docs(ms-ai-architect): KB-refresh tema-b — Foundry-navnesveip «Azure AI Foundry»→«Microsoft Foundry» (233 filer)

Verifisert mot offisiell MS-doc (juni 2026): «Microsoft Foundry» er det gjeldende produkt-/portalnavnet; «Foundry (classic)» = gamle «Azure AI Foundry» (/azure/foundry/ vs /azure/foundry-classic/). Premiss bekreftet før sveip. Multi-regel, IKKE naiv s/Azure AI Foundry/Microsoft Foundry/ — MS dropper «Azure AI» (legger IKKE til «Microsoft») for to produktvarianter: - «Azure AI Foundry Agent[ Service|s]» → «Foundry Agent Service/Agents» (MS-form) - «Azure AI Foundry Models» → «Foundry Models» (i «Azure OpenAI in Foundry Models») - «Azure AI Foundry SDK» → «Microsoft Foundry SDK» (operatør-valg) - «Azure AI Foundry portal/project» + generisk → «Microsoft Foundry» - Pre-eksisterende «Microsoft Foundry Models» (4) normalisert → «Foundry Models» Bevart: «Azure OpenAI», «Azure AI Inference SDK», «Azure AI Search», «Azure AI Services», kode-IDer. Historisk ref «(tidligere Azure AI Foundry)» i model-catalog-2026.md beskyttet via lookbehind. URL /azure/ai-foundry/→ /azure/foundry/ kun i owasp-llm-top10 (KB-ref); docs/-filer deferred. Scope: skills (inkl. 3 SKILL.md) + commands + agents + README + CLAUDE. Ekskludert: docs/ (interne), playground/+tests/ fixtures (testdata), CHANGELOG.md (historisk logg), STATE.md (gitignored). 3 SKILL.md endret (advisor/engineering/security) → judge-cache teknisk invalidert for disse, men scorer uendret: advisor 91, eng/gov/infra/sec 96 (alle ≥90). validate 239/0. 0 «Azure AI Foundry» igjen (utenom bevart ref). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-23 21:00:27 +02:00 · 2026-06-23 21:00:27 +02:00 · 03d596e4ec
commit 03d596e4ec
parent 20b522ab10
233 changed files with 810 additions and 810 deletions
--- a/skills/ms-ai-advisor/references/prompt-engineering/adversarial-prompting-and-jailbreaks.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/adversarial-prompting-and-jailbreaks.md
@ -61,7 +61,7 @@ Azure AI Content Safety Prompt Shields detekterer fire hovedkategorier:
 | **Prompt Shields** | Real-time attack detection | Azure AI Content Safety |
 | **Content Filters** | Multi-layered filtering (input/output) | Default på alle modeller |
 | **Safety Meta-Prompts** | System-level behavior guidance | Model deployment config |
-| **Azure AI Red Teaming Agent** | Automated adversarial testing | Azure AI Foundry |
+| **Azure AI Red Teaming Agent** | Automated adversarial testing | Microsoft Foundry |
 | **PyRIT** | Python Risk Identification Tool | Open-source + Azure integration |

 ---
@ -352,7 +352,7 @@ if result.jailbreak_analysis.detected:

