEDICAL` (medisinsk/vitenskapelig) og `GENERIC` (generelt formål)
+
+**Task typer:** `Summarization` og `QnA`
+
+**Grounding correction (preview):** API kan automatisk korrigere ikke-grounded tekst basert på dine grounding sources. Respons inkluderer `correctionText`-felt med korrigert innhold.
+
+**Begrensninger:** Kun engelsk tekst støttes. Tilgjengelig i utvalgte Azure-regioner.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-iterative-refinement.md
@ -1,6 +1,6 @@
 # Iterative RAG and Multi-Turn Refinement

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -439,3 +439,25 @@ public async Task ApplyRetentionPolicyAsync()
 **Forfatter:** Cosmo Skyberg (AI Architect)
 **For:** KTG Microsoft AI Architect Plugin
 **MCP Research:** microsoft-learn (4 searches, 2 fetches), microsoft-code-samples (1 search)
+
+
+### .NET AI IChatClient-interface (oppdatert 2026-04)
+
+`IChatClient` er .NET-standarden for interaksjon med AI chat services (Microsoft.Extensions.AI). Støtter stateless og stateful samtaler, tool calling, streaming, caching, og OpenTelemetry.
+
+```csharp
+// Stateful iterativ RAG med IChatClient
+List<ChatMessage> history = [];
+while (true) {
+    history.Add(new(ChatRole.User, userInput));
+    ChatResponse response = await client.GetResponseAsync(history);
+    history.AddMessages(response); // akkumulerer kontekst
+}
+```
+
+**Viktige egenskaper:**
+- `ConversationId` støtter stateful tjenester (slipper å sende full historikk)
+- `FunctionInvokingChatClient` gir automatisk tool invocation for agentic loops
+- `DistributedCachingChatClient` wrapper cacher identiske historikker
+- `ChatHistoryTruncationReducer` / `ChatHistorySummarizationReducer` håndterer context window limits
+- Pipeline-komposisjon: `ChatClientBuilder` stacker cache, tool invocation, og telemetri
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-query-understanding.md
@ -1,6 +1,6 @@
 # Query Understanding and Expansion

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** RAG Architecture & Semantic Search

@ -576,3 +576,22 @@ Multi-Query RAG med 3 varianter = ~3x søkekostnad + 1 LLM-kall for generering.
 - **ROI-tall (15-30% precision improvement):** Baseline — industry benchmarks, ikke Microsoft-spesifikk data

 **Totalt antall kilder:** 7 Microsoft Learn URLer (Verified) + 1 GitHub repo (Verified) = 8 kilder
+
+
+### Simple Query Syntax for RAG (oppdatert 2026-04)
+
+Azure AI Search simple query syntax er default parser for full-text søk i RAG:
+
+**Boolske operatorer (tegn-basert):**
+- `+` — AND (påkrevd term)
+- `|` — OR (alternativ term)
+- `-` — NOT (ekskluder term) — `searchMode=all` anbefales for presis NOT-atferd
+
+**Prefix queries:** `lingui*` — matcher "linguistic", "linguini" etc.
+
+**Phrase search:** `"eksakt frase"` — krever eksakt ordrekkefølge
+
+**Begrensninger:** Ingen fuzzy search, ingen suffix/infix wildcard (bruk full Lucene syntax for det).
+
+**Bruk i RAG query expansion:**
+Simple syntax egner seg for keyword-delen av hybrid queries. For agentic RAG bruker LLM query planning til å generere fokuserte subqueries som kombinerer full-text + vector search parallelt.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/rag-security-rbac.md
@ -1,6 +1,6 @@
 # RAG Security - RBAC, Filtering, and Access Control

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Preview (native ACL/RBAC), GA (security filters)
 **Category:** RAG Architecture & Semantic Search

@ -531,3 +531,24 @@ Authorization: Bearer <user-token>
 **GA features:** Security filters (alle API-versjoner)

 **Note:** Preview features kan endre seg. Konsulter alltid nyeste dokumentasjon før produksjon.
+
+
+### Dokumentnivå-tilgangskontroll — oppdatering 2026-04
+
+**4 tilnærminger (oppdatert):**
+
+| Tilnærming | Status | Beskrivelse |
+|-----------|--------|-------------|
+| **Security filters** | GA | String-sammenligning med `search.in()` — API-agnostisk |
+| **POSIX-like ACL/RBAC scopes** | Preview | Microsoft Entra ID-autentisering mot dokument-ACLer (ADLS Gen2) |
+| **Microsoft Purview sensitivity labels** | Preview | Entra-token + Purview policy enforced ved query-tid |
+| **SharePoint M365 ACLs** | Preview | SharePoint-tilganger ekstraheres av indexer og håndheves ved søk |
+
+**ADLS Gen2 ACL/RBAC (preview):**
+- RBAC: container-nivå (grov tilgangskontroll for alle dokumenter i container)
+- ACL: fil/mappe-nivå (finkornet per-dokument tilgangskontroll)
+- ABAC: **ikke støttet** i Azure AI Search
+- Tilgangsevaluering: RBAC sjekkes først, deretter ACL. Tilgang gis om én av dem tillater det
+- Permissions synkroniseres ved: første full indexer-kjøring, nye dokumenter, eller manuell trigger via `/resync` (preview)
+
+**Query-enforcement:** `x-ms-query-source-authorization`-header med Entra-token aktiverer automatisk trimming.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/semantic-ranker-reranking.md
@ -1,6 +1,6 @@
 # Semantic Ranker and Reranking Models

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (core), Preview (query rewrite, prerelease models)
 **Category:** RAG Architecture & Semantic Search

