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

# Add a custom search tool, memory, and a schedule

> Replace provider search with a Tavily tool, then add durable memory and a daily schedule to the research assistant from the quickstart.

This tutorial continues from the [quickstart](/langsmith/python/managed-deep-agents-quickstart). Use the `research-assistant` project you created there, with your model, instructions, and a working `mda dev` setup.

`mda init` may also scaffold files such as `identity` and `sandbox/`. Leave those as they are; this tutorial does not change them.

This guide replaces the quickstart's built-in provider search with an authored [Tavily](https://tavily.com) search tool, enables durable memory, adds a daily schedule, then deploys.

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

## Extend the agent

<Steps>
  <Step title="Add a custom search tool" id="add-tool">
    Built-in provider search is convenient for a first run. Authored tools give you more control: choose the search API, tune parameters, and keep the tool code in your project.

    <Note>
      If you followed the steps to use Tavily in the [Quickstart](/langsmith/python/managed-deep-agents-quickstart), skip to the next step.
    </Note>

    Add a [Tavily API key](https://app.tavily.com) to `.env`:

    ```text .env theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    TAVILY_API_KEY=<TAVILY_API_KEY>
    ```

    Install the Tavily client:

    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    uv add tavily-python
    ```

    Create a custom `internet_search` tool:

    ```python tools/search.py theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    import os
    from typing import Literal

    from langchain.tools import tool
    from tavily import TavilyClient


    tavily_client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])


    @tool
    def internet_search(
        query: str,
        max_results: int = 5,
        topic: Literal["general", "news", "finance"] = "general",
    ) -> dict:
        """Search the internet for relevant sources."""
        return tavily_client.search(
            query,
            max_results=max_results,
            topic=topic,
        )
    ```

    Replace the provider search tool dict with your authored tool. Keep the `model` value from the quickstart:

    ```python agent.py theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    from managed_deepagents import define_deep_agent

    from tools.search import internet_search

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

    Restart `mda dev` if it is already running. In Studio, ask:

    ```txt wrap theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    What were the main announcements from the latest LangChain release?
    ```

    Confirm the agent calls `internet_search` and returns an answer with citations. For more authored tools, see [Custom tools](/langsmith/python/managed-deep-agents-tools).
  </Step>

  <Step title="Update the instructions for memory" id="instructions">
    Extend `instructions.md` so the agent knows what shared knowledge to keep. Keep the research behavior and add a memory policy:

    ```markdown instructions.md theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    # Research assistant

    You are a careful research assistant. Use internet search to find sources,
    keep notes, and return concise answers with citations.

    ## Memory

    - Record reusable research procedures and project knowledge that can improve future work.
    - For release research, check the project's official changelog before secondary sources.
    - Never store personal data or secrets in memory.
    ```
  </Step>

  <Step title="Enable and use durable memory" id="memory">
    Durable memory is opt-in. Before asking the agent to remember anything, add a memory declaration at the project root:

    ```python memory.py theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    from managed_deepagents import define_memory

    memory = define_memory(scope="agent")
    ```

    Memory is shared across the deployment and visible to all callers, so do not store personal data or secrets.

    Restart `mda dev` so it discovers the new file. In one thread, ask the agent to research a release and to record a reusable project rule, such as "For release research, check the official changelog before secondary sources." Then create a **new thread** in Studio and ask how it will research the next release. Confirm that it applies the shared rule even though the new thread has no conversation history.

    See [Memory](/langsmith/python/managed-deep-agents-memory) for details.
  </Step>

  <Step title="Schedule a daily digest" id="schedule">
    Add a `schedules/` module so the agent runs on a cron cadence without a user message. This schedule runs every weekday at 8am Pacific:

    ```python schedules/daily_digest.py theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    from managed_deepagents import define_schedule

    schedule = define_schedule(
        cron="0 8 * * 1-5",
        timezone="America/Los_Angeles",
        prompt=(
            "Review durable memory for reusable research rules. "
            "Summarize anything useful, then list open questions for today."
        ),
    )
    ```

    If memory is empty on the first fire, the agent still returns open questions.

    `mda deploy` reconciles this schedule into a LangSmith cron job after the deployment is live. After you deploy in the next step, you should see:

    * `mda deploy` finish without schedule errors (do not pass `--no-wait`, or schedules are not reconciled).
    * A managed cron for this file on the deployment. The schedule name matches the module stem: `daily_digest` (Python) or `daily-digest` (TypeScript).
    * No immediate digest run from this cron. The first fire waits until 8:00 America/Los\_Angeles on a weekday.

    For thread behavior and constraints, see [Schedules](/langsmith/python/managed-deep-agents-schedules).
  </Step>

  <Step title="Deploy and inspect" id="deploy">
    Deploy the project to LangSmith:

    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    mda deploy .
    ```

    On success, the CLI prints the deployment dashboard URL. The deploy syncs the instructions to Context Hub, uploads the compiled project, and reconciles the daily schedule.

    Open that URL and confirm:

    * The deployment is ready.
    * The `daily_digest` or `daily-digest` cron exists.
    * A test chat run shows model calls, `internet_search` tool calls, and memory reads or writes in the traces.

    For deploy flags and troubleshooting, see [Deploy an agent](/langsmith/python/managed-deep-agents-deploy) and the [CLI reference](/langsmith/python/managed-deep-agents-cli#deploy-projects).
  </Step>
</Steps>

## Next steps

<CardGroup cols={2}>
  <Card title="Custom middleware" icon="code" href="/langsmith/python/managed-deep-agents-middleware">
    Add logging, retries, limits, and guardrails around model and tool calls.
  </Card>

  <Card title="Identity" icon="fingerprint" href="/langsmith/python/managed-deep-agents-identity">
    Authenticate callers and use verified identity in tools and middleware.
  </Card>

  <Card title="Evals" icon="flask" href="/langsmith/python/managed-deep-agents-evals">
    Author Harbor tasks and compile the managed agent for Harbor.
  </Card>
</CardGroup>

***

<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-tutorial.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>