Browserbase icon

Browserbase

Browser automation, web search, and page fetches with Browserbase.

Actions7

Search → Run an Agent

AI-generated

Overview

This node runs an AI agent to perform browser automation tasks starting from a specified URL. It uses a selected AI model to navigate and interact with web pages based on given instructions, such as extracting data or completing tasks on websites. This is useful for automating complex web interactions, data extraction, and testing workflows that require AI-driven browsing and reasoning.

Use Case Examples

  1. Extract pricing information from a website by instructing the agent to find the pricing page and list all plan names and prices.
  2. Automate form filling and submission on a web page by providing instructions to the agent.
  3. Navigate through multiple pages of a website to collect specific data points as per the instruction.

Properties

Name Meaning
Model The AI model that drives the browser and runs the agent, handling navigation and reasoning by default. Different models can be selected based on provider and capabilities.
Starting URL The initial web page URL where the agent begins its task.
Instruction The specific task or instructions for the agent to complete on the web page.
Model Options Optional settings to override the reasoning model based on the interaction mode (CUA, DOM, Hybrid). Includes agent model selection, cursor highlighting, max steps, mode, model source, and system prompt.
Variables Sensitive data passed to the agent as placeholders in instructions, never revealed to the AI model.
Browser Options Settings for browser behavior during execution, such as blocking ads, logging, recording sessions, solving captchas, viewport size, and verified identity.
Session Options Options for session management including context reuse, keep alive, persistence, region, timeout, proxy usage, and user metadata.

Output

JSON

  • success - Indicates if the agent task was successful.
  • message - Message describing the result or status of the task.
  • actions - List of actions performed by the agent during execution.
  • completed - Boolean indicating if the task was completed.
  • usage - Usage statistics related to the agent execution.
  • sessionId - Identifier for the browser session used.
  • contextId - Optional context ID if session context was reused.

Dependencies

  • Browserbase API key credential

Troubleshooting

  • Ensure the selected Agent Model supports the chosen mode (CUA, DOM, Hybrid). For example, CUA mode requires a computer-use-capable model.
  • If using a user-provided API key, ensure the Model and Agent Model are from the same provider to avoid errors.
  • Check that the Starting URL is a valid HTTP or HTTPS URL.
  • Verify that the Browserbase API key credential is correctly configured and has necessary permissions.
  • If the agent fails to start or execute, check session management options like context ID and timeout settings.

Links

Discussion