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-security/references/ai-security-engineering/adversarial-input-robustness-testing.md
View file

@ -504,7 +504,7 @@ outputs = await simulator(
## References
- [Threat Modeling AI/ML Systems](https://learn.microsoft.com/en-us/security/engineering/threat-modeling-aiml) — Microsoft Security Engineering
- [AI Red Teaming Agent](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/ai-red-teaming-agent) — Azure AI Foundry
- [AI Red Teaming Agent](https://learn.microsoft.com/en-us/azure/foundry/concepts/ai-red-teaming-agent) — Azure AI Foundry
- [PyRIT Framework](https://azure.github.io/PyRIT/) — Microsoft open-source red teaming tool
- [Artificial Intelligence Security (MCSB)](https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security) — Azure Security Benchmark
- [Failure Modes in Machine Learning](https://learn.microsoft.com/en-us/security/engineering/failure-modes-in-machine-learning) — Microsoft Security

2
skills/ms-ai-security/references/ai-security-engineering/ai-security-scoring-framework.md
View file

@ -464,7 +464,7 @@ For statlige AI-prosjekter som krever beslutningsgrunnlag:
*Confidence: Verified* — Logging, threat detection, compliance controls
6. **Evaluate generative AI models (Azure AI Foundry)**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/evaluate-generative-ai-app
https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluate-generative-ai-app
*Confidence: Verified* — AI quality metrics (NLP + AI-assisted), risk and safety metrics (content harm, ASR)
7. **Azure Defender for Cloud - Resource Graph samples**

6
skills/ms-ai-security/references/ai-security-engineering/content-safety-filter-calibration.md
View file

@ -505,10 +505,10 @@ Denne referansen er basert på offisiell Microsoft-dokumentasjon og verifiserte
### Primærkilder (Verified)
1. [Mitigate false results in Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance) — Severity tuning, blocklists, custom categories
2. [Configure content filters - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/content-filters) — Deployment + request-level configuration
3. [Content filter configurability](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-configurability) — Severity levels, approval process
2. [Configure content filters - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/content-filters) — Deployment + request-level configuration
3. [Content filter configurability](https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/content-filter) — Severity levels, approval process
4. [Azure AI Content Safety FAQ](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/faq) — Threshold recommendations, multilingual support, pricing
5. [Transparency note: Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/content-safety/transparency-note) — Severity definitions, best practices, bias mitigation
5. [Transparency note: Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/content-safety/transparency-note) — Severity definitions, best practices, bias mitigation
6. [Python SDK code samples](https://learn.microsoft.com/en-us/python/api/overview/azure/ai-contentsafety-readme) — AnalyzeText API, blocklist usage
### Konfidensgradering

4
skills/ms-ai-security/references/ai-security-engineering/data-leakage-prevention-ai.md
View file

@ -178,8 +178,8 @@ Invoke-AzRestMethod @patchParams
**Konsept:** Implementer network security perimeter for å begrense inbound og outbound access til Azure OpenAI og Foundry-baserte prosjekter.
**Implementering:**
- [Add network security perimeter to Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/network-security-perimeter)
- [Add Foundry to a network security perimeter](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/add-foundry-to-network-security-perimeter)
- [Add network security perimeter to Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/network-security-perimeter)
- [Add Foundry to a network security perimeter](https://learn.microsoft.com/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter)
**Kombiner med:**
- Azure Private Link for network-level data isolation

2
skills/ms-ai-security/references/ai-security-engineering/entra-agent-id-zero-trust.md
View file

@ -427,7 +427,7 @@ Når en Foundry-agent publiseres, endres identiteten fra delt prosjektidentitet
1. [Security for AI agents with Microsoft Entra Agent ID](https://learn.microsoft.com/entra/agent-id/identity-professional/security-for-ai) — Oversikt over sikkerhetsrammeverket
2. [What are agent identities](https://learn.microsoft.com/entra/agent-id/identity-platform/what-is-agent-id) — Kjernekonsepted for agentidentiteter
3. [Agent identity and blueprint concepts in Microsoft Entra ID](https://learn.microsoft.com/entra/agent-id/identity-platform/key-concepts) — Blueprints og arkitektur
4. [Agent identity concepts in Microsoft Foundry](https://learn.microsoft.com/azure/ai-foundry/agents/concepts/agent-identity?view=foundry) — Foundry-integrasjon med agentidentiteter
4. [Agent identity concepts in Microsoft Foundry](https://learn.microsoft.com/azure/foundry/agents/concepts/agent-identity?view=foundry) — Foundry-integrasjon med agentidentiteter
5. [Automatically create Microsoft Entra agent identities for Copilot Studio agents](https://learn.microsoft.com/en-us/microsoft-copilot-studio/admin-use-entra-agent-identities) — Copilot Studio-integrasjon
6. [What is the Microsoft Entra Agent Registry?](https://learn.microsoft.com/entra/agent-id/identity-platform/what-is-agent-registry) — Agent Registry-konsepter
7. [Authorization in Microsoft Entra Agent ID](https://learn.microsoft.com/entra/agent-id/identity-professional/authorization-agent-id) — Roller, tillatelser og blokkerte rettigheter

6
skills/ms-ai-security/references/ai-security-engineering/jailbreak-prevention-production.md
View file

