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

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

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

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

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

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

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

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

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

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

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
This commit is contained in:
Kjell Tore Guttormsen 2026-06-18 13:37:06 +02:00
commit dd1036ab8a
141 changed files with 399 additions and 399 deletions
Download patch file Download diff file Expand all files Collapse all files

2
skills/ms-ai-advisor/references/architecture/cost-models.md
View file

@ -587,7 +587,7 @@ Azure AI Foundry er en **orkestreringsplattform** som benytter flere Azure-tjene
- [Azure Cost Management](https://azure.microsoft.com/services/cost-management/)
**Dokumentasjon:**
- [Azure OpenAI Cost Management](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/manage-costs)
- [Azure OpenAI Cost Management](https://learn.microsoft.com/azure/foundry/concepts/manage-costs)
- [Copilot Studio Billing and management](https://learn.microsoft.com/microsoft-copilot-studio/billing-rates-and-management) — Verified (MCP 2026-04)
- [AI Builder Credit Management](https://learn.microsoft.com/ai-builder/credit-management)

2
skills/ms-ai-advisor/references/architecture/migration-patterns.md
View file

@ -1182,7 +1182,7 @@ Base effort: 200 timer
### Microsoft Learn
- [Azure Migration Guide](https://learn.microsoft.com/azure/cloud-adoption-framework/migrate/)
- [Copilot Studio Migration](https://learn.microsoft.com/microsoft-copilot-studio/unified-authoring-conversion)
- [Azure AI Foundry Documentation](https://learn.microsoft.com/azure/ai-foundry/)
- [Azure AI Foundry Documentation](https://learn.microsoft.com/azure/foundry/)
### Verktøy
- **Azure Migrate:** Assessment og migrering av workloads

2
skills/ms-ai-advisor/references/architecture/poc-template.md
View file

@ -925,7 +925,7 @@ Legg til ekstra tid hvis:
### Microsoft Documentation
- [AI Adoption Framework (CAF)](https://learn.microsoft.com/azure/cloud-adoption-framework/scenarios/ai/)
- [Copilot Studio Implementation Guidance](https://learn.microsoft.com/microsoft-copilot-studio/guidance/overview)
- [Azure AI Foundry Evaluation](https://learn.microsoft.com/azure/ai-foundry/concepts/evaluation-evaluators/)
- [Azure AI Foundry Evaluation](https://learn.microsoft.com/azure/foundry/how-to/evaluate-generative-ai-app)
- [Responsible AI Standard](https://www.microsoft.com/ai/responsible-ai)
### Tools

4
skills/ms-ai-advisor/references/architecture/regional-availability-verification.md
View file

@ -248,9 +248,9 @@ Når en tjeneste ikke er tilgjengelig i Norway East:
| Ressurs | URL | Oppdateringsfrekvens |
|---------|-----|---------------------|
| Azure Products by Region | https://azure.microsoft.com/en-us/explore/global-infrastructure/products-by-region | Fortløpende |
| Azure OpenAI Models & Region | https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models | Ved modellendringer |
| Azure OpenAI Models & Region | https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure | Ved modellendringer |
| Azure AI Search Regions | https://learn.microsoft.com/azure/search/search-region-support | Ved regionsendringer |
| Microsoft Foundry Regions | https://learn.microsoft.com/azure/ai-foundry/reference/region-support | Ved regionsendringer |
| Microsoft Foundry Regions | https://learn.microsoft.com/azure/foundry/reference/region-support | Ved regionsendringer |
| Azure Status | https://status.azure.com | Sanntid |
| Azure Updates | https://azure.microsoft.com/updates | Daglig |

10
skills/ms-ai-advisor/references/copilot-extensibility/copilot-api-rate-limiting-resilience.md
View file

