Illustration of a workflow across computer apps, not a product screenshot
Fibona / illustrative artwork

Gemini Can Now Work Across Mac Apps, Starting in the US

Google announced computer use for its Gemini Mac app on 19 November. The feature can carry out multi-step tasks described by users across local files, desktop apps and websites. Initial rollout is in English in the United States. Google did not announce a date for Türkiye.

Gemini works in a separate window

Google says Gemini can navigate menus, click, type and fill in forms in an isolated background window, with a live preview in chat. The main screen and cursor remain available to the user. Users can choose which apps to grant access to, pause activity and approve key actions. The announcement does not say that every click requires separate approval.

Photo work, 3D scenes and documents

Google’s examples include batch colour grading in design software, setting up 3D scenes, extracting dimensions and weights from local PDFs to fill forms, turning dashboard data into slides, and staging resale listings. A published Blender demo shows modelling from a sketch. These are vendor examples rather than guarantees for every app or workflow.

Who can use the feature?

Computer use requires an Apple Silicon Mac running macOS Sequoia 15.0 or later, a personal Google Account for someone aged at least 18, and Google AI Plus, Pro or Ultra. Downloading the Mac app does not establish eligibility for this rollout. This is distinct from the six-country free expansion of Gemini Tasks previously covered by Fibona.

Source: Google’s 19 November announcement. Fibona’s Gemini Tasks coverage.

Image

Subscribe for Updates