Google adds computer-use agent to Gemini app for macOS
Google has rolled out a 'computer use' feature in its Gemini app for Mac that lets the assistant perform multi-step tasks across local files, desktop apps, and the web, such as filling forms or creating presentations. Users choose which apps Gemini can access, and can watch its progress through a live preview window in the chat. The feature is launching now in English for users in the US.
GoKawiil's interpretation of the reporting above, not reported fact.
The rollout comes just as Apple is introducing new 'full disk access' restrictions in the macOS 27.3 beta aimed at limiting risks from AI agents operating across a user's system, suggesting growing industry concern over the security implications of agentic AI tools. The timing could put Google's feature under extra scrutiny from Apple's upcoming permission controls, though it's unclear how the two will interact once Apple's changes roll out fully.
- Gemini for Mac now has a computer-use agent that can handle multi-step tasks across apps and files.
- Users control app permissions and can monitor Gemini's actions via a live preview window.
- The launch coincides with Apple's new full disk access restrictions aimed at AI agents with computer use.
Apple Mac mini (M4) — If you're ready to let Gemini take the wheel on your desktop, a snappy Mac mini gives you the horsepower to run AI-driven automation across apps smoothly. Its compact design and efficient performance make it a great hub for testing out new computer-use features like this one.
See Apple Mac mini (M4) on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: theverge.com — Jay Peters, 2026-11-19
Published there as: “Gemini on Mac can now use your computer”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.