@ -244,7 +244,7 @@ while True:
**Use case:** Store batch-operasjoner (Azure OpenAI, Azure AI Foundry).
**Verified:** [Batch deployments - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch)
**Verified:** [Batch deployments - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch)
---
@ -299,7 +299,7 @@ while True:
- Implementer retry logic med exponential backoff
- Unngå skarpe workload-endringer (gradvis økning)
**Verified:** [Quotas and limits - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits), [Manage quota - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/quota)
**Verified:** [Quotas and limits - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits), [Manage quota - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota)
### Copilot Studio
@ -484,9 +484,9 @@ while True:
3. [Circuit Breaker pattern - Cloud-Native .NET](https://learn.microsoft.com/en-us/dotnet/architecture/cloud-native/application-resiliency-patterns)
4. [What is rate limiting? - Microsoft Cloud Dev](https://learn.microsoft.com/en-us/microsoft-cloud/dev/dev-proxy/concepts/what-is-rate-limiting)
5. [How to handle API throttling - Microsoft Cloud Dev](https://learn.microsoft.com/en-us/microsoft-cloud/dev/dev-proxy/concepts/how-to-handle-api-throttling)
6. [Azure OpenAI quotas and limits](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits)
7. [Manage Azure OpenAI quota](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/quota)
8. [Batch deployments - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch)
6. [Azure OpenAI quotas and limits](https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits)
7. [Manage Azure OpenAI quota](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota)
8. [Batch deployments - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch)
9. [Resolve throttling errors in Copilot Studio agents](https://learn.microsoft.com/en-us/troubleshoot/power-platform/copilot-studio/licensing/throttling-errors-agents)
10. [Error codes - Copilot Studio](https://learn.microsoft.com/en-us/troubleshoot/power-platform/copilot-studio/authoring/error-codes)
11. [Optimize bot with rate limiting in Teams](https://learn.microsoft.com/en-us/microsoftteams/platform/bots/how-to/rate-limit)

6
skills/ms-ai-advisor/references/copilot-extensibility/copilot-context-window-optimization.md
View file

@ -538,11 +538,11 @@ Response + Citations
**MCP-verified sources (microsoft-learn):**
1. **Azure OpenAI Assistants API — Context Window Management**
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/assistants#context-window-management
- https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/assistants#context-window-management
- Verified: max_prompt_tokens, max_completion_tokens, truncation_strategy
2. **Troubleshooting and best practices for Azure OpenAI On Your Data**
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/on-your-data-best-practices
- https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-best-practices
- Verified: topNDocuments, strictness, chunk_size, workflow funnel
3. **Quotas and limits for Copilot Studio**
@ -558,7 +558,7 @@ Response + Citations
- Verified: Known limitations, no long-running task support, context limits
6. **Azure OpenAI Predicted Outputs**
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/predicted-outputs
- https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs
- Verified: Prediction parameter for latency optimization
7. **Copilot handoff (Teams Bot Framework)**

2
skills/ms-ai-advisor/references/development/agent-framework.md
View file

@ -465,7 +465,7 @@ result = await agent.run() # Automatisk planning
## Ressurser
- [Agent Framework Documentation](https://learn.microsoft.com/azure/ai-services/agents)
- [Azure AI Foundry Agent Service](https://learn.microsoft.com/azure/ai-foundry/agent-service)
- [Azure AI Foundry Agent Service](https://learn.microsoft.com/azure/foundry/agents/overview)
- [Migration Guide from Semantic Kernel](https://learn.microsoft.com/azure/ai-services/agents/migrate-semantic-kernel)
- [GitHub Samples](https://github.com/azure-samples/ai-agent-framework)

