Google begins rolling out Chrome's "Auto Browse" AI agent today

Google's AI-Powered Browsing Revolution: Chrome's Auto Browse Takes Center Stage

Google's Gemini AI has been making waves in the tech world, and today, it's expanding its capabilities in a major way. The company has begun rolling out Chrome's "Auto Browse" AI agent, a feature that promises to revolutionize the way we interact with the web. In this article, we'll dive into the details of Auto Browse, explore its capabilities, and discuss the implications of this technology.

Accessing Gemini: A New Era of Collaboration

Gemini, Google's AI chatbot, has been integrated into Chrome for several months now. Initially, the AI button at the top of the window opened Gemini in a pop-up window. However, Google has now updated the feature to default to a split-screen or "Sidepanel" view. This change allows Gemini to breathe more room to manipulate a page with AI, making it easier to use the chatbot while browsing.

Sidepanel with Gmail Integration

The Sidepanel view is particularly useful when calling other apps in the Chrome implementation of Gemini. For example, you can access Gmail, Calendar, YouTube, Maps, Google Shopping, and Google Flights right from the Chrome window. This level of integration is a significant improvement over the previous pop-up window experience.

Image Editing with Nano Banana

Gemini in Chrome can now also access and edit images with Nano Banana, a feature that eliminates the need to download and re-upload images to Gemini in another location. Simply open the image from the web and type in the Sidepanel with a description of the edits you want. You can choose between the slower but higher-quality Pro model and the faster standard one.

The Star of the Show: Chrome's Browsing Agent

The real star of the show is Chrome's new browsing agent, which is based on Google's latest Gemini 3 models and input from the company's work on the experimental Project Mariner agent. This agent promises to revolutionize the way we interact with the web by automating tedious tasks, such as filling out forms and copying information from emails.

Auto Browse: A Hands-Off Experience

When you launch an Auto Browse task, Chrome will open new tabs as necessary and mark them with a sparkly AI icon so you know where the robot is active. You don't have to keep that tab in the foreground, and you can even have multiple AI tasks going at once. The AI will ping you to check in when the task is done or when it needs your input.

Limits and Security Concerns

While Auto Browse is a powerful tool, it's not without its limitations. AI Pro subscribers get 20 AI browsing tasks per day, but those paying for AI Ultra get 200 per day. Additionally, having the AI churning in the background may be a concern, as generative AI can make mistakes. Google has implemented a range of security and safety rules to prevent misuse, such as not actually buying items when asked to research and purchase them.

A Cloud-Based Experience

Another thing to keep in mind is that Auto Browse doesn't run locally. All content from your robotically operated tab is streamed to a cloud-based Gemini model. This means page content will be shared with Google, but the extent is not entirely clear. Google says Auto Browse is governed by the established Gemini in Chrome policy, which says Google stores information from websites in the Gemini Apps Activity (if Keep Activity is enabled).

Forward-Looking Thoughts

Chrome's Auto Browse is a significant step forward in the development of AI-powered browsing. While there are still limitations and security concerns, this technology has the potential to revolutionize the way we interact with the web. As Google continues to develop and refine this feature, we can expect to see even more exciting advancements in the future.

Implications and Real-World Applications

The implications of Auto Browse are far-reaching, with potential applications in a variety of industries, including:

Customer service: Auto Browse can help automate tasks such as responding to customer inquiries and resolving issues.
Marketing: Auto Browse can help with tasks such as lead generation and data entry.
Healthcare: Auto Browse can help with tasks such as medical research and data analysis.
Education: Auto Browse can help with tasks such as grading and data analysis.

As we move forward, it will be exciting to see how Auto Browse and other AI-powered browsing technologies continue to evolve and shape the future of the web.

Source: https://arstechnica.com/google/2026/01/google-begins-rolling-out-chromes-auto-browse-ai-agent-today/