Google adds computer use to the Gemini app for Mac, letting it click, type and fill forms across apps

The agent works in an isolated background window with a live preview; users pick which apps it can touch and approve key actions. It is rolling out in English in the US.
Why it matters
Desktop agents that operate a computer directly are a new front among the big labs, and this puts Google's version on the Mac rather than only in a browser. Google says Gemini handles the clicking, typing, menus and forms while the user's own screen and cursor stay free. Safety controls are central to the design: users choose which apps Gemini can access, watch every step, can pause at any time and approve key actions first. What to watch: how widely it rolls out beyond English in the US.
Key facts
- Feature: computer use in the Gemini app for Mac
- Works across local files, desktop apps and the web
- Runs in an isolated background window with live preview
- Users choose accessible apps and approve key actions
- Availability: rolling out in English in the US
- Announced 19 November 2026