azure-microsoft-foundry
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: This file may be large. Use the Category Index below to locate relevant sections, then use
read_filewith specific line ranges (e.g.,L136-L144) to read the sections needed for the user's question
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-L43 | Troubleshooting Foundry issues: Azure Marketplace purchase/deployment problems, recovering Agent Service after data/resource loss, and known platform bugs with workarounds. |
| Best Practices | L44-L58 | Best practices for prompts, tools, safety, fine-tuning (incl. vision), synthetic data, and optimizing Azure OpenAI latency, throughput, traffic, and cost in Foundry. |
| Decision Making | L59-L84 | Guidance on choosing and upgrading models, SDKs, and deployments, handling deprecations, data isolation, regions, and migrating between Azure OpenAI, GitHub Models, and Foundry services. |
| Architecture & Design Patterns | L85-L90 | Designing resilient Foundry solutions, including high availability patterns, redundancy, and disaster recovery strategies for Foundry Agent Service and project architectures. |
| Limits & Quotas | L91-L107 | Quotas, limits, and capacity for Foundry models, agents, vector stores, evals, batch jobs, Sora, fine-tuning, PTU costs, and how to manage or increase Azure OpenAI-related quotas. |
| Security | L108-L135 | Security, identity, and compliance for Foundry: auth (Entra ID, keyless, RBAC), private networking, encryption, policies, safety filters, and data privacy for models and Agent Service. |
| Configuration | L136-L191 | Configuring and operating Foundry agents and models: tools, workflows, storage, security, tracing, evaluation, monitoring, rate limits, and Azure/Anthropic/OpenAI integration. |
| Integrations & Coding Patterns | L192-L247 | Patterns and APIs for integrating Foundry agents with tools, data sources, Azure OpenAI, MCP, web search, speech, UI automation, tracing, and external apps/services. |
| Deployment | L248-L264 | Deploying and managing Foundry agents/models in production: hosting options, infra provisioning (CLI/Bicep/Terraform), CI/CD and evaluations, M365/Teams integration, and outage recovery. |
Troubleshooting
| Topic | URL |
|---|---|
| Resolve Azure Marketplace issues for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-marketplace |
| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery |
| Review 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
| Topic | URL |
|---|---|
| Plan disaster recovery strategy for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery |
| Design high availability and resiliency for Foundry projects | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency |