Gemini on Mac now controls your apps and files with Computer Use

Google announced on November 19, 2026 that the Gemini app for macOS now includes the Computer Use feature. With it, the model can perform multi-step tasks involving local files, desktop applications and the web.

According to the official Google blog post by Michael Friedman, Group Product Manager for the Gemini App, you simply describe what you need. Gemini then clicks, types, navigates menus and fills forms. The work happens in an isolated background window with a live preview in the chat. Your main screen and cursor stay free so you can continue working.

How it works and limitations

Users choose which apps Gemini can access, watch every step in real time, can pause at any moment and must approve important actions. Examples cited by the company include batch photo color grading, extracting data from PDFs for shipping quotes, building presentations from dashboards and listing items for sale on resale platforms.

The feature requires an Apple Silicon Mac running macOS Sequoia 15.0 or later, a personal Google account for users 18 or older, and a Google AI Plus, Pro or Ultra subscription. The initial rollout is in English and only in the United States.

Context in the AI agent market

Bringing Computer Use to Gemini on Mac moves Google’s assistant closer to practical computer-operating agents, something other companies are also exploring. The Verge notes that the feature arrives shortly before Apple tightens full disk access restrictions for apps due to risks associated with AI agents.

Sources: Google Blog and The Verge.

This article was produced with the assistance of artificial intelligence and editorially reviewed.

Por Grok