24
skills/ms-ai-advisor/references/platforms/azure-ai-foundry.md
View file

@ -371,18 +371,18 @@ Microsoft.CognitiveServices/account (kind: AIServices)
Adapted from Microsoft Learn documentation ([CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)):
- [What is Microsoft Foundry?](https://learn.microsoft.com/azure/ai-foundry/what-is-foundry?view=foundry-classic)
- [What's new in Microsoft Foundry (December 2025)](https://learn.microsoft.com/azure/ai-foundry/whats-new-foundry?view=foundry-classic)
- [What's new in Azure OpenAI](https://learn.microsoft.com/azure/ai-foundry/openai/whats-new?view=foundry-classic)
- [What's new in Foundry Agent Service](https://learn.microsoft.com/azure/ai-foundry/agents/whats-new?view=foundry-classic)
- [GPT-5 models](https://learn.microsoft.com/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic)
- [Build a workflow in Microsoft Foundry](https://learn.microsoft.com/azure/ai-foundry/agents/concepts/workflow?view=foundry)
- [Foundry Local](https://learn.microsoft.com/azure/ai-foundry/foundry-local/what-is-foundry-local?view=foundry-classic)
- [Computer Use (preview)](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/computer-use?view=foundry-classic)
- [Deep Research tool](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools-classic/deep-research?view=foundry-classic)
- [A2A Agent endpoint (preview)](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools/agent-to-agent?view=foundry)
- [MCP tool](https://learn.microsoft.com/azure/ai-foundry/agents/how-to/tools-classic/model-context-protocol?view=foundry-classic)
- [Model region availability](https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models)
- [What is Microsoft Foundry?](https://learn.microsoft.com/azure/foundry/what-is-foundry?view=foundry-classic)
- [What's new in Microsoft Foundry (December 2025)](https://learn.microsoft.com/azure/foundry/whats-new-foundry?view=foundry-classic)
- [What's new in Azure OpenAI](https://learn.microsoft.com/azure/foundry-classic/openai/whats-new?view=foundry-classic)
- [What's new in Foundry Agent Service](https://learn.microsoft.com/azure/foundry-classic/agents/whats-new?view=foundry-classic)
- [GPT-5 models](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic)
- [Build a workflow in Microsoft Foundry](https://learn.microsoft.com/azure/foundry/agents/concepts/workflow?view=foundry)
- [Foundry Local](https://learn.microsoft.com/azure/foundry-local/what-is-foundry-local?view=foundry-classic)
- [Computer Use (preview)](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/computer-use?view=foundry-classic)
- [Deep Research tool](https://learn.microsoft.com/azure/foundry-classic/agents/how-to/tools-classic/deep-research?view=foundry-classic)
- [A2A Agent endpoint (preview)](https://learn.microsoft.com/azure/foundry/agents/how-to/tools/agent-to-agent?view=foundry)
- [MCP tool](https://learn.microsoft.com/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol?view=foundry-classic)
- [Model region availability](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure)
Content has been translated to Norwegian, reorganized, and augmented with decision guidance.

18
skills/ms-ai-advisor/references/platforms/model-catalog-2026.md
View file

@ -390,15 +390,15 @@ Trenger kunden open-source/selvhostet-alternativ?
Adapted from Microsoft Learn documentation ([CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)):
- [Foundry Models sold directly by Azure (azure-openai)](https://learn.microsoft.com/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic)
- [Foundry Models sold directly by Azure (azure-direct-others)](https://learn.microsoft.com/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic&pivots=azure-direct-others)
- [Azure OpenAI in Azure AI Foundry Models — model overview](https://learn.microsoft.com/azure/ai-foundry/openai/concepts/models)
- [GPT-5 vs GPT-4.1: choosing the right model](https://learn.microsoft.com/azure/ai-foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic)
- [Azure OpenAI reasoning models](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/reasoning?view=foundry-classic)
- [PTU costs and billing](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding?view=foundry-classic)
- [Foundry Models from partners and community (Phi)](https://learn.microsoft.com/azure/ai-foundry/foundry-models/concepts/models-from-partners?view=foundry-classic)
- [Azure OpenAI models and regions for Foundry Agent Service](https://learn.microsoft.com/azure/ai-foundry/agents/concepts/model-region-support?view=foundry-classic)
- [Azure OpenAI quotas and limits](https://learn.microsoft.com/azure/ai-foundry/openai/quotas-limits?view=foundry-classic)
- [Foundry Models sold directly by Azure (azure-openai)](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic)
- [Foundry Models sold directly by Azure (azure-direct-others)](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic&pivots=azure-direct-others)
- [Azure OpenAI in Azure AI Foundry Models — model overview](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure)
- [GPT-5 vs GPT-4.1: choosing the right model](https://learn.microsoft.com/azure/foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic)
- [Azure OpenAI reasoning models](https://learn.microsoft.com/azure/foundry/openai/how-to/reasoning?view=foundry-classic)
- [PTU costs and billing](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing?view=foundry-classic)
- [Foundry Models from partners and community (Phi)](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-from-partners?view=foundry-classic)
- [Azure OpenAI models and regions for Foundry Agent Service](https://learn.microsoft.com/azure/foundry-classic/agents/concepts/model-region-support?view=foundry-classic)
- [Azure OpenAI quotas and limits](https://learn.microsoft.com/azure/foundry/openai/quotas-limits?view=foundry-classic)
Content translated to Norwegian, reorganized, and augmented with decision guidance for Norwegian public sector.

