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 Foundr
What it does
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-L42 | Diagnosing evaluation/observability problems in Foundry (metrics, logging, tracing) and checking known product issues, limitations, and workarounds. |
| Best Practices | L43-L56 | Best practices for prompts, system messages, tools, routing, safety, evaluation metrics, fine-tuning vision models, and optimizing Azure OpenAI latency/throughput in Foundry |
| Decision Making | L57-L92 | Deciding which Foundry models, SDKs, and deployment options to use, and planning migrations, lifecycle/retirement, costs, and capacity for agents and workloads across clouds and Gov. |
| Architecture & Design Patterns | L93-L103 | Designing resilient Foundry agent architectures: networking/VNet isolation, standard setups, high availability, spillover traffic, and disaster recovery from resource, data, or regional failures. |
| Limits & Quotas | L104-L122 | Quotas, rate limits, regions, timeouts, and capacity rules for Foundry agents and models, including Azure OpenAI usage, batch/eval limits, fine-tuning costs, and partner model availability. |
| Security | L123-L158 | Securing and governing Foundry: auth/RBAC, agent identities, Agent 365, MCP tools, networking, keys, policies, guardrails, content safety, and data privacy/compliance. |
| Configuration | L159-L214 | Configuring Foundry agents, models, tools, networking, security, monitoring, and storage—how to wire up endpoints, Azure OpenAI, workflows, guardrails, and infrastructure settings. |
| Integrations & Coding Patterns | L215-L277 | Patterns and code for integrating Foundry agents and models with tools, APIs, LangChain/LangGraph, MCP, Azure OpenAI (REST, Realtime, audio), search, storage, safety, and fine-tuning. |
| Deployment | L278-L287 | Deploying and hosting models/agents in Foundry: portal, CLI/Bicep, SDK/REST, importing custom models, fine-tuned model hosting, and running evaluations via Azure DevOps/GitHub Actions. |
Troubleshooting
| Topic | URL |
|---|---|
| Troubleshoot Foundry evaluation and observability issues | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/troubleshooting |
| Troubleshoot Microsoft Foundry known issues and workarounds | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |
Best Practices
Decision Making
Architecture & Design Patterns
Limits & Quotas
Security
Configuration
Integrations & Coding Patterns
Deployment
| Topic | URL |
|---|---|
| Deploy containerized Foundry hosted agents via SDK and REST | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent |
| Deploy Foundry Models using Azure CLI and Bicep templates | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments |
| Deploy Foundry Models via Foundry portal for inference | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models |
| Run Foundry evaluations in Azure DevOps | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops |
| Run Foundry evaluations in GitHub Actions | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action |
| Import and deploy custom Fireworks models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models |
| Deploy fine-tuned models on Foundry hosting | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy |
Capabilities
Install
Quality
deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 549 github stars · SKILL.md body (34,293 chars)