Google Brings Computer Use to Gemini Mac App, Trailing Rivals
Gemini can now drive a Mac on a user’s behalf, after Google announced on Thursday that it has brought computer-use capabilities to its Gemini desktop application for macOS.
The AI can control native Mac apps and browse websites in the background, completing multi-step tasks that span local files, apps and the web — but the launch leaves Google trailing rivals such as OpenAI, Anthropic and Meta, which have already offered agentic features in their desktop applications for some time.
After a user instructs the AI what to do, the agent’s work appears in a live preview in the chat, while the screen and cursor stay free for the user to continue other work. As with other computer-use agents, users can pause, stop and approve Gemini’s actions before they happen.
Starting today in the U. S., Tasks in @GeminiApp can take even more off your plate. We're rolling out new ways to hand off your to-do list with a slate of new features. 🧵
Google suggested the feature could help with tedious workflows, such as filling out forms, repeating the same task across a batch of files, organizing files into folders based on specific criteria, or creating slideshows from files or information in online dashboards.
The rollout is limited for now: the feature is available initially in English in the U.S., requires the Gemini app for Mac, and needs a Google AI Plus, Pro or Ultra subscription. The company did not say when it would expand to other markets or platforms.
Google, founded in 1998 by American computer scientists Larry Page and Sergey Brin, began as a search engine company and has since grown into one of the world’s most valuable brands. It was reorganized in August 2015 as a subsidiary of its parent company, Alphabet Inc., with Sundar Pichai appointed CEO of Google that year.
The company’s push into AI agents like Gemini builds on a portfolio that already spans Gmail, Chrome, Android, YouTube and Workspace, with Google Search and YouTube ranking as the two most-visited websites worldwide. In 2025, advertising still generated 73% of Google’s revenues, making the race to commercialize Gemini’s agentic features a significant test of the company’s next source of growth.

Computer use is the latest in a run of agentic announcements from Google. Only this week, the company began the broader rollout of Gemini’s “Tasks,” an in-app feature that lets the AI sign into websites, make online purchases or book appointments.
Google has also recently admitted early testers to its revamped “CC” AI agent, announced in September, which is designed to help families stay organized across email, calendars, chats and tasks.