4
skills/ms-ai-advisor/references/prompt-engineering/adversarial-prompting-and-jailbreaks.md
View file

@ -760,11 +760,11 @@ Start: AI system security design
*Verifisert: januar 2026, omfatter AI-1 til AI-7 controls*
3. **Azure AI Red Teaming Agent:**
https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/ai-red-teaming-agent
https://learn.microsoft.com/en-us/azure/foundry/concepts/ai-red-teaming-agent
*Verifisert: januar 2026, Public Preview*
4. **Content Filtering (default policies):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/default-safety-policies
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies
*Verifisert: januar 2026, GA*
5. **Microsoft Defender for AI Services:**

12
skills/ms-ai-advisor/references/prompt-engineering/chain-of-thought-prompting.md
View file

@ -474,11 +474,11 @@ Chain-of-thought øker token-forbruk betydelig:
| Kilde | Konfidensnivå | Verifisert dato |
|-------|---------------|-----------------|
| [Prompt engineering techniques - Chain of thought prompting](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering#chain-of-thought-prompting) | **Verified** | 2026-02 |
| [Azure OpenAI On Your Data - Best practices (Chain-of-thought prompting)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data#best-practices) | **Verified** | 2026-02 |
| [Azure OpenAI Evaluation (Preview) - Factuality (uses CoT internally)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/evaluations#types-of-testing-criteria) | **Verified** | 2026-02 |
| [Azure OpenAI reasoning models (o1, o3, GPT-5)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning) | **Verified** | 2026-02 |
| [Transparency note for Azure OpenAI - Chain-of-thought capabilities](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note?view=foundry-classic#capabilities) | **Verified** | 2026-02 |
| [Prompt engineering techniques - Chain of thought prompting](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering#chain-of-thought-prompting) | **Verified** | 2026-02 |
| [Azure OpenAI On Your Data - Best practices (Chain-of-thought prompting)](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#best-practices) | **Verified** | 2026-02 |
| [Azure OpenAI Evaluation (Preview) - Factuality (uses CoT internally)](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/evaluations#types-of-testing-criteria) | **Verified** | 2026-02 |
| [Azure OpenAI reasoning models (o1, o3, GPT-5)](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning) | **Verified** | 2026-02 |
| [Transparency note for Azure OpenAI - Chain-of-thought capabilities](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note?view=foundry-classic#capabilities) | **Verified** | 2026-02 |
### Baseline-kunnskap (fra Claude-modell)
@ -493,7 +493,7 @@ Chain-of-thought øker token-forbruk betydelig:
1. **microsoft_docs_search:** "chain of thought prompting Azure OpenAI" → 10 resultater
2. **microsoft_code_sample_search:** "chain of thought prompt examples" → 20 code snippets
3. **microsoft_docs_fetch:** [Azure OpenAI reasoning models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning) → Full dokumentasjon hentet
3. **microsoft_docs_fetch:** [Azure OpenAI reasoning models](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning) → Full dokumentasjon hentet
**Totalt:** 4 MCP-kall, 3 unike Microsoft Learn-kilder.

8
skills/ms-ai-advisor/references/prompt-engineering/domain-specific-prompt-optimization.md
View file

@ -558,19 +558,19 @@ Basert på testing (Azure OpenAI dokumentasjon):
### Microsoft Learn dokumentasjon (fetched via MCP 2026-02-04)
1. **Prompt engineering techniques** (Azure OpenAI)
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering
*Source for: Best practices, few-shot learning, chain-of-thought, output structure*
2. **Azure OpenAI On Your Data**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data
*Source for: RAG configuration, field mapping, strictness, multi-lingual support, token estimation*
3. **Transparency note for Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note
*Source for: Model capabilities, limitations, responsible AI considerations*
4. **Azure OpenAI FAQ**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/faq
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq
*Source for: Language handling, model behavior, grounding strategies*
5. **Apply prompt engineering with Azure OpenAI Service - Training**

6
skills/ms-ai-advisor/references/prompt-engineering/error-handling-and-fallback-prompting.md
View file

@ -686,14 +686,14 @@ User Request
## Kilder og verifisering
**Primærkilder (Microsoft Learn):**
1. [Azure OpenAI supported programming languages - Error handling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/supported-languages) – Offisiell dokumentasjon for retry-mekanismer i alle SDK-er
1. [Azure OpenAI supported programming languages - Error handling](https://learn.microsoft.com/en-us/azure/foundry/openai/supported-languages) – Offisiell dokumentasjon for retry-mekanismer i alle SDK-er
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
4. [Troubleshooting Azure OpenAI On Your Data](https://learn.microsoft.com/en-us/azure/foundry-classic/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) (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
6. [Azure OpenAI FAQ](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq) – Vanlige feilsituasjoner og workarounds
7. [OWASP Top 10 for LLM - Improper Output Handling](https://genai.owasp.org/llmrisk/llm052025-improper-output-handling/) – Sikkerhetshensyn ved output validation
8. [Reliability Maturity Model](https://learn.microsoft.com/en-us/azure/well-architected/reliability/maturity-model) – Graceful degradation og testing

8
skills/ms-ai-advisor/references/prompt-engineering/few-shot-learning-techniques.md
View file

@ -510,11 +510,11 @@ User Query
**Verified (MCP microsoft-learn, januar 2026):**
1. **Prompt engineering techniques** (Azure AI Foundry)
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering
- https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering
- Seksjon: Few-shot learning, Zero-shot learning, Examples
2. **Work with chat completions models**
- https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt
- https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt
- Seksjon: Few-shot learning with chat completion
3. **Zero-shot and few-shot learning** (.NET AI conceptual) (Re-verified MCP 2026-04)
@ -522,11 +522,11 @@ User Query
- 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
- https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses
- Few-shot eksempler i ChatML-format
5. **Transparency note for Azure OpenAI**
- https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/transparency-note
- https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/transparency-note
- In-context learning: Zero-shot, One-shot, Few-shot definitioner
**Code samples verified:**

12
skills/ms-ai-advisor/references/prompt-engineering/function-calling-and-tool-use.md
View file

@ -272,7 +272,7 @@ assistant = client.beta.assistants.create(
### Azure Logic Apps
[Azure Logic Apps kan integreres](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/assistants-logic-apps) med Assistants API for å håndtere function execution.
[Azure Logic Apps kan integreres](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistants-logic-apps) med Assistants API for å håndtere function execution.
### On Your Data (Azure AI Search + OpenAI)
@ -421,7 +421,7 @@ Function calling påvirker kostnaden på flere måter:
- Start med én enkel funksjon (f.eks. `get_current_time`)
- Bruk `tool_choice: "auto"` og observer modellens oppførsel
- Implementer robust error handling før produksjon
- Les Microsoft's [responsible AI guidelines](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/overview)
- Les Microsoft's [responsible AI guidelines](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/overview)
**Viderekomne (har bygget noen agenter):**
- Implementer parallel function calling for bedre performance
@ -439,11 +439,11 @@ Function calling påvirker kostnaden på flere måter:
**Verified (fra Microsoft Learn MCP-research):**
1. [How to use function calling with Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/function-calling) — **Konfidensnivå: Høy** (offisiell dokumentasjon, oppdatert januar 2026)
1. [How to use function calling with Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling) — **Konfidensnivå: Høy** (offisiell dokumentasjon, oppdatert januar 2026)
2. [Understand OpenAI function calling](https://learn.microsoft.com/en-us/dotnet/ai/conceptual/understanding-openai-functions) — **Konfidensnivå: Høy** (konseptuell guide med Semantic Kernel-eksempler)
3. [Azure OpenAI Assistants function calling](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/assistant-functions) — **Konfidensnivå: Høy** (Assistants API-spesifikk dokumentasjon)
4. [Fine-tuning functions](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-functions) — **Konfidensnivå: Høy** (for advanced use cases)
5. [Structured outputs](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/structured-outputs) — **Konfidensnivå: Høy** (komplementær teknikk til function calling)
3. [Azure OpenAI Assistants function calling](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistant-functions) — **Konfidensnivå: Høy** (Assistants API-spesifikk dokumentasjon)
4. [Fine-tuning functions](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions) — **Konfidensnivå: Høy** (for advanced use cases)
5. [Structured outputs](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs) — **Konfidensnivå: Høy** (komplementær teknikk til function calling)
**Baseline (fra modellkunnskap januar 2025):**

