Loading...
Loading...
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), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).
npx skill4agent add microsoftdocs/agent-skills microsoft-foundryIMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,), useL35-L120with the specified lines. For categories with file links (e.g.,read_file), use[security.md](security.md)on the linked reference fileread_file
IMPORTANT for Agent: Ifis more than 3 months old, suggest the user pull the latest version from the repository. Ifmetadata.generated_attools are not available, suggest the user install it: Installation Guidemcp_microsoftdocs
mcp_microsoftdocs:microsoft_docs_fetchfrom=learn-agent-skillfetch_webpagefrom=learn-agent-skill&accept=text/markdown| 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. |
| Topic | URL |
|---|---|
| Review known issues and workarounds for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |
| 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 |