microsoft-foundry

Expert knowledge for Microsoft Foundry (aka Azure AI Foundry) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents with Azure OpenAI, RAG/indexing, MCP/OpenAPI tools, eval workflows, or CI/CD deployments, 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).

471 stars

Best use case

microsoft-foundry is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

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, RAG/indexing, MCP/OpenAPI tools, eval workflows, or CI/CD deployments, 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).

Teams using microsoft-foundry should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/microsoft-foundry/SKILL.md --create-dirs "https://raw.githubusercontent.com/MicrosoftDocs/Agent-Skills/main/skills/microsoft-foundry/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/microsoft-foundry/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How microsoft-foundry Compares

Feature / Agentmicrosoft-foundryStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

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, RAG/indexing, MCP/OpenAPI tools, eval workflows, or CI/CD deployments, 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).

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# 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 | Lines | Description |
|----------|-------|-------------|
| Troubleshooting | L37-L41 | Known Microsoft Foundry bugs, error codes, limitations, and their workarounds, plus steps to diagnose and resolve common platform and deployment issues. |
| 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 |
| Decision Making | L54-L82 | Guides for choosing models, SDKs, APIs, and deployment options, plus planning migrations, upgrades, costs, capacity, and deprecations across Foundry and Azure OpenAI. |
| Architecture & Design Patterns | L83-L94 | Architectural patterns for Foundry agents: standard setup, RAG/indexing, HA/DR, regional recovery, provisioned throughput, spillover traffic, and LLM routing optimization. |
| Limits & Quotas | L95-L109 | Quotas, rate limits, regions, and constraints for Foundry agents and models, including vector/file search, evals, batching, prompt caching, fine-tuning costs, and Azure OpenAI access limits. |
| Security | L110-L142 | Security, privacy, and compliance for Foundry: auth/RBAC, keys & encryption, network isolation, guardrails & safety, policy/governance, and secure use of agents, tools, and models |
| Configuration | L143-L192 | Configuring Foundry agents, models, guardrails, storage, monitoring, and Azure OpenAI integrations, including workflows, evaluators, tracing, and deployment/runtime settings. |
| Integrations & Coding Patterns | L193-L266 | Integrating Foundry agents and models with SDKs, REST, tools, memory, search, MCP/OpenAPI, Azure OpenAI, speech/audio, safety, LangChain/LangGraph, and fine-tuning workflows |
| Deployment | L267-L283 | 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. |

### Troubleshooting
| Topic | URL |
|-------|-----|
| Troubleshoot Microsoft Foundry known issues and workarounds | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-known-issues |

### Best Practices
| Topic | URL |
|-------|-----|
| Apply tool configuration best practices for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/tool-best-practice |
| Evaluate Azure AI agents with task-specific metrics | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/agent-evaluators |
| Evaluate Foundry agents with built-in quality and safety tests | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/evaluate-agent |
| Optimize Foundry agent prompts with Prompt Optimizer | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/prompt-optimizer |
| Design effective system messages for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/advanced-prompt-engineering |
| Apply prompt engineering techniques for vision-enabled GPT models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/gpt-4-v-prompt-engineering |
| Fine-tune GPT-4 vision models with images | 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 |