@ -276,3 +276,25 @@ Preview-funksjon (2025) som integrerer iterativ søk med semantic ranking.
 ### Baseline (modellkunnskap)
 - Cross-encoder-eksempler basert på Sentence Transformers-dokumentasjon
 - Offentlig sektor-anbefalinger basert på norsk kontekst
+
+
+### Semantic Ranker i Hybrid Search (oppdatert 2026-04)
+
+Semantic ranker (L2 reranking) fungerer optimalt i hybrid search-kontekst:
+
+- Aksepterer opp til **50 resultater** fra RRF-merger som input
+- Bruker maskinlesningsforståelse (MRC) for å re-ranke basert på semantisk relevans
+- `@search.rerankerScore` erstatter `@search.score` som primær rankingmetrikk
+- Valgfritt: `captions` (ekstraktiv) og `answers` (ekstraktiv) fra verbatim tekst
+
+**Konfigurasjon:**
+```json
+{
+  "queryType": "semantic",
+  "semanticConfiguration": "min-konfig",
+  "captions": "extractive",
+  "answers": "extractive"
+}
+```
+
+**Viktig:** Sett `k=50` i vectorQueries — semantic ranker trenger tilstrekkelig input. Pre-filtre som er for strenge kan redusere antall input-dokumenter og svekke reranking-kvaliteten.
--- a/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-engineering/references/rag-architecture/vector-indexing-techniques.md
@ -1,6 +1,6 @@
 # Vector Indexing - Techniques and Configuration

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA (Hybrid search), Preview (Scalar quantization)
 **Category:** RAG Architecture & Semantic Search

@ -410,3 +410,18 @@ Azure AI Search krever ingen spesifikk Microsoft 365-lisens, men:
 - [Semantic ranking in Azure AI Search](https://learn.microsoft.com/en-us/azure/search/semantic-search-overview) — **Verified** (2025-11)

 **Konfidensnivå:** Verified (90%) — All info basert på offisiell Microsoft-dokumentasjon og prising per feb 2026.
+
+
+### Vector Indexing i Hybrid Search-kontekst (oppdatert 2026-04)
+
+Vector fields og tekstfelt coeksisterer i hybrid search-indekser:
+
+- **HNSW** (Hierarchical Navigable Small World) — standard ANN-algoritme, `efSearch` og `maxConnections` tunable
+- **eKNN** (exhaustive K-Nearest Neighbors) — fullstendig søk, brukes med `"exhaustive": true` i query
+- **Multi-vector fields (preview)** — `Collection(Edm.ComplexType)` støtter opp til 100 vektorer per dokument
+  - `perDocumentVectorLimit: 1` — én vektor per dokument i resultater
+  - `perDocumentVectorLimit: 0` — ubegrenset (alle matchende vektorer)
+  - Nyttig for multimodal data (scene embeddings i video, fragmenter i lange dokumenter)
+
+**Tuning ved overbelastning:**
+Reduser `efSearch` (f.eks. 800 → 128-192) og `maxConnections` (64 → 32) FØR du skalerer ut med flere replicas. Hybrid queries med aggressive vector-innstillinger + semantic ranker øker CPU/minne-press betydelig.
--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/custom-dashboards-ai-operations.md
@ -1,7 +1,7 @@
 # Custom Dashboards for AI Operations

 **Kategori:** Monitoring & Observability
-**Sist oppdatert:** 2026-04
+**Sist oppdatert:** 2026-04 | Verified: MCP 2026-04
 **Brukes av:** Cosmo Skyberg, Microsoft AI Solution Architect

 ---
@ -88,7 +88,7 @@ Workbooks kan deployes via ARM templates for consistency across teams:
  "name": "ai-operations-workbook",
  "type": "microsoft.insights/workbooks",
  "location": "[resourceGroup().location]",
-  "apiVersion": "2022-04-01",  // For workbook instances; use 2020-11-20 for workbook templates
+  "apiVersion": "2022-04-01",  // For workbook instances; workbook templates bruker 2020-11-20 (workbooktemplates resource type). Bicep støttes nå offisielt som alternativ til ARM JSON. *(Verified MCP 2026-04)*
  "properties": {
    "displayName": "AI Operations Dashboard",
    "serializedData": "{\"version\":\"Notebook/1.0\",\"items\":[...]}",
@ -484,7 +484,7 @@ Når kunden spør om dashboards for AI operations:
 - [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)
- [Workbooks programmatic management](https://learn.microsoft.com/en-us/azure/azure-monitor/visualize/workbooks-automate)
+- [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)

 ### Code Samples
--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/endpoint-health-and-capacity-planning.md
@ -269,16 +269,32 @@ AzureMetrics
 **Metric alert for availability:**

 ```bash
+# Anbefalt CLI-syntaks (2026): Bruk condition sub-command for betingelser
+scope=$(az cognitiveservices account show \
+  --resource-group "rg-ai-prod" --name "{account}" --output tsv --query id)
+
+action=$(az monitor action-group show \
+  --resource-group "rg-ai-prod" --name "{actionGroup}" --output tsv --query id)
+
+condition=$(az monitor metrics alert condition create \
+  --aggregation Average \
+  --metric "AzureOpenAIAvailabilityRate" \
+  --op LessThan \
+  --type static \
+  --threshold 99 \
+  --output tsv)
+
 az monitor metrics alert create \
  --name "OpenAI-LowAvailability" \
  --resource-group "rg-ai-prod" \
-  --scopes "/subscriptions/{sub}/resourceGroups/{rg}/providers/Microsoft.CognitiveServices/accounts/{account}" \
-  --condition "avg AzureOpenAIAvailabilityRate < 99" \
+  --scopes $scope \
+  --condition $condition \
+  --action $action \
  --window-size 5m \
  --evaluation-frequency 1m \
-  --action "/subscriptions/{sub}/resourceGroups/{rg}/providers/microsoft.insights/actionGroups/{actionGroup}" \
  --description "Alert hvis availability < 99% over 5 min"
 ```
+*(Verified MCP 2026-04 — nytt mønster med `condition create` sub-command)*

