Google is rolling out a practical new update for its Gemini assistant inside the Chrome browser: the "Select from screen" tool. This feature lets you quickly capture any text or image from the current tab and drop it straight into Gemini's prompt box. When activated, the page dims, and you simply draw a selection around the content—the image is then automatically pasted into the input field, making it easier to ask questions with visual context. The feature is being introduced gradually with Chrome 149; if you don't see it yet, restarting the browser should enable it.
At the same time, Google has announced that the Gemini 3.5 Flash model now comes with a built-in computer use tool. Developers can call this capability through the Gemini API, allowing the model to control desktop environments just like a human would. For example, 3.5 Flash can "open the Gemini app and return a categorized list of features," enabling it to analyze and interact with on-screen elements. This advancement expands AI's potential in areas like automated office tasks and smart testing.
