Browser Automation

The agent controls the browser through a built-in tool set, so you can ask it to do things on the web, not just answer questions.

What it can do

• Navigate — open URLs, go back/forward.
• Read — get a page's text or Markdown, and an accessibility-tree snapshot of its structure.
• Interact — click, type, fill fields, scroll, and upload files. It can target elements by description or by a stable element id.
• Inspect — find elements, query the DOM, and read element details.
• Tabs — list, query, and switch between open tabs.
• Capture — take screenshots.
• Run JS — evaluate JavaScript on the page.
• Wait — wait for elements or conditions before continuing.

It also has a smart input engine that probes a target field, picks the best strategy to enter text, and verifies the result.

Examples

Open Hacker News and give me the titles of the top 5 stories.

Fill the signup form on this page with my details from my User profile, but stop
before submitting so I can review it.

Browser actions respect your permission setting. With Confirm before actions, you approve each step; with Auto-execute, the agent proceeds on its own.