Chrome auto browse lets Gemini in Chrome carry out multi-step tasks on websites for you, such as comparing products and adding them to a cart, finding accommodation or booking a restaurant. Click Ask Gemini, describe the task, check Gemini's plan and click Start Task. You need to be 18 or over and in the US, with Google AI Pro or Ultra on a personal account.
Gemini in Chrome answers questions about the page you're on. Auto browse goes further: Gemini clicks, scrolls and fills in pages while you watch. Here's who can use it, how to run and control a task, and the risks Google itself flags.
Who can use auto browse
The rules are much stricter than for Gemini in Chrome itself, which Google opens to people aged 13 and over in supported regions. For auto browse on a computer, Google's help page says you need to:
- Be 18 or over and in the US.
- Be eligible for and opted in to Gemini in Chrome, on the latest version of Chrome.
- Set your device's language to English.
- Have Google AI Pro or Ultra on your personal account, and sign in to Chrome with that personal Google Account.
- Set Safe Browsing to Enhanced or Standard protection.
It doesn't work in Incognito mode or with a school account, and on a work account your administrator has to enable it. Google is releasing it gradually, so it may not show up yet even if you qualify. It isn't available in Live chats or in Gemini in Chrome on iPhone or iPad.
How to run a task
- Open Chrome and click Ask Gemini at the top of the browser.
- Describe the task in the text box.
- Review the plan: check Gemini understood your request, the page and your personal details correctly.
- Click Start Task. The tab Gemini is using shows an auto browse icon.
- When Gemini needs you, a notification appears at the top of the browser. Click Check your task.
Google notes that Gemini chooses which sites to use, and it may share your personal information with those sites to complete the task.
Taking over, resuming and stopping
| You want to | Do this |
|---|---|
| Go to the tab Gemini is using | Click Switch tabs next to the task in the chat |
| Do a step yourself | Click Take over task on the task tab |
| Hand it back | Click Resume or Give back task in Gemini in Chrome |
| Stop the task | Click Stop in Gemini in Chrome, or close the task tab |
| Turn auto browse off on this device | Settings, AI innovations, Gemini in Chrome |
Some steps always need you: confirming sensitive actions, doing steps only you should do, and giving permission for Gemini to sign in to a site. The first time Gemini browses on a device, Chrome asks permission to connect auto browse to Gemini, and after that every browsing task asks for confirmation first.
Local browser or remote browser
Auto browse can use the Chrome on your desktop, with access to every site you're signed into, or a separate remote browser in the cloud. With your local browser you need to keep your device and Chrome awake; if you close the laptop before the task's done, Gemini might switch to the remote browser to finish. With your permission it can also use logins saved in Password Manager.
How it fits with the rest of Gemini in Chrome
Auto browse arrived with a wider Chrome update Google announced in January 2026, built on Gemini 3. That update also added a side panel so the assistant stays beside whatever tab you're in, and Nano Banana image editing in the browser. Google says its testers used the side panel to compare options across lots of tabs, summarise product reviews from different sites and find time in busy calendars. Gemini in Chrome can also look at up to 10 open tabs at once on a computer.
Not sure which Google tool to use? See Google AI Mode vs Gemini.
What about Android?
Google announced in May 2026 that Gemini in Chrome, including auto browse, was coming to Chrome for Android, for jobs like booking parking or updating orders, on devices running Android 12 or higher with at least 4GB of RAM. Its Chrome help page still says auto browse is only available on desktop, so check your own phone rather than assuming.
The same idea inside the Gemini app is explained in the Gemini Agent guide.
Want AI doing the heavy lifting in your marketing?
I build the systems that handle the boring 80 percent, so you get your week back. Done properly, with the human kept in.
The risks Google spells out
When it acts for you, Gemini shares the information a task needs with third parties, which can include your name, contact details, files and preferences. Google also says sensitive steps need your confirmation. My advice on top: keep tasks to sites you trust, check the plan before you start, and stay nearby for anything involving payment or personal details. For the basics of the side panel, see how to use Gemini in Chrome.
Good first tasks
- Compare three products across shops and put the best one in your cart, then check out yourself.
- Find a hotel near a conference venue within your dates and shortlist three.
- Book a restaurant table for a client lunch.
- Schedule an appointment on a booking page you use often.
My verdict
Auto browse is the most practical AI agent Google has put in front of ordinary users, because you can watch it work and take over at any point. Start with low-risk errands, read every plan before you click Start Task, and do the final payment step yourself.
If you'd like help choosing which AI tools your team should use and setting them up around the way you work, here's how we can work together.
Frequently asked questions
What is Chrome auto browse?
It's a Gemini in Chrome feature that completes multi-step tasks on websites for you, such as comparing products, booking accommodation or making restaurant reservations, while you watch in a browser tab.
Who can use Chrome auto browse?
You must be 18 or over and in the US, have Google AI Pro or Ultra on a personal account, sign in to Chrome with that account, set your device language to English and use Standard or Enhanced Safe Browsing.
How do I stop an auto browse task?
Click Stop in Gemini in Chrome or close the task tab. To do a step yourself, click Take over task, then Resume or Give back task when you're done.
Is Chrome auto browse on Android?
Google announced auto browse for Chrome on Android in May 2026 for devices with Android 12 or higher and at least 4GB of RAM, but its help page still lists auto browse as desktop only.
How do I turn off auto browse in Chrome?
Go to Chrome's Settings, then AI innovations, then Gemini in Chrome, and turn off Gemini's ability to auto browse on that device.
