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
AI Visibility → Browser Task
AI-generatedSummary
Run a natural-language browser automation task using an AI-driven browser, optionally starting from a specified URL or a saved session, and receive structured or unstructured output.
Inputs
- Prompt (required) — The natural language description of the browser task to perform. Be specific about the goal and what the task should return. Avoid including sensitive information such as passwords; use Session ID for authenticated sites.
- URL — Optional URL to navigate to before starting the task. If left empty, the agent will follow URLs mentioned in the prompt.
- Session ID — ID of a saved browser session, enabling the task to run logged in if authentication is required.
- Max Steps — Maximum number of agent steps allowed (such as navigation, clicking, and typing). Set to 0 to use the API default.
- Max Wait Time (Seconds) — Maximum time to wait for the browser task to complete, defaulting to 360 seconds (6 minutes).
- Timeout (Ms) — Timeout for the task in milliseconds. The server caps runs at approximately 330 seconds regardless. Set to 0 to use the API default.
- Output Schema (JSON) — An optional JSON Schema to define the structure of the returned result, ensuring the agent returns data conforming to this schema.
- Poll Interval (Seconds) — Interval in seconds between status checks while waiting for the task to complete, defaulting to 3 seconds.
Output shape
A single record containing the task status and result data, including a success flag, operation name, workflow ID, and either structured data conforming to the provided schema or unstructured data returned by the AI agent.
The operation runs asynchronously by default. It submits the task to the API, then polls for completion up to the specified max wait time. If the task completes successfully, the structured or unstructured output is returned; if it fails or times out, an error is thrown. The output includes task identifiers and result details for further processing in the workflow.