{"id":"1b6b1d67-d126-4bf7-ac34-e79891e286e4","shortId":"AQZj57","kind":"skill","title":"microsoft-foundry","tagline":"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","description":"# Microsoft Foundry Skill\n\nThis 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.\n\n## How to Use This Skill\n\n> **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\n\n> **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)\n\nThis skill requires **network access** to fetch documentation content:\n- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.\n- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.\n\n## Category Index\n\n| Category | Lines | Description |\n|----------|-------|-------------|\n| Troubleshooting | L37-L41 | Known Microsoft Foundry bugs, error codes, limitations, and their workarounds, plus steps to diagnose and resolve common platform and deployment issues. |\n| Best Practices | L42-L53 | Best practices for configuring tools, prompts, system messages, evaluation, fine-tuning (incl. vision), and optimizing performance/latency for Azure OpenAI/Foundry agents |\n| Decision Making | L54-L86 | Guidance on choosing and upgrading Foundry models, tools, and deployments, planning migrations (Azure OpenAI, GitHub Models, Assistants), and optimizing cost, performance, and versioning strategies. |\n| Architecture & Design Patterns | L87-L98 | Architectural patterns for Foundry agents: standard setup, RAG/indexing, HA/DR, regional recovery, provisioned throughput, spillover traffic, and LLM routing optimization. |\n| Limits & Quotas | L99-L112 | Quotas, rate limits, regions, and cost controls for Foundry agents, models, vector stores, evals, batch jobs, prompt caching, Azure OpenAI usage, and limited-access policies. |\n| Security | L113-L145 | Security, privacy, and governance for Foundry: auth/RBAC, keys and encryption, network isolation, guardrails/safety, compliance, and secure use of tools, agents, and model connections |\n| Configuration | L146-L193 | Configuring Foundry agents, models, tools, storage, monitoring, security/guardrails, and Azure OpenAI integrations, including workflows, tracing, evaluations, and external resource setup. |\n| Integrations & Coding Patterns | L194-L261 | Patterns and APIs for integrating Foundry agents and models with tools, gateways, LangChain/LangGraph, Azure OpenAI, search, speech, image, tracing, security, and external services. |\n| Deployment | L262-L278 | Deploying agents and models: infra setup, Bicep/CLI/portal deployment, publishing to M365/Teams/Azure, lifecycle management, CI/CD evaluations, regions, and custom/fine-tuned models. |\n\n### Troubleshooting\n| Topic | URL |\n|-------|-----|\n| Troubleshoot Microsoft Foundry known issues and workarounds | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |\n\n### Best Practices\n| Topic | URL |\n|-------|-----|\n| Apply tool configuration best practices for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice |\n| Evaluate Azure AI agents with task-specific metrics | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators |\n| Evaluate Foundry agents with built-in quality and safety tests | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent |\n| Optimize Foundry agent prompts with Prompt Optimizer | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer |\n| Design effective system messages for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering |\n| Apply prompt engineering techniques for vision-enabled GPT models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering |\n| Fine-tune GPT-4 vision models with images | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision |\n| Optimize Azure OpenAI latency and throughput in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency |\n\n### Decision Making\n| Topic | URL |\n|-------|-----|\n| Migrate from Assistants API to Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate |\n| Use Bing grounding tools with agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools |\n| Choose web grounding tools for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview |\n| Use Foundry model benchmarks and leaderboards for selection | https://learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks |\n| Plan for Foundry model deprecation and retirement | https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement |\n| Plan Microsoft Foundry rollout and environment strategy | https://learn.microsoft.com/en-us/azure/foundry/concepts/planning |\n| Optimize Foundry model cost and performance | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance |\n| Choose Foundry deployment types and data residency options | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types |\n| Choose Foundry deployment types in Azure Government | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types-gov |\n| Manage model versioning and upgrade policies in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions |\n| Decide on model versioning and upgrade policies in Azure Government | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions-gov |\n| Choose Foundry partner and community models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners |\n| Select Azure-sold Foundry Models by capabilities and regions | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure |\n| Select Foundry models sold by Azure in Government | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-gov |\n| Decide between GPT-5 and GPT-4.1 for your use case | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/model-choice-guide |\n| Upgrade workloads from GitHub Models to Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models |\n| Use Foundry model leaderboard to compare and choose models | https://learn.microsoft.com/en-us/azure/foundry/how-to/benchmark-model-in-catalog |\n| Choose integration patterns for Microsoft Foundry APIs | https://learn.microsoft.com/en-us/azure/foundry/how-to/integrate-with-other-apps |\n| Migrate from Azure AI Inference SDK to OpenAI SDK | https://learn.microsoft.com/en-us/azure/foundry/how-to/model-inference-to-openai-migration |\n| Plan migration from classic Foundry portal | https://learn.microsoft.com/en-us/azure/foundry/how-to/navigate-from-classic |\n| Decide and execute upgrade from Azure OpenAI to Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/upgrade-azure-openai |\n| Use Ask AI to upgrade or switch Foundry models | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/optimization-model-upgrade |\n| Choose content streaming and filtering modes in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-streaming |\n| Review retired Azure OpenAI models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models |\n| Manage Azure OpenAI model deprecations in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirements |\n| Enable and choose priority processing for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing |\n| Estimate and manage fine-tuning costs in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management |\n| Plan PTU costs and capacity for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding |\n| Migrate from preview to GA Realtime API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide |\n\n### Architecture & Design Patterns\n| Topic | URL |\n|-------|-----|\n| Design standard agent setup with isolated resources | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup |\n| Apply RAG and indexing patterns in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation |\n| Plan disaster recovery for Foundry Agent Service in standard mode | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery |\n| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery |\n| Recover Foundry Agent Service from regional platform outages | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery |\n| Plan high availability and resiliency for Foundry projects and agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency |\n| Plan provisioned throughput architecture for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput |\n| Design spillover traffic management for provisioned deployments | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management |\n\n### Limits & Quotas\n| Topic | URL |\n|-------|-----|\n| Quotas, limits, and regions for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/limits-quotas-regions |\n| Use vector stores and file search limits in agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/vector-stores |\n| Evaluation rate limits and region support in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network |\n| Configure token