6
skills/ms-ai-advisor/references/prompt-engineering/grounding-and-knowledge-injection.md
View file

@ -496,12 +496,12 @@ Sources:
## Kilder og verifisering
**MCP-kilder (Verified):**
1. Microsoft Learn: [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering) – Groundedness context, citation best practices
2. Microsoft Learn: [Groundedness Detection Filter](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-groundedness) – RAG definition, ungroundedness detection
1. Microsoft Learn: [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering) – Groundedness context, citation best practices
2. Microsoft Learn: [Groundedness Detection Filter](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness) – RAG definition, ungroundedness detection
3. Microsoft Learn: [Secure Multitenant RAG](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/secure-multitenant-rag) – Tenant isolation, API-layer, security trimming
4. Microsoft Learn: [Copilot Studio Knowledge Sources](https://learn.microsoft.com/en-us/microsoft-copilot-studio/knowledge-copilot-connectors) – SharePoint, connectors, tenant graph grounding
5. Microsoft Learn: [Web Search in Copilot Studio](https://learn.microsoft.com/en-us/microsoft-copilot-studio/data-privacy-security-web-search) – Bing integration, privacy considerations
6. Microsoft Learn: [Azure AI Agents (Bing Grounding)](https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/web-overview) – Web grounding workflow
6. Microsoft Learn: [Azure AI Agents (Bing Grounding)](https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview) – Web grounding workflow
**Konfidensnivå per seksjon:**
| Seksjon | Konfidensnivå | Kilde |

12
skills/ms-ai-advisor/references/prompt-engineering/multi-turn-conversation-management.md
View file

@ -294,7 +294,7 @@ AgentSession resumedSession = await agent.DeserializeSessionAsync(serializedSess
| gpt-35-turbo | 16K tokens | 14K |
| o1, o3-mini, o4-mini | 128K-200K | Varierer per modell |
**Viktig:** Sjekk alltid [models page](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models) for oppdaterte limits.
**Viktig:** Sjekk alltid [models page](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure) for oppdaterte limits.
### Truncation-strategi
@ -638,7 +638,7 @@ User → Copilot Studio → Azure OpenAI
### Microsoft Learn (offisiell dokumentasjon)
1. **Work with chat completions models**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt
*Kjernereferanse for Chat Completion API, conversation loop patterns, token management*
2. **Multi-turn conversations with an agent**
@ -646,19 +646,19 @@ User → Copilot Studio → Azure OpenAI
*Agent Framework session management, stateless architecture*
3. **Azure OpenAI stored completions & distillation**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/stored-completions
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/stored-completions
*Stored completions feature, metadata enrichment*
4. **Azure OpenAI quotas and limits**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits
https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
*Token limits per modell, TPM/RPM relationship, rate limiting*
5. **Manage Azure OpenAI quota**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/quota
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota
*Rate limit mechanics, best practices, token counting for rate limits*
6. **Azure OpenAI Assistants API context window management**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/assistants
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/assistants
*Truncation strategies, max_prompt_tokens, max_completion_tokens*
7. **CLU multi-turn conversations**

4
skills/ms-ai-advisor/references/prompt-engineering/multimodal-prompt-design.md
View file

@ -542,10 +542,10 @@ AzureDiagnostics
## Kilder og verifisering
**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
- [Use vision-enabled chat models](https://learn.microsoft.com/en-us/azure/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) (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
- [Azure OpenAI models](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure) — 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

10
skills/ms-ai-advisor/references/prompt-engineering/prompt-testing-and-evaluation.md
View file

