Published Mar 8, 2026, 1:30 PM EDT
Brady is a technology journalist for MakeUseOf with years of experience covering all things mobile, computing, and general tech. He has a focus on Android phones and audio gear, and holds a B.S. in Journalism from St. John's University.
Brady has written for publications like Android Central, Android Authority, XDA, Android Police, iMore, and others. He has experience reporting on major events held by Google, Apple, and Samsung, as well as trade shows like Lenovo Innovation World and IFA.
When he's not writing about and testing the latest gadgets, you'll find Brady watching Big East basketball and running.
Letting an AI agent into your most crucial workflows isn't an easy decision. There are privacy concerns, and if an AI feature ends up messing with a mission-critical task, you'll be left wondering why you even used it in the first place. However, just about every mainstream browser in 2026 has some AI tools, and eventually you might want to give them a shot. I tried Gemini in Chrome for the first time, and it proved to be more useful than I thought.
Gemini in Chrome got a major upgrade this year, and it's called auto browse. It's a feature that delivers on the prospect of having AI agents complete actions for you while you spend your time doing other things. You'll give Chrome's auto browse tool a prompt via Gemini, and it takes over your Chrome window. It can load new sites, navigate current ones, and fill out forms or login prompts. If you're still wondering how AI agents can actually work for you, Chrome auto browse is the perfect example, and it's just one of the Gemini in Chrome features that saves me time.
Gemini's side panel taps into your websites
It's an effortless way to inject web context into Gemini chats
Credit: Brady Snyder / MakeUseOfThe best thing about using Gemini in Chrome is having the power of Google AI models at your fingertips. The new Gemini experience lives in a sidebar, similar to using Gemini in Workspace apps. It's stashed away until you need it, but is easy to access when you do. Look out for a Browse with AI icon in the top-right corner of your Chrome window, or just the Gemini sparkle icon. When clicked, this opens the Gemini sidebar. You can also launch Gemini in Chrome by entering Ctrl + G or CMD + G, or by clicking the menu bar icon for Gemini in Chrome on macOS.
Speaking of, the menu bar shortcut for Gemini is a pretty neat perk of using Chrome's AI features on macOS. It's the closest thing to a dedicated Gemini desktop app we've seen, even if this is just a windowed Gemini in Chrome wrapper. You can access it from anywhere on macOS, even if Chrome is only running in the background.
Credit: Brady Snyder / MakeUseOfBy default, using the Gemini sidebar in Chrome shares your current tab with Google for processing. You'll want to turn this off, or avoid using it for certain tabs, when viewing sensitive content. However, the functionality gives Gemini the context of your browsing activity instantly, allowing it to be more helpful. You can ask it to summarize or compare information across multiple tabs, extract specific information from crowded sites, or find free time in your day while reviewing personal and work calendars simultaneously.
Gemini in Chrome is essentially saving you a step or two compared to using the regular Gemini web app. You could screenshot, copy, or link to web information in the usual Gemini chatbot, but this takes more time as you navigate across multiple tabs and windows. By using the sidebar instead, Gemini automatically has access to the sites you're viewing for ample context, saving you time and hassle.
Gemini can edit web images without downloading them
Nano Banana remixes images on the web directly in your Chrome browser
Credit: Brady Snyder / MakeUseOfI download way too many images to edit them once and never go back to the original files again. Eventually, I'm left with a Downloads folder filled with random web images and files that need to be painstakingly cleared. Gemini in Chrome lets you edit photos with Nano Banana 2 found on the web without first downloading them onto your computer, and it's an incredible perk. Instead of loading the Gemini web app and downloading the file to your PC first, you can do it all in the Gemini sidebar.
It's easier to use than you might expect. Simply give Gemini in Chrome a command like, "Edit the photo I'm looking at and change it to a 9:16 aspect ratio." Since the AI model can see the tab you're currently viewing, it knows which image you want to edit without needing specific details. Even on pages with multiple images, Gemini in Chrome identifies the most prominent one and completes your request. You can see the results in the screenshot below:
There are a few clever things about using this method. For one, Gemini's Nano Banana 2 image-generation model can fill in the gaps with generative AI to complete your request. In this instance, I wanted Gemini to change a photo's aspect ratio to vertical from horizontal, and it did so while expanding the image using AI. This all happened without downloading anything to my PC. I can also copy the output to my clipboard and paste it somewhere else, so nothing is saved to my computer throughout the entire process.
It's easy to see practical use cases for having Nano Banana waiting in the wings of your Chrome browser. If you're looking for a new home or apartment, you could ask Gemini in Chrome to fill out sample photos to see what it'd look like after furnishing. On the flip side, those scouting for a new couch or TV could ask Gemini to make an image showing how it'd look in their home.
Related
Auto browse is the best part — it literally browses for you
It's an agentic browsing solution that can complete tasks without your input
That builds up to the flagship Gemini in Chrome feature, which is auto browse. If you've followed agentic projects like Google's Project Mariner, you may know that we're building towards a future where AI agents can control your devices and apps using "computer use" models. On a smaller scale, that's exactly what Chrome auto browse aims to do. After entering a request in the Gemini in Chrome sidebar, Gemini can completely take over your browser to complete actions on your behalf.
The first time you try Chrome auto browse, you'll have to give it permission to control your browser. After that, it's completely autonomous. You can watch Chrome auto browse work every step of the way, and have the option to click the Take over task button if things aren't going as expected. Although the AI agent works slowly, it usually manages to complete your request entirely on its own. It may stop and ask you to confirm at certain sensitive points, but other than that, it's an independent AI agent.
Chrome's auto browse feature is currently limited to Google AI Pro and Google AI Ultra subscribers in the U.S.
It's built on Gemini 3 models, so it has the multimodal capabilities to understand text, images, and videos on webpages. Chrome auto browse has support for extensive permissions, if you grant them, to the point that it can use Google Password Manager to sign in to websites to complete tasks.
How I'm using Gemini in Chrome in my workflow
I use at least three browsers at any given time — Arc, Safari, and Chrome — using the best one for each task. I don't plan on using Gemini in Chrome for all my browsing needs, as I find Arc to be a lighter and more productive browser. However, when I need to use Gemini while browsing, I'll absolutely switch to Chrome to save time. Being able to work within a single browser without needing to download and reupload information from multiple sources is a game-changer for AI automation.
