Pod Insights How I AI Guillermo Rauch: Vercel CEO on how v0 hit 3,200 PRs merged per day (and lets anyone ship) About this episode Guillermo Rauch, the CEO of Vercel, demonstrates how v0 has evolved from a simple prototyping tool to a complete development environment that supports the entire Git workflow. Guillermo shows how Vercel built skills.sh—a viral marketplace with over 34,000 community-submitted skills—using v0, and how the tool enables non-technical team members to contribute production-ready code changes. He walks through creating branches, implementing features, previewing changes, and submitting pull requests, all within v0.
What you’ll learn:
How v0’s new Git workflow integration enables anyone to contribute production-ready code changesWhy skills.sh became a viral hub for AI skills, with 500 new submissions per hourHow to implement features in v0 that consider production concerns like abuse prevention and rate limitingThe benefits of branch previews for testing changes in a production-like environment before mergingHow v0 eliminates development environment setup challenges for non-technical team membersWhy the “terminal core” design aesthetic became central to skills.sh’s interfaceHow Vercel uses v0 internally to democratize code contributions across teamsThe future of AI at Vercel, including upcoming tools for text-to-SVG and video generation—
In this episode, we cover:
(00:00) Introduction
(01:22) Overview of skills.sh
(04:40) Demonstration of v0’s GitHub integration and branch creation
(06:40) Exploring the v0 development environment
(09:05) Building a rating system feature for skills.sh
(11:18) Testing the new feature in the preview environment
(13:20) Creating a pull request and deploying to a preview environment
(15:25) How Vercel is using v0 internally for production work
(17:48) Organizational adoption and cultural impact
(22:04) Favorite non-coding AI use cases
(25:17) AI-powered chess game built with v0
(27:57) Teaching kids about coding with AI
(31:44) Troubleshooting techniques when AI gets stuck
(34:43) Final thoughts and audience Q&A
—
Tools referenced:
• v0: https://v0.dev/
• Skills by Vercel: https://skills.sh/vercel
• Vercel: https://vercel.com/
• GitHub: https://github.com/
• Nano Banana: https://gemini.google/overview/image-generation/
• Vestaboard: https://vestaboard.com/
—
Other references:
• v0 Chess Match: https://v0-chess-match.app/
• React Native: https://reactnative.dev/
—
Where to find Guillermo Rauch:
LinkedIn: linkedin.com/in/rauchg http://linkedin.com/in/rauchg
X: https://twitter.com/rauchg
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected] .
Transcript Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.
0:00 Speaker 00 I'll say one thing about vibe coding. It's really easy to go from zero to one. I think we've all seen the demos of I prompt something and it's cool. I think what's harder is to iterate on a project at scale and to deploy changes safely. Every marketer or sell wants to change this page at some point. And the old way was one of two ways. One is what I called, you had a petition to the government. You had to go to engineers and say, engineers, can you please add a logo over here or whatnot? Or pray that the CMS was perfectly wired up for any ambition or dream or idea you had. So now they can just open this page in B0 and prompt anything that they want.
0:38 Claire Vo? It reduces the friction of getting something live really, really low. The humiliation ritual of prioritization goes away. And you can actually focus your time on defending the merits of an idea on the actual idea as opposed to the hypothesis of the idea that then has to be implemented. And so I think it changes the speed of companies in a really significant way.
1:03 Claire Vo? So this is truly a first time vibe podcast that we're doing together. And I wanted to introduce myself. I'm Claire Voe, I'm a product leader and obsessed with AI. And I have a podcast, How AI, where I teach people how to build better with all these new tools, including ones that we're going to see today. And I'm really excited to have you here. Jeet, first, we're just going to get to the thing that everybody's wondering about. What is your most favorite feature that you released this week on B0?
1:35 Speaker 00 Well, I'll tell you, the hottest thing in AI today is skills. And one is excited about the fact that we can now augment agents and AI applications and agentic engineering with skills, like skills that the model doesn't yet have. And so we launched skills.sh. And the beautiful thing about what we'll show you today is that B0 can seriously go from prototype all the way to production. So we're able to conceive changes to things like skills.sh. I'm going to show you really quickly. Skills.sh is a new, you can think of it as like NPM. It's a hub, an open ecosystem of skills. And it's pretty dramatic what's happening to this site.
2:17 Speaker 00 So you can see that we now have 34,000 skills submitted by the community.
2:24 Speaker 00 And this website has gone viral all over the internet. It's hosted on Vercel, but the most exciting part to me is that it was conceived in B0.
