Google has added computer-use capabilities to the Gemini app for Mac, allowing its AI assistant to carry out multi-step tasks across local files, desktop applications and websites.
The company announced the feature in a November 19 blog post and said it is designed to handle repetitive workflows that would otherwise require users to move between apps and complete a series of manual actions.
Users can describe what they want done, and Gemini will click through menus, type information and fill out forms. The agent runs in an isolated background window, with a live preview shown in the chat. The main screen and cursor remain available for other work. Google gave examples including batch color-grading photos, setting up 3D scenes, extracting details from local PDFs to complete shipping quotes, and creating presentations from live dashboards.
Users choose which apps Gemini can access, watch its progress, pause a task and approve key actions before they happen. That gives the feature access to parts of a Mac workflow that a conventional chatbot cannot handle directly. It also extends Gemini’s existing file tools, including its ability to create and download documents and spreadsheets.
Google said computer use is initially rolling out in English in the United States through the Gemini app for Mac. It requires an Apple Silicon Mac running macOS Sequoia 15.0 or later, a personal Google Account for someone aged 18 or older, and a Google AI Plus, Pro or Ultra subscription. The announcement did not give a timetable for availability in other countries or on other platforms.



