Browser AI Tasks
Browser AI Tasks combines advanced AI capabilities with robust browser automation to make web interactions
seamless for AI agents. We use Browser-Use, a powerful operator that enables natural language browser automation,
allowing agents to autonomously navigate websites, interact with web elements, and complete complex multi-step
workflows. Key features include vision + HTML extraction for comprehensive web interaction, intelligent
element tracking, self-correcting error handling, and support for asynchronous task execution with
progress tracking and screenshot capture. Browser AI Tasks are a more advanced version of Browser AI Actions.
📄️ Presigned Upload URL
Returns a presigned URL for uploading a file to the user's files bucket.
📄️ Run Task
Execute a browser task using the browser-use operator. This endpoint starts a new browser automation
📄️ Run Synchronous Task
Execute a browser task synchronously using browser-use operator. This endpoint starts a new browser
📄️ List Tasks
List all browser-use tasks with pagination. Returns a paginated list of all tasks
📄️ Task Details
Get comprehensive information about a specific browser-use task, including its current status,
📄️ Task Status
Get just the current status of a browser-use task (created, running, finished, stopped, paused, or failed).
📄️ Task Summary
Get a detailed execution summary of a browser-use task. Returns a formatted text summary
📄️ Stop Task
Stop a running browser automation task immediately using browser-use operator.
📄️ Pause Task
Pause execution of a running browser-use task. The task can be resumed later
📄️ Resume Task
Resume execution of a previously paused browser-use task. The task will continue
📄️ Screenshots
Get all screenshot URLs for a browser-use task. Returns a list of URLs to screenshots
📄️ Download Screenshot
Download a specific screenshot file from a browser-use task execution.
📄️ Generate GIF
Generate a GIF from the screenshots of a browser-use task's execution.
📄️ Download GIF
Download the animated GIF file generated from the screenshots of a browser-use task's execution.
📄️ Media
Get task recordings/media files from browser-use task execution.
📄️ Download Output File
Download output files generated during browser-use task execution.