Introducing computer use in Gemini 3.5 Flash

Google has updated its Gemini 3.5 Flash model with the ability to interact directly with desktop computers by observing screens, moving cursors, and clicking buttons. This capability allows the AI to perform complex, multi-step workflows like data entry or software navigation autonomously through a standard user interface. By moving beyond text and code generation to acting as an agent within existing desktop environments, the tool signals a significant shift toward AI systems that can execute tasks across various installed applications on behalf of users.