> microsoft-foundry
Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, vector search/RAG, Sora video, realtime audio, or MCP/LangChain APIs, and other Microsoft Foundry related development tasks. Not for Microsoft Foundry Classic (use microsoft-foundry-classic),
curl "https://skillshub.wtf/MicrosoftDocs/Agent-Skills/microsoft-foundry?format=md"Microsoft Foundry Skill
This skill provides expert guidance for Microsoft Foundry. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
How to Use This Skill
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120), useread_filewith the specified lines. For categories with file links (e.g.,[security.md](security.md)), useread_fileon the linked reference file
IMPORTANT for Agent: If
metadata.generated_atis more than 3 months old, suggest the user pull the latest version from the repository. Ifmcp_microsoftdocstools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
- Preferred: Use
mcp_microsoftdocs:microsoft_docs_fetchwith query stringfrom=learn-agent-skill. Returns Markdown. - Fallback: Use
fetch_webpagewith query stringfrom=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
| Category | Lines | Description |
|---|---|---|
| Troubleshooting | L37-L41 | Known issues, error codes, limitations, and current workarounds for Microsoft Foundry features, deployments, integrations, and runtime behavior. |
| Best Practices | L42-L52 | Best practices for configuring tools, prompts, system messages, vision models, fine-tuning, evaluation, and performance (latency/throughput) for Azure OpenAI agents in Foundry |
| Decision Making | L53-L80 | Guides for choosing models, SDKs, deployment types, costs, and migrations (Azure OpenAI, GitHub Models, classic/preview) to design and upgrade Foundry-based AI solutions. |
| Architecture & Design Patterns | L81-L93 | Architectural patterns for Foundry agents: standard setup, RAG/indexing, HA/DR, regional recovery, provisioned throughput, spillover traffic, and LLM routing optimization. |
| Limits & Quotas | L94-L109 | Limits, quotas, rate limits, regions, timeouts, caching, and cost controls for Foundry agents, models, vector search, batch jobs, Sora video, RFT, and Azure OpenAI access. |
| Security | L110-L142 | Security, identity, and compliance for Foundry: auth/RBAC, private networking, encryption/CMK, safety guardrails, policy/governance, data privacy, and secure tool/agent configuration. |
| Configuration | L143-L202 | Configuring Foundry agents, models, tools, storage, safety/guardrails, tracing, evaluators, and Azure OpenAI/Fireworks integrations for deployment, monitoring, and advanced capabilities. |
| Integrations & Coding Patterns | L203-L268 | Integrating Foundry agents and models with external apps, tools, and services: SDK usage, REST APIs, MCP/LangChain, search/speech/browsing tools, fine-tuning, realtime audio, safety, and evaluations. |
| Deployment | L269-L286 | Deploying and managing Foundry agents/models: infra setup, container/hosted deployments, Azure/M365 publishing, IaC (Bicep/Terraform), CI/CD evals, and regional availability. |
Troubleshooting
| Topic | URL |
|---|---|
| Review known issues and workarounds for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |
Best Practices
| Topic | URL |
|---|---|
| Apply tool configuration best practices for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice |
| Evaluate Foundry agents with built-in quality and safety tests | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent |
| Optimize Foundry agent prompts with Prompt Optimizer | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer |
| Design effective system messages for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering |
| Apply prompt engineering techniques for vision-enabled GPT models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering |
| Fine-tune GPT-4 vision models with images | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision |
| Optimize Azure OpenAI latency and throughput in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency |
Decision Making
Architecture & Design Patterns
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment
> related_skills --same-repo
> microsoft-foundry-tools
Expert knowledge for Microsoft Foundry Tools (aka Azure AI services, Azure Cognitive Services) development including best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using Content Understanding analyzers, Content Moderator APIs, Foundry containers, VNet/Key Vault security, or Entra auth, and other Microsoft Foundry Tools related development tasks. Not for Microsoft Foundry (use micr
> microsoft-foundry-local
Expert knowledge for Microsoft Foundry Local (aka Azure AI Foundry Local) development including troubleshooting, best practices, decision making, configuration, and integrations & coding patterns. Use when using Foundry Local CLI, chat/transcription APIs, tools, OpenAI/LangChain clients, or upgrading legacy SDKs, and other Microsoft Foundry Local related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foun
> microsoft-foundry-classic
Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with RAG, tools, evaluators, Azure OpenAI, VNet/Private Link, or CI/CD deployments, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry
> azure-static-web-apps
Expert knowledge for Azure Static Web Apps development including troubleshooting, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when wiring SWA APIs to Azure DBs, configuring custom domains/auth, CI/CD, preview slots, or Front Door/CDN, and other Azure Static Web Apps related development tasks. Not for Azure App Service (use azure-app-service), Azure Functions (use azure-functions), Azure Container Apps (use azure-container-apps),