Actions108
- AI Visibility Actions
- List Sources
- Search
- Agentic Search
- AI Visibility Search
- AI Visibility Sources
- Browser Task
- Control Monitor
- Crawl
- Create Monitor
- Delete Session
- Get Monitor Changes
- List Monitors
- List Sessions
- Map
- Scrape URL
- Wire: Browse Catalog
- Wire: Discover Actions
- Wire: List Identities
- Wire: Request New Action
- Wire: Run Read Action
- Wire: Run Write Action
- Wire: Sign In
- Browser Actions
- Delete Session
- List Sessions
- Run Task
- Agentic Search
- AI Visibility Search
- AI Visibility Sources
- Browser Task
- Control Monitor
- Crawl
- Create Monitor
- Get Monitor Changes
- List Monitors
- Map
- Scrape URL
- Search
- Wire: Browse Catalog
- Wire: Discover Actions
- Wire: List Identities
- Wire: Request New Action
- Wire: Run Read Action
- Wire: Run Write Action
- Wire: Sign In
- Monitor Actions
- Control
- Create
- Get Changes
- List
- Agentic Search
- AI Visibility Search
- AI Visibility Sources
- Browser Task
- Control Monitor
- Crawl
- Create Monitor
- Delete Session
- Get Monitor Changes
- List Monitors
- List Sessions
- Map
- Scrape URL
- Search
- Wire: Browse Catalog
- Wire: Discover Actions
- Wire: List Identities
- Wire: Request New Action
- Wire: Run Read Action
- Wire: Run Write Action
- Wire: Sign In
- Web Actions
- Agentic Search
- Crawl
- Map
- Scrape URL
- Search
- AI Visibility Search
- AI Visibility Sources
- Browser Task
- Control Monitor
- Create Monitor
- Delete Session
- Get Monitor Changes
- List Monitors
- List Sessions
- Wire: Browse Catalog
- Wire: Discover Actions
- Wire: List Identities
- Wire: Request New Action
- Wire: Run Read Action
- Wire: Run Write Action
- Wire: Sign In
- Wire Actions
Monitor → Browser Task
AI-generatedSummary
Run a natural-language browser automation task using an AI-driven browser to perform actions such as navigation, clicking, and data extraction on a target website.
Inputs
- Prompt (required) — A natural language description of the specific task to perform in the browser, including what goal to achieve and data to return. Do not include passwords or secrets here; use Session ID for authenticated sessions.
- Additional Options — Optional parameters to customize the task execution, including:
- Max Steps: limit the number of browser interaction steps (navigation, clicks, typing).
- Max Wait Time (Seconds): maximum time to wait for task completion (default 360 seconds).
- Output Schema (JSON): a JSON Schema describing the expected structured data result.
- Poll Interval (Seconds): interval between status checks (default 3 seconds).
- Session ID: saved browser session ID to run the task in an authenticated context.
- Timeout (Ms): task timeout in milliseconds; server caps at approximately 330 seconds.
- URL: initial URL to navigate before starting; if empty, the agent will follow URLs mentioned in the prompt.
Output shape
a single JSON object containing the task execution result with success status, operation name, workflow ID, and the retrieved or parsed data conforming to the specified schema if any.
The operation submits the task asynchronously and polls the API until completion or failure within the specified max wait time. If no workflow ID is returned, the API response is returned immediately. Errors are thrown or returned in the output depending on error handling settings.
Examples
Example 1: Find product information on a website
Set Prompt to describe the task in natural language, e.g., 'Find the cheapest 65-inch TV on this site and list its specs'. Optionally provide a URL to start from, and a JSON schema to shape the output.