rate limits and quotas for models | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-enforce-limits-models |\n| Reference quotas and limits for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/quotas-limits |\n| Use Azure OpenAI global batch processing efficiently | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch |\n| Configure prompt caching and understand cache limits in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching |\n| Use reinforcement fine-tuning with cost limits | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning |\n| Reference Azure OpenAI quotas and limits in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits |\n| Understand limited access policy for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/limited-access |\n\n### Security\n| Topic | URL |\n|-------|-----|\n| Understand and govern agent identities in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-identity |\n| Configure authentication methods for Agent2Agent tools | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication |\n| Configure authentication for MCP servers in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/mcp-authentication |\n| Configure computer use tool securely for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use |\n| Govern MCP tools with an AI gateway in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/governance |\n| Set up private networking for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/virtual-networks |\n| Configure authentication and authorization for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/authentication-authorization-foundry |\n| Configure customer-managed keys for Microsoft Foundry encryption | https://learn.microsoft.com/en-us/azure/foundry/concepts/encryption-keys-portal |\n| Understand and apply RBAC roles in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/rbac-foundry |\n| Govern Foundry agent infrastructure as Entra admin | https://learn.microsoft.com/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin |\n| Manage Foundry compliance and security integrations | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-manage-compliance-security |\n| Create guardrail policies for model deployments | https://learn.microsoft.com/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy |\n| Configure keyless Entra ID authentication for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-entra-id |\n| Add Microsoft Foundry resources to a network security perimeter | https://learn.microsoft.com/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter |\n| Configure Private Link network isolation for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/configure-private-link |\n| Configure and manage Microsoft Foundry connections | https://learn.microsoft.com/en-us/azure/foundry/how-to/connections-add |\n| Create custom Azure Policies to govern Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/custom-policy-definition |\n| Apply Azure AI Content Safety in LangChain agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-middleware |\n| Disable preview features in Microsoft Foundry using tags and RBAC | https://learn.microsoft.com/en-us/azure/foundry/how-to/disable-preview-features |\n| Set up managed virtual networks for Microsoft Foundry projects | https://learn.microsoft.com/en-us/azure/foundry/how-to/managed-virtual-network |\n| Use built-in Azure Policy definitions for Foundry model deployment | https://learn.microsoft.com/en-us/azure/foundry/how-to/model-deployment-policy |\n| Secure Foundry MCP Server with RBAC and policies | https://learn.microsoft.com/en-us/azure/foundry/mcp/security-best-practices |\n| Understand default guardrail safety policies in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies |\n| Use safety system message templates for Azure OpenAI apps | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates |\n| Author safety-focused system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message |\n| Apply safety evaluation to fine-tuned models | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation |\n| Data privacy and security for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/data-privacy-security |\n| Understand data privacy and security for Anthropic Claude in Foundry | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/claude-models/data-privacy |\n| Understand data, privacy, and security for Azure Direct Models | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy |\n\n### Configuration\n| Topic | URL |\n|-------|-----|\n| Configure capability hosts for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/capability-hosts |\n| Manage and disable Grounding with Bing in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing |\n| Configure and manage memory in Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/memory-usage |\n| Configure a private tool catalog with Azure API Center | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/private-tool-catalog |\n| Configure structured inputs for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/structured-inputs |\n| Configure custom MCP-based code interpreter runtime | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter |\n| Configure file search tool for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/file-search |\n| Configure and use web search tool in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search |\n| Configure Foundry Agent Service to use existing Azure resources | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-your-own-resources |\n| Configure declarative agent workflows in VS Code | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code |\n| Create and deploy hosted Foundry agent workflows | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code |\n| Reference for all Foundry built-in evaluators | https://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators |\n| Configure AI Gateway token controls in Foundry | https://learn.microsoft.com/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal |\n| Register custom agents with Foundry Control Plane | https://learn.microsoft.com/en-us/azure/foundry/control-plane/register-custom-agent |\n| Configure synthetic data generation in Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation |\n| Use Foundry Models endpoints and authentication correctly | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/endpoints |\n| Generate text with Foundry Models using the Responses API | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/generate-responses |\n| Configure Azure Monitor for Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/monitor-models |\n| Configure guardrails and controls in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-create-guardrails |\n| Configure bring-your-own storage for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry |\n| Bind customer-managed storage to Foundry Speech and Language | https://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-speech-language-services |\n| Provision Microsoft Foundry resources using Terraform | https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-terraform |\n| Configure cloud-based evaluations with Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation |\n| Enable and use Fireworks models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models |\n| Connect VS Code to Foundry MCP Server | https://learn.microsoft.com/en-us/azure/foundry/mcp/get-started |\n| Configure Foundry Agent Monitoring Dashboard and metrics | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard |\n| Configure tracing for LangChain and other AI agent frameworks | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework |\n| Configure tracing for AI agents in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-setup |\n| Use Azure OpenAI v1 API in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle |\n| Configure Prompt Shields for Foundry model security | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields |\n| Call chat completion models with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt |\n| Generate and edit images with Azure OpenAI image models | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/dall-e |\n| Run deep research with o3-deep-research via Responses API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/deep-research |\n| Generate and use embeddings with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/embeddings |\n| Configure DPO fine-tuning for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization |\n| Configure and use function calling with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling |\n| Call vision-enabled chat models with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision |\n| Enable and tune JSON mode for Azure OpenAI chat completions | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode |\n| Use predicted outputs to reduce Azure OpenAI latency | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs |\n| Create and tune provisioned deployments in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started |\n| Use Azure OpenAI Responses API with tools and streaming | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses |\n| Enforce JSON schema with structured outputs in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs |\n| Work with Azure OpenAI model deployments in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/working-with-models |\n| Monitor Foundry OpenAI with Azure Monitor data | https://learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference |\n\n### Integrations & Coding Patterns\n| Topic | URL |\n|-------|-----|\n| Use agents, conversations, and responses in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/runtime-components |\n| Integrate enterprise AI gateways with Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway |\n| Connect Foundry agents to Foundry IQ knowledge bases | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-connect |\n| Invoke Foundry Agent Applications via Responses API protocol | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-responses |\n| Connect Foundry agents to external A2A endpoints | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/agent-to-agent |\n| Connect Azure AI Search indexes to agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search |\n| Integrate Azure Speech MCP tool with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech |\n| Integrate Azure Functions as tools for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-functions |\n| Use Browser Automation tool with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation |\n| Enable Code Interpreter tool for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/code-interpreter |\n| Connect Microsoft Fabric data agent to Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/fabric |\n| Use function calling tools with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/function-calling |\n| Use image generation tool in Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/image-generation |\n| Connect Foundry agents to MCP servers | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/model-context-protocol |\n| Connect OpenAPI tools to Microsoft Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/openapi |\n| Integrate Foundry agents with SharePoint content | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/sharepoint |\n| Run fine-tuning jobs with azd extension | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/fine-tune-cli |\n| Configure Claude Code CLI and VS Code with Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-claude-code |\n| Integrate FLUX image generation models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-flux |\n| Deploy and call MAI-Image-2 in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-mai |\n| Deploy and call DeepSeek-R1 in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1 |\n| Integrate third-party safety tools with Foundry | https://learn.microsoft.com/en-us/azure/foundry/guardrails/third-party-integrations |\n| Integrate LangChain and LangGraph with Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain |\n| Build LangGraph agents with Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-agents |\n| Add Foundry long-term memory to LangChain apps | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-memory |\n| Use LangChain models with Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-models |\n| Trace LangChain apps with Foundry and Azure Monitor | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-traces |\n| Run AI Red Teaming Agent scans in cloud | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud |\n| Run local AI Red Teaming scans with SDK | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent |\n| Set up an Azure Key Vault connection for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/set-up-key-vault-connection |\n| Use Foundry MCP Server tools and prompts | https://learn.microsoft.com/en-us/azure/foundry/mcp/available-tools |\n| Build and register custom MCP server for Foundry | https://learn.microsoft.com/en-us/azure/foundry/mcp/build-your-own-mcp-server |\n| Add OpenTelemetry client-side tracing to Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-client-side |\n| Call Azure OpenAI audio models via API | https://learn.microsoft.com/en-us/azure/foundry/openai/audio-completions-quickstart |\n| Authoring operations for Foundry OpenAI REST API | https://learn.microsoft.com/en-us/azure/foundry/openai/authoring-reference-preview |\n| Use groundedness detection with Foundry OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness |\n| Integrate Codex CLI and VS Code with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/codex |\n| Fine-tune Foundry models via SDK and REST | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning |\n| Fine-tune tool calling behavior in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions |\n| Call Foundry model router via Chat Completions API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router |\n| Implement GPT Realtime audio with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio |\n| Use GPT Realtime API over SIP | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip |\n| Use GPT Realtime API over WebRTC | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc |\n| Use GPT Realtime API over WebSockets | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-websockets |\n| Call Azure OpenAI reasoning models via Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning |\n| Use web_search tool with Azure OpenAI Responses API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search |\n| Set up and secure Azure OpenAI webhooks in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |\n| Implement realtime audio events for Foundry OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/realtime-audio-reference |\n| Call Azure OpenAI inference REST APIs in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/reference |\n| Use Foundry OpenAI preview inference REST API | https://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview |\n| Call Foundry OpenAI v1 preview REST endpoints | https://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview-latest |\n| Build document search with Azure OpenAI embeddings API | https://learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings |\n| Use Azure OpenAI Whisper for speech to text | https://learn.microsoft.com/en-us/azure/foundry/openai/whisper-quickstart |\n| Call Microsoft Foundry REST APIs for projects | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project |\n| Use Microsoft Foundry Project REST API (preview) | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project-rest-preview |\n\n### Deployment\n| Topic | URL |\n|-------|-----|\n| Set up infrastructure for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/environment-setup |\n| Deploy Foundry agents as digital workers in Agent 365 | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-365 |\n| Deploy custom hosted agents to Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent |\n| Manage lifecycle of hosted agent deployments | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent |\n| Publish Foundry agents as managed Azure resources | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-agent |\n| Publish Foundry agents to Microsoft 365 Copilot and Teams | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-copilot |\n| Deploy Foundry Models using Azure CLI and Bicep templates | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments |\n| Deploy Foundry Models via Foundry portal for inference | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models |\n| Deploy Microsoft Foundry resources using Bicep templates | https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-template |\n| Run Foundry evaluations in Azure DevOps pipelines | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops |\n| Run Foundry evaluations in GitHub Actions CI | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action |\n| Import and deploy custom Fireworks models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models |\n| Deploy fine-tuned models on Foundry hosting | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy |\n| Check Microsoft Foundry feature availability by region | https://learn.microsoft.com/en-us/azure/foundry/reference/region-support |","tags":["microsoft","foundry","agent","skills","microsoftdocs","agent-skills","agentic-skills","agentskill","ai-agents","ai-coding","azure","azure-functions"],"capabilities":["skill","source-microsoftdocs","skill-microsoft-foundry","topic-agent","topic-agent-skills","topic-agentic-skills","topic-agentskill","topic-ai-agents","topic-ai-coding","topic-azure","topic-azure-functions","topic-azure-kubernetes-service","topic-azure-openai","topic-azure-sql-database","topic-azure-storage"],"categories":["Agent-Skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/MicrosoftDocs/Agent-Skills/microsoft-foundry","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add MicrosoftDocs/Agent-Skills","source_repo":"https://github.com/MicrosoftDocs/Agent-Skills","install_from":"skills.sh"}},"qualityScore":"0.698","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 497 github stars · SKILL.md body (32,851 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:53:40.185Z","embedding":null,"createdAt":"2026-04-18T22:00:33.974Z","updatedAt":"2026-04-22T00:53:40.185Z","lastSeenAt":"2026-04-22T00:53:40.185Z","tsv":"'-4':543 '-4.1':720 '-5':717 '/en-us/azure/foundry/agents/concepts/agent-identity':1101 '/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication':1110 '/en-us/azure/foundry/agents/concepts/capability-hosts':1423 '/en-us/azure/foundry/agents/concepts/limits-quotas-regions':989 '/en-us/azure/foundry/agents/concepts/runtime-components':1910 '/en-us/azure/foundry/agents/concepts/standard-agent-setup':895 '/en-us/azure/foundry/agents/concepts/tool-best-practice':477 '/en-us/azure/foundry/agents/concepts/vector-stores':1001 '/en-us/azure/foundry/agents/environment-setup':2601 '/en-us/azure/foundry/agents/how-to/agent-365':2613 '/en-us/azure/foundry/agents/how-to/ai-gateway':1921 '/en-us/azure/foundry/agents/how-to/deploy-hosted-agent':2624 '/en-us/azure/foundry/agents/how-to/foundry-iq-connect':1932 '/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing':1434 '/en-us/azure/foundry/agents/how-to/manage-hosted-agent':2633 '/en-us/azure/foundry/agents/how-to/mcp-authentication':1120 '/en-us/azure/foundry/agents/how-to/memory-usage':1444 '/en-us/azure/foundry/agents/how-to/migrate':576 '/en-us/azure/foundry/agents/how-to/private-tool-catalog':1456 '/en-us/azure/foundry/agents/how-to/publish-agent':2643 '/en-us/azure/foundry/agents/how-to/publish-copilot':2655 '/en-us/azure/foundry/agents/how-to/publish-responses':1943 '/en-us/azure/foundry/agents/how-to/structured-inputs':1465 '/en-us/azure/foundry/agents/how-to/tools/agent-to-agent':1953 '/en-us/azure/foundry/agents/how-to/tools/ai-search':1963 '/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech':1974 '/en-us/azure/foundry/agents/how-to/tools/azure-functions':1984 '/en-us/azure/foundry/agents/how-to/tools/bing-tools':585 '/en-us/azure/foundry/agents/how-to/tools/browser-automation':1994 '/en-us/azure/foundry/agents/how-to/tools/code-interpreter':2003 '/en-us/azure/foundry/agents/how-to/tools/computer-use':1130 '/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter':1476 '/en-us/azure/foundry/agents/how-to/tools/fabric':2013 '/en-us/azure/foundry/agents/how-to/tools/file-search':1486 '/en-us/azure/foundry/agents/how-to/tools/function-calling':2023 '/en-us/azure/foundry/agents/how-to/tools/governance':1142 '/en-us/azure/foundry/agents/how-to/tools/image-generation':2034 '/en-us/azure/foundry/agents/how-to/tools/model-context-protocol':2043 '/en-us/azure/foundry/agents/how-to/tools/openapi':2053 '/en-us/azure/foundry/agents/how-to/tools/sharepoint':2062 '/en-us/azure/foundry/agents/how-to/tools/web-overview':595 '/en-us/azure/foundry/agents/how-to/tools/web-search':1497 '/en-us/azure/foundry/agents/how-to/use-your-own-resources':1509 '/en-us/azure/foundry/agents/how-to/virtual-networks':1153 '/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code':1519 '/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code':1529 '/en-us/azure/foundry/concepts/authentication-authorization-foundry':1163 '/en-us/azure/foundry/concepts/built-in-evaluators':1540 '/en-us/azure/foundry/concepts/encryption-keys-portal':1175 '/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators':489 '/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network':1012 '/en-us/azure/foundry/concepts/model-benchmarks':606 '/en-us/azure/foundry/concepts/model-lifecycle-retirement':616 '/en-us/azure/foundry/concepts/planning':626 '/en-us/azure/foundry/concepts/rbac-foundry':1186 '/en-us/azure/foundry/concepts/retrieval-augmented-generation':905 '/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal':1550 '/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin':1196 '/en-us/azure/foundry/control-plane/how-to-enforce-limits-models':1023 '/en-us/azure/foundry/control-plane/how-to-manage-compliance-security':1205 '/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance':635 '/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy':1214 '/en-us/azure/foundry/control-plane/register-custom-agent':1560 '/en-us/azure/foundry/fine-tuning/data-generation':1569 '/en-us/azure/foundry/fine-tuning/fine-tune-cli':2073 '/en-us/azure/foundry/foundry-models/concepts/deployment-types':646 '/en-us/azure/foundry/foundry-models/concepts/deployment-types-gov':656 '/en-us/azure/foundry/foundry-models/concepts/endpoints':1579 '/en-us/azure/foundry/foundry-models/concepts/model-versions':667 '/en-us/azure/foundry/foundry-models/concepts/model-versions-gov':680 '/en-us/azure/foundry/foundry-models/concepts/models-from-partners':689 '/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure':702 '/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-gov':713 '/en-us/azure/foundry/foundry-models/how-to/configure-claude-code':2085 '/en-us/azure/foundry/foundry-models/how-to/configure-entra-id':1225 '/en-us/azure/foundry/foundry-models/how-to/create-model-deployments':2667 '/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models':2678 '/en-us/azure/foundry/foundry-models/how-to/generate-responses':1591 '/en-us/azure/foundry/foundry-models/how-to/model-choice-guide':727 '/en-us/azure/foundry/foundry-models/how-to/monitor-models':1601 '/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models':738 '/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-flux':2095 '/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-mai':2108 '/en-us/azure/foundry/foundry-models/quotas-limits':1033 '/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1':2120 '/en-us/azure/foundry/guardrails/how-to-create-guardrails':1611 '/en-us/azure/foundry/guardrails/third-party-integrations':2131 '/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter':1237 '/en-us/azure/foundry/how-to/agent-service-disaster-recovery':918 '/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery':930 '/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery':941 '/en-us/azure/foundry/how-to/benchmark-model-in-catalog':750 '/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry':1623 '/en-us/azure/foundry/how-to/bring-your-own-azure-storage-speech-language-services':1636 '/en-us/azure/foundry/how-to/configure-private-link':1248 '/en-us/azure/foundry/how-to/connections-add':1257 '/en-us/azure/foundry/how-to/create-resource-template':2688 '/en-us/azure/foundry/how-to/create-resource-terraform':1645 '/en-us/azure/foundry/how-to/custom-policy-definition':1268 '/en-us/azure/foundry/how-to/develop/cloud-evaluation':1656 '/en-us/azure/foundry/how-to/develop/langchain':2140 '/en-us/azure/foundry/how-to/develop/langchain-agents':2150 '/en-us/azure/foundry/how-to/develop/langchain-memory':2162 '/en-us/azure/foundry/how-to/develop/langchain-middleware':1279 '/en-us/azure/foundry/how-to/develop/langchain-models':2171 '/en-us/azure/foundry/how-to/develop/langchain-traces':2182 '/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud':2193 '/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent':2204 '/en-us/azure/foundry/how-to/disable-preview-features':1292 '/en-us/azure/foundry/how-to/evaluation-azure-devops':2698 '/en-us/azure/foundry/how-to/evaluation-github-action':2708 '/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models':1666 '/en-us/azure/foundry/how-to/fireworks/import-custom-models':2719 '/en-us/azure/foundry/how-to/high-availability-resiliency':954 '/en-us/azure/foundry/how-to/integrate-with-other-apps':760 '/en-us/azure/foundry/how-to/managed-virtual-network':1304 '/en-us/azure/foundry/how-to/model-deployment-policy':1318 '/en-us/azure/foundry/how-to/model-inference-to-openai-migration':772 '/en-us/azure/foundry/how-to/navigate-from-classic':781 '/en-us/azure/foundry/how-to/set-up-key-vault-connection':2217 '/en-us/azure/foundry/how-to/upgrade-azure-openai':793 '/en-us/azure/foundry/mcp/available-tools':2227 '/en-us/azure/foundry/mcp/build-your-own-mcp-server':2238 '/en-us/azure/foundry/mcp/get-started':1676 '/en-us/azure/foundry/mcp/security-best-practices':1329 '/en-us/azure/foundry/observability/how-to/evaluate-agent':503 '/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard':1686 '/en-us/azure/foundry/observability/how-to/optimization-model-upgrade':805 '/en-us/azure/foundry/observability/how-to/prompt-optimizer':513 '/en-us/azure/foundry/observability/how-to/trace-agent-client-side':2250 '/en-us/azure/foundry/observability/how-to/trace-agent-framework':1698 '/en-us/azure/foundry/observability/how-to/trace-agent-setup':1709 '/en-us/azure/foundry/openai/api-version-lifecycle':1720 '/en-us/azure/foundry/openai/audio-completions-quickstart':2260 '/en-us/azure/foundry/openai/authoring-reference-preview':2270 '/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering':525 '/en-us/azure/foundry/openai/concepts/content-filter-groundedness':2279 '/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields':1730 '/en-us/azure/foundry/openai/concepts/content-streaming':816 '/en-us/azure/foundry/openai/concepts/default-safety-policies':1339 '/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering':538 '/en-us/azure/foundry/openai/concepts/legacy-models':826 '/en-us/azure/foundry/openai/concepts/model-retirements':836 '/en-us/azure/foundry/openai/concepts/priority-processing':847 '/en-us/azure/foundry/openai/concepts/provisioned-throughput':964 '/en-us/azure/foundry/openai/concepts/safety-system-message-templates':1351 '/en-us/azure/foundry/openai/concepts/system-message':1363 '/en-us/azure/foundry/openai/how-to/batch':1043 '/en-us/azure/foundry/openai/how-to/chatgpt':1742 '/en-us/azure/foundry/openai/how-to/codex':2291 '/en-us/azure/foundry/openai/how-to/dall-e':1754 '/en-us/azure/foundry/openai/how-to/deep-research':1768 '/en-us/azure/foundry/openai/how-to/embeddings':1780 '/en-us/azure/foundry/openai/how-to/fine-tuning':2303 '/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management':859 '/en-us/azure/foundry/openai/how-to/fine-tuning-deploy':2730 '/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization':1791 '/en-us/azure/foundry/openai/how-to/fine-tuning-functions':2315 '/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation':1374 '/en-us/azure/foundry/openai/how-to/fine-tuning-vision':550 '/en-us/azure/foundry/openai/how-to/function-calling':1802 '/en-us/azure/foundry/openai/how-to/gpt-with-vision':1816 '/en-us/azure/foundry/openai/how-to/json-mode':1829 '/en-us/azure/foundry/openai/how-to/latency':561 '/en-us/azure/foundry/openai/how-to/model-router':2326 '/en-us/azure/foundry/openai/how-to/predicted-outputs':1840 '/en-us/azure/foundry/openai/how-to/prompt-caching':1056 '/en-us/azure/foundry/openai/how-to/provisioned-get-started':1850 '/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding':870 '/en-us/azure/foundry/openai/how-to/realtime-audio':2336 '/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide':880 '/en-us/azure/foundry/openai/how-to/realtime-audio-sip':2345 '/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc':2354 '/en-us/azure/foundry/openai/how-to/realtime-audio-websockets':2363 '/en-us/azure/foundry/openai/how-to/reasoning':2373 '/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning':1067 '/en-us/azure/foundry/openai/how-to/responses':1862 '/en-us/azure/foundry/openai/how-to/spillover-traffic-management':974 '/en-us/azure/foundry/openai/how-to/structured-outputs':1874 '/en-us/azure/foundry/openai/how-to/web-search':2385 '/en-us/azure/foundry/openai/how-to/webhooks':2397 '/en-us/azure/foundry/openai/how-to/working-with-models':1885 '/en-us/azure/foundry/openai/latest':2409,2421,2433,2445,2457,2469,2481,2493,2505 '/en-us/azure/foundry/openai/monitor-openai-reference':1895 '/en-us/azure/foundry/openai/quotas-limits':1078 '/en-us/azure/foundry/openai/realtime-audio-reference':2515 '/en-us/azure/foundry/openai/reference':2526 '/en-us/azure/foundry/openai/reference-preview':2536 '/en-us/azure/foundry/openai/reference-preview-latest':2546 '/en-us/azure/foundry/openai/tutorials/embeddings':2557 '/en-us/azure/foundry/openai/whisper-quickstart':2568 '/en-us/azure/foundry/reference/foundry-known-issues':463 '/en-us/azure/foundry/reference/foundry-project':2578 '/en-us/azure/foundry/reference/foundry-project-rest-preview':2588 '/en-us/azure/foundry/reference/region-support':2740 '/en-us/azure/foundry/responsible-ai/agents/data-privacy-security':1385 '/en-us/azure/foundry/responsible-ai/claude-models/data-privacy':1398 '/en-us/azure/foundry/responsible-ai/openai/data-privacy':1410 '/en-us/azure/foundry/responsible-ai/openai/limited-access':1088 '/microsoftdocs/mcp/blob/main/readme.md)':164 '2':2102 '3':135 '365':2610,2649 'a2a':1949 'accept':203 'access':169,346,1081 'action':2704 'add':1226,2151,2239 'admin':1193 'agent':84,128,187,201,262,302,331,371,381,411,433,474,481,492,506,572,582,592,888,911,921,933,951,985,998,1095,1127,1149,1189,1276,1381,1419,1441,1462,1483,1500,1512,1525,1553,1679,1694,1703,1902,1917,1924,1935,1946,1960,1971,1981,1991,2000,2008,2020,2030,2037,2050,2056,2143,2146,2187,2247,2597,2604,2609,2617,2620,2629,2636,2646 'agent2agent':1106 'ai':11,480,764,796,1136,1271,1542,1693,1702,1913,1956,2184,2196 'aka':9 'anthrop':1392 'api':407,569,757,877,1452,1588,1714,1765,1855,1939,2257,2267,2323,2340,2349,2358,2382,2404,2416,2428,2440,2452,2464,2476,2488,2500,2521,2533,2554,2573,2584 'app':1348,2159,2174 'appli':468,526,896,1178,1269,1364 'applic':1936 'architectur':20,53,292,298,881,958 'ask':795 'assist':284,568 'audio':2254,2330,2508 'auth/rbac':358 'authent':1103,1112,1155,1219,1575 'author':1157,1352,2261 'autom':1987 'avail':154,944,2735 'azd':2069 'azur':10,260,280,340,388,418,479,519,552,652,676,692,708,763,787,819,828,1035,1052,1069,1084,1260,1270,1309,1346,1359,1405,1451,1505,1593,1711,1736,1748,1774,1787,1798,1810,1823,1835,1852,1870,1877,1890,1955,1965,1976,2178,2208,2252,2287,2311,2332,2365,2379,2390,2400,2412,2424,2436,2448,2460,2472,2484,2496,2517,2551,2559,2639,2660,2693 'azure-sold':691 'base':1470,1649,1929 'batch':336,1038 'behavior':2309 'benchmark':599 'best':16,49,237,242,464,471 'bicep':2663,2684 'bicep/cli/portal':438 'bind':1624 'bing':578,1429 'bring':1614 'bring-your-own':1613 'browser':1986 'bug':219 'build':34,2141,2228,2547 'built':495,1307,1535 'built-in':494,1306,1534 'cach':339,1046,1049 'call':1731,1796,1803,2016,2098,2111,2251,2308,2316,2364,2516,2537,2569 'capabl':76,697,1415 'capac':864 'case':724 'catalog':1449 'categori':87,95,111,207,209 'center':1453 'chat':1732,1807,1825,2321 'check':2731 'choos':270,586,636,647,681,746,751,806,839 'ci':2705 'ci/cd':445 'classic':776 'claud':1393,2075 'cli':2077,2282,2661 'client':2242 'client-sid':2241 'cloud':1648,2190 'cloud-bas':1647 'code':28,61,221,400,1471,1516,1669,1897,1996,2076,2080,2285 'codex':2281 'combin':66 'common':232 'communiti':685 'compar':744 'complet':1733,1826,2322 'complianc':365,1199 'comput':1122 'configur':26,59,245,375,379,470,1013,1044,1102,1111,1121,1154,1164,1215,1238,1249,1411,1414,1435,1445,1457,1466,1477,1487,1498,1510,1541,1561,1592,1602,1612,1646,1677,1687,1699,1721,1781,1792,2074 'connect':374,1254,1667,1922,1944,1954,2004,2035,2044,2211 'content':71,173,807,1272,2059 'control':328,1545,1556,1605 'convers':1903 'copilot':2650 'correct':1576 'cost':287,327,630,854,862,1063 'cover':47 'creat':1206,1258,1520,1841 'custom':1166,1259,1467,1552,1626,2231,2615,2712 'custom/fine-tuned':449 'customer-manag':1165,1625 'dashboard':1681 'data':641,926,1375,1387,1400,1563,1892,2007 'decid':668,714,782 'decis':18,51,263,562 'declar':1511 'deep':1756,1761 'deepseek':2113 'deepseek-r1':2112 'default':1331 'definit':1311 'deploy':31,64,235,277,428,432,439,638,649,971,1211,1315,1522,1598,1845,1880,2096,2109,2589,2602,2614,2630,2656,2668,2679,2711,2720 'deprec':611,831 'descript':211 'design':21,54,293,514,882,886,965 'detect':2273 'develop':13 'devop':2694 'diagnos':229 'digit':2606 'direct':1406 'disabl':1280,1426 'disast':907 'doc':179 'document':74,172,2548 'dpo':1782 'e.g':99,115 'edit':1745 'effect':515 'effici':1040 'embed':1772,2553 'enabl':533,837,1657,1806,1817,1995 'encrypt':361,1172 'endpoint':1573,1950,2543 'enforc':1863 'engin':528 'enterpris':1912 'entra':1192,1217 'environ':622 