Skip to main content

Browser Use Agent

The Browser Use Agent is a built-in AI agent that can interact with web pages in your browser tabs. It reads page content, clicks elements, fills in forms, and extracts structured information — all within the tab you point it to.

Capabilities​

The agent can perform the following actions on a target tab:

  • Extract page content — read the full text content of a web page
  • Extract DOM elements — identify interactive elements (links, buttons, inputs, etc.)
  • Click elements — click buttons, links, and other interactive elements
  • Input text — fill in form fields and search boxes
  • Submit forms — simulate pressing Enter to submit forms

Each task is scoped to a single tab. The agent does not open new tabs or navigate to new URLs on its own — it only interacts with the page you specify.

Approval Workflow​

Before the Browser Use Agent takes any action on a page, it asks for your approval. A confirmation message shows the planned actions and gives you three options:

  • Approve — approve the current batch of actions only
  • Approve for this domain — automatically approve all future actions on this domain for the current chat session
  • Approve all — automatically approve all future actions for the current chat session

This ensures you stay in control of what the agent does on your behalf.

Auto-Approve Domains​

You can configure a list of domains where the Browser Use Agent is automatically approved without prompting. This is useful for sites you frequently use and trust.

By default, the following domains are auto-approved:

  • google.com
  • *.wikipedia.org

To manage the auto-approve domain list, open the Browser Use Agent settings from the tools configuration panel.

caution

Be careful when adding domains to the auto-approve list. The agent will take actions on these sites without asking for confirmation.

Example Use Cases​

  • Web research: "Search for 'best project management tools' on Google and return the top 5 results"
  • Form filling: "Fill in the contact form on this page with the following details…"
  • Data extraction: "List all article titles on this Wikipedia page"
  • Workflow automation: "Search for flights from NYC to London on this travel site"

Tips​

  • Keep tasks focused and specific — describe exactly what data you need or what action should be taken
  • The agent works best with one clear goal per task (e.g., one search query, one form to fill, one page to read)
  • Provide relevant context in your message, since the agent does not have access to previous results