### Decision Making
| Topic | URL |
|-------|-----|
| Migrate to new Foundry Agent Service APIs | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/migrate |
| Use Bing grounding tools with agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/bing-tools |
| Choose web grounding tools for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-overview |
| Use Foundry model benchmarks and leaderboards for selection | https://learn.microsoft.com/en-us/azure/foundry/concepts/model-benchmarks |
| Plan for Foundry model deprecation and retirement | https://learn.microsoft.com/en-us/azure/foundry/concepts/model-lifecycle-retirement |
| Plan Microsoft Foundry rollout and environment strategy | https://learn.microsoft.com/en-us/azure/foundry/concepts/planning |
| Optimize Foundry model cost and performance | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-optimize-cost-performance |
| Choose Foundry deployment types and data residency options | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/deployment-types |
| Manage model versioning and upgrade policies in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/model-versions |
| 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 |
| 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 |
| Upgrade workloads from GitHub Models to Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/quickstart-github-models |
| Use Foundry model leaderboard to compare and choose models | https://learn.microsoft.com/en-us/azure/foundry/how-to/benchmark-model-in-catalog |
| Choose appropriate Microsoft Foundry SDKs and endpoints | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/sdk-overview |
| Migrate from Azure AI Inference SDK to OpenAI SDK | https://learn.microsoft.com/en-us/azure/foundry/how-to/model-inference-to-openai-migration |
| Plan migration from classic Foundry portal | https://learn.microsoft.com/en-us/azure/foundry/how-to/navigate-from-classic |
| Decide and execute upgrade from Azure OpenAI to Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/upgrade-azure-openai |
| Use Ask AI to upgrade or switch Foundry models | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/optimization-model-upgrade |
| Choose content streaming and filtering modes in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-streaming |
| Review retired Azure OpenAI models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/legacy-models |
| Manage Azure OpenAI model deprecations in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirements |
| Enable and choose priority processing for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/priority-processing |
| Estimate and manage fine-tuning costs in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-cost-management |
| Estimate PTU costs and plan capacity for Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-throughput-onboarding |
| Migrate from preview to GA Realtime API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-preview-api-migration-guide |

### Architecture & Design Patterns
| Topic | URL |
|-------|-----|
| Design standard agent setup with isolated resources | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/standard-agent-setup |
| Apply RAG and indexing patterns in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation |
| Plan disaster recovery for Foundry Agent Service in standard mode | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-disaster-recovery |
| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-operator-disaster-recovery |
| Recover Foundry Agent Service from regional platform outages | https://learn.microsoft.com/en-us/azure/foundry/how-to/agent-service-platform-disaster-recovery |
| Plan high availability and resiliency for Foundry projects and agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/high-availability-resiliency |
| Plan provisioned throughput architecture for Foundry models | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput |
| Design spillover traffic management for provisioned deployments | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/spillover-traffic-management |

### Limits & Quotas
| Topic | URL |
|-------|-----|
| Quotas, limits, and regions for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/limits-quotas-regions |
| Use vector stores and file search limits in agents | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/vector-stores |
| Evaluation rate limits and region support in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-regions-limits-virtual-network |
| Configure token rate limits and quotas for models | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-enforce-limits-models |
| Capabilities and constraints of partner Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-from-partners |
| Reference quotas and limits for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/quotas-limits |
| Use Azure OpenAI global batch processing efficiently | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/batch |
| Configure prompt caching and understand cache limits in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/prompt-caching |
| Use reinforcement fine-tuning with cost limits | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reinforcement-fine-tuning |
| Azure OpenAI quotas, rate limits, and timeouts in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/quotas-limits |
| Understand limited access policy for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/limited-access |

### Security
| Topic | URL |
|-------|-----|
| Configure agent identities and RBAC in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-identity |
| Configure authentication methods for Agent2Agent tools | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/agent-to-agent-authentication |
| Configure authentication for MCP servers in agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/mcp-authentication |
| Configure computer use tool securely for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/computer-use |
| Govern MCP tools with an AI gateway in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/governance |
| Set up private networking for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/virtual-networks |
| Configure authentication and authorization for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/authentication-authorization-foundry |
| Configure customer-managed keys for Microsoft Foundry encryption | https://learn.microsoft.com/en-us/azure/foundry/concepts/encryption-keys-portal |
| Understand and apply RBAC roles in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/rbac-foundry |
| Govern Foundry agent infrastructure as Entra admin | https://learn.microsoft.com/en-us/azure/foundry/control-plane/govern-agent-infrastructure-entra-admin |
| Manage Foundry compliance and security integrations | https://learn.microsoft.com/en-us/azure/foundry/control-plane/how-to-manage-compliance-security |
| Create guardrail policies for model deployments | https://learn.microsoft.com/en-us/azure/foundry/control-plane/quickstart-create-guardrail-policy |
| Configure keyless Entra ID authentication for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-entra-id |
| 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 |
| Configure private endpoint network isolation for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/configure-private-link |
| Configure and manage Microsoft Foundry connections | https://learn.microsoft.com/en-us/azure/foundry/how-to/connections-add |
| Create custom Azure Policies to govern Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/custom-policy-definition |
| Apply Azure AI Content Safety in LangChain agents | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-middleware |
| Disable preview features in Microsoft Foundry using tags and RBAC | https://learn.microsoft.com/en-us/azure/foundry/how-to/disable-preview-features |
| Set up managed virtual networks for Microsoft Foundry projects | https://learn.microsoft.com/en-us/azure/foundry/how-to/managed-virtual-network |
| Use built-in Azure Policy definitions for Foundry model deployment | https://learn.microsoft.com/en-us/azure/foundry/how-to/model-deployment-policy |
| Secure Foundry MCP Server with RBAC and policies | https://learn.microsoft.com/en-us/azure/foundry/mcp/security-best-practices |
| Understand default guardrail safety policies in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/default-safety-policies |
| Use safety system message templates for Azure OpenAI apps | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/safety-system-message-templates |
| Author safety-focused system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/system-message |
| Apply safety evaluation to fine-tuned models | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-safety-evaluation |
| Data privacy and security for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/agents/data-privacy-security |
| Understand data privacy and security for Anthropic Claude in Foundry | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/claude-models/data-privacy |
| Understand data, privacy, and security for Azure Direct Models | https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy |

### Configuration
| Topic | URL |
|-------|-----|
| Configure capability hosts for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/capability-hosts |
| Manage and disable Grounding with Bing in Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-grounding-with-bing |
| Configure a private tool catalog with Azure API Center | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/private-tool-catalog |
| Configure structured inputs for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/structured-inputs |
| Configure custom MCP-based code interpreter runtime | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/custom-code-interpreter |
| Configure Foundry Agent Service to use existing Azure resources | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/use-your-own-resources |
| Configure declarative agent workflows in VS Code | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-low-code |
| Create and deploy hosted Foundry agent workflows | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/vs-code-agents-workflow-pro-code |
| Reference for all Foundry built-in evaluators | https://learn.microsoft.com/en-us/azure/foundry/concepts/built-in-evaluators |
| Create and configure custom evaluators in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/custom-evaluators |
| Configure risk and safety evaluators in Foundry | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/risk-safety-evaluators |
| Use textual similarity evaluators and metrics | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/textual-similarity-evaluators |
| Configure AI Gateway limits in Foundry | https://learn.microsoft.com/en-us/azure/foundry/configuration/enable-ai-api-management-gateway-portal |
| Register custom agents with Foundry Control Plane | https://learn.microsoft.com/en-us/azure/foundry/control-plane/register-custom-agent |
| Configure synthetic data generation in Foundry | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/data-generation |
| Use Foundry Models endpoints and authentication correctly | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/endpoints |
| Generate text with Foundry Models using the Responses API | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/generate-responses |
| Configure Azure Monitor for Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/monitor-models |
| Configure Foundry guardrails and safety controls | https://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-create-guardrails |
| Configure Task Adherence signals for agents | https://learn.microsoft.com/en-us/azure/foundry/guardrails/task-adherence |
| Configure bring-your-own storage for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/bring-your-own-azure-storage-foundry |
| 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 |
| Provision Microsoft Foundry resources using Terraform | https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-terraform |
| Configure cloud-based evaluations with Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/cloud-evaluation |
| Enable and use Fireworks models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/enable-fireworks-models |
| Connect VS Code to Foundry MCP Server | https://learn.microsoft.com/en-us/azure/foundry/mcp/get-started |
| Monitor Foundry agents with Agent Monitoring Dashboard | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/how-to-monitor-agents-dashboard |
| Add client-side OpenTelemetry tracing to Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-client-side |
| Configure tracing for LangChain and other AI agent frameworks | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-framework |
| Configure tracing for AI agents in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/observability/how-to/trace-agent-setup |
| Use Azure OpenAI v1 API in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/openai/api-version-lifecycle |
| Configure Prompt Shields for Foundry guardrails | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-prompt-shields |
| Call chat completion models with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/chatgpt |
| Generate and edit images with Azure OpenAI image models | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/dall-e |
| Run deep research with o3-deep-research via Responses API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/deep-research |
| Generate and use embeddings with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/embeddings |
| Configure DPO fine-tuning for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-direct-preference-optimization |
| Configure and use function calling with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/function-calling |
| Call vision-enabled chat models with Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/gpt-with-vision |
| Enable and tune JSON mode for Azure OpenAI chat completions | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/json-mode |
| Use predicted outputs to reduce Azure OpenAI latency | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/predicted-outputs |
| Create and tune provisioned deployments in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/provisioned-get-started |
| Use Azure OpenAI Responses API with tools and streaming | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/responses |
| Enforce JSON schema with structured outputs in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/structured-outputs |
| Work with Azure OpenAI model deployments in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/working-with-models |
| Monitor Foundry OpenAI with Azure Monitor data | https://learn.microsoft.com/en-us/azure/foundry/openai/monitor-openai-reference |