 ### Azure AI Red Teaming Agent

-**Setup via Azure AI Foundry SDK:**
+**Setup via Microsoft Foundry SDK:**

 ```python
 from azure.ai.evaluation import RedTeamingAgent
@ -561,7 +561,7 @@ Pricing not publicly disclosed — contact Microsoft for quote
 ### Azure AI Red Teaming Agent

 **Pricing:**
- Inkludert i Azure AI Foundry subscription
+- Inkludert i Microsoft Foundry subscription
 - No separate charge for red teaming runs
 - Underlying model costs apply (GPT-4o for adversarial model)

--- a/skills/ms-ai-advisor/references/prompt-engineering/chain-of-thought-prompting.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/chain-of-thought-prompting.md
@ -14,7 +14,7 @@ Teknikken er spesielt kraftfull for oppgaver som krever logisk resonnering, mate

 **Viktig distinksjon:** Tradisjonelle GPT-modeller (GPT-4, GPT-4o) krever eksplisitt CoT-prompting for å vise resonneringsteg. Reasoning models (o-serien, GPT-5-serien) utfører intern resonnering automatisk, og Microsoft anbefaler å **ikke bruke** CoT-teknikker med disse modellene, da det kan redusere ytelsen.

-Chain-of-thought ble først dokumentert i akademisk forskning (Wei et al., 2022) og har siden blitt adoptert som en standard teknikk i produksjonssystemer. Microsoft har integrert CoT-prinsipper både i Azure OpenAI Service documentation, Azure AI Foundry prompt engineering guidance, og i evalueringsrammeverk som Azure OpenAI Evaluation (Preview).
+Chain-of-thought ble først dokumentert i akademisk forskning (Wei et al., 2022) og har siden blitt adoptert som en standard teknikk i produksjonssystemer. Microsoft har integrert CoT-prinsipper både i Azure OpenAI Service documentation, Microsoft Foundry prompt engineering guidance, og i evalueringsrammeverk som Azure OpenAI Evaluation (Preview).

 ---

@ -188,9 +188,9 @@ Azure OpenAI Evaluation (Preview) bruker CoT internt for faktasjekking:
 ```python
 # Factuality evaluation using chain-of-thought grading
 evaluation_result = evaluator.evaluate_factuality(
-    query="What is Azure AI Foundry?",
-    ground_truth="Azure AI Foundry is a unified platform for building, testing, and deploying generative AI applications. Released: Nov 2024.",
-    response="Azure AI Foundry is Microsoft's platform for AI development, launched in late 2024."
+    query="What is Microsoft Foundry?",
+    ground_truth="Microsoft Foundry is a unified platform for building, testing, and deploying generative AI applications. Released: Nov 2024.",
+    response="Microsoft Foundry is Microsoft's platform for AI development, launched in late 2024."
 )

 # Evaluator uses CoT internally:
@ -292,7 +292,7 @@ When answering from knowledge sources, always:
 Format: [Source 1]: <info>, [Source 2]: <info> → Conclusion: <answer>
 ```

-### Azure AI Foundry
+### Microsoft Foundry

 I Prompt Flow kan du opprette en CoT-node:

--- a/skills/ms-ai-advisor/references/prompt-engineering/domain-specific-prompt-optimization.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/domain-specific-prompt-optimization.md
@ -334,7 +334,7 @@ For public sector:

 *(Confidence: MEDIUM-HIGH — Copilot Studio best practices)*

-### Azure AI Foundry
+### Microsoft Foundry

 **Domain-specific deployment pattern:**

@ -369,7 +369,7 @@ safety:
      action: "block"
 ```

-*(Confidence: MEDIUM — Azure AI Foundry er relativt nytt, pattern basert på generell guidance)*
+*(Confidence: MEDIUM — Microsoft Foundry er relativt nytt, pattern basert på generell guidance)*

 ---

@ -537,7 +537,7 @@ Basert på testing (Azure OpenAI dokumentasjon):

 | Fase | Verktøy | Formål |
 |------|---------|--------|
-| **Prompt-testing** | Azure AI Foundry Playground | Iterativ testing av system messages |
+| **Prompt-testing** | Microsoft Foundry Playground | Iterativ testing av system messages |
 | **Evaluation** | Prompt Flow + Custom evaluators | Måle domain accuracy (presisjon, recall, F1) |
 | **Deployment** | Azure OpenAI API + RAG | Produksjon med logging og monitoring |
 | **Monitoring** | Azure Monitor + Application Insights | Token usage, latency, error rate |
--- a/skills/ms-ai-advisor/references/prompt-engineering/error-handling-and-fallback-prompting.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/error-handling-and-fallback-prompting.md
@ -422,7 +422,7 @@ APIM kan enforces content safety checks automatisk:
 }
 ```

-### Azure AI Foundry Safety Evaluations
+### Microsoft Foundry Safety Evaluations

 For systematisk testing av error handling før produksjon:

--- a/skills/ms-ai-advisor/references/prompt-engineering/few-shot-learning-techniques.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/few-shot-learning-techniques.md
@ -316,7 +316,7 @@ var fewShotFunction = kernel.CreateSemanticFunction(fewShotPrompt);
 var result = await fewShotFunction.InvokeAsync("I want a refund for my purchase");
 ```