'error':220 'estim':848 'eval':335 'evalu':250,394,446,478,490,1002,1366,1537,1650,2691,2701 'event':2509 'execut':784 'exist':1504 'expert':4,42 'extens':2070 'extern':396,426,1948 'fabric':2006 'fallback':191 'featur':1282,2734 'fetch':75,171,180,193 'file':105,113,120,125,994,1478 'filter':810 'fine':252,540,852,1060,1369,1784,2065,2293,2305,2722 'fine-tun':251,539,851,1059,1368,1783,2064,2292,2304,2721 'firework':1660,2713 'flux':2087 'focus':1355 'foundr':35 'foundri':3,8,12,37,46,218,273,301,330,357,380,410,456,491,505,522,558,571,591,597,609,619,628,637,648,664,682,694,704,734,740,756,777,790,801,813,823,833,843,856,866,902,910,920,932,948,960,984,1009,1029,1075,1098,1117,1139,1148,1160,1171,1183,1188,1198,1221,1228,1245,1253,1265,1285,1300,1313,1320,1336,1380,1395,1418,1431,1440,1461,1482,1494,1499,1524,1533,1547,1555,1566,1571,1583,1596,1608,1620,1630,1639,1652,1663,1671,1678,1706,1716,1725,1739,1777,1813,1847,1882,1887,1907,1916,1923,1926,1934,1945,1970,1990,2010,2019,2029,2036,2049,2055,2082,2092,2105,2116,2128,2137,2145,2152,2168,2176,2214,2219,2235,2246,2264,2275,2295,2317,2370,2394,2406,2418,2430,2442,2454,2466,2478,2490,2502,2511,2523,2528,2538,2571,2581,2596,2603,2619,2635,2645,2657,2669,2672,2681,2690,2700,2716,2726,2733 'framework':1695 'function':1795,1977,2015 'ga':875 'gateway':416,1137,1543,1914 'generat':1564,1580,1743,1769,2026,2089 'github':282,731,2703 'github.com':163 'github.com/microsoftdocs/mcp/blob/main/readme.md)':162 'global':1037 'govern':355,653,677,710,1094,1131,1187,1263 'gpt':534,542,716,719,2328,2338,2347,2356 'ground':579,588,1427 'grounded':2272 'guardrail':1207,1332,1603 'guardrails/safety':364 'guid':161 'guidanc':43,268 'ha/dr':306 'high':943 'host':1416,1523,2616,2628,2727 'id':1218 'ident':1096 'imag':422,547,1746,1750,2025,2088,2101 'implement':2327,2506 'import':82,126,2709 'incl':254 'includ':14,391 'index':88,208,899,1958 'infer':765,2519,2531,2675 'infra':436 'infrastructur':1190,2594 'input':1459 'instal':158,160 'integr':27,60,390,399,409,752,1202,1896,1911,1964,1975,2054,2086,2121,2132,2280,2398,2410,2422,2434,2446,2458,2470,2482,2494 'interpret':1472,1997 'invok':1933 'iq':1927 'isol':363,891,1242 'issu':236,458 'job':337,2067 'json':1820,1864 'key':359,1168,2209 'keyless':1216 'knowledg':5,1928 'known':216,457 'l112':321 'l113':350 'l113-l145':349 'l120':102 'l145':351 'l146':377 'l146-l193':376 'l193':378 'l194':403 'l194-l261':402 'l261':404 'l262':430 'l262-l278':429 'l278':431 'l35':101 'l35-l120':100 'l37':214 'l37-l41':213 'l41':215 'l42':240 'l42-l53':239 'l53':241 'l54':266 'l54-l86':265 'l86':267 'l87':296 'l87-l98':295 'l98':297 'l99':320 'l99-l112':319 'langchain':1275,1690,2133,2158,2164,2173 'langchain/langgraph':417 'langgraph':2135,2142 'languag':1633 'latenc':554,1837 'latest':143 'leaderboard':601,742 'learn':186,200 'learn-agent-skil':185,199 'learn.microsoft.com':462,476,488,502,512,524,537,549,560,575,584,594,605,615,625,634,645,655,666,679,688,701,712,726,737,749,759,771,780,792,804,815,825,835,846,858,869,879,894,904,917,929,940,953,963,973,988,1000,1011,1022,1032,1042,1055,1066,1077,1087,1100,1109,1119,1129,1141,1152,1162,1174,1185,1195,1204,1213,1224,1236,1247,1256,1267,1278,1291,1303,1317,1328,1338,1350,1362,1373,1384,1397,1409,1422,1433,1443,1455,1464,1475,1485,1496,1508,1518,1528,1539,1549,1559,1568,1578,1590,1600,1610,1622,1635,1644,1655,1665,1675,1685,1697,1708,1719,1729,1741,1753,1767,1779,1790,1801,1815,1828,1839,1849,1861,1873,1884,1894,1909,1920,1931,1942,1952,1962,1973,1983,1993,2002,2012,2022,2033,2042,2052,2061,2072,2084,2094,2107,2119,2130,2139,2149,2161,2170,2181,2192,2203,2216,2226,2237,2249,2259,2269,2278,2290,2302,2314,2325,2335,2344,2353,2362,2372,2384,2396,2408,2420,2432,2444,2456,2468,2480,2492,2504,2514,2525,2535,2545,2556,2567,2577,2587,2600,2612,2623,2632,2642,2654,2666,2677,2687,2697,2707,2718,2729,2739 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-identity':1099 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication':1108 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/capability-hosts':1421 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/limits-quotas-regions':987 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/runtime-components':1908 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup':893 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice':475 'learn.microsoft.com/en-us/azure/foundry/agents/concepts/vector-stores':999 'learn.microsoft.com/en-us/azure/foundry/agents/environment-setup':2599 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-365':2611 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway':1919 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent':2622 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-connect':1930 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing':1432 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent':2631 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/mcp-authentication':1118 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/memory-usage':1442 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate':574 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/private-tool-catalog':1454 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-agent':2641 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-copilot':2653 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-responses':1941 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/structured-inputs':1463 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/agent-to-agent':1951 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search':1961 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech':1972 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-functions':1982 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools':583 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation':1992 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/code-interpreter':2001 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use':1128 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter':1474 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/fabric':2011 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/file-search':1484 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/function-calling':2021 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/governance':1140 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/image-generation':2032 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/model-context-protocol':2041 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/openapi':2051 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/sharepoint':2060 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview':593 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search':1495 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-your-own-resources':1507 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/virtual-networks':1151 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code':1517 'learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code':1527 'learn.microsoft.com/en-us/azure/foundry/concepts/authentication-authorization-foundry':1161 'learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators':1538 'learn.microsoft.com/en-us/azure/foundry/concepts/encryption-keys-portal':1173 'learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators':487 'learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network':1010 'learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks':604 'learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement':614 'learn.microsoft.com/en-us/azure/foundry/concepts/planning':624 'learn.microsoft.com/en-us/azure/foundry/concepts/rbac-foundry':1184 'learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation':903 'learn.microsoft.com/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal':1548 'learn.microsoft.com/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin':1194 'learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-enforce-limits-models':1021 'learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-manage-compliance-security':1203 'learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance':633 'learn.microsoft.com/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy':1212 'learn.microsoft.com/en-us/azure/foundry/control-plane/register-custom-agent':1558 'learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation':1567 'learn.microsoft.com/en-us/azure/foundry/fine-tuning/fine-tune-cli':2071 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types':644 