### Integrations & Coding Patterns
| Topic | URL |
|-------|-----|
| Use agents, conversations, and responses via SDKs | https://learn.microsoft.com/en-us/azure/foundry/agents/concepts/runtime-components |
| Connect enterprise AI gateways to Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/ai-gateway |
| Connect Foundry agents to Foundry IQ knowledge bases | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/foundry-iq-connect |
| Create and manage memory in Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/memory-usage |
| Invoke Foundry Agent Applications via Responses API protocol | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-responses |
| Connect Foundry agents to external A2A endpoints | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/agent-to-agent |
| Connect Azure AI Search indexes to agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/ai-search |
| Integrate Azure Speech MCP tool with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-ai-speech |
| Integrate Azure Functions as tools for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/azure-functions |
| Use Browser Automation tool with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/browser-automation |
| Enable Code Interpreter tool for agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/code-interpreter |
| Connect Microsoft Fabric data agent to Foundry | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/fabric |
| Configure file search tool for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/file-search |
| Use function calling tools with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/function-calling |
| Use image generation tool in Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/image-generation |
| Connect Foundry agents to MCP servers | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/model-context-protocol |
| Connect OpenAPI tools to Microsoft Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/openapi |
| Ground Foundry agents with SharePoint content via API | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/sharepoint |
| Integrate web search tool in Foundry agents | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/tools/web-search |
| Use Azure OpenAI graders in Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry/concepts/evaluation-evaluators/azure-openai-graders |
| Run fine-tuning jobs with azd extension | https://learn.microsoft.com/en-us/azure/foundry/fine-tuning/fine-tune-cli |
| Configure Claude Code CLI and VS Code with Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/configure-claude-code |
| Deploy and use Claude models in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-claude |
| Integrate FLUX image generation models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/use-foundry-models-flux |
| 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 |
| Deploy and call DeepSeek-R1 in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/tutorials/get-started-deepseek-r1 |
| Apply Task Adherence checks in agent workflows | https://learn.microsoft.com/en-us/azure/foundry/guardrails/how-to-task-adherence |
| Integrate third-party safety tools with Foundry | https://learn.microsoft.com/en-us/azure/foundry/guardrails/third-party-integrations |
| Integrate LangChain and LangGraph with Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain |
| Build LangGraph agents with Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-agents |
| Add Foundry long-term memory to LangChain apps | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-memory |
| Use LangChain models with Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-models |
| Trace LangChain apps with Foundry and Azure Monitor | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/langchain-traces |
| Run AI Red Teaming Agent scans in cloud | https://learn.microsoft.com/en-us/azure/foundry/how-to/develop/run-ai-red-teaming-cloud |
| 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 |
| Integrate Microsoft Foundry endpoints via REST APIs | https://learn.microsoft.com/en-us/azure/foundry/how-to/integrate-with-other-apps |
| 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 |
| Use Foundry MCP Server tools and prompts | https://learn.microsoft.com/en-us/azure/foundry/mcp/available-tools |
| Build and register custom MCP server for Foundry | https://learn.microsoft.com/en-us/azure/foundry/mcp/build-your-own-mcp-server |
| Call Azure OpenAI audio models via API | https://learn.microsoft.com/en-us/azure/foundry/openai/audio-completions-quickstart |
| Authoring operations for Foundry OpenAI REST API | https://learn.microsoft.com/en-us/azure/foundry/openai/authoring-reference-preview |
| Use groundedness detection with Foundry OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/content-filter-groundedness |
| Integrate Codex CLI and VS Code with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/codex |
| Fine-tune Foundry models via SDK and REST | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning |
| Fine-tune tool calling behavior in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-functions |
| Call Foundry model router via Chat Completions API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/model-router |
| Implement GPT Realtime audio with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio |
| Use GPT Realtime API over SIP | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-sip |
| Use GPT Realtime API over WebRTC | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-webrtc |
| Use GPT Realtime API over WebSockets | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/realtime-audio-websockets |
| Call Azure OpenAI reasoning models via Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/reasoning |
| Use web_search tool with Azure OpenAI Responses API | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/web-search |
| Set up and secure Azure OpenAI webhooks in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/webhooks |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Integrate with Azure OpenAI v1 REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/latest |
| Implement realtime audio events for Foundry OpenAI | https://learn.microsoft.com/en-us/azure/foundry/openai/realtime-audio-reference |
| Call Azure OpenAI inference REST APIs in Foundry | https://learn.microsoft.com/en-us/azure/foundry/openai/reference |
| Use Foundry OpenAI preview inference REST API | https://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview |
| Call Foundry OpenAI v1 preview REST endpoints | https://learn.microsoft.com/en-us/azure/foundry/openai/reference-preview-latest |
| Build document search with Azure OpenAI embeddings API | https://learn.microsoft.com/en-us/azure/foundry/openai/tutorials/embeddings |
| Use Azure OpenAI Whisper for speech to text | https://learn.microsoft.com/en-us/azure/foundry/openai/whisper-quickstart |
| Call Microsoft Foundry REST APIs for projects | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project |
| Use Microsoft Foundry Project REST API (preview) | https://learn.microsoft.com/en-us/azure/foundry/reference/foundry-project-rest-preview |

