
Gemini app for Mac adds computer use to control desktop apps
Google is upgrading the Gemini app on Mac with computer use capabilities that can work across local desktop applications and the web.
via 9to5GoogleReported by 3 outlets
The story so far
AI summary of the reporting below · Updated · How we work
Google is introducing computer use capabilities to its Gemini app on macOS, allowing the artificial intelligence to click, type, and complete multi-step tasks across local programs and websites. The tool is launching initially in US English for subscribers of Google AI Plus, Pro, and Ultra tiers. [1][2][3]
The agent operates in an isolated background window with a live preview inside the chat interface, leaving the user's primary screen and mouse cursor free to work uninterrupted. Users can choose which applications Gemini accesses, stop actions with a single click, and confirm sensitive operations, with Google stating the software will pause for logins and payment steps. [1][2][3]
According to TechCrunch, Google arrives late to desktop computer use compared to rivals such as OpenAI, Anthropic, and Meta, which have already deployed agentic features in desktop apps. The rollout expands on Gemini's existing Tasks tool, enabling workflows like filling forms, building presentations from dashboards, and connecting to software such as Blender and Autodesk Fusion. [1][3]

Google is upgrading the Gemini app on Mac with computer use capabilities that can work across local desktop applications and the web.
via 9to5Google
Google's latest update to Gemini brings an AI agent to the Mac that can organize files, fill out forms, and tackle multistep workflows.
via TechCrunch
Google's Gemini app for macOS now has computer use, meaning it can help you "get multi-step tasks done across your local files, desktop apps, and the web," the company says. Google suggests the feature might be useful for things like speeding up workflows, filling in forms, making presentations, and listing items for sale. Users will…
via The Verge