Gemini on Mac Can Now Use Your Computer to Finish Tasks
Google is adding computer use to the Gemini app for Mac, letting the assistant click, type and fill out forms across desktop apps and websites in a background window. It starts in English in the U.S. for paying subscribers.
Published 3 min read

Google's Gemini app for Mac can now do more than answer questions about what is on your screen. As of November 19, 2026, it can take over repetitive chores itself, moving through desktop apps, local files and websites to finish multistep tasks while you keep working on something else.
In its announcement, Google describes the idea simply: "Just describe what you need, and Gemini handles the clicking, typing, menus, and forms for you." The company pitches the feature at work that would otherwise take dozens of clicks.
How Gemini computer use works on a Mac
Instead of taking control of your actual desktop, Gemini runs the task in an isolated window in the background. A live preview appears inside the Gemini chat, so you can watch each step as it happens, while your own screen and cursor stay free for other work.
Google says users stay in charge throughout. You choose which apps Gemini is allowed to access, you can pause the task at any time, and Gemini asks you to approve key actions before it carries them out.

What Google says it can do
Google gives a handful of examples. Gemini can batch color-grade photos in design software or set up complex 3D scenes. It can pull weights, dimensions and addresses out of local PDF files and use them to fill in multi-box shipping quote forms. It can gather metrics and screenshots from live dashboards across regions and turn them into a deck in Google Slides.
Another example covers online selling: Gemini can look through photos of clothing in a local folder, research prices, log the details of each item and stage listings on resale platforms. The common thread is work that is tedious rather than difficult.
Who can use it, and what you need
The rollout is narrow for now. Computer use is available only in English and only in the U.S. It requires a Mac with Apple Silicon running macOS Sequoia 15.0 or later, a personal Google account for someone 18 or older, and a Google AI Plus, Pro or Ultra subscription. Google points people to gemini.google/mac to download the app.
That means readers outside the U.S., including in Türkiye, cannot use the feature yet, even with a paid plan. Google has not said when it will reach other countries or languages.
The Mac app itself is only a few months old. Google launched the native Gemini app for macOS in April 2026, with a keyboard shortcut and screen sharing. This update is its first step from an assistant that looks at your screen to one that acts on it. Rivals have offered similar agent features in their own desktop apps for some time, so Google is arriving a little late to this particular race.
If you are weighing whether a higher Gemini plan is worth it, we recently looked at how Google AI Ultra now includes ad-free YouTube for the whole household. You can also read about Gemini 4 Neon, Google's newest model.