Google rolls out Gemini sidebar and Nano Banana in Chrome
Google has begun rolling out Gemini-powered tools to the Chrome browser starting today, including a sidebar for multitasking chats, an image generator, and previews of task automation, following its recent AI updates to Gmail.
The initial feature introduced is a sidebar accessible to all Gemini in Chrome users. This interface enables continuous conversations with Gemini across multiple open tabs. Google describes its utility for multitaskers through specific tester applications. “Our testers have been using it for all sorts of things: comparing options across too‑many‑tabs, summarizing product reviews across different sites, and helping find time for events in even the most chaotic of calendars,” the company writes. Users can maintain dialogue without switching contexts, supporting tasks that span various pages simultaneously.
Within this sidebar, Google integrates Nano Banana, its in-house image generator, previously rolled out successfully in the Gemini app. This addition allows direct image creation or editing inside the browser. Users no longer open new tabs for generation requests or handle file downloads and uploads for modifications. Both processes occur from any existing open tab via the sidebar, streamlining workflows for visual content tasks.
Gemini in Chrome currently supports Connected Apps, a feature that permits the assistant to access data from Google’s services such as Gmail and Calendar. In a press briefing demonstration, a Google employee requested the dates for their children’s March break. Gemini retrieved the precise timeframe from the employee’s email inbox without explicit instructions on the source location, showcasing seamless integration across Google applications.
Google previews an auto-browse feature in Chrome, demonstrated during the briefing. An employee instructed Gemini to locate and purchase the identical winter jacket bought a few seasons prior. The assistant first outlined a step-by-step plan: initiate by searching the employee’s email inbox to identify the exact model and size. It proceeded to conduct shopping searches based on that information. Throughout execution, the employee continued browsing independently in Chrome. Gemini paused at key points requiring user input, such as providing login credentials and confirming credit card details before finalizing the purchase. This pause mechanism ensures user oversight for sensitive actions.
The auto-browse capability targets repetitive routines. For example, users who order the same produce weekly from a grocery delivery service can have Gemini automate the process. Although the demo indicated a pace slower than manual execution for one-off tasks like jacket repurchase, the preview status accommodates early testing. Access is limited to Google AI Pro and Ultra subscribers in the United States, available starting today.
In the coming months, Google will extend Personal Intelligence to Chrome. This functionality, which debuted in the Gemini app at the start of January, enables the browser to retain records of prior Gemini conversations. Google states this enhances personalization: “Personal Intelligence in Chrome transforms the browsing experience from a general purpose tool into a trusted partner that understands you and provides relevant, proactive, and context‑aware assistance.” The feature builds continuity by leveraging conversation history for tailored responses.
These developments follow Google’s recent AI enhancements to Gmail, positioning Chrome as a central hub for Gemini integrations. The sidebar rollout marks the immediate availability for broad user testing, while Connected Apps demonstrates real-time data linkage. Nano Banana expands creative tools within the browser environment, eliminating tab proliferation. The auto-browse preview introduces agent-like task handling with safeguards, and Personal Intelligence promises longitudinal context retention. All features align with Gemini’s expansion across Google products.