> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-harris-1786029617-6b0a55e.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Define a Managed Deep Agent

> Configure the model and core capabilities of a Managed Deep Agent.

The agent definition selects the model and core capabilities of a Managed Deep Agent. Export it as a named `agent` from `agent.py`, `agent.ts`, or `agent.tsx` at the project root.

<Note>
  Managed Deep Agents is in **public [beta](/langsmith/release-stages)** and available on [LangSmith Cloud](/langsmith/cloud) in the US region only.
</Note>

## Define an agent

Use `define_deep_agent` in Python or `defineDeepAgent` in TypeScript:

<CodeGroup>
  ```python agent.py theme={null}
  from managed_deepagents import define_deep_agent

  agent = define_deep_agent(
      name="research-assistant",
      model="openai:gpt-5.5",
  )
  ```

  ```ts agent.ts theme={null}
  import { defineDeepAgent } from "managed-deepagents";

  export const agent = defineDeepAgent({
    name: "research-assistant",
    model: "openai:gpt-5.5",
  });
  ```
</CodeGroup>

## Name

`name` is required. Pass a static string that starts with a letter and contains only letters, numbers, underscores, or hyphens, such as `"research-assistant"`.

MDA uses the name as the LangGraph assistant ID and the default LangSmith deployment name. You can override the deployment name with `mda deploy --name` without changing the agent definition.

## Model

Set `model` to the chat model the agent uses. The simplest option is a `provider:model` string, such as `"openai:gpt-5.5"`. Add the provider's API key to `.env` so the model works locally and in the deployment.

Pass a LangChain chat model instance instead when you need to configure model parameters in code. For model options and supported providers, see [Models](/oss/python/deepagents/models).

## Tools

Pass tools in the `tools` list to let the agent call application logic or external services. Define tools in local modules, import them into the agent entry, and add them to the definition. See [Custom tools](/langsmith/managed-deep-agents-tools).

## Middleware

Pass middleware in the `middleware` list to add behavior around model calls, tool calls, and the agent lifecycle. Middleware runs in list order. See [Custom middleware](/langsmith/managed-deep-agents-middleware).

## Subagents

Pass subagent definitions in `subagents` when the agent should delegate specialized or context-heavy work. Each subagent can have its own prompt, model, and tools. See [Subagents](/oss/python/deepagents/subagents).

## Permissions

Pass filesystem permission rules in `permissions` to control which paths the agent's built-in filesystem tools can read or write. See [Permissions](/oss/python/deepagents/permissions).

## Human-in-the-loop

Set `interrupt_on` in Python or `interruptOn` in TypeScript to pause before selected tool calls. Use this for actions that require a person to approve, edit, or reject the call before it runs. See [Human-in-the-loop](/langsmith/managed-deep-agents-middleware#human-in-the-loop).

## Structured output

Set `response_format` in Python or `responseFormat` in TypeScript when the agent must return data that matches a schema instead of an unconstrained text response. See [Structured output](/oss/python/langchain/structured-output).

Configure the system prompt, skills, memory, sandbox, identity, channels, and schedules through their project files rather than the agent definition. See [Project structure](/langsmith/managed-deep-agents-project-structure).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/managed-deep-agents-agent-definition.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>