Google continues preparing its Gemini desktop app to close the gap with competitors. The company has finally started working on computer-use functionality, which would allow Gemini to control other apps, access files in selected folders, and perform tasks similar to those currently supported by Claude and ChatGPT.
Traces of the feature have appeared in the app’s settings, suggesting Google may have begun testing it with a limited group of trusted testers. Computer use will likely arrive alongside a slightly updated Gemini Spark interface. Instead of being activated through a toggle in the navigation bar, it is expected to appear as a “Task” option in the prompt-bar selector, similar to the existing controls for generating images and videos.
While Gemini is operating the computer, users will be able to follow its actions through a mini-view of the active screen. The app is also expected to include practical controls, such as preventing the device from going to sleep while a task is running. Another notable addition is an optional safety feature that automatically backs up selected folders to Google Drive before Gemini begins a task. This could provide a useful safety net for people who do not use Git or another version-control system.
However, the feature is also a double-edged sword. Its existence suggests Gemini could potentially make unwanted changes to a workspace, while the backup process raises practical questions. If a selected folder contains hundreds of gigabytes, up it to Google Drive could take a long time and consume substantial storage before the task can even begin.
Computer use appears to be Google’s next major frontier for Gemini. Its value will depend not only on what the agent can do, but also on how Google handles permissions, recovery, large folders, and user oversight.