@ -519,7 +519,7 @@ print(f"Jailbreak resistance score: {results['jailbreak_resistance']}")
### Microsoft Learn Documentation
1. **Prompt Shields in Azure AI Foundry**
[https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-prompt-shields](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-prompt-shields)
[https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields)
*Offisiell dokumentasjon for Prompt Shields i Azure OpenAI content filtering-systemet.*
2. **Prompt Shields in Azure AI Content Safety**
@ -527,7 +527,7 @@ print(f"Jailbreak resistance score: {results['jailbreak_resistance']}")
*Unified API for jailbreak detection med user scenarios og implementation guide.*
3. **Safety System Messages - Step-by-step Authoring Best Practices**
[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)
[https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message)
*Best practices for system message design som første forsvarslinje.*
4. **Security Planning for LLM-based Applications**
@ -535,7 +535,7 @@ print(f"Jailbreak resistance score: {results['jailbreak_resistance']}")
*Comprehensive security planning guide med threat modeling for LLM apps.*
5. **Azure OpenAI Default Safety Policies**
[https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/default-safety-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](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies)
*Default safety policies inkludert jailbreak detection thresholds.*
6. **API Management - llm-content-safety Policy**

2
skills/ms-ai-security/references/ai-security-engineering/model-fingerprinting-watermarking.md
View file

@ -541,7 +541,7 @@ Trenger kunde watermarking/fingerprinting?
## Kilder
1. **C2PA Specification** — https://c2pa.org/specifications/specifications/2.1/specs/C2PA_Specification.html
2. **Azure OpenAI Content Credentials** — https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-credentials
2. **Azure OpenAI Content Credentials** — https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-credentials
3. **Azure Text to Speech Content Credentials** — https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech-avatar/content-credentials
4. **Microsoft 365 Watermarking** — https://learn.microsoft.com/en-us/copilot/microsoft-365/watermarks
5. **Azure Machine Learning Model Management** — https://learn.microsoft.com/en-us/azure/machine-learning/concept-model-management-and-deployment

8
skills/ms-ai-security/references/ai-security-engineering/output-validation-grounding-verification.md
View file

@ -647,19 +647,19 @@ def cached_groundedness_check(key):
[Verified: 2026-02]
3. **Content Filter Groundedness (Azure OpenAI):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter-groundedness
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness
[Verified: 2026-02]
4. **Azure AI Evaluation SDK (Groundedness Evaluator):**
https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/develop/evaluate-sdk
https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk
[Verified: 2026-02]
5. **Azure AI Search Grounding (Transparency Note):**
https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/search/transparency-note
https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/search/transparency-note
[Verified: 2026-02]
6. **Bing Grounding Tools for Agents:**
https://learn.microsoft.com/en-us/azure/ai-foundry/agents/how-to/tools/bing-tools
https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools
[Verified: 2026-02]
7. **Security Planning for LLM Applications (Output Validation):**

2
skills/ms-ai-security/references/ai-security-engineering/pii-detection-norwegian-context.md
View file

@ -419,7 +419,7 @@ df_masked = df.withColumn("text_masked", mask_pii_udf(df.text))
- [Recognized PII and PHI Entities](https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/concepts/entity-categories) (inkluderer NOIdentityNumber)
- [How to: Redact Text PII](https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/how-to/redact-text-pii) — Oppdatert: ny DisableEntityValidation, EntitySynonyms, ValueExclusionPolicy, per-entity confidence threshold overrides (2025-11-15-preview)
- [Quickstart: Detect PII](https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/quickstart) — Quickstart er nå for native document PII; link til text/conversation how-to-guides for tekst-PII
- [Transparency Note for PII](https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/language-service/transparency-note-personally-identifiable-information) (GDPR compliance, nå under Azure AI Foundry responsible AI)
- [Transparency Note for PII](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/language-service/transparency-note-personally-identifiable-information) (GDPR compliance, nå under Azure AI Foundry responsible AI)
**Baseline (modellkunnskap):**
- Norsk fødselsnummer-format (11 siffer, mod11-checksumvalidering)

4
skills/ms-ai-security/references/ai-security-engineering/prompt-injection-defense-patterns.md
View file

@ -445,8 +445,8 @@ Når du diskuterer prompt injection-forsvar med kunder, still disse spørsmålen
- [Prompt Shields - Azure AI Content Safety](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/concepts/jailbreak-detection) (GA)
- [Microsoft Security Benchmark - AI Security Controls](https://learn.microsoft.com/en-us/security/benchmark/azure/mcsb-v2-artificial-intelligence-security) (AI-2, AI-3)
- [Security Planning for LLM Applications](https://learn.microsoft.com/en-us/ai/playbook/technology-guidance/generative-ai/mlops-in-openai/security/security-plan-llm-application)
- [Content Filtering Overview](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/content-filter)
- [Default Safety Policies](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/default-safety-policies)
- [Content Filtering Overview](https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/content-filter)
- [Default Safety Policies](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies)
**Tools and Services:**
- Azure AI Content Safety: [Overview](https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview)

2
skills/ms-ai-security/references/ai-security-engineering/zero-trust-ai-services.md
View file

@ -907,7 +907,7 @@ Logging & Monitoring:
Denne guiden er basert på følgende Microsoft Learn-dokumentasjon (sist verifisert 2026-04):
1. [Secure networks with SASE, Zero Trust, and AI](https://learn.microsoft.com/en-us/security/zero-trust/deploy/networks) — Offisiell Zero Trust nettverksguide
2. [How to configure Azure OpenAI with managed identities](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/managed-identity) — Managed Identity-konfigurasjon for Azure OpenAI
2. [How to configure Azure OpenAI with managed identities](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/managed-identity) — Managed Identity-konfigurasjon for Azure OpenAI
3. [Managed identities: role-based access control (RBAC)](https://learn.microsoft.com/en-us/azure/ai-services/translator/document-translation/how-to-guides/create-use-managed-identities) — RBAC-implementering for AI Services
4. [Azure security baseline for Azure OpenAI](https://learn.microsoft.com/en-us/security/benchmark/azure/baselines/azure-openai-security-baseline) — Sikkerhetsbaseline med Identity Management-krav
5. [Build a strong security posture for AI](https://learn.microsoft.com/en-us/security/security-for-ai/posture) — Zero Trust-prinsipper for AI-sikkerhet

