The update is rolling out on macOS, Windows, and Chromebook Plus, with some features initially limited to users in the United States.

Gemini moves into Chrome’s sidebar

The most visible change is where Gemini now lives. Instead of opening in a separate window, it’s embedded directly into Chrome’s sidebar, staying accessible over any open tab.

That small shift makes a big difference. You can keep reading an article, browsing a store, or checking flight options while simultaneously asking questions, comparing information across sites, or pulling quick summaries – without losing your place or breaking your flow.

It’s especially useful for research-heavy tasks like comparing product reviews, planning trips, or scanning long pages for key points.

Image editing and visual tools, right in the browser

Chrome now supports an image tool called Nano Banana, letting users work with visuals directly on the page.

You can edit images without downloading files or opening third-party apps. It’s designed for practical use cases – mocking up interior design ideas, creating simple visuals for presentations, or turning online data into quick infographics.

Everything happens inside the browser, which keeps the process fast and surprisingly friction-free.

Deep integration with Google Services

Gemini in Chrome connects tightly with Google’s own ecosystem. This includes:

• Gmail
• Google Calendar
• YouTube
• Google Maps
• Google Flights
• Google Shopping

With permission, the assistant can pull context from emails, calendar events, or saved plans. That means it can help draft messages, surface relevant travel details, suggest routes, or find products based on what you’re already working on.

All integrations can be managed and limited through Gemini’s settings, giving users control over what’s connected.

Auto Browse: Chrome that can do the clicking for you

For U.S. users subscribed to AI Pro and Ultra plans, Google is introducing a new feature called Auto Browse.

This turns Chrome into something closer to a task-runner than a traditional browser. Auto Browse can:

• search for hotels and flights
• fill out forms
• gather documents
• review bills and subscriptions
• handle routine online tasks

It also supports visual input. Show it an image, and it can identify similar products, compare prices, apply discounts, add items to a cart, and stay within a budget you define.

Purchases and other sensitive actions always pause for user confirmation before anything is finalized.

Built with safety in mind

Google emphasizes that these features were designed with safeguards from the start. Any action involving payments, public posting, or account changes requires explicit approval.

Automatic workflows stop when confirmation is needed, ensuring users stay in control even when Chrome is doing most of the heavy lifting.

The first step toward a more active WEB

Google describes this update as an early move toward an “agent-driven web.” In practice, that means browsers stop acting like passive viewers and start functioning as helpers saving time on repetitive tasks and reducing friction across everyday online activities.

The post Google is turning Chrome into more than a browser appeared first on Geeknify.