Google integrated a computer use tool into its Gemini 3.5 Flash model. This feature allows developers to build AI agents that interact with desktop, mobile, and web applications.
The AI observes screens to click, type, and navigate like a human user. This capability automates complex workflows without requiring specific application integrations.
Google released the tool through the Gemini API and Gemini Enterprise Agent Platform. The enhancement targets enterprise tasks such as software testing and multi-application data entry. The update also includes new safety features to prevent misuse.