14
skills/ms-ai-security/references/cost-optimization/azure-ai-foundry-cost-governance.md
View file

@ -805,27 +805,27 @@ Savings with PTU: 3 000 NOK/month (17% reduction)
*Confidence: Verified (Feb 2026)* — Comprehensive governance framework, 8-step cost governance process
2. **Manage and increase quotas for hub resources**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/hub-quota
URL: https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-quota
*Confidence: Verified (Feb 2026)* — Quota management UI, VM quota, model quota allocation
3. **Plan and manage costs for Microsoft Foundry**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/manage-costs
URL: https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
*Confidence: Verified (Feb 2026)* — Budget creation, cost monitoring, RBAC for cost visibility
4. **Azure OpenAI Dynamic quota (Preview)**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/dynamic-quota
URL: https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota
*Confidence: Verified (Feb 2026)* — When to use dynamic quota, cost implications
5. **Consolidated view for Foundry Tools in the Azure portal**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/ai-foundry-consolidated-view
URL: https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/ai-foundry-consolidated-view
*Confidence: Verified (Feb 2026)* — Dashboard for costs, quota utilization, alerts
6. **Azure OpenAI quotas and limits**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/quotas-limits
URL: https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits
*Confidence: Verified (Feb 2026)* — Model-specific TPM/RPM limits by tier
7. **Azure OpenAI in Azure AI Foundry Models quota management**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/quota
URL: https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota
*Confidence: Verified (Feb 2026)* — Quota view, request increases, migrating deployments
8. **Manage AI costs (Cloud Adoption Framework)**
@ -833,7 +833,7 @@ Savings with PTU: 3 000 NOK/month (17% reduction)
*Confidence: Verified (Feb 2026)* — Monthly reviews, model selection optimization
9. **Microsoft Foundry rollout across organization (Governance section)**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/planning#governance
URL: https://learn.microsoft.com/en-us/azure/foundry/concepts/planning#governance
*Confidence: Verified (Feb 2026)* — Azure Policy for model access, TPM limits at deployment level
10. **Azure API Management generative AI gateway capabilities**

10
skills/ms-ai-security/references/cost-optimization/batch-processing-cost-reduction.md
View file

@ -307,7 +307,7 @@ Kreves respons < 5 sekunder?
### Microsoft Learn (Verified via MCP)
1. **Getting started with Azure OpenAI batch deployments**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch
- URL: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch
- Konfidens: **Verified** (fetched 2026-02)
- Innhold: Deployment types, pricing (50% reduction), dynamic quota, exponential backoff, supported models, API versions
@ -317,24 +317,24 @@ Kreves respons < 5 sekunder?
- Innhold: 50% cost reduction for batch vs. global standard
3. **What's new in Azure OpenAI (August 2024)**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/whats-new#august-2024
- URL: https://learn.microsoft.com/en-us/azure/foundry-classic/openai/whats-new#august-2024
- Konfidens: **Verified**
- Innhold: Batch API announcement, key use cases, GA status
4. **Azure OpenAI deployment types**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/deployment-types
- URL: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types
- Konfidens: **Verified**
- Innhold: Global-Batch vs. Data Zone Batch, dynamic quota
### Code samples (Verified via MCP)
5. **Python: Create batch job with DefaultAzureCredential**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch?pivots=programming-language-python
- URL: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch?pivots=programming-language-python
- Konfidens: **Verified**
- Innhold: OpenAI Python SDK examples for batch job creation
6. **Python: Upload batch file with expiration**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch?pivots=programming-language-python#upload-batch-file
- URL: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch?pivots=programming-language-python#upload-batch-file
- Konfidens: **Verified**
- Innhold: File upload with 14-30 day expiration

4
skills/ms-ai-security/references/cost-optimization/budget-forecasting-ai-projects.md
View file

@ -467,7 +467,7 @@ Korrekt forecasting driver kostnadsoptimalisering:
*Confidence: Verified* — Komplett guide til forecasting i Azure
2. **Plan to Manage Costs for Azure OpenAI**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs
https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
*Confidence: Verified* — Token-basert pricing, forecasting, budgets
3. **Azure Cost Management - Create Budgets**
@ -491,7 +491,7 @@ Korrekt forecasting driver kostnadsoptimalisering:
*Confidence: Verified* — Well-Architected Framework
8. **Fine-Tuning Cost Management**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-cost-management
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management
*Confidence: Verified* — Training + hosting + inference cost
---

12
skills/ms-ai-security/references/cost-optimization/gpt5-gpt41-pricing-models.md
View file

