/microsoft-foundry

name: microsoft-foundry
description: 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, Azure OpenAI, VNet/private connectivity, CI/CD, or Copilot/Teams publishing, and other Microsoft Foundry related development tasks. Not for Content Safety in Foundry Control Plane (use azure-content-safety), Azure Content Understanding in Foundry Tools (use azure-content-understanding), Azure Speech in Foundry Tools (use azure-speech), Microsoft Foundry Classic (use microsoft-foundry-classic).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-08-09"
  generator: "docs2skills/1.0.0"

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`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file

> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

This skill requires **network access** to fetch documentation content:

• **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
• **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.

Category Index

| Category | Lines | Description | |----------|-------|-------------| | Troubleshooting | L37-L46 | Diagnosing and fixing hosted agent, evaluation/observability, webhook, and service issues, including health checks, recovery from data loss, and known bugs/workarounds. | | Best Practices | L47-L61 | Best practices for configuring and tuning Foundry agents: tools, routing, system messages, safety, evaluation, latency/throughput, and operating provisioned deployments. | | Decision Making | L62-L105 | Guides for choosing models, deployments, hosting, networking, billing modes, and upgrade/migration paths (Assistants→Foundry, preview→GA, Azure OpenAI→Foundry), plus cost/perf optimization and DR. | | Architecture & Design Patterns | L106-L113 | Design patterns for secure, scalable Foundry agents: VNet networking, private retrieval with Foundry IQ, shared session pooling, and high availability architectures. | | Limits & Quotas | L114-L133 | Quotas, rate limits, regions, and throughput settings for agents, models (Claude, Azure OpenAI, partner), vector stores, sessions, AI Gateway, and evaluation, including gov/enterprise options. | | Security | L134-L181 | Identity, RBAC, networking, guardrails, data privacy, compliance, and policy controls for securing Foundry agents, models, tools, traces, and infrastructure. | | Configuration | L182-L250 | Configuring and operating Foundry agents and models: YAML schemas, runtime contracts, networking, storage, observability, evaluations, OpenTelemetry, Azure OpenAI, and private/managed connectivity. | | Integrations & Coding Patterns | L251-L341 | Patterns and code to integrate Foundry agents and models with tools, data, MCP, Azure/OpenAI APIs, tracing, memory, voice, search, and external services for end-to-end agent solutions. | | Deployment | L342-L367 | Deploying and managing Foundry hosted agents and models: infrastructure setup, CI/CD, private registries, publishing to Copilot/Teams, evaluations, red teaming, and healthcare/model-specific deployments. |

Troubleshooting

| Topic | URL | |-------|-----| | Check hosted agent project health with agent doctor | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-doctor | | Troubleshoot Microsoft Foundry hosted agent issues | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/debug-hosted-agent | | 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

| Topic | URL | |-------|-----| | Apply tool usage best practices in Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice | | Optimize hosted agent instructions, tools, skills, and models | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/optimize-agent-targets | | Optimize toolbox tool search to reduce context costs | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/tool-search | | Use Task Adherence signals for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/guardrails/task-adherence | | Evaluate Microsoft Foundry AI agents with built-in evaluators | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent | | Design effective system messages for Azure Ope