Gemini and Apple IntelligenceGoogle announced computer use for its Gemini Mac app on November 19, expanding the assistant’s ability to complete multi-step tasks across local files, desktop apps, and websites. The feature builds on the company’s existing Mac app by letting Gemini perform actions instead of simply helping users prepare them.
Users can describe a task, and Gemini will navigate menus, click buttons, enter information, and move between apps to finish it. Google suggests using the feature to batch-edit photographs or extract information from PDFs to complete shipping forms.
Gemini works in a separate virtual screen, leaving the main display and cursor available for other work. A live preview shows what the agent is doing, and users can stop the task at any time.