Google has added a “computer use” capability to its Gemini app for macOS, allowing the assistant to carry out multi-step tasks across a user’s local files, desktop applications, and the web. According to Google, the feature is aimed at speeding up workflows and could help with tasks such as filling in forms, creating presentations, and listing items for sale.

Users control which applications Gemini is permitted to access. The company says the assistant runs in its own background window and shows a live preview in the chat, so users can follow along as it performs actions. The feature is rolling out now in English for users in the US.

Why it matters

Extending Gemini beyond chat into direct control of a Mac moves the assistant toward agentic, task-completing behavior. The user-controlled app access and live preview are presented as ways to keep users aware of and in control of what the assistant does.

Who should care

Mac users in the US who want to automate repetitive, multi-step tasks are the immediate audience, along with those tracking how AI assistants gain hands-on control of personal devices.