-### Azure AI Foundry
+### Microsoft Foundry

 **Prompt Flow:**
 - Few-shot templates i "Prompt" node
@ -509,7 +509,7 @@ User Query

 **Verified (MCP microsoft-learn, januar 2026):**

-1. **Prompt engineering techniques** (Azure AI Foundry)
+1. **Prompt engineering techniques** (Microsoft Foundry)
   - https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering
   - Seksjon: Few-shot learning, Zero-shot learning, Examples

--- a/skills/ms-ai-advisor/references/prompt-engineering/function-calling-and-tool-use.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/function-calling-and-tool-use.md
@ -236,7 +236,7 @@ raise Exception("Max iterations reached without final answer")

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry
+### Microsoft Foundry

 Function calling integreres sømløst med:
 - **Azure AI Search:** Bruk function calling til å bygge queries basert på brukerintent
@ -364,7 +364,7 @@ Function calling påvirker kostnaden på flere måter:
 | **Microsoft 365 E3/E5** | Ikke inkludert | N/A (må kjøpe separat) |
 | **Azure subscription** | Pay-as-you-go | Full support (alle modeller) |
 | **Copilot Studio (standalone)** | Begrenset via Actions | Indirekte (via Copilot Studio abstraksjon) |
-| **Azure AI Foundry** | Inkludert | Full support + Prompt Flow orkestrering |
+| **Microsoft Foundry** | Inkludert | Full support + Prompt Flow orkestrering |

 **Viktig:** Azure OpenAI krever godkjenning (application form). Offentlig sektor i Norge har vanligvis raskere godkjenning.

--- a/skills/ms-ai-advisor/references/prompt-engineering/grounding-and-knowledge-injection.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/grounding-and-knowledge-injection.md
@ -52,12 +52,12 @@ System: You are an AI assistant. Answer ONLY using the provided context.

 Context:
 ---
-[DOCUMENT 1]: Azure AI Foundry is a unified platform for building, testing,
+[DOCUMENT 1]: Microsoft Foundry is a unified platform for building, testing,
 and deploying generative AI applications. Released: Nov 2024.
 [DOCUMENT 2]: Azure OpenAI Service offers GPT-4, GPT-4 Turbo, and o-series models...
 ---

-User: What is Azure AI Foundry?
+User: What is Microsoft Foundry?
 ```

 **Fordeler:** Enkel å implementere, full kontroll over context.
--- a/skills/ms-ai-advisor/references/prompt-engineering/multi-turn-conversation-management.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/multi-turn-conversation-management.md
@ -391,7 +391,7 @@ chatHistory.AddAssistantMessage(response.Content);

 **Fordeler:** Plugin-integrasjon, function calling, planlegging.

-### Azure AI Foundry (tidligere Azure AI Studio)
+### Microsoft Foundry (tidligere Azure AI Studio)

 **Stored Completions:** Synliggjøres automatisk i AI Foundry portal under "Stored Completions" pane.

--- a/skills/ms-ai-advisor/references/prompt-engineering/multimodal-prompt-design.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/multimodal-prompt-design.md
@ -266,7 +266,7 @@ client = OpenAI(
 )
 ```

-### Azure AI Foundry (tidligere Azure AI Studio)
+### Microsoft Foundry (tidligere Azure AI Studio)