2:34 Claire Vo? I have a quick question for the audience. How many of you have installed a skill in the last week?
2:39 Speaker 00 Oh, wow.
2:40 Claire Vo? Okay, a lot of people.
2:41 Speaker 00 Skill build.
2:41 Claire Vo? Um, how many of you have the top three installed? Actually, top.
2:46 Speaker 00 It's very heavy at the top, right? It's like, these are ripping.
2:50 Claire Vo? No, I have top seven. Okay, yeah, I have the top seven installed right now. Um, this is a really great resource. So for folks that are maybe watching this later or haven't been familiar with skills, skills is now this standard that a lot of these agentic frameworks are using to help you repurpose and reuse best practices, step-by-step flows. And so, for example, I use this remotion best practices one um to let me import components and regularly create videos really, really quickly. And I would not have been able to do this without the expertise that's been packaged in these best practices that were installed with one line um using skills.sh.
3:31 Speaker 00 I think it's also worth noting, maybe to peel the covers of how Vercel builds products.
3:37 Claire Vo? Yep.
3:37 Speaker 00 Skills.sh was a thing that was just conceived at the moment of inspiration. We started prompting, hey, wouldn't it be cool?
3:44 Claire Vo? Yep.
3:44 Speaker 00 If this thing took shape? Would we discuss, for example, what it should look like? We've been calling this a style Terminal Core, because it looks a little bit like, this is my contribution to the project. I was like, hey, wouldn't it be cool if we make the top of the website look like a terminal? And so the the process itself of building this was very much prompt-driven, LSA, like chatting in Slack and saying, hey, wouldn't it be nice if we had a hub for this? Just very iterative, very collaborative between the team members at Vercel. And what's really cool about this, again, is it's really fast. So it takes advantage of all of the Vercel infrastructure primitives, even though it has 35,000 of these skills. Like if I started like, like hardcore scrolling this.
4:27 Speaker 00 And then pick a random one, all right, Swift, Taylor Swift. You're gonna see like the patient decisions are, it's probably Swift UI, okay. But all the patient decisions are instant, production grade. You needed to scale, there were gonna be a lot of eyes on this thing.
4:41 Claire Vo? Okay, so I think we want to get to our first workflow for how AI. You just want to show us how you either develop this or how you and the team improve this over time using the tool.
4:51 Speaker 00 I'll say one thing about Vip coding. It's really easy to go from zero to one. Like, I think we've all seen the demos of I prom something and it's cool. And I think what's harder is to iterate on a project at scale and to deploy changes safely. In the case of how we work on Versale products, we always work on branches and we take advantage of branch previews. And then we code review and then we merge them. So we're basically gonna be showing you today is how we brought those ideas of hardcore, heavy duty, production grade engineering to V0 itself. So I'm here and finding that same project that you just saw.
5:33 Speaker 00 Skills out of SH, which is piped into, is basically backed by Git. The engineer who built this pushed some code three hours ago. And you have this new button within V0, which is new branch. So what this is showing you is that V0 is making the Git flow of creating branches at first class citizen of the product. So I'm gonna create a branch.
6:01 Speaker 00 And basically, this is gonna give me the same sort of like chat experience you're used to. But notice here at the top, I got this beautiful new convention of project slash branch, right? So I have the V0 slash route G branch.
6:19 Speaker 00 And here, within the preview, you're gonna notice that, just like if you had cloned the project to your local device, we both have a full, full-scale VS Code editor, as well as the real project running within V0.
6:40 Claire Vo? One thing I want to pause and notice, because I just have a laser eye for product, is I love that you use the convention that all of us with engineering teams use on our Git branches, which is who's the contributor slash what's the feature? And so what I think this is really interesting, you know, we're gonna talk about how you actually use these tools to build, but I also think there's a flip side of how you design great AI products and agentic products, and I still like the small design tweaks that make something like a V0 feel like a collaborative teammate on your tool. So I, for all the engineers out there, I noticed, I noticed that little convention.
7:14 Speaker 00 So, and what you're gonna see in the design philosophy of the product is that we really wanted to embed those little details of what makes a real engineering workflow come to life, but in a really easy way, right? Like, at the end of the day, I didn't have to go to a terminal or boot up GitHub Desktop in branch manually, like it's the Stone Age. I just press a button and now I have a branch running. So, the main idea here is that, within this preview, I have the full Skills out of Sage project running, it downloaded dependencies, it installed the exact versions of Next.js and every dependency within the project. I have it all running here. I have it, obviously, within a staging or dev sort of environment.
