Gemini 3.5 Flash gets computer use, Gemini in Chrome adds screen select

Gemini in Chrome is rolling out a practical new tool called “Select from screen” that makes it easier to feed visual context into your prompts. Located at the bottom of the plus menu, this feature highlights your active tab and lets you choose any text or image to ask Gemini about. Once selected, that content is instantly added to the prompt box. This update arrives as part of Chrome 149, and if the option isn’t visible yet, a simple browser restart should bring it in.

Meanwhile, Google has also announced a significant upgrade for developers: the Gemini 3.5 Flash model now includes native computer use capabilities. This built-in tool replaces the standalone Gemini 2.5 Computer Use model and joins existing grounding features for Search and Maps. Developers can leverage this integration to “build custom agents that can see, reason and take action across browser, mobile and desktop environments.”

The new functionality is designed to handle complex, long-running tasks with better performance, making it suitable for “continuous software testing and knowledge work across professional applications.” In one demonstration, 3.5 Flash used computer use to “analyze the Gemini app and return a categorized list of features.”

On the safety side, enterprise customers gain control over sensitive actions. They can require explicit user confirmation for irreversible steps and automatically halt tasks if an indirect prompt injection is detected. Gemini 3.5 Flash is available today through the Gemini API.