ThinkPatternGet the app
Story
TECHNOLOGY · NOV 19, 2026

Google Launches Gemini Computer Use Feature for Mac

Google released a computer use feature for Gemini on macOS that allows the AI to automate multi-step tasks across desktop apps and the web.

Google launched a computer use feature for its Gemini desktop application on macOS, granting the AI agentic control to perform multi-step tasks on a user's behalf. By using the @Computer use command, the AI can click buttons, type, navigate menus, and fill out forms across local files, native Mac applications, and the web.

To prevent interruption of the user's primary workflow, Gemini operates within an isolated background window. This allows users to continue working on their device while the AI handles tasks such as batch color-grading photos, creating 3D scenes in Blender, extracting data from PDFs, or preparing Google Slides presentations. To mitigate risks of AI errors, Google implemented granular access controls, live previews in the chat window, and a system that creates temporary backup copies of any modified files.

The feature is currently available in English for users aged 18 and older in the United States who have a personal Google account and a subscription to AI Plus, Pro, or Ultra plans. Technical requirements include an Apple Silicon Mac running macOS Sequoia 15 or later. This rollout follows similar releases from OpenAI, Anthropic, and Meta, and arrives as Apple Inc. prepares new restrictions for apps requesting full disk access to address AI agent security risks.


Reported across 17 outlets
Actors
GoogleApple Inc.

Keep reading in the app

The full story and every source, free in the app.