 **Log alert for 429 errors:**

--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/sla-monitoring-ai-services.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/monitoring-observability/sla-monitoring-ai-services.md
@ -360,7 +360,7 @@ Metric Alert

 3. **Monitoring and diagnostics guidance**
   https://learn.microsoft.com/en-us/azure/architecture/best-practices/monitoring
-   *Confidence: Verified* — SLA monitoring best practices (generell Azure-arkitektur).
+   *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
@ -372,7 +372,7 @@ Metric Alert

 6. **Azure Monitor alerts overview**
   https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview
-   *Confidence: Verified* — Alert-typer: metric, log search, simple log search (preview, per-row evaluering), activity log, smart detection, Prometheus. Alerts lagres i 30 dager. Stateful log search alerts har detaljerte resolusjonskriterier per evalueringsfrekvens. Query-based metric alerts for Prometheus/OpenTelemetry i public preview. *(Verified MCP 2026-04)*
+   *Confidence: Verified* — Alert-typer: metric, log search, simple log search (preview, per-row evaluering), activity log, smart detection, Prometheus. Alerts lagres i 30 dager. Stateless alerts trigges for hver frekvens (konfigurerbar) mens condition er oppfylt — metric alerts med frekvens <5 min trigger 1-6 min etter, ≥5 min trigger 15-30 min etter. Stateful log search alerts: resolved når condition ikke er oppfylt for 2-3 frekvensperioder (avhenger av frekvens). Query-based metric alerts for Prometheus/OpenTelemetry i public preview. *(Verified MCP 2026-04)*

 7. **Reliability in Azure AI Search (SLA example)**
   https://learn.microsoft.com/en-us/azure/reliability/reliability-ai-search#service-level-agreement
--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/norwegian-public-sector-governance/norge-ai-strategy-government.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/norwegian-public-sector-governance/norge-ai-strategy-government.md
@ -132,13 +132,14 @@ Microsoft tilbyr spesialtilpassede løsninger:
 - [Govern AI](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/govern) — Strukturert governance-prosess
 - [Secure AI](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/secure) — Sikkerhetsrammeverk *(Verified MCP 2026-04)*

-**Oppdatert innhold i Secure AI (CAF):**
- Faseinndeling: Discover risks → Protect resources → Detect threats (kontinuerlig prosess)
- Nye trusselkilder: MITRE ATLAS og OWASP Generative AI risk supplerer STRIDE-rammeverket
- AI asset inventory via Azure Resource Graph + Microsoft Defender for Cloud
- MCP server-sikkerhet: Azure API Management beskytter Model Context Protocol (MCP)-endepunkter
- Microsoft Purview Insider Risk Management for prompt-basert dataeksfiltrering
- AI Security Posture Management (DSPM) i Defender for Cloud for automatisk deteksjon
+**Oppdatert innhold i Secure AI (CAF):** *(Verified MCP 2026-04)*
+- **3-fase prosess:** Discover AI risks → Protect AI resources & data → Detect AI threats (kontinuerlig)
+- **Trusselmodellering:** STRIDE som grunnlag, supplementert med MITRE ATLAS og OWASP Generative AI risk
+- **AI asset inventory:** Azure Resource Graph for å oppdage AI-ressurser + Microsoft Defender for Cloud for å identifisere generative AI workloads
+- **Sikre kommunikasjonskanaler:** Managed identities (uten lagrede credentials), Virtual Networks for isolasjon, Azure API Management for å sikre MCP-endepunkter
+- **Datavern:** Microsoft Purview Insider Risk Management for prompt-basert dataeksfiltrering + identifikasjon av risikabelt AI-atferd
+- **AI Security Posture Management (DSPM):** Automatisk deteksjon og remediation av generative AI-risikoer i Defender for Cloud
+- **DLP for AI:** Microsoft Purview DLP scanner og blokkerer sensitive data i AI-workflows; custom content filtering for organisasjonsspesifikke mønstre

 **AI Impact Assessment:**
 - [AI Impact Assessment Template](https://www.microsoft.com/ai/tools-practices) — For risikovurdering
--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/responsible-ai/ai-center-of-excellence-setup.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/responsible-ai/ai-center-of-excellence-setup.md
@ -1,7 +1,7 @@
 # AI Center of Excellence - Building Organizational Capability

 **Kategori:** Responsible AI & Governance
-**Opprettet:** 2026-04
+**Opprettet:** 2026-04 | **Verified:** MCP 2026-04
 **Confidence:** HIGH (basert på Microsoft Cloud Adoption Framework og offisiell dokumentasjon)

 ## Introduksjon
@ -652,6 +652,40 @@ Executive sponsorship tilgjengelig? ──No──> Ikke etabler CoE nå
 - **Custom model development:** Eskalere til Data Science Lead for advanced model training/fine-tuning
 - **Agent orchestration:** Eskalere til Agent Framework Specialist for complex multi-agent systems

