Google brings Gemini 'computer use' to Mac to handle multi-step tasks, starting in the US

Google says the Gemini app for Mac can now handle multi-step tasks across local files, desktop apps and websites with its new 'computer use' feature, rolling out first in English in the US.
Google announced on Thursday (19 November) that its Gemini app for Mac is gaining a 'computer use' feature that can complete multi-step tasks across local files, desktop apps and websites, such as batch-processing photos, filling in forms or listing items on resale platforms.
Pictured: the Gemini interface on a MacBook, in a file photo. (Image: ZDNet Japan)
Handling repetitive work
According to Google, users simply describe what they need in natural language and Gemini handles the clicking, typing, menus and forms. Google's examples include batch colour-grading photos, setting up complex 3D scenes in design software, extracting weights and dimensions from local PDFs to fill in multi-field shipping quotes, pulling data from live dashboards into a presentation, or analysing clothing photos in a local folder, researching prices and staging listings on resale platforms.
Works in the background
Gemini works inside an isolated background window and shows a live preview in the chat, so it does not take over the user's screen or cursor and the user can keep working normally. It can only use apps and programs the user has given it access to, and it asks for approval before key actions.
US and English only for now
At launch the feature is available only in English in the United States, for personal Google accounts held by users aged 18 or older, with a Google AI Plus, Pro or Ultra subscription. It requires an Apple silicon Mac running macOS Sequoia 15.0 or later. Google said the feature is rolling out gradually and has not announced a timetable for other countries or platforms.
Safety note
Google's help page warns that computer use may reach logged-in sessions, visible authentication codes and actions that change files, and that content on screen can try to manipulate the agent across applications. When it is first enabled, macOS may prompt for Accessibility and screen-recording permissions.
N環球 
💬 Comments
No comments yet. Be the first!