With auto browse, you can ask Gemini in Chrome to complete multi-step tasks for you on the web. For example, you can ask it to:
- Compare products, search for deals, and add items to your cart
- Help you find and book travel accommodations based on specific criteria
- Make restaurant reservations and schedule appointments
- Help you with many more tasks
What you need
To use auto browse on your computer, you need to:
- Be 18 or over and in the US.
- Be eligible and opt in to Gemini in Chrome. Learn how to get Gemini in Chrome .
- Update to the latest version of Chrome. Learn how to update Chrome .
- Have Google AI Ultra or Google AI Pro on your personal account. Learn how to upgrade .
- Sign in to Chrome with a personal Google Account. Learn how to sign in to Chrome
.
- This feature isn’t available in Incognito mode. It’s also not available if you sign in to Chrome with a work or school Google Account.
Important:
- We’re gradually releasing auto browse in Gemini in Chrome, so it might not be available to you just yet.
- For now, this feature is not available in Live chats or Gemini in Chrome on iPhone devices.
Ask Gemini in Chrome to complete tasks for you
Important:Gemini in Chrome can use a broad range of sites on the web to complete tasks for you. This is true even if you haven't connected the related apps to Gemini Apps. Learn more about connected apps .
- On your computer, open Chrome.
- At the top of your browser, click Gemini in Chrome
.
- In the text box, describe the task you want it to complete.
- Click Submit
.
- While Gemini in Chrome is performing the task, there’s an auto browse icon
on the tab that it’s using.
- When Gemini in Chrome needs you to complete a step, you’ll get a notification at the top of your browser.
- While Gemini in Chrome is performing the task, there’s an auto browse icon
- If needed to complete a task:
- Review and confirm any sensitive steps.
- Take over a task for steps you need to complete personally.
- Give Gemini in Chrome permission to sign in to a site for you.
Tips:
- To go to the task tab:Next to the task in the chat, click Switch tabs.
- If a task needs your attention, at the top of your browser, click Check your task.
- To take over a task from Gemini in Chrome:On the task tab, click Take over task
.
- To resume a task:In Gemini in Chrome, click Resumeor Give back task.
- To stop a task:In Gemini in Chrome, click Stop
. You can also close the task tab.
- Learn how to report a problem or send feedback about Gemini in Chrome .
Examples
You can ask Gemini in Chrome to:
- Find and book travel accommodations based on specific criteria
- Manage dining reservations and food delivery
- Search for tickets for events and group entertainment
- Find and compare products for online shopping
- Draft communications and organize calendar schedules
- Research job markets and professional networking opportunities
- Assist with online finance chores like fetching receipts
- Perform other administrative web tasks
Take over a task
While Gemini in Chrome is performing a task, you can take over the task at any time. For certain tasks that you need to complete personally, Gemini will ask you to take over.
To take over a task:
- Go to the tab that Gemini in Chrome is using for the task.
- Click Take over task
.
- Complete the steps you want to do yourself or Gemini asked you to do.
- To give back the task, in the Gemini in Chrome chat, click Resumeor Give back task.
Manage sites that Gemini in Chrome signs you in to
With your permission, Gemini in Chrome can get help from Google Password Manager to sign in to sites for you. Google Password Manager does not share your passwords with Gemini in Chrome. You can remove this permission at any time.
To remove permission for Gemini in Chrome to sign in to a site for you:
- On your computer, open Chrome.
- At the top right, click More
Passwords and autofill
Google Password Manager.
- On the left, click Settings.
- Under “Gemini can sign in for you,” review sites that you’ve allowed Gemini to automatically sign in to.
- To remove a site, click Delete
.
Change whether Gemini in Chrome can browse for you
- On your computer, open Chrome.
- At the top, click More
Settings.
- In the Settings menu, click AI innovations
Gemini in Chrome
.
- If the menu is hidden, first click Menu
.
- If the menu is hidden, first click Menu
- Under “Permissions,” turn Let Gemini browse for youoff or on.
About Gemini in Chrome’s limits
In Gemini in Chrome, there are limits for the number of:
- Multi-step tasks that you can request each day
- With a Google AI Pro plan: up to 20 requests per day
- With a Google AI Ultra plan: up to 200 requests per day
- Multi-step tasks that Gemini in Chrome can perform at the same time
When you reach your limit, Gemini in Chrome lets you know.