7:59 Speaker 00 And now, you know, I could navigate it, like, I could navigate the production website, I could explore it, I could, you know, use all the capabilities that V0 brings to the table. But I figured, let's actually build a feature that we could ship to product.
8:14 Claire Vo? Yeah, and one thing I want to pause on what you I think glossed over a little bit, which is the fact that you have this VS Code instance, the fact that you have all your dependencies installed, the fact that this is running both with code and a preview. For anybody who's less technical out there, and maybe a lot of your users that are using v0.app are less technical. This even like downloading VS Code, getting your local environment set up. Like I spent this morning with my designer installing Homebrew. Like, like it just wasn't on her laptop.
8:43 Speaker 00 It's nightmare feel.
8:44 Claire Vo? It's nightmare. And so if you're trying to step from this like vibe coding prototype in web experience into feeling more like a software engineer without having to have Claire hand hold you through like brew install. This gets you like halfway there. And so I think there's also this learning aspect of it. I want to make sure people don't miss, but let's get into building something on this.
9:08 Speaker 00 One, another part of our product development process is really listening to community and listening to customers. So people have been asking for a lot of different tools so that we could guide them towards knowing if a skill is high quality, vetted, verified, because there's so many skills. At last we checked, there were 500 skills being added every hour. And so one of the ideas that we came up with is like, could we add a rating system? So let's add a five star based rating system for the skills. Put it on the sidebar.
9:48 Speaker 00 Be mindful. So I'll also give you like a little bit of my real time consciousness on if I were talking to an engineer and say like, what could go wrong if we accept ratings from the internet? What is that can go wrong if you accept ratings from there is abuse. So let's say, let's still be zero, be mindful that we should rate limit or prevent abuse on the scores that we receive.
10:11 Speaker 00 And again, for me, it's all about thinking from a production readiness point of view when I think about the new V0 and make it make sense within the style of this skills website.
10:25 Claire Vo? What I love about what you're showing us is you have this very, very high sophistication prompt here, which is make it make sense. So we have three, three incomplete sentences on a production app serving thousands, millions of people.
10:40 Speaker 00 So let's
10:40 Claire Vo? And you're gonna fire it off. And while you do this, one of the things I want to just call out that I think, you know, why this feature is maybe important right now is I don't know if you've heard, there's like this crustacean crawling all over everybody's MacBook minis. And skills can be a, a prompt injected vector for things. And so as you're trying to make sure that this becomes the centralized hub for discovering skills, which I think it's starting to be. It is upon you to kind of make sure that the quality is there. At least you have the right thing, right things in place to people to make good decisions.
11:09 Speaker 00 Follow with your analogy. This is a little bit like we're vibe coding on top. GitHub.com or npmjs.com. It's like a really, really big deal. All right. So I was gonna walk you through what V0 is doing, which of course, if you've used V0 before.
11:25 Speaker 00 Everyone does the whole like talk over the thinking strays because agents are not the fastest. But I do want to point out a few things that are really important. So
11:34 Speaker 00 V0 is all about leveraging the integration and marketplace capabilities of herself. So in this case, it knows what the data source is of this project, right? We're storing data in Redis by Appstash. Obviously it's going to go through the whole file system. It's going to try to interpret my requirements. This is already like really nice to see that it's not inventing a new way to store the data, like it's actually paying attention to the data that I use. And so we'll take a look at again here, like it actually gave me something that. It meets my requirements, right? Like, it fits within the design style. I can submit a rating. It stores the rating. So I have now my five star one rating. I guess I'm in a
12:19 Claire Vo? It's terminal core. You got your monospace font.
12:23 Speaker 00 Let's refresh the page to see that persistence actually works. Beautiful. There's a tiny bit of layout shift that triggers my neurosis. So we'll tell it, hey, when we don't have data, make sure there's no layout shift. By the way, for those of you that are like less neurotic, I guess. So it bothered me that when we refresh the page, when we didn't have data, like it jittered the sidebar a little bit. So we're just gonna have easier
12:48 Claire Vo? So while we're jibber jabbering, while it's thinking, which I have to get very good at as a podcast. So I will call out that I have observed a Vercel internal hackathon. And I have seen this man screenshot like rounded corners that are not right. And just put them in the chat with like a question mark. And so I, it's, it's, yeah, it speaks to my, um, my very attention to detail heart that you saw, you saw that.
13:15 Speaker 00 Let's see.
13:16 Claire Vo? Did it work?
13:16 Speaker 00 Yeah, no, I'm fairly satisfied. Like the
13:18 Claire Vo? Yeah.