+
+
+## Oppdatert CAF-guidance for AI CoE (2026) *(Verified MCP 2026-04)*
+
+Microsoft Cloud Adoption Framework (CAF) har oppdatert sin AI CoE-veiledning med en strukturert tilnærming til å bygge og modne et AI Center of Excellence.
+
+### CAF AI CoE — Bygge teamet (5 steg)
+
+1. **Sikre executive sponsorship** — Styr-komité med business- og IT-ledere, månedlige progress reviews, direkte tilgang til C-nivå beslutningstakere
+2. **Utnevne AI CoE-leder** — Dedikert leder med sterk AI-ekspertise, lederferdigheter og evne til å påvirke interessenter
+3. **Sette sammen AI CoE-teamet** — Tverrfaglig team: senior data scientists, ML-ingeniører, AI governance-eksperter, AI-sikkerhetsspecialister, AI ops-profesjonelle
+4. **Plassering i organisasjonen** — Integrer i eksisterende Cloud CoE (CCoE) hvis det finnes. Unngå unødvendig kompleksitet — bygg på sterke fundamenter fremfor isolert drift
+5. **Definere driftsmodell** — Sentralisert CoE i tidlig fase → Advisory-modell etter hvert som AI-adopsjonen modnes
+
+### CAF AI CoE — Ansvarsområder
+
+| Fokusområde | Ansvarsoppgaver |
+|-------------|----------------|
+| **AI-strategi** | Strategisk alignment med forretningmål, use case-identifikasjon, responsible AI-strategi |
+| **AI-kompetanse** | Skills-vurdering, læringsprogrammer, hands-on eksperimentering |
+| **Pilotprosjekter** | Strategiske POCer for å validere AI-tilnærminger og demonstrere forretningsverdi |
+| **Standarder og governance** | [Governance policies](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/govern) og [sikkerhetsstandareder](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/secure), bias-review, compliance-audit |
+| **Intake og prioritering** | Strukturert inntak av AI-prosjektforespørsler med konsistente kriterier |
+| **Gjenbrukbare assets** | Compliance-sjekklister, templates, kode-repositories, intern knowledge sharing |
+| **Resultater og rapportering** | KPIer: adoption rates, compliance levels, project cycle times |
+
+### CAF AI CoE — Evolusjon (Advisory-modell)
+
+Signaler på at CoE bør gå fra sentralisert kontroll til advisory-modell:
+- Godkjenningsforsinkelser og knowledge bottlenecks hos CoE-eksperter
+- Friksjon mellom produktteam og CoE om prioriteringer fremfor verdi-levering
+
+**Overgang:** Distribuer AI-ekspertise til produktteam, plattformteam og enabling-teams. CoE fokuserer på retningslinjer og policy fremfor direkte kontroll.
+
 ## Kilder og verifisering

 ### Microsoft Learn & Cloud Adoption Framework
--- a/plugins/ms-ai-architect/skills/ms-ai-governance/references/responsible-ai/ai-impact-assessment-framework.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-governance/references/responsible-ai/ai-impact-assessment-framework.md
@ -552,6 +552,39 @@ Impact Assessment for offentlig sektor i Norge må adressere:

 *(Verified MCP 2026-04)*

+
+
+## Purview SDK-integrasjon for AI-applikasjonstesting *(Verified MCP 2026-04)*
+
+Microsoft Purview tilbyr nå API-basert integrasjon for AI-applikasjoner via Microsoft Graph, som muliggjør automatisert testing og compliance-verifisering av AI-systemer.
+
+### Test-oppsett (DSPM for AI)
+
+For å teste Purview-integrasjon i AI-applikasjoner:
+
+1. **Aktiver DSPM for AI** — Enable 1-click policies i DSPM for AI Overview:
+   - "DSPM for AI - Capture interactions for enterprise AI apps"
+   - "DSPM for AI - Unethical behavior in AI apps" (Communication Compliance)
+   - "DSPM for AI - Risky AI usage" (Insider Risk Management)
+
+2. **Verifiser datafangst** i Purview etter AI-interaksjoner:
+   - **Activity Explorer:** Filtrer på "AI interaction" og "Sensitive info types"
+   - **Purview Audit:** Søk på `ConnectedAIApp` i Workloads eller `connectedAIAppInteraction` i Activities
+
+3. **Insider Risk Management:** Opprett "Risky AI Usage (preview)"-policy med "Generative AI app → Enterprise AI apps" indikatorer
+
+4. **eDiscovery:** Søk med KQL `ItemClass=IPM.SkypeTeams.Message.ConnectedAIApp.Entra.*{EntraAppID}*` for å finne AI-interaksjoner
+
+5. **Data Lifecycle Management:** Opprett retention policy med location = "Enterprise AI app" for å definere hva som skal beholdes og hvor lenge
+
+### Relevans for Impact Assessment
+
+Purview SDK-integrasjon gir:
+- **Observerbarhet:** Hvem spurte hva, når, og hvilke sensitive data ble eksponert
+- **Etterprøvbarhet:** eDiscovery-søkbarhet av AI-interaksjoner for juridiske prosesser
+- **Risikodeteksjon:** Automatisk identifisering av risikabel AI-bruk via IRM-policies
+- **Compliance-dokumentasjon:** Audit logs for AI Act Article 72 og Forvaltningsloven
+
 ## Kilder og verifisering

