Gemini Computer Use Arrives on Mac to Run Apps for You
By Ganesh Karki
Key facts
- Section
- Tech & AI
- Country
- Global
- Published
- 22 Nov 2026
Google announced on Thursday 19 November that Gemini computer use is coming to the Gemini app for Mac, letting the AI assistant click through menus, type into forms and complete multi-step tasks across local files, desktop apps and the web on behalf of the user. Gemini works inside an isolated background window with a live preview in the chat, so the main screen and cursor stay free while it works.
| Organisation |
What Gemini computer use on Mac does
Starting on 19 November, computer use in the Gemini app for Mac helps with multi-step tasks across local files, desktop apps and the web. Google says users only need to describe what they want, and Gemini handles the clicking, typing, menus and forms. Suggested uses include batch colour-grading photos in design software, setting up complex 3D scenes, and extracting weights, dimensions and addresses from local PDFs to fill out multi-box shipping quotes. The feature is initially available in English in the United States and requires the Gemini app for Mac and a Google AI Plus, Pro or Ultra subscription. It runs on Apple Silicon Macs with macOS Sequoia 15.0 or later, for users aged 18 and over. Readers can also read our report on Google Gemini 4 Neon launch, and more AI news in our Tech section.
What it means
Computer use moves Gemini from answering questions in a chat window to taking actions directly on the computer, the same agentic direction rivals are pursuing with their own desktop agents. Because the work happens in a separate background window, users can keep typing, designing or taking calls without interruption. The paid-subscription gate also shows Google treating desktop automation as a premium feature rather than a free part of the Gemini app.
What the sources do not say
Google has not said when computer use will reach Windows, other countries or languages, or the free tier of Gemini. The sources do not give accuracy figures or limits on what Gemini can safely do unsupervised, and they do not say how long the live preview history is kept. One report says Gemini makes temporary backup copies of files it touches, but Google own announcement quoted in the coverage does not confirm that detail.
Sources: TechCrunch, the 19 November announcement, the United States and paid-subscription limits; BetaNews, how computer use works across files, apps and the web and the isolated background window; Phandroid, the rollout and the example tasks Google suggests.
Frequently asked questions
Who can use Gemini computer use on Mac?
Does Gemini take over my screen?
Is computer use available on Windows?
Sources and references
Information checked: 22 November 2026
Related stories
Science Corporation Raises $400M for Vision Chip PRIMA
Science Corporation raised $400 million in Series D funding to expand its PRIMA vision-restoration system in Europe and prepare a US launch.
22 November 2026US Smartphone Shipments Fall 9% as Apple Hits 57% Share
US smartphone shipments fell 9% in Q3 2026, as memory constraints hit low-end Android. Apple was the only maker to grow, reaching a 57% share.
22 November 2026Claude Solves Two Black Hole Physics Problems, Anthropic Says
Claude black hole physics results solved two open problems, Anthropic said on 17 November, finishing a 2003 calculation and finding an exact limit.
22 November 2026OpenAI GPT-Live-1.1 Cuts Idle Voice Agent Costs by 60%
OpenAI GPT-Live-1.1 is now in the API with a standby mode that bills idle WebRTC time at $0.02 a minute, 60% less than the $0.05 active rate for voice agents.