 **Supported models for multimodal:**
 - GPT-5 series (gpt-5, gpt-5-mini, gpt-5-nano)
@ -551,7 +551,7 @@ AzureDiagnostics

 **Code samples:**
 - Azure-Samples/cognitive-services-sample-data-files (GitHub)
- Azure AI Foundry multimodal RAG sample app (https://aka.ms/azs-multimodal-sample-app-repo)
+- Microsoft Foundry multimodal RAG sample app (https://aka.ms/azs-multimodal-sample-app-repo)

 **Confidence markers:**
 - ✅ **High confidence:** Token counts, API structure, detail parameter behavior (direkte fra offisiell docs)
--- a/skills/ms-ai-advisor/references/prompt-engineering/prompt-testing-and-evaluation.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/prompt-testing-and-evaluation.md
@ -8,12 +8,12 @@

 ## Introduksjon

-Evaluering av prompt-baserte LLM-løsninger er kritisk for å måle ytelse, kvalitet og sikkerhet i generative AI-applikasjoner. Microsoft tilbyr en omfattende evalueringsplattform gjennom Azure AI Foundry og Prompt Flow som støtter både automatisert testing, AI-assistert evaluering og kontinuerlig overvåking.
+Evaluering av prompt-baserte LLM-løsninger er kritisk for å måle ytelse, kvalitet og sikkerhet i generative AI-applikasjoner. Microsoft tilbyr en omfattende evalueringsplattform gjennom Microsoft Foundry og Prompt Flow som støtter både automatisert testing, AI-assistert evaluering og kontinuerlig overvåking.

 Denne referansen dekker evalueringsrammeverket for prompt testing, iterasjon og optimalisering på tvers av Microsoft AI-stakken — fra utviklingsfasen (prototyping), via eksperimentering (evaluation flows), til produksjon (continuous evaluation).

 **Hovedkomponenter:**
- **Azure AI Foundry Evaluation**: UI-basert evalueringsportal med innebygde metrics
+- **Microsoft Foundry Evaluation**: UI-basert evalueringsportal med innebygde metrics
 - **Prompt Flow Evaluation**: SDK-basert rammeverk for programmatisk evaluering
 - **Azure AI Evaluation SDK**: Python SDK for custom evaluators og batch-evaluering
 - **Continuous Evaluation**: Automatisk evaluering av agent-responser i produksjon
@ -29,9 +29,9 @@ Denne referansen dekker evalueringsrammeverket for prompt testing, iterasjon og

 ## Kjernekomponenter

-### 1. Azure AI Foundry Evaluation Portal
+### 1. Microsoft Foundry Evaluation Portal

-**Beskrivelse:** UI-basert evalueringsverktøy i Azure AI Foundry portalen som lar deg opprette evaluation runs med innebygde metrics, visualisere resultater og sammenligne evalueringer.
+**Beskrivelse:** UI-basert evalueringsverktøy i Microsoft Foundry portalen som lar deg opprette evaluation runs med innebygde metrics, visualisere resultater og sammenligne evalueringer.

 **Kapabiliteter:**
 - Wizard-basert opprettelse av evaluation runs (Evaluation → Create)
@ -158,7 +158,7 @@ pfazure run stream --name <evaluation-run-name>

 ### 3. Azure AI Evaluation SDK

-**Beskrivelse:** Python SDK (`azure-ai-evaluation`) for programmatisk evaluering av LLM-applikasjoner, med støtte for custom evaluators, batch evaluation og integration med Azure AI Foundry.
+**Beskrivelse:** Python SDK (`azure-ai-evaluation`) for programmatisk evaluering av LLM-applikasjoner, med støtte for custom evaluators, batch evaluation og integration med Microsoft Foundry.

 **Installasjon:**

@ -319,7 +319,7 @@ continuous_eval_rule = project_client.evaluation_rules.create_or_update(

 ### 5. Evaluator Library & Version Management

-**Beskrivelse:** Sentralisert bibliotek i Azure AI Foundry for lagring, versjonering og deling av custom evaluators.
+**Beskrivelse:** Sentralisert bibliotek i Microsoft Foundry for lagring, versjonering og deling av custom evaluators.

