Source: techcrunch.com/2026/11/19/google-gives-gemini-the-ability-to-use-your-mac-for-you
Google announced that Gemini's desktop application on macOS can now use the computer on a user's behalf, navigating native Mac apps and browsing websites in the background. The tasks can span local files, apps and the web. Users watch the agent work in a live preview inside their chat, while their screen and cursor stay free for other work.
Users can pause, stop and approve Gemini's actions before they happen. Google suggests uses such as filling out forms, repeating a task across a batch of files, sorting files into folders by set criteria and building slideshows from files or online dashboards.
Google is somewhat late here, since OpenAI, Anthropic and Meta already offer agentic features in their desktop apps. The announcement came the same week Google broadened the rollout of Gemini's "Tasks" feature. The company did not say when the feature would reach other markets or platforms.
Why it matters if you build agents
Agent builders who target Mac users now have a consumer-side example of an assistant that drives native apps and websites, with per-action approval built in. The feature is limited to the Gemini Mac app and a paid Google AI subscription, so it does not give developers an API to call. Teams planning around desktop automation should watch for when Google expands it beyond English, the U.S. and macOS.
Get stories like this every weekday
One short email with the day's agent tooling news.