Introducing computer use in Gemini 3.5 Flash

Google announced that computer use is now a built-in tool supported in Gemini 3.5 Flash, delivering its best performance yet for agentic computer use tasks. Previously available only as a standalone Gemini 2.5 computer use model, the capability is now integrated natively in the main Gemini Flash model. The company said Gemini already excels at function calling and using built-in tools like Search and Maps grounding. With built-in computer use capability, developers can use 3.5 Flash to reliably build custom agents that can see, reason and take action across browser, mobile and desktop environments. This unlocks improved performance for long-horizon and enterprise automation tasks like continuous software testing and knowledge work across professional applications. To mitigate prompt injection risks for agents operating in live environments, Google uses targeted adversarial training for computer use in Gemini 3.5 Flash. The company is also releasing two optional enterprise safeguard systems that enable enterprises to require explicit user confirmation for sensitive or irreversible actions and automatically stop tasks if an indirect prompt injection is identified. Taking a defense-in-depth approach, Google encourages developers to combine these features with secure sandboxing, human-in-the-loop verification and strict access controls. Customers are already driving value with computer use. Developers can test capabilities in a demo environment hosted by Browserbase or access reference implementation and documentation via Gemini API and Gemini Enterprise Agent Platform.