 **Registrere Custom Evaluator:**

@ -622,7 +622,7 @@ if p_value < 0.05:
 |----------|-------------------|-------------|
 | **Prototyping (5-50 samples)** | Playground + Manual Review | Rask iterasjon, minimal overhead |
 | **Development (100-500 samples)** | Prompt Flow Batch Evaluation | Strukturert testing, metrics logging |
-| **Pre-Production (1000+ samples)** | Azure AI Foundry Evaluation (UI/SDK) | Golden dataset testing, A/B comparison |
+| **Pre-Production (1000+ samples)** | Microsoft Foundry Evaluation (UI/SDK) | Golden dataset testing, A/B comparison |
 | **Production Monitoring** | Continuous Evaluation + HITL | Real-time safety, drift detection |

 ---
@ -670,7 +670,7 @@ if p_value < 0.05:

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry
+### Microsoft Foundry

 **Evaluation Workflow:**

@ -775,8 +775,8 @@ steps:

 **Workaround:**
 1. **Eksporter conversation logs** fra Copilot Studio til Dataverse
-2. **Sync til Azure AI Foundry** via API
-3. **Kjør evaluation** i Azure AI Foundry mot eksporterte logs
+2. **Sync til Microsoft Foundry** via API
+3. **Kjør evaluation** i Microsoft Foundry mot eksporterte logs

 **Alternativ:** Bruk **Power Automate** flow for å samle conversation logs og kalle Azure AI Evaluation API.

@ -787,8 +787,8 @@ steps:
 **Limitation:** AI Builder har ikke native evaluation support for prompt-baserte modeller.

 **Workaround:**
-1. Test prompts i **Azure AI Foundry Playground**
-2. Evaluer via **Azure AI Foundry Evaluation Portal**
+1. Test prompts i **Microsoft Foundry Playground**
+2. Evaluer via **Microsoft Foundry Evaluation Portal**
 3. Deploy finalized prompt til AI Builder (via custom connector til Azure OpenAI)

 ---
@ -905,7 +905,7 @@ def grade(sample: dict, item: dict) -> float:

 ## Kostnad og lisensiering

-### Azure AI Foundry Evaluation Costs
+### Microsoft Foundry Evaluation Costs

 | Komponent | Kostnadsmodell | Estimat (NOK/måned) |
 |-----------|----------------|---------------------|
@ -926,7 +926,7 @@ def grade(sample: dict, item: dict) -> float:

 | Komponent | Lisenskrav | Inkludert i |
 |-----------|------------|-------------|
-| **Azure AI Foundry Evaluation Portal** | Azure-subscription | Azure AI Foundry Hub |
+| **Microsoft Foundry Evaluation Portal** | Azure-subscription | Microsoft Foundry Hub |
 | **Prompt Flow SDK** | Ingen lisens (open-source) | Gratis (pip install) |
 | **Azure AI Evaluation SDK** | Ingen lisens (open-source) | Gratis (pip install) |
 | **Azure OpenAI (for GPT-4 judges)** | Azure-subscription + model deployment | Pay-as-you-go pricing |
@ -951,13 +951,13 @@ def grade(sample: dict, item: dict) -> float:

 ## For arkitekten (Cosmo)

-### Når foreslå Azure AI Foundry Evaluation?
+### Når foreslå Microsoft Foundry Evaluation?

 ✅ **JA, når:**
 - Kunden jobber med RAG, conversational agents eller content generation
 - Kunden trenger **systematisk prompt testing** for å sikre kvalitet før produksjon
 - Kunden er underlagt **compliance-krav** (AI Act, GDPR, norsk offentlig sektor)
- Kunden har **eksisterende Azure AI Foundry infrastructure**
+- Kunden har **eksisterende Microsoft Foundry infrastructure**
 - Kunden trenger **continuous evaluation** for production monitoring

