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**: 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 | Location | Description | |----------|----------|-------------| | Troubleshooting | L37-L79 | Monitoring, debugging, and fixing Foundry agents: logs, traces, evaluations, voice agent data, Agent Insights, sessions, deletions, webhooks, HTTP/auth errors, and recovery from failures. | | Best Practices | L80-L103 | Best practices for building and running Foundry agents: prompts, tools, voice, latency, resiliency, safety, routing, memory, testing, and Azure OpenAI performance/fine-tuning. | | Decision Making | L104-L154 | Guides for choosing models, hosting, billing, networking, and migration paths in Foundry, including agents, Azure Gov, lifecycle/retirement, and cost/throughput planning. | | Architecture & Design Patterns | L155-L165 | Patterns for agent networking, isolation, resilience, human-in-the-loop flows, scalable tool search, network-isolated toolboxes, and programmatic tool calling with the Responses API. | | Limits & Quotas | L166-L198 | Quotas, limits, and rate caps for agents, models, storage, uploads, audio/WS sessions, and regions, plus how to monitor, configure, and optimize token and throughput usage. | | Security | L199-L260 | Securing Foundry agents and models: auth/authorization, identities, RBAC, networks, guardrails, data privacy, trace controls, and Azure/Entra governance for tools and hosted agents. | | Configuration | L261-L357 | Configuring and operating Foundry agents and infrastructure: schemas, networking, security, tools, evaluations, monitoring, model/router settings, and voice/telephony setup. | | Integrations & Coding Patterns | [integrations.md](integrations.md) | Integrating agents, tools, models, and telephony with Foundry: SDK and REST APIs for agent hosting, MCP/tool wiring, external services, evaluations, fine-tuning, and realtime voice/audio/video. | | Deployment | [deployment.md](deployment.md) | Deploying and promoting Foundry agents and models: container/source deployments, CI/CD (azd, GitHub, Azure DevOps), Terraform/Bicep, browser automation, regions, resilience, and evaluations. | ### Troubleshooting | Topic | URL | |-------|-----| | Monitor and trace voice agents in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/voice-agent-observability | | Check hosted agent project health with agent doctor | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-doctor | | Inspect local Foundry agents with Agent Inspector | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-inspector | | Diagnose and fix Microsoft Foundry hosted agent issues | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/debug-hosted-agent | | Monitor and troubleshoot Foundry hosted agent logs with azd | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/monitor-hosted-agent-logs | | Monitor and troubleshoot Foundry Browser automation runs | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation-manage-troubleshoot | | Troubleshoot publishing Foundry agents to Copilot and Teams | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/troubleshoot-publish-copilot | | Resolve authorization errors for Foundry agents in Copilot | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/troubleshoot-publish-copilot-authorization | | Troubleshoot Programmed Training issues in Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/programmed-training/troubleshoot | | Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery | | Debug Foundry agents with Agent Inspector in VS Code | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/vs-code-agent-inspector | | Collect and analyze Foundry agent traces in VS Code | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/vs-code-tracing | | Retrieve and troubleshoot Foundry cloud evaluation results | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/cloud-evaluation-results | | Troubleshoot Foundry evaluation and observability issues | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/troubleshooting | | Troubleshoot HTTP errors for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/troubleshoot-errors | | Set up and troubleshoot Azure OpenAI webhooks | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks | | Resolve known issues and workarounds for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues | | Get audio metadata for voice agent conversation items | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-get-agent-conversation-audio-item | | Retrieve generated audio metadata for interrupted playback | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-get-agent-conversation-generated-audio-item | | Retrieve specific voice agent conversation items via REST | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-get-agent-conversation-item | | Get detailed voice agent conversation response data | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-get-agent-conversation-response | | List output items from a voice agent response | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-list-agent-conversation-response-items | | List model responses in a voice agent conversation | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-endpoint-conversations-list-agent-conversation-responses | | Cancel Agent Insights monitoring runs | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-cancel-run | | Delete Agent Insights monitors and associated data | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-delete | | Get full insight details from an Agent Insights monitor | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-get-insight | | Get details of an Agent Insights run | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-get-run | | List current insights from an Agent Insights monitor | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-list-insights | | List Agent Insights runs for a monitor | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-list-runs | | Reset Agent Insights monitor overview and checkpoints | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-insight-monitors-reset | | Cancel Foundry agent invocations via REST | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-invocations-cancel-agent-invocation | | Retrieve Foundry agent invocations and handle 404s | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-invocations-get-agent-invocation | | Cancel optimization jobs and handle terminal state conflicts | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-optimization-jobs-cancel | | Delete files and directories in agent session sandboxes | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agent-session-files-delete-session-file | | Delete agents with active session conflict handling | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agents-delete-agent | | Delete agent versions with active session handling | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agents-delete-agent-version | | Delete hosted agent sessions and interpret 204 responses | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agents-delete-session | | Stream SSE console logs for hosted agent sessions | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agents-get-session-log-stream | | Stop hosted agent sessions and handle termination responses | https://learn.microsoft.com/en-us/azure/foundry/reference/rest/agents-stop-session | ### 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 | | Apply best practices for Microsoft Foundry voice agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/voice-agent-best-practice | | Reduce Microsoft Foundry hosted agent startup latency | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/optimize-hosted-agent-latency | | Optimize instructions and prompts for Foundry voice agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/optimize-voice-agent-instructions | | Make Foundry hosted agents crash-recoverable | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/recover-long-running-work | | Test Microsoft Foundry hosted agents across levels | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/test-hosted-agent | | Use Browser automation tool safely with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation | | Enable memory snapshots to cut hosted agent cold starts | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-hosted-agent-memory-snapshots | | Optimize Foundry prompt agents using portal wizard | https://learn.microsoft.com/en-us/azure/foundry/agents/quickstarts/quickstart-optimize-prompt-agent | | Use Task Adherence signals for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/guardrails/task-adherence | | Use Foundry Skill prompts for common workflows | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/foundry-skills-scenarios-example-prompts | | Fine-tune MedImageInsight Premium for medical imaging | https://learn.microsoft.com/en-us/azure/foundry/how-to/healthcare-ai/fine-tune-medimageinsight-premium | | Plan high availability and resiliency for Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency | | Design effective system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering | | Use groundedness detection filter for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness | | Understand and optimize Foundry model router behavior | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-router-how-it-works | | Apply safety system message templates in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates | | Apply vision fine-tuning best practices in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision | | Optimize Azure OpenAI latency and throughput in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency | | Operate provisioned throughput deployments in production | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started | ### Decision Making | Topic | URL | |-------|-----| | Choose networking options for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/networking-options | | Understand pricing for Foundry voice agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/voice-agent-pricing | | Plan migration to Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate | | Decide and migrate to new Foundry agent model | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate-agent-applications | | Migrate Voice Live integrations to Foundry voice agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate-from-voice-live | | Choose the right web grounding tool for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview | | Choose the right Microsoft Foundry capability | https://learn.microsoft.com/en-us/azure/foundry/concepts/capabilities | | Use Foundry in Azure Government regions and endpoints | https://learn.microsoft.com/en-us/azure/foundry/concepts/foundry-azure-government | | Plan general availability adoption of Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/general-availability | | Compare Foundry models using benchmarks and leaderboards | https://learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks | | Plan organizational rollout and governance for Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/planning | | Estimate and compare fine-tuning costs in Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/cost-management | | Use Foundry to generate synthetic training data | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation | | Choose fine-tuning options in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/overview | | Decide when to use Programmed Training in Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/programmed-training/overview | | Choose and compare Claude models in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models | | Plan Claude CCU billing for Microsoft Foundry models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models-billing | | Choose Azure vs Anthropic Claude hosting in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models-hosting-comparison | | Choose Foundry model deployment types by scenario | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types | | Select Foundry deployment types in Azure Government | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types-gov | | Plan and execute model migration in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-migration | | Manage model versioning and upgrade policies in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions |