Google is rolling out computer use in the Gemini app for Mac, letting the assistant carry out multi-step tasks across local files, desktop apps and the web on your behalf. Why it matters: Gemini stops being only a chat window and starts doing the clicking, typing and form-filling itself — in a background window, while you keep using your own screen.
November 19, 2026 — Tested Intelligence
What happened?
Google announced the feature on November 19 in a post by Michael Friedman, Group Product Manager for the Gemini app. Starting today, you describe what you need, and Gemini handles the clicking, typing, menus and forms for you, working across your local files, desktop apps and websites to finish the job.
The work does not take over your machine. Gemini operates inside an isolated background window, with a live preview right in your chat. Your main screen and cursor remain free, so you can keep typing, designing or taking calls while it works.
What can it actually do?
Google’s examples are deliberately practical, focused on repetitive work that normally takes dozens of clicks:
- Creative workflows: batch color-grade photos in design software, or set up complex 3D scenes.
- Manual form entry: pull weights, dimensions and addresses out of local PDFs and fill in multi-box shipping quotes.
- Decks from live data: pull metrics and screenshots from live dashboards across multiple regions and build a presentation in Google Slides.
- Resale listings: analyze clothing photos from a local folder, research pricing, log item details and stage listings on resale platforms.
TechCrunch notes Google is arriving later than rivals here — OpenAI, Anthropic and Meta already offer agentic features in their desktop apps — and that the launch follows this week’s broader rollout of Gemini’s “Tasks” feature.
What are the controls, and who gets it?
Google says privacy and safety controls are built in: you choose which apps Gemini can access, you can watch every step live in the preview, you can pause at any time, and key actions need your approval before they happen.
Computer use is rolling out in English in the U.S. in the Gemini app for Mac, which you can download at gemini.google/mac. TechCrunch reports it requires a Google AI Plus, Pro or Ultra subscription. Google did not announce a date for expansion to other markets or platforms.
Why it matters
This is the desktop-agent race reaching the app most Mac users would actually install. The interesting design choice is the background window: an agent you have to watch full-screen is a demo, but an agent that works in parallel — visible, pausable and asking before key steps — is a tool you might leave running on the boring parts of your day. That is the “everything AI, tested” question here: not whether Gemini can click, but whether the approval and preview controls are good enough that people trust it with real files and real forms. The U.S.-only, paid-plan start means that test begins with a narrow group first.
Frequently asked questions
What is computer use in the Gemini app for Mac?
It is a new Gemini feature that lets the assistant navigate Mac apps and websites in the background to complete multi-step tasks — clicking, typing, using menus and filling forms — across local files, desktop apps and the web.
Does Gemini take over my screen?
No. Google says it works inside an isolated background window with a live preview in your chat, leaving your main screen and cursor free. You can pause it at any time and must approve key actions.
Who can use Gemini computer use on Mac?
It is rolling out in English in the U.S. in the Gemini app for Mac. TechCrunch reports it requires a Google AI Plus, Pro or Ultra subscription.
Sources: Google (official Gemini app blog, Nov 19, 2026), TechCrunch