How Gemini in Chrome works with you to keep you & your info safe
Gemini in Chrome working as an agent is an experimental feature. As we continuously work to improve its safeguards, use auto browse in Gemini in Chrome carefully and safely to prevent unintended and potentially harmful results. You’re responsible for Gemini's actions during a task, including mistakes and unexpected results like purchases.
AI agents, like auto browse in Gemini in Chrome, are helpful and powerful tools, but it’s important to be aware of possible risks. Remember that Gemini in Chrome can make mistakes and do unexpected things.
About prompt injection
Prompt injection is an attempt to elicit an unintended or harmful response from generative AI tools like Gemini in Chrome. This happens when content, like a website, an email, a document, or multimedia, has malicious instructions that might be hidden from you but visible to the AI agent.
If an AI agent reads these instructions while doing a task, it might be tricked into doing unintended things. For example, a malicious instruction could tell the agent to:
- Take your private info from your emails or documents and post it on a public website
- Send your emails in Gmail to an external service without you knowing
- Expose insights about you based on your data in connected apps
Gemini in Chrome can share your info with websites
When you use auto browse in Gemini in Chrome, it can share information from your chat with websites. This can create privacy risks, for example when Gemini in Chrome uses connected apps like Google Workspace which allows it to access your private info.
Gemini in Chrome can make mistakes
Gemini in Chrome might misunderstand what you want it to do or the website it’s browsing. This could lead to unintended actions, like:
- Following instructions incorrectly or clicking the wrong link or button
- Completing a purchase or ordering something without your permission
- Adding the wrong quantity of an item to your cart or forgetting to add an item
- Confirming a task is done when it’s not or could have done more
- Asking you to take over when it can normally do the step
Learn about how we address these risks in Gemini in Chrome .
Chrome has safeguards for auto browse that aim to reduce the possible risks of AI agents , including unintended or potentially harmful actions. While these do not guarantee protection against all risks, these safeguards include:
- “Take over task”:Gemini in Chrome may ask you to take over the task to complete specific actions, like:
- Finalizing financial transactions
- Accepting terms of service
- Creating an account
- Requests for user confirmation:Gemini in Chrome aims to ask for your review and confirmation before it completes certain actions, like:
- Sending communications
- Modifying your data
- Submitting web forms
- Scheduling events
- Accessing sites with highly sensitive financial or health data
- Requests for permission:Gemini in Chrome asks for your permission before it gets help from Google Password Manager to sign in to sites for you. Google Password Manager does not share your passwords with Gemini in Chrome. You can remove this permission at any time.
- Prohibited task recognition:Gemini in Chrome has safeguards designed to help it recognize and not act on certain types of requests that could be harmful or are outside of its intended purpose, including tasks that may violate the Generative AI Prohibited Use Policy .
- Site & action restrictions:Gemini in Chrome restricts its activity to the websites and actions relevant to your task. This helps protect your data on other unrelated sites and helps prevent actions that don't align with your task. These are just some ways we protect against prompt injection.
Chrome’s safeguards for auto browse described above don’t guarantee protection against all risks.
Monitor important & sensitive tasks
Monitoring your tasks is the most important way to protect against risk while using auto browse. Review confirmation requests and clarifying questions closely. Use auto browse carefully and safely , and only give Gemini in Chrome tasks you’re comfortable with. Be extra watchful when Gemini in Chrome:
- Handles an important task
- Is signed in to websites with sensitive info, like financial, legal, and medical info
- Does anything where a mistake could be a problem
- Uses connected apps , like Google Workspace, in the same chat
You’re in control
If Gemini in Chrome is doing something you don't like, you can stop it by clicking Stopin Gemini in Chrome or Take over task
on the tab that Gemini in Chrome is using. Gemini in Chrome’s safeguards aren’t intended to replace your monitoring.
About your data & Gemini in Chrome
You can review your chats with Gemini in Chrome in Gemini Apps Activity . Learn how to manage and delete your Gemini Apps activity .
You can review the sites Gemini in Chrome visits in your Chrome history. These sites have Gemini action iconnext to them. Learn how to check and delete your Chrome browsing history
.
Learn more about what happens to your data when you use Gemini in Chrome .

