/microsoft-foundry-classic

name: microsoft-foundry-classic
description: Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents, model router setups, Azure OpenAI/RAG apps, Terraform deployments, or secure Private Link hubs, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Content Safety in Foundry Control Plane (use azure-content-safety), Azure Speech in Foundry Tools (use azure-speech).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-11-08"
  generator: "docs2skills/1.0.0"

Microsoft Foundry Classic Skill

This skill provides expert guidance for Microsoft Foundry Classic. 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 Foundry issues: Prompt Flow compute sessions, deployments/monitoring, private endpoints, Azure OpenAI fine-tuning, Risks & Safety alerts, and known portal problems. | | Best Practices | L47-L63 | Designing safe, efficient Azure OpenAI/Foundry apps: system messages, safety templates, fine-tuning (incl. vision/reasoning), latency/throughput, token budgets, and chat app evaluation. | | Decision Making | L64-L91 | Guidance for choosing models, regions, deployments, billing, and migration paths in Foundry, including sizing PTU, lifecycle/retirement planning, and disaster recovery decisions. | | Architecture & Design Patterns | L92-L98 | Designing multi-agent architectures, configuring Foundry Agent Service for resilience, and understanding model router behavior, failover, and disaster recovery strategies. | | Limits & Quotas | L99-L114 | Quotas, rate limits, and regional availability for Foundry agents, models (incl. Claude, Azure OpenAI), plus how to manage, request, and increase deployment and throughput quotas. | | Security | L115-L160 | Securing Foundry: identity/RBAC, network isolation & Private Link, Azure Policy guardrails, content filters/PII, CMK & storage, and privacy/security for Azure OpenAI and other models. | | Configuration | L161-L210 | Configuring and monitoring Foundry classic: agents, evaluators, models, storage, networking, tracing, OpenAI usage, and deployment/compute settings, plus Terraform and cross-project access. | | Integrations & Coding Patterns | L211-L306 | Integrating Foundry classic agents and models with external tools, data, and APIs (Azure AI Search, Bing, SharePoint, MCP, OpenAPI, LangChain, SK), plus Azure OpenAI usage, fine-tuning, RAG, and realtime audio. | | Deployment | L307-L326 | Deploying Foundry hubs/models at scale: regions, deployment types, Bicep/Terraform/CLI, managed and serverless compute, HF models, fine-tunes, evaluations, and region feature support |

Troubleshooting

| Topic | URL | |-------|-----| | Troubleshoot Prompt Flow compute session issues in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-troubleshoot | | Troubleshoot Foundry deployments and monitoring issues | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-deploy-and-monitor | | Troubleshoot Foundry private endpoint connection errors | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-secure-connection-project | | Diagnose and fix Azure OpenAI fine-tuning issues | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-troubleshoot | | Monitor and troubleshoot Risks & Safety in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor | | Resolve known issues in Microsoft Foundry classic portal | https://learn.microsoft.com/en-us/azure/foundry-classic/reference/foundry-known-issues |

Best Practices

| Topic | URL | |-------|-----| | Design effective system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/advanced-prompt-engineering | | Apply safety system message templates in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/safety-system-message-templates | | Author safety system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/system-message | | Manage chat completions and token budgets in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/chatgpt | | Use direct preference optimization for Azure Ope