v7

latestOpenAPI 3.0.3raw.githubusercontent.com2026-05-056151218.0 KB

Automate

AI Task

Execute AI-powered browser automation tasks using natural language with optional geotargeting. This endpoint always streams responses using Server-Sent Events (SSE).

Streaming Response:

All responses are streamed using Server-Sent Events (text/event-stream)
Real-time progress updates and results as they're generated

Geotargeting:

Optionally specify a country code for geotargeted browsing

Use Cases:

Web scraping and data extraction
Form filling and interaction
Navigation and information gathering
Multi-step web workflows
Content analysis from web pages

post/automate

Request body

dataobject

JSON data to provide context for form filling or complex tasks

guardrailsstring

Safety constraints for execution

interactiveboolean

Enable interactive mode to allow human-in-the-loop input during task execution

maxIterationsinteger

Maximum task iterations

maxValidationAttemptsinteger

Maximum validation attempts

taskstring required

The task description in natural language

urlstring uri

Starting URL for the task

Example request

{
  "geo_target": {
    "country": "US"
  },
  "guardrails": "browse and extract data only, don't star or fork repositories",
  "maxIterations": 50,
  "maxValidationAttempts": 3,
  "task": "Find the top 3 trending repositories on GitHub and extract their names, descriptions, and star counts",
  "url": "https://github.com/trending"
}

Response

Task executed successfully (always streaming)

Streaming Response using Server-Sent Events: All responses from the automate endpoint are streamed using Server-Sent Events.

Event Format:

Each event starts with event: <type> followed by data: <JSON>
Empty lines separate events

Event Types:

Task Events:

start: Task initialization
task:setup: Task configuration
task:started: Task execution begins
task:completed: Task finished successfully
task:aborted: Task was terminated
task:validated: Task completion validation
task:validation_error: Validation failed

Agent Events:

agent:processing: Agent thinking/planning
agent:status: Status updates and plans
agent:step: Processing step iterations
agent:action: Actions being performed
agent:reasoned: Agent reasoning output
agent:extracted: Data extraction results
agent:waiting: Agent waiting for operations

Browser Events:

browser:navigated: Page navigation events
browser:action_started: Browser action initiated
browser:action_completed: Browser action finished
browser:screenshot_captured: Screenshot taken

System Events:

system:debug_compression: Debug compression info
system:debug_message: Debug messages

Stream Control:

complete: End of stream with results
done: Stream termination
error: Error occurred

All 6 operations