@ -536,17 +536,17 @@ GPT-4o mini og GPT-4o brukes fortsatt i US Government regions (offer comparable
### Primærkilder (Microsoft Learn, bekreftet februar 2026)
1. **GPT-5 vs GPT-4.1: choosing the right model for your use case**
URL: https://learn.microsoft.com/azure/ai-foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic
Hentet: 2026-02
Innhold: Modellsammenligning, reasoning-nivåer, latens-trade-offs, use-case guidance
2. **Foundry Models sold directly by Azure — GPT-4.1 og GPT-5-serien**
URL: https://learn.microsoft.com/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure?view=foundry-classic
Hentet: 2026-02
Innhold: Kontekstvindu, max output tokens, treningsdata, versjonsoversikt, tilgjengelighetskrav
3. **Provisioned throughput unit (PTU) costs and billing**
URL: https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing?view=foundry-classic
Hentet: 2026-02
Innhold: PTU-kapasitet per modell (TPM/PTU), min deployment, latens-SLA, input/output-ratio (1:4 for gpt-4.1, 1:8 for gpt-5)
@ -556,7 +556,7 @@ GPT-4o mini og GPT-4o brukes fortsatt i US Government regions (offer comparable
Innhold: Priseksempler med gpt-4.1 Global ($2/$8) og gpt-4.1-mini Global ($0.40/$1.60) bekreftet
5. **Azure OpenAI in Microsoft Foundry Models quotas and limits**
URL: https://learn.microsoft.com/azure/ai-foundry/openai/quotas-limits?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/openai/quotas-limits?view=foundry-classic
Hentet: 2026-02
Innhold: GPT-5- og GPT-4.1-seriens kvotestruktur, usage tiers, deployment-typer
@ -566,12 +566,12 @@ GPT-4o mini og GPT-4o brukes fortsatt i US Government regions (offer comparable
Innhold: Copilot Credits-klassifisering (Basic/Standard/Premium) per modell, tilgjengelige modeller
7. **Cost management for fine-tuning**
URL: https://learn.microsoft.com/azure/ai-foundry/openai/how-to/fine-tuning-cost-management?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/openai/how-to/fine-tuning-cost-management?view=foundry-classic
Hentet: 2026-02
Innhold: Fine-tuning kostnad, hosting $1.70/time (o4-mini eksempel)
8. **Plan and manage costs for Microsoft Foundry**
URL: https://learn.microsoft.com/azure/ai-foundry/concepts/manage-costs?view=foundry-classic
URL: https://learn.microsoft.com/azure/foundry/concepts/manage-costs?view=foundry-classic
Hentet: 2026-02
Innhold: Billing-modell, token-basert prising, 1K-token enheter

6
skills/ms-ai-security/references/cost-optimization/inference-endpoint-cost-optimization.md
View file

@ -571,9 +571,9 @@ Hvis inference-kostnad per prediction >10% av business value per prediction, er
- [Plan to manage costs for Azure Machine Learning](https://learn.microsoft.com/en-us/azure/machine-learning/concept-plan-manage-cost?view=azureml-api-2) — **Verified**
**Serverless API Endpoints:**
- [Deploy models as serverless API deployments (AI Foundry Portal)](https://learn.microsoft.com/en-us/azure/ai-foundry/how-to/deploy-models-serverless?view=foundry-classic) — **Verified**
- [Plan and manage costs for Microsoft Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/manage-costs?view=foundry-classic) — **Verified**
- [Plan to manage costs for Azure OpenAI in Azure AI Foundry Models](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs) — **Verified**
- [Deploy models as serverless API deployments (AI Foundry Portal)](https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-serverless?view=foundry-classic) — **Verified**
- [Plan and manage costs for Microsoft Foundry](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs?view=foundry-classic) — **Verified**
- [Plan to manage costs for Azure OpenAI in Azure AI Foundry Models](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs) — **Verified**
**Cost Governance:**
- [Govern Azure platform services (PaaS) for AI](https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/scenarios/ai/platform/governance) — **Verified**

12
skills/ms-ai-security/references/cost-optimization/model-selection-price-performance.md
View file

@ -497,32 +497,32 @@ Bruk alltid confidence markers når du anbefaler modeller:
### Primærkilder (Microsoft Learn)
1. **GPT-5 vs GPT-4.1: choosing the right model for your use case**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic
URL: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/model-choice-guide?view=foundry-classic
Hentet: 2026-02
Innhold: Modellsammenligninger, latency trade-offs, reasoning-nivåer
2. **Plan to manage costs for Azure OpenAI in Azure AI Foundry Models**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs
URL: https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
Hentet: 2026-02
Innhold: Billing models, token pricing, cost monitoring
3. **Cost management for fine-tuning**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-cost-management?view=foundry-classic
URL: https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management?view=foundry-classic
Hentet: 2026-02
Innhold: Training costs, hosting costs, deployment types
4. **Optimize model cost and performance**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/control-plane/how-to-optimize-cost-performance?view=foundry
URL: https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance?view=foundry
Hentet: 2026-02
Innhold: Model Router, cost optimization workflows
5. **Azure OpenAI in Azure AI Foundry Models**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models
URL: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
Hentet: 2026-02
Innhold: Model catalog, capabilities, regional availability
6. **Understanding costs associated with provisioned throughput units (PTU)**
URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding
URL: https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing
Hentet: 2026-02
Innhold: PTU pricing, throughput per PTU, when to use PTU

8
skills/ms-ai-security/references/cost-optimization/multi-model-strategy-costs.md
View file

@ -638,11 +638,11 @@ az consumption usage list --start-date 2026-02-01 --end-date 2026-02-28 \
## Kilder og verifisering
**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)
1. [Model router for Azure AI Foundry](https://learn.microsoft.com/en-us/azure/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). 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)
3. [Understanding costs associated with provisioned throughput units (PTU)](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing) — **Verified** (MCP search, 2026-04)
4. [Azure OpenAI in Azure AI Foundry Models](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure) — **Verified** (MCP search, 2026-04)
5. [GPT-4o vs GPT-4o mini model selection](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/whats-new) — **Verified** (MCP search, 2026-04)
**GitHub samples (MCP-referenced):**
1. [Smart load balancing for Azure OpenAI (Azure API Management)](https://github.com/Azure-Samples/openai-apim-lb) — **Verified**

12
skills/ms-ai-security/references/cost-optimization/prompt-engineering-cost-reduction.md
View file

