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 IQ retrieval, Entra RBAC, Azure OpenAI, M365/Teams publishing, or MCP tools, 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).From its SKILL.md
npx -y skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
46.2 KB, ~10.8k tokens by cl100k_base, as published. Nobody here has run it
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-L47 | Diagnosing and fixing hosted agent and partner model issues, log-based troubleshooting, recovery from data/resource loss, webhook problems, and known Foundry service errors/workarounds. |
| Best Practices | L48-L66 | Best practices for designing, optimizing, testing, routing, evaluating, and safely operating Foundry/Azure OpenAI agents, including prompts, tools, models, latency, fine-tuning, and human review. |
| Decision Making | L67-L110 | Guidance for planning and decision-making: choosing models, deployment and networking options, cost/billing modes, migrations, lifecycle/retirement, DR, and integration patterns for Foundry. |
| Architecture & Design Patterns | L111-L118 | Design patterns for Foundry agent architectures: network/subnet planning, private retrieval with Foundry IQ, shared user sessions, and high availability strategies. |
| Limits & Quotas | L119-L136 | Quotas, rate limits, regions, and capacity planning for Foundry agents, models, Azure OpenAI, vector stores, sessions/timeouts, batch jobs, and cost safeguards (incl. gov/enterprise). |
| Security | L137-L180 | Identity, RBAC, networking, encryption, and policy controls for securing Foundry agents/models, including guardrails, data privacy, compliance, and governance with Entra and Azure Policy. |
| Configuration | L181-L258 | Configuring Microsoft Foundry agents and models: schemas, deployment, networking, tools, monitoring, evaluations, Azure OpenAI integration, security/guardrails, and enterprise connectivity (BYOS, private access). |
| Integrations & Coding Patterns | L259-L343 | Coding patterns and integrations for Foundry agents and models: SDK usage, tools/MCP, external AI gateways, OpenAI/Azure OpenAI, LangChain/LangGraph, tracing, voice/real-time, and grounding data sources. |
| Deployment | L344-L368 | Deploying and operating Foundry hosted agents and models: azd scaffolding, container builds, CI/CD, local testing, publishing to M365/Teams, evaluations, red teaming, and outage recovery. |
Troubleshooting
| Topic | URL |
|---|---|
| Check hosted agent project health with agent doctor | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-doctor |
| Diagnose and fix common hosted agent issues | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/debug-hosted-agent |
| Monitor and troubleshoot Foundry hosted agent logs | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/monitor-hosted-agent-logs |
| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery |
| Troubleshoot Foundry evaluation and observability issues | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/troubleshooting |
| Set up and troubleshoot Azure OpenAI webhooks | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks |
| Known issues and workarounds for Microsoft Foundry services | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |
Best Practices
Decision Making
Architecture & Design Patterns
| Topic | URL |
|---|---|
| Design networking and subnet sizing for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agents-networking-deep-dive |
| Design private agentic retrieval architecture with Foundry IQ | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-tutorial-private-overview |
| Pool multiple users into shared Foundry agent sessions | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/multiplex-session-users |
| Design high availability for Microsoft Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency |
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.