 ❌ **NEI, når:**
@ -1048,7 +1048,7 @@ def grade(sample: dict, item: dict) -> float:
 **High Confidence (>95%):**
 - Built-in evaluators (Groundedness, Relevance, Safety) er production-ready og widely used
 - Prompt Flow SDK evaluation workflow er stable (GA siden 2023), men utfases 20. april 2027 — migrer til Microsoft Agent Framework / Azure AI Evaluation SDK for ny utvikling
- Azure AI Foundry Evaluation Portal er GA (as of 2024)
+- Microsoft Foundry Evaluation Portal er GA (as of 2024)

 **Medium Confidence (70-95%):**
 - Synthetic data generation quality (Preview-feature, limited regions)
@ -1065,7 +1065,7 @@ def grade(sample: dict, item: dict) -> float:
 ## Kilder og verifisering

 **Primary Sources (Microsoft Learn):**
-1. [Evaluate generative AI models and applications - Azure AI Foundry](https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app?view=foundry-classic) — GA
+1. [Evaluate generative AI models and applications - Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app?view=foundry-classic) — GA
 2. [Evaluation flows and metrics - Azure Machine Learning Prompt Flow](https://learn.microsoft.com/en-us/azure/machine-learning/prompt-flow/how-to-develop-an-evaluation-flow?view=azureml-api-2) — GA. Re-verifisert MCP 2026-06-19: Prompt Flow utfases 20. april 2027 → migrer til Microsoft Agent Framework. `log_metric()`/aggregation-mønster uendret.
 3. [Azure AI Evaluation SDK - Python API](https://learn.microsoft.com/en-us/python/api/overview/azure/ai-evaluation-readme?view=azure-python) — GA
 4. [Agent evaluation with Azure AI Evaluation SDK](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/agent-evaluate-sdk?view=foundry-classic) — GA
@ -1076,5 +1076,5 @@ def grade(sample: dict, item: dict) -> float:
 3. [Custom evaluator registration](https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation?view=foundry-classic#specify-custom-evaluators)

 **Last Verified:** 2026-06-19
-**Version:** Azure AI Foundry v2 (2024-2026), Prompt Flow v1.13+ (2024-2026; utfases 2027-04-20 → Microsoft Agent Framework)
+**Version:** Microsoft Foundry v2 (2024-2026), Prompt Flow v1.13+ (2024-2026; utfases 2027-04-20 → Microsoft Agent Framework)
 **MCP Calls:** 3 (microsoft_docs_search × 2, microsoft_docs_fetch × 2, microsoft_code_sample_search × 1)
--- a/skills/ms-ai-advisor/references/prompt-engineering/real-time-reasoning-performance.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/real-time-reasoning-performance.md
@ -290,7 +290,7 @@ Deployment C: Chatbot (variabel prompt, medium output)

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry
+### Microsoft Foundry

 **Realtime Audio Playground:**
 - Deploy `gpt-4o-mini-realtime-preview` i Foundry.
--- a/skills/ms-ai-advisor/references/prompt-engineering/reasoning-models-o1-o3-optimization.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/reasoning-models-o1-o3-optimization.md
@ -297,9 +297,9 @@ if status.status == "completed":

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry
+### Microsoft Foundry

-Reasoning models er tilgjengelige i Azure AI Foundry (tidligere Azure AI Studio):
+Reasoning models er tilgjengelige i Microsoft Foundry (tidligere Azure AI Studio):
 - Deploy via **Foundry Tools resource** for full kontroll
 - Bruk **Playground** for testing med reasoning summary visualisering
 - Kombiner med **Prompt Flow** for orchestration (merk: reasoning tokens telles i cost tracking)
@ -523,7 +523,7 @@ Denne kunnskapsreferansen er basert på offisiell Microsoft Learn-dokumentasjon
   https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
   *Confidence: Verified (MCP fetch 2026-02)*

-3. **Reasoning models with Microsoft Foundry Models**
+3. **Reasoning models with Foundry Models**
   https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-chat-reasoning
   *Confidence: Verified (MCP search 2026-02)*

