Meteor builds AI-native browser with autonomous agents to automate repetitive web tasks
Sep 10, 2025 · Full transcript · This transcript is auto-generated and may contain errors.
Featuring Farhan Khan
How you doing? Nice to meet you. Uh introduce yourself for the stream. Who are you? What are you building? Yeah. Uh, I'm Prenav. Um, we're building Meteor. And this is for Han. Uh, the AI native browser that's going to kill Google Chrome. Oh, okay. We got the browser wars going. Let's go. Yes. Meteor.
You guys going after Comet, too. Yeah, absolutely. Everyone. Yeah. Okay. Well, what's the plan? I mean, everyone has installed Chrome at this point. Everyone runs it. It's so hard to rip it out. How do you How do you create a solution that's 10x better? Yeah.
Well, I mean, we all spend seven or eight hours every day on our browser, right? We spend we do most of our work on the browser, right? Most of it is redundant work. Y we're saying we can automate all of that away, right?
We're saying we want AI we want to spawn AI agents that work with you as your co-pilot to the web that can do your work for you so you don't have to waste your 7 8 hours. Okay. But but but like what does that look like as I use the product? How do you pitch to somebody who says Chrome works well enough for me? Right.
Chrome does work well enough for you if you're okay wasting many hours a day. What we're saying is we're giving you time savings. It's sort of like people pay thousands of dollars for personal assistants, right? People pay thousands of dollars for employees to hire like to create automations.
We're saying we want to create virtual employees that run on your browser, right? And that's Meteor. So like let's say you want to handle your calendar, right? Just automate all like meeting creation, you know, based on your your emails.
Like if you want um if you want, you know, some kind of like data entry, just hand like tell me Meteor and we'll handle it for you, right? How is the AI agent interfacing with the actual data? Are you screen scraping, taking screenshots, trying to interpret it that way?
Are you you doing computer use or, you know, interacting with the HTML API underneath? Yeah. So, we're in alpha right now. So, we're trying out a bunch of things. Um, right now we're primarily using vision. So, we use screenshots. Um, also helps a little bit with like some of the the the prompt injection stuff.
So, definitely uh we're primarily using vision, but you know, we've been playing around with a bunch of things. And yeah, I think uh what's the best frontier model right now for what you do?
Uh right now it's it's probably cloud set but you know we use a mixture of models right um we use GPT we use cloud we use all of them and we are state-ofthe-art yeah so what were you guys doing before YC we were at the UDub we were both doing computer science to build Meteor there you going we have a lightning round uh who's your favorite entrepreneur it's got to be Steve Jobs Steve Jobs okay and how did you make your first money online your first dollar in business or online selling Pokemon cards selling Pokemon cards There we go.
There we go. Well, congratulations on demo day. Thank you so much. How's the race going? First year college dropouts. You're here. You're going through YC. Oh, it's been it's been going great. Yeah. Uh we're you know, we're both second time entrepreneurs and a bunch of cool in the past. That's first time dropout.
Second time. First time dropouts. Yeah. Unfortunately, you can only do that once. Yeah. This is all No, you could go back and get you could get an MBA immediately like you go to med school at 35. Drop. What was your What was your last company?
Um, so he built Maxima, which is an FPJ ID that was 10 times faster than the industry standard. Okay. Yeah. Yeah. A lot of lot of code code optimization. I built a bunch of projects at UDub that went viral. He almost got kicked out twice. I did all the story. When what was the worst the worst thing you did to get? Okay.
So, what the thing that went most viral was u I figured out there was a data leak that allowed students to get access to their professors before Udub published it. And I published it within eight down within eight days. It got taken down. I got called in. Uh, but you know, everything's okay now.
We're We're Everything's okay now. Congrats, guys. Appreciate it. Good luck out there. Good luck. Thank you so much. If you see Sarpai, just run the other direction. Just run the other direction. Thank you so much, guys. Thanks for