Live updates
Google's Gemini app for Mac can now use your computer, clicking and typing in a background window
First seen on X 33 hours ago@GeminiApp ♥ 69924 views
Google has added computer use to the Gemini app for Mac. Describe a task and Gemini works through Mac apps, local files and websites on its own, picking menus, clicking buttons and filling in forms. It runs in a separate background window with a live preview in the chat, so the user's own screen and cursor stay free.
The feature is rolling out in English in the U.S. to Google AI Plus, Pro and Ultra subscribers, according to Google's blog and the Gemini app account on Nov 19, and needs an Apple silicon Mac on macOS Sequoia 15 or later. Google hasn't said when it will reach other countries. Its suggested uses include batch color-grading photos, pulling weights, dimensions and addresses from PDFs into shipping quote forms, and turning dashboard metrics into a Google Slides deck. Users choose which apps Gemini can touch and approve key actions before they happen. TechCrunch called Google "a little late to the game," since OpenAI, Anthropic and Meta already offer agent features in their desktop apps. AppleInsider ran the headline "you still shouldn't let it," pointing to Google's own support docs, which warn that Gemini can reach signed-in app sessions and multifactor codes on screen, and that hidden instructions in one app could steer its actions in another. Apple previewed tighter "full disk access" controls aimed at AI agents in this week's macOS 27.3 beta.
Comments 0
Select a sentence in the story (long-press on phones) to comment on it.
“With computer use in the Gemini app for Mac, you can now hand off tasks across your folders, apps, and the web, while your screen and cursor stay yours.”