@ -1063,15 +1063,15 @@ 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/ai-foundry/how-to/evaluate-generative-ai-app?view=foundry-classic) — GA
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
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
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/ai-foundry/how-to/develop/agent-evaluate-sdk?view=foundry-classic) — 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
**Code Samples (Microsoft Learn):**
1. [Cloud evaluation with Azure AI Projects SDK](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/cloud-evaluation?view=foundry-classic)
2. [Continuous evaluation setup](https://learn.microsoft.com/en-us/azure/ai-foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry)
3. [Custom evaluator registration](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/cloud-evaluation?view=foundry-classic#specify-custom-evaluators)
1. [Cloud evaluation with Azure AI Projects SDK](https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation?view=foundry-classic)
2. [Continuous evaluation setup](https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard?view=foundry)
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:** 2026-02-04
**Version:** Azure AI Foundry v2 (2024-2026), Prompt Flow v1.13+ (2024-2026)

6
skills/ms-ai-advisor/references/prompt-engineering/real-time-reasoning-performance.md
View file

@ -485,15 +485,15 @@ Deployment C: Chatbot (variabel prompt, medium output)
**Primary sources:**
1. **Performance and latency** (Azure OpenAI)
[https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/latency](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/latency)
[https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency)
Hentet: januar 2026. Dekker streaming, max_tokens, content filtering, workload separation, metrics.
2. **GPT Realtime API for speech and audio**
[https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/realtime-audio](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/realtime-audio)
[https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio)
Hentet: januar 2026. Dekker WebRTC/WebSocket, VAD modes, session configuration, supported models.
3. **GPT-4o Realtime API quickstart**
[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)
[https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio)
Hentet: januar 2026. Kode-eksempler for Python, JavaScript, deployment steps.
4. **Lower speech synthesis latency using Speech SDK** (Re-verified MCP 2026-04)

8
skills/ms-ai-advisor/references/prompt-engineering/reasoning-models-o1-o3-optimization.md
View file

@ -516,19 +516,19 @@ Denne kunnskapsreferansen er basert på offisiell Microsoft Learn-dokumentasjon
**Primary sources:**
1. **Azure OpenAI reasoning models**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning
*Confidence: Verified (MCP fetch 2026-02)*
2. **Azure OpenAI model availability and pricing**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models
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**
https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/how-to/use-chat-reasoning
https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-chat-reasoning
*Confidence: Verified (MCP search 2026-02)*
4. **Azure OpenAI function calling support**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/function-calling
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling
*Confidence: Verified (MCP search 2026-02)*
5. **GPT-5 prompting guide (OpenAI)**

4
skills/ms-ai-advisor/references/prompt-engineering/regulatory-and-compliance-prompting.md
View file

@ -860,7 +860,7 @@ Før produksjonsdeploy, gjennomfør en 2-dagers compliance sprint:
### Microsoft Official Documentation
1. **Data, privacy, and security for Azure OpenAI** (februar 2026)
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy
→ Autoritativ kilde for data processing, abuse monitoring, residency
2. **Govern AI apps and data for regulatory compliance** (februar 2026)
@ -868,7 +868,7 @@ Før produksjonsdeploy, gjennomfør en 2-dagers compliance sprint:
→ Compliance Manager, Purview integration, EU AI Act readiness
3. **Azure OpenAI Content Filtering** (februar 2026)
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter
https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/content-filter
→ Content Safety API, thresholds, custom policies
4. **Azure Data Residency** (februar 2026)

10
skills/ms-ai-advisor/references/prompt-engineering/role-playing-and-persona-techniques.md
View file

@ -666,22 +666,22 @@ If uncertain, explain limitations.
**Microsoft Learn (offisielle kilder):**
1. [System message design - Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/advanced-prompt-engineering)
1. [System message design - Azure AI 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/ai-foundry/openai/concepts/system-message)
2. [Safety system messages - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message)
*Authoring techniques, safety components, og testing strategies*
3. [Prompt engineering techniques - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering)
3. [Prompt engineering techniques - Azure OpenAI](https://learn.microsoft.com/en-us/azure/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) (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)
5. [Azure OpenAI On Your Data - Best practices](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data)
*System message bruk i RAG-scenarier*
6. [Responsible AI practices for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/overview)
6. [Responsible AI practices for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/overview)
*Metaprompt tuning som mitigation strategy*
**Code samples verifisert:**

8
skills/ms-ai-advisor/references/prompt-engineering/structured-output-formatting.md
View file

