Google launched 'Chrome Auto Browse,' an agentic AI feature powered by the Gemini 3 model. Integrated via a persistent side panel, the AI autonomously handles multi-step web tasks like online shopping or filling out complex forms.
The AI performs actions including scrolling, clicking, and text entry directly on the user's device. Users must approve sensitive steps, such as completing a purchase, to ensure control.
Initially, the functionality is available in the US. It targets AI Pro and Ultra subscribers.