The computer use feature is now a built-in tool in Gemini 3.5 Flash, enabling developers to create agents that can interact across platforms. Previously available only in the standalone Gemini 2.5 model, this feature is now natively integrated into the main model. Gemini excels at function calling and using built-in tools like Search and Maps grounding, and with the built-in computer use capability, developers can now 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.
Developers and enterprises can start using computer use in 3.5 Flash via the Gemini API and Gemini Enterprise Agent Platform. 3.5 Flash uses computer use to analyze the Gemini app and return a categorized list of features. It also audits its own documentation for accessibility issues.
To mitigate some of the prompt injection risks for agents operating in live environments, targeted adversarial training for computer use has been implemented in Gemini 3.5 Flash. Additionally, two optional enterprise safeguard systems are being released that allow enterprises to:
- Require explicit user confirmation for sensitive or irreversible actions.
- Automatically stop tasks if an indirect prompt injection is identified.
Taking a “defense-in-depth” approach, we encourage developers to combine these features with secure sandboxing, human-in-the-loop verification, and strict access controls. More information on safety measures can be found in our best practices documentation.
We are already seeing customers drive value with computer use. Here’s what some of them have to say:
To start building with computer use today:
- Try it now: Test the capabilities in a demo environment hosted by Browserbase.
- Start building: Dive into our reference implementation and documentation via Gemini API and Gemini Enterprise Agent Platform.
Blogger's Review: The integration of the computer use feature in Gemini 3.5 Flash significantly enhances the capability to build intelligent agents across multiple platforms, improving user experience and providing robust support for enterprise automation. The security measures also reflect a commitment to user data protection, making it a noteworthy development for developers to explore and implement.