13:19 Speaker 00 The skeleton was stable.
13:20 Claire Vo? Yeah, yeah, yeah.
13:22 Speaker 00 Zero layout shift. So let's continue with the, we, we talked about this hardcore engineering workflow. Like if, if we were making a change like this on skills at its age, again, receiving hundreds of skills per hour with lots of visitors. We first want to make sure that things work, right? And right now, you, you can think of this as a very capable dev environment. We're booting up the next JS dev server in a virtual machine. It's, it's, it's basically very true to the actual end result. In fact, thank you to the next JS engineers who sweated all the details of mirroring to the best of their ability, the dev environment and the production environment. But there is another layer of assurance that we can get, right?
14:06 Speaker 00 Which is, so if you're more familiar with the, like the GitHub world, the GitHub side of things, you know that when you push a new PR to GitHub, the, this beautiful Vercel bot comes to sort of save the day, right? You know that it builds what you, what you're changing and then it previews it. Not only that, but notice that V0 really cooked. V0 is making me look so good here.
14:32 Speaker 00 I haven't written a PR description in like 25 years, 84 years. So V0 produced a PR, described it.
14:41 Speaker 00 And then the magic of Vercel is coming in, right? So it's giving me that preview. So I'm gonna, I'm gonna open it here. I'm gonna say visit preview.
14:47 Claire Vo? I'm just, again, I'm gonna be a software engineer for a second. Can we appreciate how quickly that preview branch deployed?
14:54 Speaker 00 Well, don't trigger me because it can be 10 times quicker. But yeah, I'm proud of it.
14:58 Claire Vo? Question mark, explain.
15:00 Speaker 00 Now I have a production-like environment. So when you see this URL ending on dot versal at SH. Dot versal at SH is our enterprise Vercel environment. That's why I had the 17 steps of logging in. But this is basically running on the production-grade CDN, on the production-grade rendering infrastructure, hosting infrastructure, et cetera. So now when I'm seeing that, you know, rating there, I have pretty, pretty good confidence. I was like, yeah, this is shippable.
15:26 Claire Vo? Okay, so I have to ask a couple of questions about the, you know, inside-the-house view of this. Is this how you all are shipping code? Or is this a big chunk of how you're shipping code to this? Is it 100%? How are you actually using this for production?
15:40 Speaker 00 So it's really interesting. We, when we cook on a, on a project or a product internally, we hold ourselves to the same sort of high bar as if you had launched a product externally. Because you want to make sure that people are actually adopting it, right? And so before, before we started chatting, and I'm gonna give you a glimpse of, again, the behind-the-scenes of Vercel. We've talked a lot publicly about our data analyst agent, D0. Yes, we're very creative with, with names. We take the first initial and we add a zero. So this is our data AI-powered assistant. And I was actually asking it, I said, Um, V0, this is me, by the way. Tell me about PR smudge with V0 in the recent weeks.
16:24 Speaker 00 Tell me about its growth. So again, PR smudge with V0 is a totally novel thing. And V0 cooked. Thank you, V0. It said, PR smudge via V0 have seen explosive growth in the last week. Wow, explosive growth.
16:39 Claire Vo? I have to appreciate whoever prompt managed this one because it did not put the explosion emoji in there, which I think would also trigger G.
16:47 Speaker 00 All right, we should. Yeah. True warning. Starting from near zero in early January, the feature hit thirty to hundred PR smudge per day by January twenty eight, twenty nine, which is basically today. An extra area a hundred X. The bots, the AIs do like to like, like, yeah, like sweet to talk us, but it's pretty amazing. So this is in very, very, very early preview, right? Like we were just letting people in. But I mean, this is just such a beautiful workflow. I mean, imagine triggering a task like this from your phone, from Slack, from V0.app. Another convenience that we're adding is that you can take a GitHub repo like this
17:32 Speaker 00 and I can go to the homepage and then I can paste it. And so now I could import something that I already have and create a chat from it. So anytime I have an idea for a real world project and product that Vercel has in production, I can now prompt. So I estimate that this is going to change fundamentally how we work, right? It's also very visual in nature, which is really cool. Obviously, there is a lot of ways of like getting preview, getting changes made by agents today out there in the world. Is that everyone's very excited about what AI can do. But this is actually showing me the actual results and like things that are gonna happen. So I grade it's really high for the kind of products that we build at Vercel and I expect this to continue to have a lot of traction.