@ -40,7 +40,7 @@ Prompt caching er en kraftig funksjon for kostnadsreduksjon når du har repetere
| **Prisreduksjon** | 50% rabatt (Standard), opptil 100% (Provisioned) |
| **Støttede modeller** | GPT-4o, GPT-4o-mini, o1-serien, GPT-4.1-serien, o3-mini |
**Verified (MCP):** [Azure AI Foundry - Prompt Caching](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/prompt-caching)
**Verified (MCP):** [Azure AI Foundry - Prompt Caching](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching)
### Token-effektivitet per dataformat
@ -238,7 +238,7 @@ AI Foundry Model Catalog støtter prompt caching for:
- o1-serien og o3-mini
- GPT-4.1-serien
**Verified (MCP):** [AI Foundry Models - Prompt Caching](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/prompt-caching)
**Verified (MCP):** [AI Foundry Models - Prompt Caching](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching)
### Copilot Studio
@ -369,11 +369,11 @@ Copilot Studio bruker underliggende Azure OpenAI, men:
### Microsoft Learn (Verified via MCP)
1. [Prompt Caching - Azure AI Foundry](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/prompt-caching) – **Verified**
2. [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/prompt-engineering) – **Verified**
1. [Prompt Caching - Azure AI Foundry](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching) – **Verified**
2. [Prompt Engineering Techniques](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/prompt-engineering) – **Verified**
3. [Azure OpenAI Pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) – **Verified**
4. [Manage Costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs) – **Verified**
5. [Token Usage Estimation](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data) – **Verified**
4. [Manage Costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs) – **Verified**
5. [Token Usage Estimation](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data) – **Verified**
### Konfidensnivå per seksjon

14
skills/ms-ai-security/references/cost-optimization/ptu-vs-paygo-economics.md
View file

@ -403,23 +403,23 @@ En hybrid tilnærming, der man kombinerer PTU for stabil baseline-traffic og Pay
**Microsoft Learn-ressurser (MCP-verified, februar 2026):**
1. **Provisioned Throughput Concepts:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/provisioned-throughput
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput
*Confidence: Verified* – Offisiell kilde på PTU-konsepter, deployment types, benefits.
2. **PTU Cost Management:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding
https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing
*Confidence: Verified* – Detaljert prisinformasjon, hourly billing, reservations, capacity calculator.
3. **Provisioned Get Started Guide:**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-get-started
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started
*Confidence: Verified* – Deployment workflow, quota vs. capacity, utilization monitoring.
4. **Provisioned Migration (Payment Model Framework):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/provisioned-migration
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-migration
*Confidence: Verified* – Commitment vs. Reservation models, coexistence, best practices.
5. **Performance and 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
*Confidence: Verified* – Throughput vs. latency, TPM estimation, monitoring metrics.
6. **GenAI Gateway (APIM + PTU Optimization):**
@ -431,11 +431,11 @@ En hybrid tilnærming, der man kombinerer PTU for stabil baseline-traffic og Pay
*Confidence: Verified* – Reservation purchase, scope, discounts, management.
8. **Dynamic Quota (Preview):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/dynamic-quota
https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota
*Confidence: Verified* – PayGo deployment optimization, opportunistic quota increase.
9. **Spillover Traffic Management (Preview):**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/spillover-traffic-management
https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management
*Confidence: Verified* – Automatic routing fra PTU til PayGo ved capacity limit.
**Code samples (MCP-verified):**

2
skills/ms-ai-security/references/cost-optimization/rag-query-cost-reduction.md
View file

@ -433,7 +433,7 @@ User → Container App LB → [Azure OpenAI Region 1]
**Verified:**
1. [Plan and manage costs of an Azure AI Search service](https://learn.microsoft.com/en-us/azure/search/search-sku-manage-costs) - Comprehensive cost minimization strategies, tier pricing, indexing optimization.
2. [Azure OpenAI On Your Data - Token usage estimation](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data) - Exact token consumption per model, RAG pipeline breakdown, parameter impacts.
2. [Azure OpenAI On Your Data - Token usage estimation](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data) - Exact token consumption per model, RAG pipeline breakdown, parameter impacts.
3. [RAG chunking phase - Understand chunking economics](https://learn.microsoft.com/en-us/azure/architecture/ai-ml/guide/rag/rag-chunking-phase) - Cache-Aside pattern, cost factors for chunking strategies.
4. [Agentic retrieval in Azure AI Search - Pricing example](https://learn.microsoft.com/en-us/azure/search/agentic-retrieval-overview) - Detailed cost calculation for agentic retrieval with subqueries.
5. [Tips for better performance in Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-performance-tips) - Query design optimization, search tier switching, cost-performance balance.

4
skills/ms-ai-security/references/cost-optimization/request-batching-aggregation.md
View file

@ -493,7 +493,7 @@ Bruk denne matrisen for raskt å avgjøre om batching er riktig:
### Microsoft Learn (Verified via MCP)
1. **Azure OpenAI Batch API:**
- [Getting started with Azure OpenAI batch deployments](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch) — **Verified 2026-02**
- [Getting started with Azure OpenAI batch deployments](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch) — **Verified 2026-02**
- Dekker: JSONL input format, Global-Batch deployment, 50% cost reduction, exponential backoff queuing
2. **Microsoft Graph JSON Batching:**
@ -505,7 +505,7 @@ Bruk denne matrisen for raskt å avgjøre om batching er riktig:
- Dekker: Asynchronous inferencing, pipeline component deployments, low-priority VMs, scale-to-zero
4. **Code Samples (Python):**
- [Azure OpenAI Batch API - Create batch job](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/batch?pivots=programming-language-python#create-batch-job) — **Verified 2026-02**
- [Azure OpenAI Batch API - Create batch job](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch?pivots=programming-language-python#create-batch-job) — **Verified 2026-02**
- [Azure Cosmos DB Transactional Batch](https://learn.microsoft.com/en-us/azure/cosmos-db/transactional-batch#how-to-create-a-transactional-batch-operation) — **Baseline (ikke AI-spesifikk, men relevant pattern)**
### Konfidensnivå per Seksjon

8
skills/ms-ai-security/references/cost-optimization/reserved-capacity-planning.md
View file

