Get API usage statistics including active scout counts, rate limits, and activity metrics.

List all scouts for the authenticated user. Returns basic metadata; use get_scout_detail for full fields.

Get detailed information about a specific scout.

Get paginated updates/reports for a scout. Each update contains findings from a run.

Create a monitoring scout for continuous web monitoring. Scouts track changes relevant to a query and alert you. Examples: 'news about Yutori', 'H100 pricing below $1.50'.

Update an existing scout's query, schedule, webhook configuration, or status. Use status='paused' to pause, 'active' to resume, or 'done' to archive.

Permanently delete a scout and all its data. This action cannot be undone.

Execute a one-time web browsing task. The navigator agent runs a browser and operates it like a person. Returns a task_id for polling. Example: 'list employees'. Set browser='local' to use the desktop app with the user's logged-in sessions.

List one-time browsing tasks for the authenticated user. Supports cursor pagination and status filtering. List status is approximate (running also covers queued and not-yet-reconciled tasks); call get_browsing_task_result for a task's authoritative status.

Poll for browsing task status and result. Call until status is 'succeeded' or 'failed'.

Execute a one-time deep web research task. The research agent searches, reads, and synthesizes information from across the web. Returns a task_id for polling. Example: 'latest AI startup funding announcements'.

List one-time research tasks for the authenticated user. Supports cursor pagination and status filtering. List status is approximate (running also covers queued and not-yet-reconciled tasks); call get_research_task_result for a task's authoritative status.

Poll for research task status and result. Call until status is 'succeeded' or 'failed'.