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types-gov':654 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/endpoints':1577 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions':665 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions-gov':678 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners':687 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure':700 'learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-gov':711 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-claude-code':2083 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-entra-id':1223 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments':2665 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models':2676 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/generate-responses':1589 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/model-choice-guide':725 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/monitor-models':1599 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models':736 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-flux':2093 'learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-mai':2106 'learn.microsoft.com/en-us/azure/foundry/foundry-models/quotas-limits':1031 'learn.microsoft.com/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1':2118 'learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-create-guardrails':1609 'learn.microsoft.com/en-us/azure/foundry/guardrails/third-party-integrations':2129 'learn.microsoft.com/en-us/azure/foundry/how-to/add-foundry-to-network-security-perimeter':1235 'learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery':916 'learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery':928 'learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery':939 'learn.microsoft.com/en-us/azure/foundry/how-to/benchmark-model-in-catalog':748 'learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry':1621 'learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-speech-language-services':1634 'learn.microsoft.com/en-us/azure/foundry/how-to/configure-private-link':1246 'learn.microsoft.com/en-us/azure/foundry/how-to/connections-add':1255 'learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-template':2686 'learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-terraform':1643 'learn.microsoft.com/en-us/azure/foundry/how-to/custom-policy-definition':1266 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation':1654 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain':2138 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-agents':2148 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-memory':2160 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-middleware':1277 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-models':2169 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-traces':2180 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud':2191 'learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-scans-ai-red-teaming-agent':2202 'learn.microsoft.com/en-us/azure/foundry/how-to/disable-preview-features':1290 'learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops':2696 'learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action':2706 'learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models':1664 'learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models':2717 'learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency':952 'learn.microsoft.com/en-us/azure/foundry/how-to/integrate-with-other-apps':758 'learn.microsoft.com/en-us/azure/foundry/how-to/managed-virtual-network':1302 'learn.microsoft.com/en-us/azure/foundry/how-to/model-deployment-policy':1316 'learn.microsoft.com/en-us/azure/foundry/how-to/model-inference-to-openai-migration':770 'learn.microsoft.com/en-us/azure/foundry/how-to/navigate-from-classic':779 'learn.microsoft.com/en-us/azure/foundry/how-to/set-up-key-vault-connection':2215 'learn.microsoft.com/en-us/azure/foundry/how-to/upgrade-azure-openai':791 'learn.microsoft.com/en-us/azure/foundry/mcp/available-tools':2225 'learn.microsoft.com/en-us/azure/foundry/mcp/build-your-own-mcp-server':2236 'learn.microsoft.com/en-us/azure/foundry/mcp/get-started':1674 'learn.microsoft.com/en-us/azure/foundry/mcp/security-best-practices':1327 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent':501 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard':1684 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/optimization-model-upgrade':803 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer':511 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-client-side':2248 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework':1696 'learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-setup':1707 'learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle':1718 'learn.microsoft.com/en-us/azure/foundry/openai/audio-completions-quickstart':2258 'learn.microsoft.com/en-us/azure/foundry/openai/authoring-reference-preview':2268 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering':523 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness':2277 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields':1728 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-streaming':814 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies':1337 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering':536 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models':824 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirements':834 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing':845 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput':962 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates':1349 'learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message':1361 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch':1041 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt':1740 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/codex':2289 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/dall-e':1752 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/deep-research':1766 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/embeddings':1778 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning':2301 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management':857 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy':2728 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization':1789 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions':2313 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation':1372 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-vision':548 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling':1800 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision':1814 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode':1827 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/latency':559 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router':2324 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs':1838 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching':1054 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started':1848 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding':868 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio':2334 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide':878 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip':2343 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc':2352 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-websockets':2361 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning':2371 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning':1065 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses':1860 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management':972 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs':1872 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search':2383 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks':2395 'learn.microsoft.com/en-us/azure/foundry/openai/how-to/working-with-models':1883 'learn.microsoft.com/en-us/azure/foundry/openai/latest':2407,2419,2431,2443,2455,2467,2479,2491,2503 'learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference':1893 'learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits':1076 'learn.microsoft.com/en-us/azure/foundry/openai/realtime-audio-reference':2513 'learn.microsoft.com/en-us/azure/foundry/openai/reference':2524 'learn.microsoft.com/en-us/azure/foundry/openai/reference-preview':2534 'learn.microsoft.com/en-us/azure/foundry/openai/reference-preview-latest':2544 'learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings':2555 