@ -543,11 +543,11 @@ Tilgjengelig i deployment workflow:
| Kilde | Type | Last Verified |
|-------|------|---------------|
| [Save costs with Microsoft Foundry Provisioned Throughput Reservations](https://learn.microsoft.com/en-us/azure/cost-management-billing/reservations/azure-openai) | Offisiell docs | 2026-01 |
| [Understanding costs associated with provisioned throughput units (PTU)](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) | Offisiell docs | 2026-01 |
| [Azure OpenAI provisioned Managed offering updates](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/provisioned-migration) | Offisiell docs | 2025-08 |
| [Understanding costs associated with provisioned throughput units (PTU)](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing) | Offisiell docs | 2026-01 |
| [Azure OpenAI provisioned Managed offering updates](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-migration) | Offisiell docs | 2025-08 |
| [Purchase commitment tier pricing](https://learn.microsoft.com/en-us/azure/ai-services/commitment-tier) | Offisiell docs | 2026-01 |
| [What is provisioned throughput?](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/provisioned-throughput) | Offisiell docs | 2026-01 |
| [Azure OpenAI Provisioned Managed Offering in Azure Government](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/gov-provisioned) | Offisiell docs | 2025-05 |
| [What is provisioned throughput?](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput) | Offisiell docs | 2026-01 |
| [Azure OpenAI Provisioned Managed Offering in Azure Government](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-gov) | Offisiell docs | 2025-05 |
| [View Azure reservation utilization](https://learn.microsoft.com/en-us/azure/cost-management-billing/reservations/reservation-utilization) | Cost Management | 2025-12 |
| [How reservation discounts are applied](https://learn.microsoft.com/en-us/azure/cost-management-billing/reservations/reservation-discount-application) | Cost Management | 2025-12 |
| [Azure Pricing Calculator](https://azure.microsoft.com/pricing/calculator/) | Pricing tool | Live |

4
skills/ms-ai-security/references/cost-optimization/small-language-models-economics.md
View file

@ -603,12 +603,12 @@ az webapp create --name webapp-slm-phi4 --resource-group rg-slm-norway --plan pl
- Innhold: KAITO deployment, Phi-4-mini på AKS, GPU-krav
5. **Azure OpenAI in Azure AI Foundry Models**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models
- URL: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure
- Confidence: **Verified**
- Innhold: GPT-4o, GPT-4o-mini pricing, capabilities
6. **Foundry Models from partners and community (Microsoft)**
- URL: https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-from-partners
- URL: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners
- Confidence: **Verified**
- Innhold: Phi-4-mini-instruct, Phi-4-multimodal specs

10
skills/ms-ai-security/references/cost-optimization/token-counting-optimization.md
View file

@ -570,13 +570,13 @@ def track_token_usage(prompt, completion, model="gpt-4o"):
## Kilder og verifisering
**Microsoft Learn Documentation:**
1. [Prompt caching - Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/prompt-caching)
2. [Work with chat completions models - Token management](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/chatgpt#manage-conversations)
3. [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs)
1. [Prompt caching - Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching)
2. [Work with chat completions models - Token management](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt#manage-conversations)
3. [Plan and manage costs for Azure OpenAI](https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs)
4. [Token counting in AI - Dynamics 365 Business Central](https://learn.microsoft.com/en-us/dynamics365/business-central/dev-itpro/developer/ai-system-app-token-counting)
5. [Use Microsoft.ML.Tokenizers for text tokenization](https://learn.microsoft.com/en-us/dotnet/ai/how-to/use-tokenizers)
6. [Azure OpenAI On Your Data - Token usage estimation](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data)
7. [Cost management for fine-tuning](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/fine-tuning-cost-management)
6. [Azure OpenAI On Your Data - Token usage estimation](https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data#token-usage-estimation-for-azure-openai-on-your-data)
7. [Cost management for fine-tuning](https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management)
**OpenAI Resources:**
8. [OpenAI Cookbook - Token counting](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb)

4
skills/ms-ai-security/references/cost-optimization/vector-storage-cost-optimization.md
View file

@ -549,11 +549,11 @@ Hvis vector search brukes som grunnlag for Copilot for Microsoft 365:
Confidence: Verified (MCP search results, januar 2026)
6. **Azure OpenAI embeddings models**
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 search results, januar 2026)
7. **Azure OpenAI cost management**
https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/manage-costs
https://learn.microsoft.com/en-us/azure/foundry/concepts/manage-costs
Confidence: Verified (MCP search results, januar 2026)
8. **Storage optimization for vectors**

6
skills/ms-ai-security/references/performance-scalability/async-processing-patterns.md
View file

@ -527,9 +527,9 @@ def publish_ordered_event(
## Referanser
- [Azure OpenAI Batch API](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/batch) — Batch processing
- [Azure OpenAI Responses API — Background tasks](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/responses) — Background mode
- [Azure OpenAI Webhooks](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/webhooks) — Event notifications
- [Azure OpenAI Batch API](https://learn.microsoft.com/azure/foundry/openai/how-to/batch) — Batch processing
- [Azure OpenAI Responses API — Background tasks](https://learn.microsoft.com/azure/foundry/openai/how-to/responses) — Background mode
- [Azure OpenAI Webhooks](https://learn.microsoft.com/azure/foundry/openai/how-to/webhooks) — Event notifications
- [Event-driven architecture style](https://learn.microsoft.com/azure/architecture/guide/architecture-styles/event-driven) — Architecture patterns
- [Azure Functions on Container Apps](https://learn.microsoft.com/azure/container-apps/functions-unified-platform) — Event-driven compute

2
skills/ms-ai-security/references/performance-scalability/batch-api-usage-optimization.md
View file

