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
Web → Browser Task
AI-generatedSummary
Run a natural-language-driven browser automation task using an AI-powered real browser session to navigate, interact, and extract data from web pages as specified by the user prompt.
Inputs
- Prompt (required) — A natural language description detailing the specific browsing task to perform and the desired output. Should be clear and avoid sensitive information.
- Additional Options — Optional parameters to fine-tune task execution, including:
- URL: URL to navigate to before starting; if empty, the browser follows URLs described in the prompt.
- Session ID: an existing saved browser-session ID to run the task as a logged-in user.
- Max Steps: limit on the number of browser actions (navigation, clicking, typing).
- Max Wait Time (Seconds): maximum allowed time for the task to complete (default 360 seconds).
- Timeout (Ms): milliseconds after which to timeout the task; 0 uses the API default.
- Output Schema (JSON): a JSON Schema to enforce structured data output from the task.
- Poll Interval (Seconds): frequency to poll for task status (default 3 seconds).
Output shape
a single result object containing the success status, operation name, workflow ID, and the task's result data as returned by the API.
The execution triggers an asynchronous task and polls the service until completion, failure, timeout, or task error. The node returns structured data that may conform to the supplied Output Schema if provided. On failure or timeout, an error is thrown. If no workflow ID is returned (synchronous response), the response JSON is returned immediately.
Examples
Example 1: Find the cheapest 65-inch TV on a site and list specs
Set the Prompt input to a clear natural language instruction describing this goal; optionally provide the site's URL in Additional Options URL and a Session ID if login is required.