--- a/skills/ms-ai-advisor/references/prompt-engineering/regulatory-and-compliance-prompting.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/regulatory-and-compliance-prompting.md
@ -354,7 +354,7 @@ Metaprompt for Transparency:
 Lagre denne rapporten for audit trail."
 ```

-**Implementering i Azure AI Foundry:**
+**Implementering i Microsoft Foundry:**

 - **AI Reports:** Auto-generate PDF/SPDX documentation
 - **Model Card:** Dokumenter training data, biases, intended use
@ -519,12 +519,12 @@ audit_client.log_event({
 })
 ```

-### Azure AI Foundry
+### Microsoft Foundry

 **Compliance Workflow:**

 ```
-1. Model Development → Azure AI Foundry Studio
+1. Model Development → Microsoft Foundry Studio
 2. Safety Evaluation → Automated fairness/robustness tests
 3. Model Card Generation → Document intended use, limitations
 4. AI Report Export → PDF for regulators (includes eval metrics)
@ -749,7 +749,7 @@ Kritisk: Compliance-features koster minimalt, men gir juridisk trygghet

 3. **Documentation Debt:**
   - AI projects uten DPIA/Model Cards er "technical debt"
-   - Microsoft Purview + Azure AI Foundry reports automatiserer dette
+   - Microsoft Purview + Microsoft Foundry reports automatiserer dette

 4. **Human-in-the-Loop er ikke valgfritt for high-risk:**
   - EU AI Act krever human oversight for rekruttering, kreditt, lovhåndhevelse
@ -830,7 +830,7 @@ Før produksjonsdeploy, gjennomfør en 2-dagers compliance sprint:
 - [ ] Configure content filters (threshold tuning)
 - [ ] Setup Purview logging + retention policies
 - [ ] Document MADR for model/deployment choices
- [ ] Generate AI Report (Azure AI Foundry)
+- [ ] Generate AI Report (Microsoft Foundry)

 **Deliverables:**

--- a/skills/ms-ai-advisor/references/prompt-engineering/role-playing-and-persona-techniques.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/role-playing-and-persona-techniques.md
@ -666,7 +666,7 @@ If uncertain, explain limitations.

 **Microsoft Learn (offisielle kilder):**

-1. [System message design - Azure AI Foundry](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering)
+1. [System message design - Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering)
   *Komplett guide til system message design, key concepts, og best practices*

 2. [Safety system messages - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message)
--- a/skills/ms-ai-advisor/references/prompt-engineering/structured-output-formatting.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/structured-output-formatting.md
@ -231,7 +231,7 @@ completion = client.beta.chat.completions.parse(

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry / Azure OpenAI
+### Microsoft Foundry / Azure OpenAI

 **API-versjon:** Structured outputs introdusert i `2024-08-01-preview`, tilgjengelig i GA-versjon `v1`.

--- a/skills/ms-ai-advisor/references/prompt-engineering/system-message-design-patterns.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/system-message-design-patterns.md
@ -12,7 +12,7 @@ System messages (også kalt system prompts eller metaprompts) er grunnleggende f

 System messages sender du som del av chat completions API, hvor meldinger er organisert i roller: **system**, **user** og **assistant**. System-rollen plasseres typisk først og setter premissene for hele samtalen. Til forskjell fra prompt engineering for eldre completion-APIer, hvor alt er fritekst, gir chat-modellene en strukturert tilnærming som gjør det lettere å skille instruksjoner fra brukerinput.

-I Azure AI Foundry (tidligere Azure OpenAI Studio) og via REST API kan utviklere definere system messages både programmatisk og via UI. Forståelse av hvordan disse virker – og hvilke begrensninger de har – er essensielt for å bygge produksjonsklare AI-løsninger.
+I Microsoft Foundry (tidligere Azure OpenAI Studio) og via REST API kan utviklere definere system messages både programmatisk og via UI. Forståelse av hvordan disse virker – og hvilke begrensninger de har – er essensielt for å bygge produksjonsklare AI-løsninger.

