Google says the Gemini app for Mac can now carry out multi-step tasks across local files, desktop apps and the web, working in the background while you keep using the computer, according to its Nov. 19 announcement.
What the announcement says
- What it does: Gemini "handles the clicking, typing, menus, and forms for you" once you describe the task.
- How it runs: in an isolated background window with a live preview in the chat, so the main screen and cursor stay free.
- Examples Google lists: batch color-grading photos, filling shipping quotes from details in local PDFs, building a Slides deck from live dashboards, and listing clothing photos for resale.
- Controls: you choose which apps Gemini can access, watch each step live, pause at any time, and approve key actions before they happen.
Who gets it
- Mac: an Apple Silicon Mac running macOS Sequoia 15.0 or later.
- Plans: Google AI Plus, Pro and Ultra subscribers on personal Google accounts, ages 18 and up.
- Where: rolling out in English in the U.S. in the Gemini app for Mac.
- Get the app: Google points to gemini.google/mac.
What is not known
The post does not say whether Intel Macs will be supported, when other countries or languages will follow, or what limits apply to how many tasks you can run. It does not say whether the work runs on the Mac or in Google's cloud, and it names no macOS permissions the app will ask for. Google's examples are its own; we have not tested how reliably it completes them.
What this means for you
If you have a qualifying Mac and plan, you can try it through the Gemini app. Letting an AI operate your apps means it can open and change real files, so start with low-stakes tasks and use the approval step Google describes.
For more on the app, see Gemini 4 Neon in the Gemini app and Gemini on lower-memory Android Go phones.
What we checked
On Nov. 19 we read Google's post in full. All details above are Google's; we did not install or test the feature.



