Google has released an AI agent based on the new Gemini 2.5 Computer Use model, which, in turn, is based on Gemini 2.5 Pro.
The agent can work anywhere inside the browser and independently perform actions on sites: enter URLs, fill in forms, drag and drop files, select parameters in pop-up menus and checklists. This allows the agent to independently solve most tasks on sites without distracting the user.
To activate an action, use the Gemini 2.5 computer, taking a screenshot of the screen, analyzing it, the action history and the task. The neural network then generates a command, which the agent executes, and then repeats the cycle.
In the demo video, the AI agent itself finds information about a pet in Google sheets, and then records all its data in a CRM system for a doctor’s appointment.
Google says its AI agent outperforms competitors in many tests.
You can test using Gemini 2.5 on your computer on the Browserbase website. Developers can get the API from Google AI Studio and Vertex AI. [Google]
Source: Iphones RU
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