@ -206,7 +206,7 @@ with open("large_batch.jsonl", "rb") as data:
)
# 2. Konfigurer Azure OpenAI til a bruke Blob Storage
# Se: https://learn.microsoft.com/azure/ai-foundry/openai/how-to/batch-blob-storage
# Se: https://learn.microsoft.com/azure/foundry-classic/openai/how-to/batch-blob-storage
```
### Filgrenser

6
skills/ms-ai-security/references/performance-scalability/concurrent-request-optimization.md
View file

@ -418,9 +418,9 @@ class FairScheduler:
## Referanser
- [Manage Azure OpenAI quota](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/quota) — RPM/TPM grenser
- [Performance and latency](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/latency) — Concurrent requests og throughput
- [Provisioned throughput](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-get-started) — PTU utilization
- [Manage Azure OpenAI quota](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/quota) — RPM/TPM grenser
- [Performance and latency](https://learn.microsoft.com/azure/foundry/openai/how-to/latency) — Concurrent requests og throughput
- [Provisioned throughput](https://learn.microsoft.com/azure/foundry/openai/how-to/provisioned-get-started) — PTU utilization
## For Cosmo

4
skills/ms-ai-security/references/performance-scalability/gpu-compute-sizing.md
View file

@ -419,8 +419,8 @@ ml_client.online_deployments.begin_create_or_update(deployment).result()
## Referanser
- [What is provisioned throughput?](https://learn.microsoft.com/azure/ai-foundry/openai/concepts/provisioned-throughput) — PTU oversikt
- [PTU costs and billing](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) — PTU-prising per modell
- [What is provisioned throughput?](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput) — PTU oversikt
- [PTU costs and billing](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing) — PTU-prising per modell
- [Foundry PTU calculator](https://ai.azure.com/resource/calculator) — Kapasitetskalkulator
- [GPU optimized VM sizes](https://learn.microsoft.com/azure/virtual-machines/sizes-gpu) — Azure GPU VM-oversikt
- [Deploy models in Azure ML](https://learn.microsoft.com/azure/machine-learning/how-to-deploy-online-endpoints) — ML endpoint deployment

4
skills/ms-ai-security/references/performance-scalability/load-testing-ai-services.md
View file

@ -416,10 +416,10 @@ azure-openai-benchmark \
## Referanser
- [Run a benchmark](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-get-started#run-a-benchmark) — Azure OpenAI benchmarking guide
- [Run a benchmark](https://learn.microsoft.com/azure/foundry/openai/how-to/provisioned-get-started#run-a-benchmark) — Azure OpenAI benchmarking guide
- [Azure OpenAI Benchmark Tool](https://github.com/Azure/azure-openai-benchmark) — Offisielt CLI-verktøy
- [Azure Load Testing overview](https://learn.microsoft.com/azure/load-testing/overview-what-is-azure-load-testing) — Managed lasttesting
- [Performance and latency](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/latency) — Throughput vs latency forklaring
- [Performance and latency](https://learn.microsoft.com/azure/foundry/openai/how-to/latency) — Throughput vs latency forklaring
- [Capacity planning](https://learn.microsoft.com/azure/well-architected/performance-efficiency/capacity-planning) — WAF kapasitetsplanlegging
## For Cosmo

6
skills/ms-ai-security/references/performance-scalability/model-distillation-performance.md
View file

@ -428,9 +428,9 @@ def route_to_model(user_input: str) -> str:
## Referanser
- [Azure OpenAI stored completions & distillation](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/stored-completions) — Distillation workflow
- [Fine-tuning considerations](https://learn.microsoft.com/azure/ai-foundry/openai/concepts/fine-tuning-considerations) — Når fine-tuning er riktig
- [Customize a model with fine-tuning](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/fine-tuning) — Fine-tuning guide
- [Azure OpenAI stored completions & distillation](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/stored-completions) — Distillation workflow
- [Fine-tuning considerations](https://learn.microsoft.com/azure/foundry/openai/concepts/fine-tuning-considerations) — Når fine-tuning er riktig
- [Customize a model with fine-tuning](https://learn.microsoft.com/azure/foundry/openai/how-to/fine-tuning) — Fine-tuning guide
- [Choose the right AI model](https://learn.microsoft.com/azure/architecture/ai-ml/guide/choose-ai-model) — Modellvalg-guide
## For Cosmo

6
skills/ms-ai-security/references/performance-scalability/performance-benchmarking-frameworks.md
View file

@ -536,9 +536,9 @@ async def ci_benchmark_gate(
- [Azure OpenAI Benchmark Tool](https://github.com/Azure/azure-openai-benchmark) — Offisielt CLI-verktøy
- [Azure Load Testing](https://learn.microsoft.com/azure/load-testing/overview-what-is-azure-load-testing) — Managed lasttesting
- [Performance and latency](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/latency) — Ytelseskonsepter
- [Evaluate generative AI models](https://learn.microsoft.com/azure/ai-foundry/how-to/evaluate-generative-ai-app) — Kvalitetsevaluering
- [Azure Monitor metrics](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/monitor-openai) — Azure OpenAI monitoring
- [Performance and latency](https://learn.microsoft.com/azure/foundry/openai/how-to/latency) — Ytelseskonsepter
- [Evaluate generative AI models](https://learn.microsoft.com/azure/foundry/how-to/evaluate-generative-ai-app) — Kvalitetsevaluering
- [Azure Monitor metrics](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/monitor-openai) — Azure OpenAI monitoring
## For Cosmo

4
skills/ms-ai-security/references/performance-scalability/prompt-caching-performance.md
View file

@ -360,8 +360,8 @@ class CacheAwarePromptManager:
## Referanser
- [Prompt caching](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/prompt-caching) — Offisiell guide
