Google Chrome’s “Auto Browse” AI Agent Launches Today
▼ Summary
– Google has significantly expanded Gemini’s capabilities within its Chrome browser, most notably by adding an autonomous browsing agent called Auto Browse.
– The AI is now easier to access, defaulting to a split-screen “Sidepanel” view instead of just a pop-up window when the omnipresent button is clicked.
– Gemini in Chrome can directly connect to and manipulate several Google services, including Gmail, Calendar, YouTube, Maps, Shopping, and Flights.
– A new feature allows users to access and edit web images directly within the Sidepanel using Nano Banana, eliminating the need to download and re-upload them.
– Users can choose between Gemini’s slower, higher-quality Pro model and its faster standard model directly within the Chrome implementation.
Google Chrome is introducing a significant expansion of its integrated Gemini AI capabilities, with the headline feature being a new autonomous agent called Auto Browse. This tool is designed to automate repetitive web tasks directly within the browser, aiming to streamline user workflows. The update also includes a redesigned interface and deeper integration with core Google services, making the AI assistant more accessible and functional for everyday use.
Accessing these new features remains straightforward through the dedicated AI button at the top of the Chrome window. However, its behavior has changed. Instead of simply opening a pop-up, the button now defaults to launching Gemini in a split-screen or “Sidepanel” view. This layout provides the AI more space to operate while you view your current webpage, which is particularly useful for tasks that involve manipulating page content. While a floating window option is still available, the side panel offers a more integrated experience.
This update significantly broadens Gemini’s reach within the Chrome ecosystem. The chatbot can now interact directly with several key Google applications without leaving the browser. Users can leverage Gemini to manage information from Gmail, Google Calendar, YouTube, Maps, Google Shopping, and Google Flights from the side panel. Although this functionality was technically added in January, Google is now formally highlighting it alongside the other new features.
A notable addition is the ability to edit images directly. Through a feature involving Nano Banana, users can now open an image from the web and instruct Gemini to modify it through text prompts in the side panel, eliminating the need to download and re-upload files to a separate AI tool. As with the standalone Gemini app, Chrome users can select between two model tiers: the slower but higher-quality Pro model and the faster standard option, allowing a choice between speed and output fidelity.
The most anticipated component is Auto Browse. This autonomous agent functions as a digital helper capable of executing multi-step tasks in the browser. For example, it could be instructed to research a topic, compile a summary from various sources, or handle complex form entries. By automating these often tedious processes, Google aims to enhance productivity and reduce the manual effort required for common online activities, positioning Chrome as a more intelligent and proactive browsing platform.
(Source: Ars Technica)
