I spent my morning with Gemini in Chrome, the new integration that puts the AI-powered assistant right in your browser. Instead of going to the chatbotโs web app, you can click the new Gemini button in Chromeโs top-right corner to start a conversation โ but the key difference is that the browserโs built-in assistant can โseeโ whatโs on your screen while you navigate the web.
To me, Geminiโs integration in Chrome seems like just the start of Googleโs mission to make its AI more โagentic,โ as I found myself wanting it to do more than it actually could. For now, you can only try out the early access version of Gemini in Chrome if youโre an AI Pro or AI Ultra subscriber, and use either the Beta, Dev, or Canary version of Chrome.
I started out by using Gemini to summarize some of the articles on The Verge, as well as even find some gaming-related news on the homepage, where it pointed out the new Game Boy games Nintendo added to its Switch Online service, the upcoming Elden Ring film adaptation, and Valveโs massive Steam Deck update.
But Gemini can only โseeโ whatโs on your screen, so I found that if you want it to summarize certain elements, like The Vergeโs comments section, youโll need to make it visible before the chatbot can provide a response. Gemini will follow you when you switch tabs, too, but it can only pull information from one at a time.
If you donโt feel like typing, Gemini in Chrome also lets you switch to its โLiveโ feature by selecting the button in the bottom-right corner of the dialogue box. From there, you can simply ask a question out loud, and Gemini will respond by speaking to you.
I found this especially useful to use alongside YouTube videos, where I cued up a bathroom remodeling video and asked, โWhat tool is he using?โ Gemini responded, โIt looks like heโs using a nail gun to fasten some wood pieces together.โ In another video, Gemini correctly identified a capacitor on a motherboard, along with the tweezers and hot air tool the YouTuber used to remove it. It can summarize videos and tell you about specific parts you havenโt watched as well, but I found that this isnโt always accurate if a video doesnโt have labeled chapters that it can draw information from.
Probably my favorite use case for the integration is having Gemini pull recipes from YouTube videos, so I didnโt have to write the recipes down myself or search for a link in the description. It also came in handy when I asked it to point out the waterproof bags on an Amazon search page.
Gemini wasnโt always consistent, though. When I asked Gemini where MrBeast is during a video of him exploring ancient Mayan cities, including Chichรฉn Itzรก, it replied, โI donโt have access to real-time information, so I canโt pinpoint MrBeastโs exact current location.โ When I asked it again, it responded with the location listed in the videoโs description: Mexico. Another time, I asked Gemini for a link to buy a specific pair of pliers shown in a video, but Gemini again told me that it didnโt โhave access to real-time information, including product listings or store inventories.โ However, Gemini provided me with links to other products when prompted.
At times, I felt that Geminiโs responses were just too long for just a little pop-up window in Chrome. You can extend it, but it doesnโt leave much room on my MacBook Airโs 13-inch display. Plus, one of AIโs main selling points is that itโs supposed to help you save time by providing quick and concise answers, which it doesnโt always do unless I specifically ask for that. Geminiโs follow-up questions, like whether I would like to know more about a particular topic, also got a bit repetitive.
Even with these hiccups, I can easily see Google extending Chromeโs Gemini integration beyond just simple questions and answers. Google wants its AI to become โagentic,โ meaning it can perform tasks on your behalf, and Gemini in Chrome seems poised to one day adopt these kinds of features. After asking Gemini to summarize a restaurantโs menu, for example, I even thought about asking it to place a pickup order โ an agentic task it just canโt do yet. In the future, I could even see it coming in handy by having it bookmark pages related to travel research for me, or maybe even finding and saving YouTube videos of different recipes to my Watch Later playlist.
Google seems like itโs getting closer to making that a reality with Project Marinerโs โAgent Modeโ coming to the Gemini app, which will allow it to manage up to 10 tasks at once and search the web for you โ and maybe one day, it will bring these capabilities to Gemini in Chrome, too.
