> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/MicrosoftDocs/azure-ai-docs/llms.txt
> Use this file to discover all available pages before exploring further.

# What is Microsoft Foundry?

> Learn about Microsoft Foundry, a unified Azure platform for enterprise AI operations, agents, models, and tools with built-in security and governance.

# What is Microsoft Foundry?

Microsoft Foundry is a unified Azure platform-as-a-service offering for enterprise AI operations, model builders, and application development. This foundation combines production-grade infrastructure with friendly interfaces, enabling developers to focus on building applications rather than managing infrastructure.

## Unified Platform for AI Development

Microsoft Foundry unifies agents, models, and tools under a single management grouping with built-in enterprise-readiness capabilities including:

* **Tracing and Monitoring**: Full observability into agent behavior and performance
* **Evaluations**: Built-in tools to assess model and agent quality
* **Enterprise Setup**: Customizable configurations for security and compliance
* **Unified Management**: Single RBAC, networking, and policy control under one Azure resource provider namespace

## Key Capabilities

Microsoft Foundry provides developers with powerful capabilities to build production-ready AI applications:

### Agents

Build intelligent agents that can:

* Make decisions and invoke tools
* Participate in multi-agent workflows
* Access enterprise knowledge through integrated tools
* Operate with enterprise-grade security and governance

### Models

Access a comprehensive catalog of AI models:

* **Azure OpenAI models**: GPT-4o, GPT-4, GPT-3.5 with fungible provisioned throughput
* **Foundry Direct models**: DeepSeek, xAI, and other cutting-edge models
* **Partner models**: Meta Llama, Cohere, Anthropic Claude, and more
* **Community models**: 1900+ models from Hugging Face and other sources

### Tools and Integrations

Extend agent capabilities with built-in tools:

* **Code Interpreter**: Execute Python code in sandboxed environments
* **File Search**: Retrieve knowledge from uploaded documents
* **Function Calling**: Define custom tools for your agents
* **Azure AI Search**: Ground responses in your indexed data
* **Azure Functions**: Integrate with enterprise systems and APIs

## Microsoft Foundry API and SDKs

The Microsoft Foundry API provides a consistent contract for working across different model providers. SDKs are available for:

* **Python**: Full-featured SDK with agent and model support
* **C#**: Enterprise-grade SDK for .NET applications
* **JavaScript/TypeScript** (preview): Modern web development support
* **Java** (preview): Support for Java-based applications

<CodeGroup>
  ```python Python theme={null}
  from azure.ai.projects import AIProjectClient
  from azure.identity import DefaultAzureCredential

  project = AIProjectClient(
      endpoint="https://<resource-name>.services.ai.azure.com/api/projects/<project-name>",
      credential=DefaultAzureCredential(),
  )
  ```

  ```csharp C# theme={null}
  using Azure.AI.Projects;
  using Azure.Identity;

  string endpoint = "https://<resource-name>.services.ai.azure.com/api/projects/<project-name>";
  AIProjectClient projectClient = new AIProjectClient(new Uri(endpoint), new DefaultAzureCredential());
  ```

  ```typescript TypeScript theme={null}
  import { AIProjectClient } from "@azure/ai-projects";
  import { DefaultAzureCredential } from "@azure/identity";

  const endpoint = "https://<resource-name>.services.ai.azure.com/api/projects/<project-name>";
  const project = new AIProjectClient(endpoint, new DefaultAzureCredential());
  ```
</CodeGroup>

## Projects and Resource Isolation

Foundry projects provide secure units of isolation and collaboration where:

* Agents share file storage, thread storage, and search indexes
* Data is isolated between projects
* You can bring your own Azure resources for compliance and control
* Each project acts as an independent workspace

## Enterprise Features

Microsoft Foundry is designed for enterprise workloads with:

### Security and Compliance

* Microsoft Entra ID authentication
* Role-based access control (RBAC)
* Network isolation with private endpoints
* Customer-managed encryption keys
* Content safety filters

### Observability

* Full conversation tracing
* Application Insights integration
* Performance metrics and monitoring
* Evaluation and testing tools

### Data Residency

* Bring your own Azure Storage
* Bring your own Azure Cosmos DB
* Bring your own Azure AI Search
* Data stays in your tenant and region

## Pricing and Availability

Microsoft Foundry is free to explore and use. You pay only for:

* Model deployments and API calls
* Azure resources you provision (Storage, Cosmos DB, etc.)
* Specific features like Code Interpreter sessions

Foundry is available in most regions where Azure AI services are available.

## Getting Started

To start building with Microsoft Foundry:

1. [Create a Foundry project](/foundry/quickstart)
2. [Deploy a model](/foundry/models/deployment)
3. [Create your first agent](/foundry/agents/overview)
4. [Explore the SDK](/foundry/sdk-overview)

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/foundry/quickstart">
    Get started with Microsoft Foundry in minutes
  </Card>

  <Card title="Agents" icon="robot" href="/foundry/agents/overview">
    Build intelligent agents with Foundry Agent Service
  </Card>

  <Card title="Models" icon="brain" href="/foundry/models/overview">
    Explore the model catalog and deployments
  </Card>

  <Card title="SDK Overview" icon="code" href="/foundry/sdk-overview">
    Learn about SDKs and endpoints
  </Card>
</CardGroup>