AI for Business

Gemini Can Now Operate Your Mac, but Google Arrives Late to the Agent Race

Google announced Thursday that its Gemini desktop app for macOS can now use a computer on the user's behalf, moving through native Mac apps and browsing websites in the background.

Share:

Google announced Thursday that its Gemini desktop app for macOS can now use a computer on the user's behalf, moving through native Mac apps and browsing websites in the background.

The launch puts Google behind rivals OpenAI, Anthropic and Meta, which have offered agentic features in their desktop apps for some time. Google only this week announced a wider rollout of Gemini's "Tasks," which lets the AI help users sign into websites, make purchases or book appointments, and it recently began admitting early testers to its revamped "CC" agent, unveiled in September to help families stay organized across email, calendars, chats and tasks.

With computer use, users tell Gemini what they want done and watch the agent work in a live preview in their chat while their screen and cursor stay free for other work. Users can pause, stop and approve actions before they happen. Google points to tedious jobs like filling out forms, repeating tasks across batches of files, sorting files into folders by set criteria and building slideshows from files or online dashboards.

The feature starts in English in the U.S. and requires the Mac Gemini app plus a Google AI Plus, Pro or Ultra subscription. Google did not say when it would reach other markets or platforms.

Source: TechCrunch

Ready to Modernize Your Business?

Get your AI automation roadmap in minutes, not months.

Analyze Your Workflows →