 ### Primary sources (Verified)
--- a/plugins/ms-ai-architect/skills/ms-ai-infrastructure/references/bcdr/monitoring-alerting-failover-detection.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-infrastructure/references/bcdr/monitoring-alerting-failover-detection.md
@ -412,13 +412,37 @@ def main(req: func.HttpRequest) -> func.HttpResponse:
    return func.HttpResponse("Alert received, no failover needed", status_code=200)
 ```

+
+
+## Application Insights for AI-agenter i BCDR-kontekst *(Verified MCP 2026-04)*
+
+Azure Monitor Application Insights tilbyr nå dedikert støtte for AI-agenter via **Agent details view**, som er kritisk for failover-deteksjon i agent-baserte AI-systemer.
+
+### Agent details view — BCDR-relevans
+
+| Funksjon | BCDR-bruk |
+|----------|-----------|
+| **Unified agent view** | Monitorer agenter fra Foundry, Copilot Studio og tredjeparts i én visning |
+| **End-to-end transaction details** | Spor samtaler (prompts, systemInstructions, tool usage) ved incident-analyse |
+| **Live metrics** | Sanntids health under failover-scenarier |
+| **Availability tests** | Automatisk helsesjekk av agent-endepunkter |
+
+### Instrumenteringsveiledning per agent-plattform
+
+- **Azure AI Foundry-agenter:** Koble Application Insights til Foundry-prosjektet for automatisk tracing
+- **Copilot Studio-agenter:** Konfigurer built-in telemetri-eksport til App Insights
+- **Microsoft Agent Framework (self-hosted):** Bruk Azure Monitor OpenTelemetry Distro
+- **LangChain/LangGraph og OpenAI Agents SDK:** Bruk Azure AI OpenTelemetry Tracer
+
+**Anbefaling:** Gi hver agent et unikt navn for å skille dem i Agent details view. Bruk samme App Insights-ressurs for agenter som er del av et større system.
+
 ## Referanser

 - [Monitor Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/monitor-openai) — OpenAI monitoring og alerting
 - [Monitor Azure AI Search](https://learn.microsoft.com/en-us/azure/search/monitor-azure-cognitive-search) — AI Search monitoring
- [Azure Monitor alerts overview](https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview) — Alert-rammeverk
+- [Azure Monitor alerts overview](https://learn.microsoft.com/en-us/azure/azure-monitor/alerts/alerts-overview) — Alert-rammeverk *(Verified MCP 2026-04)* — Stateful vs. stateless alerts, Simple Log Search Alerts (preview) for per-row evaluering, Query-based metric alerts for Prometheus/OTel (public preview). Alert processing rules for suppression ved planlagt vedlikehold. Opptil 5 action groups per alert rule.
 - [Health modeling and observability of mission-critical workloads](https://learn.microsoft.com/en-us/azure/well-architected/mission-critical/mission-critical-health-modeling) — Health modeling
- [Application Insights overview](https://learn.microsoft.com/en-us/azure/azure-monitor/app/app-insights-overview) — APM for applikasjoner
+- [Application Insights overview](https://learn.microsoft.com/en-us/azure/azure-monitor/app/app-insights-overview) — APM for applikasjoner *(Verified MCP 2026-04)* — Nå OpenTelemetry-basert (OTel) som primær instrumentering. Nye features: **Agent details view** for AI-agenter fra Foundry, Copilot Studio og tredjeparts agenter. Støtter: Azure AI Foundry (via Foundry SDK tracing), Copilot Studio (built-in telemetri → App Insights), Microsoft Agent Framework (self-hosted), LangChain/LangGraph og OpenAI Agents SDK. Batch og continuous evaluations for produksjonstraffic. Live Metrics for sanntids observabilitet under failover-scenarier.
 - [Azure Service Health](https://learn.microsoft.com/en-us/azure/service-health/overview) — Azure-tjenestestatus

 ## For Cosmo
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/ai-incident-response-procedures.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/ai-incident-response-procedures.md
@ -1,6 +1,6 @@
 # AI Incident Response and Breach Handling Procedures

-**Last updated:** 2026-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Established Practice
 **Category:** AI Security Engineering

@ -586,7 +586,7 @@ Set-AzSecurityContact -Name "default1" `

 ### Konfidensnivå

-**Verified (High Confidence)** — Alle Azure-native tools, services og incident response procedures er verifisert via Microsoft Learn MCP-research (februar 2026). Prisestimater basert på offisiell Azure pricing, men kan variere ved currency fluctuation og regional pricing.
+**Verified (High Confidence)** — Alle Azure-native tools, services og incident response procedures er verifisert via Microsoft Learn MCP-research (februar 2026, re-verifisert april 2026). CAF Secure AI-dokumentet bekrefter: AI asset inventory via Azure Resource Graph, AI communication channel security (Managed Identities, Virtual Networks, APIM for MCP server-endepunkter), og Purview Insider Risk Management for prompt-basert data exfiltration-deteksjon. Prisestimater basert på offisiell Azure pricing, men kan variere ved currency fluctuation og regional pricing.

 **Baseline (Model Knowledge)** — Generell incident response framework (NIST SP 800-61), MITRE ATT&CK for ML, og best practices for forensics/chain of custody basert på industry standards. Norwegian regulatory requirements verifisert via offentlige kilder (Datatilsynet, NSM, Lovdata).

--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/ai-threat-modeling-stride.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/ai-threat-modeling-stride.md
@ -1,6 +1,6 @@
 # AI Threat Modeling Using STRIDE Framework

-**Last updated:** 2026-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** Established Practice
 **Category:** AI Security Engineering

--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/data-leakage-prevention-ai.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/data-leakage-prevention-ai.md
@ -1,7 +1,7 @@
 # Data Leakage Prevention in AI Contexts

 **Kategori:** AI Security Engineering
-**Sist oppdatert:** 2026-04
+**Sist oppdatert:** 2026-04 | Verified: MCP 2026-04
 **Målgruppe:** Enterprise AI architects og security teams

 ## Oversikt
@ -758,6 +758,6 @@ az monitor metrics alert create \
 **Microsoft Learn kilder:**
 - [Microsoft Purview DLP for Copilot](https://learn.microsoft.com/en-us/purview/dlp-microsoft365-copilot-location-learn-about)
 - [Azure AI Services DLP](https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-data-loss-prevention)
- [Secure AI (Cloud Adoption Framework)](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/secure)
+- [Secure AI (Cloud Adoption Framework)](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/secure) — Verified MCP 2026-04: Bekrefter bruk av Microsoft Purview DLP for AI-workflows, content filtering for å forhindre sensitiv informasjonslekkasje, og Purview Insider Risk Management for prompt-basert data exfiltration-deteksjon og identifisering av risikofull AI-atferd.
 - [Artificial Intelligence Security (MCSB)](https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security)
 - [Confidential AI](https://learn.microsoft.com/en-us/azure/confidential-computing/confidential-ai)
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md
@ -1,7 +1,7 @@
 # Microsoft Entra Agent ID — Zero Trust for AI-agentidentiteter

 **Kategori:** AI Security Engineering
-**Sist oppdatert:** 2026-04
+**Sist oppdatert:** 2026-04 | Verified: MCP 2026-04
 **Status:** Public Preview (annonsert Ignite november 2025, utvidet preview; opt-out er midlertidig — vil bli obligatorisk for nye agenter) *(Verified MCP 2026-04)*
 **Målgruppe:** Arkitekter som skal sikre AI-agenter med dedikerte identiteter og Zero Trust-prinsipper

@ -422,7 +422,7 @@ Når en Foundry-agent publiseres, endres identiteten fra delt prosjektidentitet
 8. [Governing Agent Identities (Preview)](https://learn.microsoft.com/entra/id-governance/agent-id-governance-overview) — Identity Governance for agenter
 9. [Conditional Access for Agent ID (Preview)](https://learn.microsoft.com/entra/identity/conditional-access/agent-id) — Conditional Access for agentidentiteter