- [Provisioned throughput](https://learn.microsoft.com/azure/ai-foundry/openai/concepts/provisioned-throughput) — PTU caching-fordeler
- [Prompt caching](https://learn.microsoft.com/azure/foundry/openai/how-to/prompt-caching) — Offisiell guide
- [Provisioned throughput](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput) — PTU caching-fordeler
- [Semantic cache with Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/gen-ai/semantic-cache) — Ekstern caching
- [Application design for AI workloads](https://learn.microsoft.com/azure/well-architected/ai/application-design) — Multi-layer caching

6
skills/ms-ai-security/references/performance-scalability/rate-limit-management.md
View file

@ -474,9 +474,9 @@ Microsoft dokumenterer multi-backend gateway som den anbefalte arkitekturmønste
## Referanser
- [Manage Azure OpenAI quota](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/quota) — Kvotehåndtering
- [Azure OpenAI quotas and limits](https://learn.microsoft.com/azure/ai-foundry/openai/quotas-limits) — Grenser per modell
- [Azure OpenAI SDK retry handling](https://learn.microsoft.com/azure/ai-foundry/openai/supported-languages) — SDK retry-konfigurasjon
- [Manage Azure OpenAI quota](https://learn.microsoft.com/azure/foundry-classic/openai/how-to/quota) — Kvotehåndtering
- [Azure OpenAI quotas and limits](https://learn.microsoft.com/azure/foundry/openai/quotas-limits) — Grenser per modell
- [Azure OpenAI SDK retry handling](https://learn.microsoft.com/azure/foundry/openai/supported-languages) — SDK retry-konfigurasjon
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region gateway (Azure OpenAI i Foundry Models) — Verified (MCP 2026-04)
## For Cosmo

2
skills/ms-ai-security/references/performance-scalability/regional-deployment-latency.md
View file

@ -399,7 +399,7 @@ Microsoft dokumenterer nå fire formelle topologier for Azure OpenAI gateway:
- [Use a gateway in front of multiple Azure OpenAI deployments or instances](https://learn.microsoft.com/azure/architecture/ai-ml/guide/azure-openai-gateway-multi-backend) — Multi-region patterns (Azure OpenAI i Foundry Models) — Verified (MCP 2026-04)
- [Azure Front Door](https://learn.microsoft.com/azure/frontdoor/front-door-overview) — Global load balancing
- [APIM multi-region deployment](https://learn.microsoft.com/azure/api-management/api-management-howto-deploy-multi-region) — Regional gateway
- [Azure OpenAI deployment types](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/deployment-types) — Global vs Regional
- [Azure OpenAI deployment types](https://learn.microsoft.com/azure/foundry/foundry-models/concepts/deployment-types) — Global vs Regional
- [AI Ready — Establish AI reliability](https://learn.microsoft.com/azure/cloud-adoption-framework/scenarios/ai/ready) — Multi-region best practices
## For Cosmo

2
skills/ms-ai-security/references/performance-scalability/response-chunking-strategies.md
View file

@ -464,7 +464,7 @@ class ResilientStreamProcessor:
## Referanser
- [Azure OpenAI streaming](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/responses) — Streaming API
- [Azure OpenAI streaming](https://learn.microsoft.com/azure/foundry/openai/how-to/responses) — Streaming API
- [Server-Sent Events with Application Gateway](https://learn.microsoft.com/azure/application-gateway/use-server-sent-events) — SSE proxy
- [API Management SSE configuration](https://learn.microsoft.com/azure/api-management/how-to-server-sent-events) — APIM SSE
- [Server-Sent Events with App Gateway for Containers](https://learn.microsoft.com/azure/application-gateway/for-containers/server-sent-events) — Container SSE

6
skills/ms-ai-security/references/performance-scalability/throughput-optimization-strategies.md
View file

@ -433,9 +433,9 @@ def submit_batch(client: AzureOpenAI, filename: str):
## Referanser
- [Performance and latency](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/latency) — Azure OpenAI latency og throughput
- [Azure OpenAI Batch API](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/batch) — Batch processing guide
- [Provisioned throughput onboarding](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) — PTU sizing og kostnader
- [Performance and latency](https://learn.microsoft.com/azure/foundry/openai/how-to/latency) — Azure OpenAI latency og throughput
- [Azure OpenAI Batch API](https://learn.microsoft.com/azure/foundry/openai/how-to/batch) — Batch processing guide
- [Provisioned throughput onboarding](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing) — PTU sizing og kostnader
- [Azure OpenAI Benchmark Tool](https://github.com/Azure/azure-openai-benchmark) — Offisielt benchmarking-verktøy
## For Cosmo

8
skills/ms-ai-security/references/performance-scalability/token-per-second-optimization.md
View file

@ -328,10 +328,10 @@ print(f"Rejected predictions: {usage.rejected_prediction_tokens}")
## Referanser
- [Performance and latency](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/latency) — TPS og throughput forklaring
- [Provisioned throughput onboarding](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding) — PTU TPS-mål per modell
- [Prompt caching](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/prompt-caching) — Cache-basert TPS-forbedring
- [Predicted outputs](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/predicted-outputs) — Spekulativ generering
- [Performance and latency](https://learn.microsoft.com/azure/foundry/openai/how-to/latency) — TPS og throughput forklaring
- [Provisioned throughput onboarding](https://learn.microsoft.com/azure/foundry/openai/concepts/provisioned-throughput-billing) — PTU TPS-mål per modell
- [Prompt caching](https://learn.microsoft.com/azure/foundry/openai/how-to/prompt-caching) — Cache-basert TPS-forbedring
- [Predicted outputs](https://learn.microsoft.com/azure/foundry/openai/how-to/predicted-outputs) — Spekulativ generering
- [Foundry PTU calculator](https://ai.azure.com/resource/calculator) — Kapasitetskalkulator
## For Cosmo