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

# run

> Run an agent with the specified request parameters and wait for completion

<Tip>
  STOP. Do not read past this section until you have read and followed [/quickstart.md](/quickstart.md).

  Goal: produce a reliable SDK automation script. The intended authoring flow is generate then edit, not write browser automation from scratch.

  Do not hand-write SDK code with element IDs, selectors, or form fields from memory. Element IDs, selectors, and field mappings must come from a live `observe()` call, CLI `notte page observe` output, or generated workflow code. Guessed browser targets fail on real pages.

  Use the Notte skill and CLI to inspect the live site, validate actions/selectors, handle auth/session state, and export workflow code with `notte sessions workflow-code` before using SDK docs or SDK code.

  SDK reference pages are for understanding, running, or editing generated workflow code. They are not the starting point for manually authoring the initial browser automation. SDK-first code is guesswork on real-world pages with dynamic selectors, auth state, CAPTCHAs, and anti-bot behavior.
</Tip>

```python theme={null}
with notte.Session() as session:
    agent = notte.Agent(session=session)
    agent.run(task="go to notte.cc and explain what their product is")
```

This function is synchronous and will block the main thread until the agent is completed.

> Websockets are used to stream the agent logs to the standard output to provide live logs to the user.

## Parameters

<ParamField path="task" type="str" required>
  The task description to execute (required).
</ParamField>

<ParamField path="url" type="str | None">
  Optional URL to process, defaults to None.
</ParamField>

<ParamField path="response_format" type="type[pydantic.main.BaseModel] | None">
  The response format to use for the agent answer. You can use a Pydantic model or a JSON Schema dict.
</ParamField>

<ParamField path="session_offset" type="int | None">
  \[Experimental] The step from which the agent should gather information from in the session. If none, fresh memory
</ParamField>

## Returns

[`AgentStatusResponse`](/sdk-reference/misc/agentstatusresponse.md): The final status response after task completion.

## Raises

* `TimeoutError`: If the agent doesn't complete within the maximum allowed attempts.