Google’s Antigravity enables browser control: AI can autonomously open web pages, test code, and perform parallel multi-tasking.

Beating AI Express: Google is gradually rolling out browser control capabilities to Antigravity users. AI can now directly operate the app’s built-in browser, including opening web pages, clicking buttons, filling out forms, and viewing console errors and network requests. Antigravity previously supported controlling external Chrome via the `/browser` command, but this update integrates browser operations directly into the app, eliminating the need for extra configuration. For example, after an AI generates a website, it can open the page to test itself, spot issues like non-functional buttons or layout problems, then modify the code and recheck. The new feature also supports multiple browser Agents working in parallel, each with independent tabs to research information or test different pages simultaneously. Users can view the AI’s mouse operations in real time and take control at any moment. Google has added access controls: the browser uses a separate login environment, pausing when encountering login or CAPTCHA prompts to let users handle them manually. AI-initiated file downloads are also subject to approval rules, blocking unauthorized downloads of programs or scripts. Currently, the feature supports macOS, Windows, and Linux, requiring Antigravity App version 2.30.0 or later. It is gradually rolling out to free, Plus, Pro, and Ultra individual accounts; enterprise accounts and remote agents do not yet support the new built-in browser control function.