Google Ships 'Auto Browse' in Chrome, Letting Gemini Take Over Shopping, Scheduling, and Paperwork
Google Chrome now lets Gemini subscribers delegate routine web tasks to an AI agent that browses, clicks, and fills forms on their behalf — with a human-in-the-loop approval step that signals how Google plans to thread the autonomy needle.
Google officially launched auto browse for Gemini inside Chrome, a feature that lets the AI model navigate websites, complete forms, compare products, and handle scheduling on behalf of the user. The feature is available now to Google AI Pro and Ultra subscribers in the United States, as @googlechrome announced. It's designed, Google says, to "keep you in the loop and ask for your sign-off" before committing to actions like purchases or bookings — a deliberate human-in-the-loop architecture that distinguishes it from fully autonomous agent frameworks.
This is the clearest signal yet that Google views the browser itself as the primary surface for agentic AI. Rather than building a standalone agent app or requiring developers to integrate APIs, auto browse works inside Chrome — the world's most-used browser with roughly 65% market share. The strategic implication is significant: if Gemini can reliably handle web tasks inside Chrome, it becomes the default agent layer for billions of users without requiring any new software installation.
Get our free daily newsletter
Get this article free — plus the lead story every day — delivered to your inbox.
Want every article and the full archive? Upgrade anytime.
No spam. Unsubscribe anytime.