Google brings computer-use capability to Gemini for Mac
Google says Gemini for Mac can now navigate apps and complete multistep tasks while users work on other things.
Google has shipped a computer-use capability to Gemini for Mac. It lets the AI navigate apps on the Mac and complete multistep tasks while the user works on other things. Google's own description, as summarized in a short AI news roundup, centers on that background operation: the assistant carries out a sequence of steps in the apps on the computer while the person does something else.
The available material is thin. It gives no detail on which apps the feature supports, how a user starts a task, what permissions it requires, or how it handles a step that goes wrong.
What changed
Gemini for Mac gains a computer-use capability that navigates apps and completes multistep tasks while the user works on other things.
Type: New capability · Applies to: Gemini for Mac
Why it matters
Desktop agents that operate apps on a Mac raise new questions about data access and oversight for employees using Gemini on work machines.
What you can do
Decide whether staff may enable computer-use features on work Macs under your existing app access and data policies.
How the story developed
Rollout is now reported for U.S. users in English, with Gemini working in an isolated background window and asking approval for sensitive actions.
Original source
We have no link to the original source for this story yet.
Further reporting
Where we saw it
Forward Future (Matthew Berman), The AI Report
AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it. How it works