### Deployment
| Topic | URL |
|-------|-----|
| Set up infrastructure for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/environment-setup |
| Deploy Foundry agents as digital workers in Agent 365 | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/agent-365 |
| Deploy custom hosted agents to Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/deploy-hosted-agent |
| Manage lifecycle of hosted agent deployments | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/manage-hosted-agent |
| Publish Foundry agents as managed Azure resources | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-agent |
| Publish Foundry agents to Microsoft 365 Copilot and Teams | https://learn.microsoft.com/en-us/azure/foundry/agents/how-to/publish-copilot |
| Deploy Foundry Models using Azure CLI and Bicep templates | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/create-model-deployments |
| Deploy Foundry Models via Foundry portal for inference | https://learn.microsoft.com/en-us/azure/foundry/foundry-models/how-to/deploy-foundry-models |
| Deploy Microsoft Foundry resources using Bicep templates | https://learn.microsoft.com/en-us/azure/foundry/how-to/create-resource-template |
| Run Foundry evaluations in Azure DevOps pipelines | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-azure-devops |
| Run Foundry evaluations in GitHub Actions CI | https://learn.microsoft.com/en-us/azure/foundry/how-to/evaluation-github-action |
| Import and deploy custom Fireworks models in Foundry | https://learn.microsoft.com/en-us/azure/foundry/how-to/fireworks/import-custom-models |
| Deploy fine-tuned models on Foundry hosting | https://learn.microsoft.com/en-us/azure/foundry/openai/how-to/fine-tuning-deploy |
| Check Microsoft Foundry feature availability by region | https://learn.microsoft.com/en-us/azure/foundry/reference/region-support |

Related Skills

microsoft-foundry-tools

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Microsoft Foundry Tools (aka Azure AI services, Azure Cognitive Services) development including best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when using Content Moderator, Content Understanding analyzers, REST/.NET APIs, quotas, or secure Foundry setups, and other Microsoft Foundry Tools related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local).

microsoft-foundry-local

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Microsoft Foundry Local (aka Azure AI Foundry Local) development including troubleshooting, best practices, decision making, configuration, and integrations & coding patterns. Use when using Foundry Local CLI, REST/SDK APIs, OpenAI clients, LangChain/Open WebUI, or Olive model builds, and other Microsoft Foundry Local related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Tools (use microsoft-foundry-tools), Azure Local (use azure-local).