 ---

@ -100,7 +100,7 @@ For domene-spesifikke use cases (customer support, entity extraction, compliance
 system_message = """
 You are a technical support assistant for Azure AI services.
 Your job is to help users troubleshoot issues with Azure OpenAI deployments.
-Only answer questions related to Azure OpenAI, Azure AI Search, and Azure AI Foundry.
+Only answer questions related to Azure OpenAI, Azure AI Search, and Microsoft Foundry.
 If the user asks about unrelated topics, politely redirect them.
 When unsure, ask clarifying questions. If you lack information, say "I don't know."
 """
@ -214,7 +214,7 @@ response = client.chat.completions.create(

 *Verified: Kodeeksempel fra Microsoft Learn (2024-02-01 API)*

-### Azure AI Foundry (Portal)
+### Microsoft Foundry (Portal)
 I AI Foundry Studio kan du sette system message via:
 1. Chat playground → System message field
 2. Deployment configuration → Default system message
@ -331,7 +331,7 @@ response = client.chat.completions.create(
 ### Arkitekturmønstre for enterprise
 For store organisasjoner med mange AI-assistenter:
 1. **Template library:** Opprett standard system message templates per use case (support, compliance, content generation)
-2. **Centralized management:** Bruk Azure AI Foundry prompt management for versjonskontroll
+2. **Centralized management:** Bruk Microsoft Foundry prompt management for versjonskontroll
 3. **A/B testing framework:** Deploy parallelle varianter av system messages, mål success metrics
 4. **Monitoring:** Logg system message effectiveness via Application Insights

--- a/skills/ms-ai-advisor/references/prompt-engineering/temperature-sampling-and-parameters.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/temperature-sampling-and-parameters.md
@ -247,7 +247,7 @@ Azure OpenAI On Your Data legger til egne system-parametere:

 ### Mønster 4: Model Router med reasoning models

-Azure AI Foundry Model Router kan automatisk velge mellom GPT-modeller og o-series reasoning models.
+Microsoft Foundry Model Router kan automatisk velge mellom GPT-modeller og o-series reasoning models.

 **Viktig:**
 Hvis Model Router velger en o-series model, ignoreres følgende parametere:
--- a/skills/ms-ai-advisor/references/prompt-engineering/token-optimization-and-efficiency.md
+++ b/skills/ms-ai-advisor/references/prompt-engineering/token-optimization-and-efficiency.md
@ -106,7 +106,7 @@ Prompt caching reduserer kostnader ved å cache de første 1024+ tokens i en pro
 | **Minimum prompt-lengde** | 1024 tokens |
 | **Cache-treff** | Første 1024 tokens må være identiske |
 | **Granularitet** | Cache-treff per 128 tokens etter første 1024 |
-| **Cache-levetid** | 5-10 min inaktivitet (max 1 time for Azure AI Foundry; 24t for Foundry Models) |
+| **Cache-levetid** | 5-10 min inaktivitet (max 1 time for Microsoft Foundry; 24t for Foundry Models) |
 | **Deling** | Ikke delt mellom Azure subscriptions |

 #### Design for cache-hits
@ -160,13 +160,13 @@ messages = [
 # ❌ Ukontrollert output (kan generere 4000+ tokens)
 response = client.chat.completions.create(
    model="gpt-4o",
-    messages=[{"role": "user", "content": "Explain Azure AI Foundry"}]
+    messages=[{"role": "user", "content": "Explain Microsoft Foundry"}]
 )

 # ✅ Kontrollert output
 response = client.chat.completions.create(
    model="gpt-4o",
-    messages=[{"role": "user", "content": "Explain Azure AI Foundry in 3 sentences"}],
+    messages=[{"role": "user", "content": "Explain Microsoft Foundry in 3 sentences"}],
    max_tokens=150,
    stop=["\n\n"]  # Stopp ved double line break
 )
@ -325,7 +325,7 @@ Start: Høye token-kostnader?

 ## Integrasjon med Microsoft-stakken

-### Azure AI Foundry: Token monitoring
+### Microsoft Foundry: Token monitoring

 ```python
 # Overvåk token-bruk i Azure Monitor