Google has introduced Gemini 2.5 Computer Use, a new AI model that can browse the web, navigate websites, and perform tasks like filling forms using a virtual browser. Unlike typical AI that relies on APIs, this model can interact directly with graphical interfaces, clicking, typing, and scrolling just like a human.
Users provide inputs such as screenshots, recent actions, and functions to guide the AI, which then performs the tasks. The AI works only within a browser environment, not the full computer.
It also performs well on mobile interfaces but isn’t optimized for desktop OS control. Developers can access it via Google AI Studio and Vertex AI.
