Google Integrates Computer‑Use Capability into Gemini 3.5 Flash
Google announced that the computer‑use capability, previously available only in the standalone Gemini 2.5 model, is now built into the Gemini 3.5 Flash model. The capability enables developers to build agents that can see, reason and take action across browser, mobile and desktop environments, improving performance for long‑horizon and enterprise automation tasks such as continuous software testing and knowledge work across professional applications. Google applied targeted adversarial training to mitigate prompt‑injection risks for agents operating in live settings and released two optional enterprise safeguard systems that require explicit user confirmation for sensitive actions and automatically stop tasks if an indirect prompt‑injection is detected. The company advises combining these features with secure sandboxing, human‑in‑the‑loop verification and strict access controls, as detailed in its best‑practice documentation. Developers and enterprises can access the computer‑use functionality through the Gemini API and the Gemini Enterprise Agent Platform, and Google provides a demo environment hosted by Browserbase for testing. The article was generated with AI support and reviewed by an editor; further information is available in the terms and conditions.