'learn.microsoft.com/en-us/azure/foundry/openai/whisper-quickstart':2566 'learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues':461 'learn.microsoft.com/en-us/azure/foundry/reference/foundry-project':2576 'learn.microsoft.com/en-us/azure/foundry/reference/foundry-project-rest-preview':2586 'learn.microsoft.com/en-us/azure/foundry/reference/region-support':2738 'learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/data-privacy-security':1383 'learn.microsoft.com/en-us/azure/foundry/responsible-ai/claude-models/data-privacy':1396 'learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy':1408 'learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/limited-access':1086 'lifecycl':443,2626 'limit':23,56,222,317,324,345,975,980,996,1004,1016,1027,1050,1064,1073,1080 'limited-access':344 'line':97,109,210 'link':114,123,1240 'llm':314 'local':67,2195 'locat':91 'long':2154 'long-term':2153 'loss':927 'm365/teams/azure':442 'mai':2100 'mai-imag':2099 'make':19,52,264,563 'manag':444,657,827,850,968,1167,1197,1251,1295,1424,1437,1627,2625,2638 'markdown':190,206 'mcp':149,176,1114,1132,1321,1469,1672,1967,2039,2220,2232 'mcp-base':1468 'memori':1438,2156 'messag':249,517,1343,1357 'metadata.generated':130 'method':1104 'metric':486,1683 'microsoft':2,7,36,45,178,217,455,618,755,1159,1170,1182,1227,1244,1252,1264,1284,1299,1607,1619,1638,1705,2005,2048,2104,2167,2213,2570,2580,2648,2680,2732 'microsoft-foundri':1 'microsoftdoc':150,177 'migrat':279,566,761,774,871 'mode':811,915,1821 'model':274,283,332,373,382,413,435,450,535,545,598,610,629,658,670,686,695,705,732,735,741,747,802,821,830,844,867,961,1020,1030,1210,1222,1314,1371,1407,1572,1584,1597,1661,1717,1726,1734,1751,1808,1879,2090,2117,2165,2255,2296,2318,2368,2658,2670,2714,2724 'monitor':385,1594,1680,1886,1891,2179 'month':136 'network':168,362,1146,1232,1241,1297 'o3':1760 'o3-deep-research':1759 'old':137 'openai':281,341,389,419,520,553,768,788,820,829,1036,1053,1070,1085,1347,1360,1712,1737,1749,1775,1788,1799,1811,1824,1836,1853,1871,1878,1888,2253,2265,2276,2288,2312,2333,2366,2380,2391,2401,2413,2425,2437,2449,2461,2473,2485,2497,2512,2518,2529,2539,2552,2560 'openai/foundry':261 'openapi':2045 'opentelemetri':2240 'oper':2262 'optim':257,286,316,504,510,551,627 'option':643 'outag':938 'output':1832,1868 'parti':2124 'partner':683 'pattern':22,29,55,62,294,299,401,405,753,883,900,1898 'perform':288,632 'performance/latency':258 'perimet':1234 'pipelin':2695 'plan':278,607,617,773,860,906,942,955 'plane':1557 'platform':233,937 'plus':226 'polici':347,662,674,1082,1208,1261,1310,1326,1334 'portal':778,2673 'practic':17,50,238,243,465,472 'predict':1831 'prefer':174 'preview':873,1281,2530,2541,2585 'prioriti':840 'privaci':353,1376,1388,1401 'privat':1145,1239,1447 'process':841,1039 'project':949,1301,2575,2582 'prompt':247,338,507,509,527,1045,1722,2224 'protocol':1940 'provid':41 'provis':309,956,970,1637,1844 'ptu':861 'publish':440,2634,2644 'pull':141 'qualiti':497 'queri':182,196 'quick':69 'quick-refer':68 'quota':24,57,318,322,976,979,1018,1025,1071 'r1':2114 'rag':897 'rag/indexing':305 'rang':98 'rate':323,1003,1015 'rbac':1179,1289,1324 'read':104,119 'realtim':876,2329,2339,2348,2357,2507 'reason':2367 'recov':919,931 'recoveri':308,908 'red':2185,2197 'reduc':1834 'refer':70,124,1024,1068,1530 'region':307,325,447,699,936,982,1006,2737 'regist':1551,2230 'reinforc':1058 'relev':92 'remot':73 'repositori':147 'requir':167 'research':1757,1762 'resid':642 'resili':946 'resolv':231 'resourc':397,892,924,1229,1506,1640,2640,2682 'respons':1587,1764,1854,1905,1938,2381 'rest':2266,2300,2403,2415,2427,2439,2451,2463,2475,2487,2499,2520,2532,2542,2572,2583 'retir':613,818 'return':189,205 'review':817 'role':1180 'rollout':620 'rout':315 'router':2319 'run':1755,2063,2183,2194,2689,2699 'runtim':1473 'safeti':499,1273,1333,1341,1354,1365,2125 'safety-focus':1353 'scan':2188,2199 'schema':1865 'sdk':766,769,1653,2201,2298 'search':420,995,1479,1491,1957,2376,2549 'section':93 'secur':25,58,348,352,367,424,1089,1125,1201,1233,1319,1378,1390,1403,1727,2389 'security.md':116,117 'security/guardrails':386 'select':603,690,703 'server':1115,1322,1673,2040,2221,2233 'servic':427,573,912,922,934,986,1150,1382,1420,1501,1918,2031,2147,2598,2621 'set':1143,1293,2205,2386,2592 'setup':304,398,437,889 'sharepoint':2058 'shield':1723 'side':2243 'sip':2342 'skill':38,40,81,166,188,202 'skill-microsoft-foundry' 'sold':693,706 'source-microsoftdocs' 'specif':485 'specifi':108 'speech':421,1631,1966,2563 'spillov':311,966 'standard':303,887,914 'step':227 'storag':384,1617,1628 'store':334,992 'strategi':291,623 'stream':808,1859 'string':183,197 'structur':1458,1867 'suggest':138,155 'support':1007 'switch':800 'synthet':1562 'system':248,516,1342,1356 'tag':1287 'task':484 'task-specif':483 'team':2186,2198,2652 'techniqu':529 'templat':1344,2664,2685 'term':2155 'terraform':1642 'test':500 'text':1581,2565 'text/markdown':204 'third':2123 'third-parti':2122 'throughput':310,556,957 'token':1014,1544 'tool':151,246,275,370,383,415,469,580,589,1107,1124,1133,1448,1480,1492,1857,1968,1979,1988,1998,2017,2027,2046,2126,2222,2307,2377 'topic':452,466,564,884,977,1090,1412,1899,2590 'topic-agent' 'topic-agent-skills' 'topic-agentic-skills' 'topic-agentskill' 'topic-ai-agents' 'topic-ai-coding' 'topic-azure' 'topic-azure-functions' 'topic-azure-kubernetes-service' 'topic-azure-openai' 'topic-azure-sql-database' 'topic-azure-storage' 'trace':393,423,1688,1700,2172,2244 'traffic':312,967 'troubleshoot':15,48,212,451,454 'tune':253,541,853,1061,1370,1785,1819,1843,2066,2294,2306,2723 'type':639,650 'understand':1048,1079,1092,1176,1330,1386,1399 'upgrad':272,661,673,728,785,798 'url':453,467,565,885,978,1091,1413,1900,2591 'usag':342 'use':32,79,85,103,118,175,192,368,577,596,723,739,794,990,1034,1057,1123,1286,1305,1340,1489,1503,1570,1585,1641,1659,1710,1771,1794,1830,1851,1901,1985,2014,2024,2163,2218,2271,2337,2346,2355,2374,2527,2558,2579,2659,2683 'user':140,157 'v1':1713,2402,2414,2426,2438,2450,2462,2474,2486,2498,2540 'vault':2210 'vector':333,991 'version':144,290,659,671 'via':1763,1937,2256,2297,2320,2369,2671 'virtual':1296 'vision':255,532,544,1805 'vision-en':531,1804 'vs':1515,1668,2079,2284 'web':587,1490,2375 'webhook':2392 'webpag':194 'webrtc':2351 'websocket':2360 'whisper':2561 'work':1875 'workaround':225,460 'worker':2607 'workflow':392,1513,1526 'workload':729","prices":[{"id":"0e5a5b3e-8d2e-454c-8b25-97502c9a524c","listingId":"1b6b1d67-d126-4bf7-ac34-e79891e286e4","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"MicrosoftDocs","category":"Agent-Skills","install_from":"skills.sh"},"createdAt":"2026-04-18T22:00:33.974Z"}],"sources":[{"listingId":"1b6b1d67-d126-4bf7-ac34-e79891e286e4","source":"github","sourceId":"MicrosoftDocs/Agent-Skills/microsoft-foundry","sourceUrl":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/microsoft-foundry","isPrimary":false,"firstSeenAt":"2026-04-18T22:00:33.974Z","lastSeenAt":"2026-04-22T00:53:40.185Z"}],"details":{"listingId":"1b6b1d67-d126-4bf7-ac34-e79891e286e4","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"MicrosoftDocs","slug":"microsoft-foundry","github":{"repo":"MicrosoftDocs/Agent-Skills","stars":497,"topics":["agent","agent-skills","agentic-skills","agentskill","ai","ai-agents","ai-coding","azure","azure-functions","azure-kubernetes-service","azure-openai","azure-sql-database","azure-storage","azure-virtual-machine","claude-code","github-copilot","microsoft-learn","openai-codex","skills"],"license":"cc-by-4.0","html_url":"https://github.com/MicrosoftDocs/Agent-Skills","pushed_at":"2026-04-19T02:43:40Z","description":"Curated Agent Skills for Microsoft & Azure – giving AI coding assistants structured, real-time expertise from Microsoft Learn docs.","skill_md_sha":"a5f23338999ff980442892e642db7123f003fc51","skill_md_path":"skills/microsoft-foundry/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/MicrosoftDocs/Agent-Skills/tree/main/skills/microsoft-foundry"},"layout":"multi","source":"github","category":"Agent-Skills","frontmatter":{"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 Azure OpenAI, tools, vector stores, RAG, CI/CD deployments, or M365/Teams apps, and other Microsoft Foundry related development tasks. Not for Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).","compatibility":"Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation."},"skills_sh_url":"https://skills.sh/MicrosoftDocs/Agent-Skills/microsoft-foundry"},"updatedAt":"2026-04-22T00:53:40.185Z"}}