 10. [Protect agent identities with Microsoft Entra](https://learn.microsoft.com/microsoft-agent-365/admin/capabilities-entra) — Microsoft Agent 365-integrasjon
-11. [What's new at Microsoft Ignite 2025 - Microsoft Entra](https://learn.microsoft.com/entra/fundamentals/whats-new-ignite-2025) — Annonsering og ny dokumentasjon
+11. [What's new at Microsoft Ignite 2025 - Microsoft Entra](https://learn.microsoft.com/entra/fundamentals/whats-new-ignite-2025) — Annonsering og ny dokumentasjon. Verified MCP 2026-04: Bekrefter 50+ nye artikler om Agent ID, nye RBAC-roller (Agent ID Administrator, Agent ID Developer, Agent Registry Administrator), Conditional Access for agentidentiteter, Identity Protection for agenter (risky agents concept), AI Prompt Shield (Entra Internet Access), og Security Copilot + Entra-integrasjoner.
 12. [Surfing the AI Wave: Manage, Govern, and Protect AI Agents with Microsoft Entra Agent ID](https://techcommunity.microsoft.com/blog/microsoft-entra-blog/surfing-the-ai-wave-manage-govern-and-protect-ai-agents-with-microsoft-entra-age/2464407) — Offisiell Microsoft Entra-blogg, Ignite 2025

 ---
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/security-copilot-integration.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/ai-security-engineering/security-copilot-integration.md
@ -1,7 +1,7 @@
 # Microsoft Security Copilot — AI-drevet sikkerhetsoperasjonsplattform

 **Kategori:** AI Security Engineering
-**Sist oppdatert:** 2026-04
+**Sist oppdatert:** 2026-04 | Verified: MCP 2026-04
 **Målgruppe:** Sikkerhetsarkitekter og SOC-ledere som vurderer AI-assistert sikkerhetsoperasjon

 ## Introduksjon
@ -420,14 +420,14 @@ Per 2026-02: Security Copilot er kun tilgjengelig på kommersielt skynivå — i

 ## Kilder

-Basert på offisiell Microsoft Learn-dokumentasjon (sist verifisert 2026-04 via MCP): *(Verified MCP 2026-04)*
+Basert på offisiell Microsoft Learn-dokumentasjon (sist verifisert 2026-04 via MCP): *(Verified MCP 2026-04)* — Inklusjonsmodellen (M365 E5 → 400 SCU/1000 lisenser, maks 10 000 SCU/mnd, zero-click provisjonering) er bekreftet via MCP-fetch av security-copilot-inclusion og get-started-security-copilot.

 1. [What is Microsoft Security Copilot?](https://learn.microsoft.com/copilot/security/microsoft-security-copilot) — Overordnet produktbeskrivelse
 2. [Microsoft Security Copilot agents overview](https://learn.microsoft.com/copilot/security/agents-overview) — Komplett agentoversikt
 3. [Deploy AI agents in Microsoft Defender](https://learn.microsoft.com/defender-xdr/security-copilot-agents-defender) — Defender-spesifikke agenter
 4. [Security Copilot with Microsoft Sentinel](https://learn.microsoft.com/azure/sentinel/sentinel-security-copilot) — Sentinel-integrasjon
-5. [Learn about Security Copilot inclusion in Microsoft 365 E5](https://learn.microsoft.com/copilot/security/security-copilot-inclusion) — E5-lisensiering og SCU-modell
-6. [Get started with Microsoft Security Copilot](https://learn.microsoft.com/copilot/security/get-started-security-copilot) — Onboarding og lisensiering
+5. [Learn about Security Copilot inclusion in Microsoft 365 E5](https://learn.microsoft.com/copilot/security/security-copilot-inclusion) — E5-lisensiering og SCU-modell. Verified MCP 2026-04: Bekrefter rollout startet 18. november 2025, 400 SCU/måned per 1000 brukerlisenser (maks 10 000 SCU/mnd), zero-click auto-provisionering med 30-dagers forhåndsvarsel, SCU nullstilles månedlig, Developer Experiences (Agent Builder, MCP og Graph API-integrasjoner) er inkludert.
+6. [Get started with Microsoft Security Copilot](https://learn.microsoft.com/copilot/security/get-started-security-copilot) — Onboarding og lisensiering. Verified MCP 2026-04: Bekrefter to kundekategorier — M365 E5-kunder (auto-provisionert) og ikke-E5-kunder (manuell onboarding med SCU-provisjonering). M365 E5-kunder trenger ikke Azure-oppsett eller manuell SCU-tildeling.
 7. [Create your own custom plugins](https://learn.microsoft.com/copilot/security/custom-plugins) — Egendefinerte plugins
 8. [Microsoft Security Copilot Phishing Triage Agent](https://learn.microsoft.com/defender-xdr/phishing-triage-agent) — Phishing Triage Agent detaljer
 9. [Security Copilot agents in Intune overview](https://learn.microsoft.com/intune/agents/) — Intune-agenter
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/cost-optimization/multi-model-strategy-costs.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/cost-optimization/multi-model-strategy-costs.md
@ -1,6 +1,6 @@
 # Multi-Model Strategy: Cost-Performance Trade-offs

-**Last updated:** 2026-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Cost Optimization & FinOps for AI

@ -638,7 +638,7 @@ az consumption usage list --start-date 2026-02-01 --end-date 2026-02-28 \

 **Microsoft Learn (MCP-verified):**
 1. [Model router for Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/model-router) — **Verified** (MCP fetch, 2026-04)
-2. [Use a gateway in front of multiple Azure OpenAI deployments](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — **Verified** (MCP fetch, 2026-04)
+2. [Use a gateway in front of multiple Azure OpenAI deployments](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — **Verified** (MCP fetch, 2026-04). Dokument bekrefter: (a) credential termination og reestablishment ved gateway anbefales fremfor pass-through client credentials, (b) gateway gir client-based usage tracking og chargeback-støtte, (c) Azure OpenAI er nå tagget som "Foundry Tools / Azure OpenAI in Foundry Models".
 3. [Understanding costs associated with provisioned throughput units (PTU)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) — **Verified** (MCP search, 2026-04)
 4. [Azure OpenAI in Azure AI Foundry Models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models) — **Verified** (MCP search, 2026-04)
 5. [GPT-4o vs GPT-4o mini model selection](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/whats-new) — **Verified** (MCP search, 2026-04)
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/cost-optimization/observability-cost-reduction.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/cost-optimization/observability-cost-reduction.md
@ -1,6 +1,6 @@
 # Observability and Monitoring Cost Optimization

-**Last updated:** 2026-04
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Cost Optimization & FinOps for AI

@ -169,6 +169,8 @@ builder.Services.AddApplicationInsightsTelemetry(new ApplicationInsightsServiceO
 | **Alerts** | Støttes | Støttes ikke | Støttes ikke |
 | **Retention** | 30-730 dager | 8 dager interactive + long-term | Long-term kun |
 | **Pris (ingestion)** | Standard | ~50% lavere | ~75% lavere |
+| **Workspace replication** | ✅ | ✅ | ❌ (data ikke replikert — ingen beskyttelse ved regional feil) |
+| **Customer Lockbox** | ✅ | ✅ | ❌ (Lockbox-grensesnitt gjelder ikke for Auxiliary-tabeller) |

 **Beslutningstre:**
 1. **Trenger du real-time alerting?** → Analytics
@ -441,7 +443,7 @@ For volumer >1 TB/dag, vurder dedicated cluster for ytterligere besparelser (clu

 10. **Azure Monitor Logs overview: Table plans:**
    https://learn.microsoft.com/en-us/azure/azure-monitor/logs/data-platform-logs#table-plans
-    *Confidence: Verified* – Analytics, Basic, Auxiliary table plans.
+    *Confidence: Verified (MCP 2026-04)* – Analytics, Basic, Auxiliary table plans. Oppdatering 2026-04: Auxiliary-plan bekrefter ingen workspace replication (data ikke beskyttet mot regional feil) og ingen Customer Lockbox-støtte.

 ### Norsk lovverk (Baseline-kunnskap)

--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/performance-scalability/async-processing-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/performance-scalability/async-processing-patterns.md
@ -1,6 +1,6 @@
 # Asynchronous Processing Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Performance & Scalability

@ -428,6 +428,84 @@ public class AIRequestController : ControllerBase
 }
 ```

+
+## Event-Driven Architecture Styles (oppdatert 2026-04)
+
+Microsoft dokumenterer to primære topologier for event-drevet AI-prosessering:
+
+### Broker-topologi vs. Mediator-topologi
+
+| Aspekt | Broker-topologi | Mediator-topologi |
+|--------|----------------|-------------------|
+| Koordinering | Events publiseres direkte til broker | Central mediator koordinerer workflow |
+| Eksempel | Azure Event Hubs + Service Bus | Azure Durable Functions |
+| Kobling | Løs kobling mellom produsenter/konsumenter | Sterkere kobling via mediator |
+| Bruksscenario | Høyvolum streaming, uavhengige konsumenter | Komplekse AI-arbeidsflyter med avhengigheter |
+
+### Azure Event Hubs vs. Azure Event Grid
+
+| Service | Type | Bruksscenario |
+|---------|------|---------------|
+| **Azure Event Hubs** | Durable event stream (log) | AI-inferensresultater som skal prosesseres av mange konsumenter |
+| **Azure Event Grid** | Publish-subscribe, reaktiv | Trigger AI-jobb ved filnedlasting, blob-endring |
+| **Azure Service Bus** | Message queue, garantert levering | Jobb-kø for AI-prosessering med retry og dead-letter |
+
+### Utfordringer i event-drevne AI-arkitekturer
+
+```python
+# Utfordring 1: Garantert levering
+# Bruk Service Bus med peek-lock for å garantere at AI-jobb fullføres
+
+from azure.servicebus import ServiceBusClient, ServiceBusMessage
+import json
+
+def process_ai_job_safely(
+    servicebus_conn: str,
+    queue_name: str,
+    ai_processor
+) -> None:
+    """Garantert levering via peek-lock mønster."""
+    with ServiceBusClient.from_connection_string(servicebus_conn) as sb:
+        with sb.get_queue_receiver(queue_name, max_wait_time=5) as receiver:
+            for message in receiver:
+                # Peek-lock: meldingen er reservert, ikke slettet
+                try:
+                    payload = json.loads(str(message))
+                    result = ai_processor(payload)
+                    # Fullfør melding (slett fra kø) kun ved suksess
+                    receiver.complete_message(message)
+                    publish_result(result)
+                except Exception as e:
+                    # Abandon: meldingen returneres til kø for ny levering
+                    receiver.abandon_message(message)
+
+# Utfordring 2: Eventual consistency
+# AI-resultater publiseres asynkront — bruk correlation ID for sporing
+
+def create_ai_job(correlation_id: str, payload: dict) -> dict:
+    """Returner job receipt umiddelbart, resultat kommer asynkront."""
+    return {
+        "correlation_id": correlation_id,
+        "status": "accepted",
+        "result_url": f"/api/results/{correlation_id}",
+        "estimated_completion_seconds": 30
+    }
+
+# Utfordring 3: Ordregaranti
+# Event Hubs garanterer ordre innen én partisjon
+# Bruk samme partisjonsnøkkel for relaterte AI-forespørsler
+
+def publish_ordered_event(
+    producer,
+    partition_key: str,  # f.eks. dokument-ID
+    event_data: dict
+) -> None:
+    from azure.eventhub import EventData
+    event = EventData(json.dumps(event_data))
+    event.properties = {"partition_key": partition_key}
+    producer.send_batch([event], partition_key=partition_key)
+```
+
 ## Norsk offentlig sektor

