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

> ## Agent Instructions
> Anchor Browser is cloud browser infrastructure for AI agents and automation: browser sessions you control over CDP or REST, natural-language web tasks, versioned automation tasks, managed authentication into third-party web apps (identities with MFA), persistent volumes and profiles, recordings, live view, batch sessions, webhooks, and network options including residential proxies, extra stealth, and captcha solving for sites that block standard browsers. AI agents should start at https://docs.anchorbrowser.io/for-agents, then get an API key with Agent Access at https://docs.anchorbrowser.io/quickstart/agent-access — no dashboard account required. Read those two pages before authentication or API calls.

# Deep Research

The following example demonstrates how to use Anchor Browser to perform web research tasks.

<CodeGroup>
  ```tsx node.js theme={null}
  import { Sessions, agentTask } from 'anchorbrowser';

  const session = await Sessions.createSession()
  const sessionId = session.data?.id

  const result = await agentTask(
    `Find the most recent NBA game played by the Milwaukee Bucks
     and provide the result.`,
    {
      taskOptions: {
        url: 'https://nba.com/',
      },
      sessionId: sessionId,
    }
  )
  console.log(result)

  const author = await agentTask(
    `Find an article discussing the game and provide the author's name.`,
    {
      sessionId: sessionId,
    }
  )
  console.log(author)
  ```

  ```python python theme={null}
  from anchorbrowser import Anchorbrowser

  anchor_client = Anchorbrowser()
  session = anchor_client.sessions.create_session()
  session_id = session.data.id

  result = anchor_client.agent.task(
    '''Find the most recent NBA game played by the Milwaukee Bucks
       and provide the result.''',
    task_options={
      'url': 'https://nba.com/',
    },
    session_id=session_id,
  )
  print(result)

  author = anchor_client.agent.task(
    'Find an article discussing the game and provide the author\'s name.',
    session_id=session_id,
  )
  print(author)
  ```
</CodeGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.