Browser Control & the Live Browser

The Browser Control ability lets an agent drive a real web browser — navigate,
click, type, read the rendered page — not just fetch text. It also lets the agent make
direct web requests.

The standout feature is the live Browser panel: you can watch the browser the
agent is driving, streamed into the app, and take over with your own mouse and
keyboard at any time. It works without a visible desktop window, so it runs fine on a
headless cloud server. When an agent starts browsing, it can even switch your view to
the Browser tab automatically (see App Control (Agent Drives Your Screen)).

This pairs naturally with Web Access: search to
find a page, then browse it to act on it.

Related: Abilities.