 - **Saksbehandlingssystemer**: Asynkron prosessering er ideelt for AI-assistert saksbehandling der analyse kan ta tid. Saksbehandler sender inn dokument, fortsetter med annet arbeid, og mottar notifikasjon når analysen er ferdig.
--- a/plugins/ms-ai-architect/skills/ms-ai-security/references/performance-scalability/connection-pooling-patterns.md
+++ b/plugins/ms-ai-architect/skills/ms-ai-security/references/performance-scalability/connection-pooling-patterns.md
@ -1,6 +1,6 @@
 # Connection Pooling Patterns

-**Last updated:** 2026-02
+**Last updated:** 2026-04 | Verified: MCP 2026-04
 **Status:** GA
 **Category:** Performance & Scalability

@ -314,6 +314,56 @@ class ConnectionPoolLoadBalancer:
        raise Exception("All backends exhausted")
 ```

+
+## Azure API Management som Connection Pooling-lag (oppdatert 2026-04)
+
+APIM håndterer backend connection pooling mot Azure OpenAI, noe som avlaster klientsiden:
+
+### APIM Backend Pool-konfigurasjon
+
+```xml
+<!-- APIM: Backend pool med automatisk connection management -->
+<policies>
+    <inbound>
+        <base />
+        <!-- APIM gjenbruker backend-connections automatisk via intern pool -->
+        <!-- Klientene ser APIM som et enkelt endepunkt -->
+        <set-backend-service id="aoai-pool" backend-id="aoai-norway-backend" />
+        
+        <!-- Legg til correlation ID for tracing -->
+        <set-header name="x-correlation-id" exists-action="skip">
+            <value>@(context.RequestId)</value>
+        </set-header>
+    </inbound>
+    
+    <backend>
+        <retry condition="@(context.Response.StatusCode == 429 || context.Response.StatusCode >= 500)"
+               count="3" interval="0" first-fast-retry="true">
+            <!-- APIM håndterer retry mot backend-pool -->
+            <forward-request timeout="120" />
+        </retry>
+    </backend>
+    
+    <outbound>
+        <!-- Eksponer backend latens-metrikk til klient -->
+        <set-header name="x-backend-latency-ms" exists-action="override">
+            <value>@(context.Elapsed.TotalMilliseconds.ToString())</value>
+        </set-header>
+    </outbound>
+</policies>
+```
+
+### Backend-konfigurasjoner i APIM (4 topologier)
+
+Microsoft anbefaler disse mønstrene for APIM connection pooling mot Azure OpenAI:
+
+1. **Single backend**: Én APIM → én Azure OpenAI (enkelt, begrenset kvote)
+2. **Multi-backend single region**: APIM med weighted round-robin mellom Azure OpenAI-instanser
+3. **Multi-subscription**: Separate Azure OpenAI-instanser i ulike subscriptions for kvote-skalering
+4. **Multi-region**: APIM i flere regioner, each med regionale backends
+
+Klientene trenger aldri kjenne til antallet backends — APIM håndterer routing transparent.
+
 ## Norsk offentlig sektor

 Connection pooling har spesielle hensyn for norsk offentlig sektor:
--- a/Show more
+++ b/Show more