Google Chrome Auto Browse Brings Agentic AI to Android Phones
Google is launching auto browse in Chrome for Android in late June, letting Gemini handle multi-step web tasks like booking and shopping on your behalf.
Quick answer
Google is rolling out Gemini-powered auto browse in Chrome for Android in late June 2026. The feature lets you give Chrome a task — like booking an appointment or adding items to a shopping cart — and the AI handles the browsing, clicking, and form-filling for you. It requires a Google AI Pro ($20/month) or AI Ultra ($250/month) subscription and launches first on Pixel 10 and Galaxy S26 devices in the US.
Google Chrome Auto Browse Brings Agentic AI to Android Phones
Google is about to turn your phone’s browser into a personal assistant that can actually do things on the web for you.
Gemini in Chrome on Android, including the new auto browse feature, is launching in late June 2026. Auto browse lets you describe a task in plain language — “find me a parking spot near the airport for next Friday” or “add everything on this grocery list to my Woolworths cart” — and Chrome handles the rest. The AI navigates websites, clicks through menus, fills in forms, and completes multi-step tasks without you touching the screen.
How It Works
Auto browse is built on Gemini and runs as an agentic tool inside Chrome’s side panel. You type or speak what you want done, and the AI takes over the browser to complete the task across the open web. It can handle things like booking appointments, updating recurring orders, comparing products, and managing reservations.
Beyond task automation, Gemini in Chrome on Android also works as a general browsing assistant. It can summarise long articles, answer questions about page content, and connect with Google apps like Calendar, Keep, and Gmail to help you act on what you find.
The feature ships baked into Android rather than as a separate app or extension, which means it integrates deeply with the operating system.
What You Need
There are a few requirements to keep in mind. Auto browse is rolling out first in the US on devices running Android 12 or higher with at least 4GB of RAM and the language set to English-US. The first devices to get it are the Pixel 10 and Samsung Galaxy S26, with Google targeting 200 million devices by the end of 2026.
The bigger catch: it requires a paid subscription. You need either Google AI Pro at $20 per month or AI Ultra at $250 per month. The standard free Gemini experience in Chrome does not include auto browse.
What This Means for You
This is Google’s clearest move yet toward agentic AI — software that does not just answer questions but takes action. If you spend time on repetitive web tasks like filling out forms, comparing prices, or managing bookings, auto browse could save real time.
For now, it is US-only and subscription-locked, so most users outside the US will need to wait. But the direction is clear: AI assistants are moving from conversation to action, and your browser is the first place it is happening on mobile.
For more on how Google’s AI tools stack up, see our ChatGPT vs Claude vs Gemini comparison. If you are exploring AI-powered browser tools, check out our guide to the best AI Chrome extensions. And to stay on top of stories like this, join our newsletter.
Frequently asked questions
What is Chrome auto browse on Android?
Is Chrome auto browse free?
Which phones support Chrome auto browse?
What tasks can Chrome auto browse handle?
When does Chrome auto browse launch on Android?
Want to keep learning?
Explore our guided learning paths or try building something with AI right now.
More from News
Claude Cowork Expands to Mobile and Web
Claude Cowork Expands to Mobile and Web
Anthropic brings Claude Cowork to web and mobile, letting AI sessions run remotely and continue across devices without a laptop.
OpenAI Launches ChatGPT Work — an AI Agent for Your Job
OpenAI Launches ChatGPT Work — an AI Agent for Your Job
OpenAI debuts ChatGPT Work, an autonomous agent that completes tasks across your apps and delivers finished documents, spreadsheets, and slides.
SpaceXAI and Cursor Launch Grok 4.5 — A Coding-First AI Model
SpaceXAI and Cursor Launch Grok 4.5 — A Coding-First AI Model
SpaceXAI and Cursor publicly launch Grok 4.5, a joint AI model built for coding, legal, and finance tasks. Available today.
Enjoyed this article?
Subscribe for more AI insights delivered to your inbox every week.