Gemini 3.5 Flash Gets Built-In Computer Use

Google has integrated computer use directly into Gemini 3.5 Flash, enabling developers to build agents that can see, reason, and act across browser, mobile, and desktop environments. Previously only available as a standalone model, the feature now supports long-horizon tasks like software testing and enterprise automation. To address security risks, Google has applied adversarial training and introduced optional enterprise safeguards, including user confirmation prompts for sensitive actions and automatic task halting upon detecting prompt injection attacks. Developers can access the feature via the Gemini API and Gemini Enterprise Agent Platform.