microsoft-foundry-classic

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents, RAG/vector search, function calling, realtime audio, or fine-tuned Azure OpenAI models, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).

azure-well-architected

471
from MicrosoftDocs/Agent-Skills

Expert guidance for designing, assessing, and optimizing Azure workloads using Azure Well Architected. Covers design review checklists, recommendations, design principles, tradeoffs, service guides, workload patterns, and assessment questions. Use when designing AI, SAP, SaaS, HPC, AVD/AVS workloads, or choosing regions/AZs with cost–reliability tradeoffs, and other Azure Well Architected related development tasks.

azure-web-pubsub

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Web PubSub development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building WebSocket/MQTT apps, using Socket.IO, geo-replication, private endpoints, or Functions bindings, and other Azure Web PubSub related development tasks. Not for Azure SignalR Service (use azure-signalr-service), Azure Event Hubs (use azure-event-hubs), Azure Service Bus (use azure-service-bus), Azure Relay (use azure-relay).

azure-web-application-firewall

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Web Application Firewall development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring Front Door/App Gateway WAF rules, rate limits, bot/CAPTCHA, Sentinel logging, or IaC deployments, and other Azure Web Application Firewall related development tasks. Not for Azure Application Gateway (use azure-application-gateway), Azure Front Door (use azure-front-door), Azure Firewall (use azure-firewall), Azure DDos Protection (use azure-ddos-protection).

azure-vpn-gateway

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure VPN Gateway development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring S2S/P2S tunnels, BGP routing, IPsec/IKE policies, Entra/RADIUS auth, or ExpressRoute VPNs, and other Azure VPN Gateway related development tasks. Not for Azure ExpressRoute (use azure-expressroute), Azure Virtual WAN (use azure-virtual-wan), Azure Virtual Network (use azure-virtual-network), Azure Virtual Network Manager (use azure-virtual-network-manager).

azure-vmware-solution

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure VMware Solution development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring AVS with HCX/NSX, vSAN/stretched clusters, Citrix/Horizon, Cloud Director, or JetStream DR, and other Azure VMware Solution related development tasks. Not for Azure Virtual Machines (use azure-virtual-machines), Azure Large Instances (use azure-large-instances), Azure Baremetal Infrastructure (use azure-baremetal-infrastructure), SAP HANA on Azure Large Instances (use azure-sap).

azure-vm-scalesets

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Virtual Machine Scale Sets development including troubleshooting, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when configuring VMSS autoscale, upgrade modes, zones/PPGs, Spot/standby pools, or disk encryption with Key Vault, and other Azure Virtual Machine Scale Sets related development tasks. Not for Azure Virtual Machines (use azure-virtual-machines), Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure App Service (use azure-app-service), Azure Service Fabric (use azure-service-fabric).

azure-virtual-wan

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Virtual WAN development including troubleshooting, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing Virtual WAN hubs, P2S VPN, ExpressRoute/SD‑WAN connectivity, NVAs/firewalls, or Entra ID VPN access, and other Azure Virtual WAN related development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure VPN Gateway (use azure-vpn-gateway), Azure ExpressRoute (use azure-expressroute), Azure Traffic Manager (use azure-traffic-manager).

azure-virtual-network

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Virtual Network development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, and configuration. Use when designing VNets, NSGs, service endpoints, VNet peering, VPN gateways, or Azure Firewall/NAT gateways, and other Azure Virtual Network related development tasks. Not for Azure Networking (use azure-networking), Azure Virtual Network Manager (use azure-virtual-network-manager), Azure Virtual WAN (use azure-virtual-wan), Azure VPN Gateway (use azure-vpn-gateway).

azure-virtual-network-manager

471
from MicrosoftDocs/Agent-Skills

Expert knowledge for Azure Virtual Network Manager development including troubleshooting, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing AVNM IPAM pools, network groups, cross-tenant connectivity, security admin rules, or ARG queries, and other Azure Virtual Network Manager related development tasks. Not for Azure Virtual Network (use azure-virtual-network), Azure Virtual WAN (use azure-virtual-wan), Azure Network Watcher (use azure-network-watcher), Azure Networking (use azure-networking).