Google has rolled out a computer-use feature for its Gemini AI app on Mac, allowing the assistant to automate multi-step tasks across local files, desktop apps, and websites. It works in a background window, so users can continue working while Gemini fills out forms, navigates menus, and transfers data between documents.
For example, Gemini can extract information from PDFs and enter it into an online shipping quote form, or create a Google Slides presentation using data from multiple dashboards.
The feature is available in the United States to paying subscribers of Google's AI Plus, Pro, and Ultra plans. It requires a Mac with Apple Silicon. Google says users must grant Gemini permission to access specific apps and approve key actions.
The launch adds to competition among AI desktop assistants, including Microsoft's Copilot and agents from OpenAI.