@ -420,10 +420,10 @@ Krever Azure OpenAI-ressurs med støttet modell (se over). Ingen spesiell lisens
| URL | Tema | Konfidensnivå |
|-----|------|---------------|
| [Structured Outputs Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/structured-outputs) | Hovedguide, API-eksempler, schema-begrensninger | **Verified** (2026-02) |
| [JSON Mode Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/json-mode) | JSON Mode (legacy), sammenlikning med structured outputs | **Verified** (2026-02) |
| [API Reference (v1)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/latest) | REST API-detaljer, response_format konfigurasjon | **Verified** (2026-02) |
| [Prompt Engineering Guide](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering) | Output structure best practices | **Verified** (2026-02) |
| [Structured Outputs Guide](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs) | Hovedguide, API-eksempler, schema-begrensninger | **Verified** (2026-02) |
| [JSON Mode Guide](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode) | JSON Mode (legacy), sammenlikning med structured outputs | **Verified** (2026-02) |
| [API Reference (v1)](https://learn.microsoft.com/en-us/azure/foundry/openai/latest) | REST API-detaljer, response_format konfigurasjon | **Verified** (2026-02) |
| [Prompt Engineering Guide](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering) | Output structure best practices | **Verified** (2026-02) |
### Azure OpenAI API-versjon
- **Introduced:** `2024-08-01-preview`

10
skills/ms-ai-advisor/references/prompt-engineering/system-message-design-patterns.md
View file

@ -340,11 +340,11 @@ For store organisasjoner med mange AI-assistenter:
## Kilder og verifisering
**Verified (fra Microsoft Learn MCP):**
- System message design concepts: [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/advanced-prompt-engineering](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/advanced-prompt-engineering)
- Prompt engineering techniques: [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering)
- Safety system messages: [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/system-message](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/system-message)
- Code samples (Python SDK): [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt)
- Azure OpenAI On Your Data best practices: [https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data)
- System message design concepts: [https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering)
- Prompt engineering techniques: [https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering)
- Safety system messages: [https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message)
- Code samples (Python SDK): [https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt)
- Azure OpenAI On Your Data best practices: [https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data)
**Baseline (modellkunnskap):**
- EU AI Act compliance patterns (February 2026)

10
skills/ms-ai-advisor/references/prompt-engineering/temperature-sampling-and-parameters.md
View file

@ -559,13 +559,13 @@ for config in test_configs:
## Kilder og verifisering
### Microsoft Learn dokumentasjon
1. [Prompt engineering techniques — Temperature and Top_p parameters](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering#temperature-and-top_p-parameters)
2. [Azure OpenAI REST API reference — Completions](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/reference#completions)
3. [Reproducible output with seed parameter](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reproducible-output)
4. [Model Router limitations (o-series)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/model-router#use-model-router-in-chats)
1. [Prompt engineering techniques — Temperature and Top_p parameters](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering#temperature-and-top_p-parameters)
2. [Azure OpenAI REST API reference — Completions](https://learn.microsoft.com/en-us/azure/foundry/openai/reference#completions)
3. [Reproducible output with seed parameter](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reproducible-output)
4. [Model Router limitations (o-series)](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router#use-model-router-in-chats)
### Code samples
5. [Azure OpenAI Python SDK — Chat Completions](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/supported-languages?pivots=programming-language-python#chat)
5. [Azure OpenAI Python SDK — Chat Completions](https://learn.microsoft.com/en-us/azure/foundry/openai/supported-languages?pivots=programming-language-python#chat)
6. [Semantic Kernel — OpenAIPromptExecutionSettings](https://learn.microsoft.com/en-us/dotnet/api/microsoft.semantickernel.connectors.openai.openaipromptexecutionsettings)
### Validert dato

8
skills/ms-ai-advisor/references/prompt-engineering/token-optimization-and-efficiency.md
View file

@ -583,10 +583,10 @@ Break-even requests/måned: $1,224 / $0.00036 = 3.4M requests
## Kilder og verifisering
**Offisiell Microsoft-dokumentasjon:**
1. [Prompt caching for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/prompt-caching)
2. [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs)
3. [Performance and latency optimization](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/latency)
4. [Batch API for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch)
1. [Prompt caching for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching)
2. [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs)
3. [Performance and latency optimization](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency)
4. [Batch API for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch)
5. [Azure OpenAI pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/)
**Verifisert:** Februar 2026 via microsoft-learn MCP-server