18:17 Claire Vo? So I have to ask you, sort of operationally, how do you imagine companies do this? And one of the things I'm thinking is I was chatting with Caroline, who interrupted you all and said we're gonna start the podcast. And she said last night, I was prepping for this demo and I V zero coded something and somebody saw it and was like, well, that's a good idea. You should just merge it and ship it. Like, do you imagine, or inside the company? Who's shipping code? How are you enabling that as a CEO? How does the culture support it? How does it not?
18:48 Speaker 00 Until now, everyone could cook, right? Everyone could create a prototype, a new design, a suggestion. In fact, moment of vulnerability, because I haven't really even opened this in a while, but like, let's see if I have. I've probably created a bunch of things that I've been suggesting to the teams that we could look at, right? Ignore this one for a second, but. So anytime I have an idea on how to improve the product, I nowadays create a V zero. Now, the difference is that until I had this mechanism to hand it off as a pull request to the engineering team, then I was kind of like playing in la la land. I was like in out there in this like prototype world. And now we have a common foundation and a common substrate.
19:32 Speaker 00 So that if you have an idea, whether you work in marketing, marketers always want to change the website. Like, imagine, like, go to vercel.com. I'll show you a page that is actually quite fun at Vercel. So our enterprise page. Every marketer at Vercel wants to change this page at some point, right? And the old way was one of two ways. One is what I called, you had a petition to the government. You had to go to engineers and say, engineers, please, can you please add a logo over here or whatnot? Or pray that the CMS was perfectly wired up for any ambition or dream or idea you had.
20:15 Speaker 00 So now they can just open this page in V0 and prompt anything that they want, but it would be somewhat irresponsible to just ship it, right? So with the Git workflow and opening up PR and being able to preview it, we can all build confidence that it's going to be a good change, roll it back if needed. And again, this is a website that's pretty, pretty large.
20:37 Claire Vo? What I think is fun about this from an org perspective is it reduces the friction of getting something live really, really low, right? And like the humiliation ritual of prioritization goes away. And you can actually focus your time on defending the merits of an idea on the actual idea as opposed to the hypothesis of the idea that then has to be implemented. And so I think it changes the speed of companies in, in a really significant way.
21:03 Speaker 00 And you worked, I mean, to say the least, at LaunchDarkly.
21:06 Claire Vo? Yeah.
21:07 Speaker 00 And you know that a true production-grade release process involves things like feature flags and experiments and things you need to be measured. And there is events that are critical to report from these product surfaces. And so this is also where I see the skills that we can add to V0 and that you can contribute yourself to play a very important role. Because sometimes, you know, like we're all operating on this like websites and pixels and whatnot. And we say like, ah, it seems easy. How risky could it be to move this button 20 pixels to the right? And so I think we can make vibe coding scale to that kind of rigor that exists within enterprises and companies at scale.
21:48 Claire Vo? Well, and if we're being honest, on that enterprise, it's not going to be moving a button two pixels. It's going to be switching the emphasis. I know this because I spent my life in enterprise, switching the emphasis between contact sales and view the product. There's going to be a perpetual debate, which one's the primary call to action? Which is the secondary? Okay, I, we, so we've shown a new V0, import GitHub, which I think is really great. Do a pull request, copy and paste your GitHub URL in to import it, actually push to production, make friends with your engineers, three sentence prompting, no more than that. I want to go to quick because we want to keep this tight. I want to go to a quick lightning round with you and ask you a couple of different AI questions. So what is your favorite non?
22:30 Claire Vo? I mean, everything's a coding use case, I'm sure with you, but what is your favorite non-coding use case of AI?
22:36 Speaker 00 Well, I'm conflicted. My mind immediately went to image generation. Because I use, so we built a banger playground. I don't want to share screen again. I want to take it from you, but.
22:47 Claire Vo? This is, oh, no, I was just gonna say image generation is how I got this pretty, pretty background.
22:51 Speaker 00 V zero nano banana pro.
22:53 Claire Vo? Nano banana.
22:54 Speaker 00 So what's really cool that's happening at Vercel today is that we're building so many of our own internal tools and agents. And so we're building our own design tools, like for example, to create new images. We created a playground for nano banana. And I use that a lot. So I use it to make memes, guilty as charged. But I also use it when I want to present information in really cool ways, when I tweet, when I sometimes have to make a, present my vision in a way that's more like on the image side of things. I combine it a lot with V zero. Because nano banana is really good at like, again, letting me, fire off twenty generations in parallel. And then pick the one that I actually like, and then I toss it into V zero.
23:36 Speaker 00 And then I actually get more fidelity when I want to implement. So image generation is, is a big one. But also I'm very excited about video generation. We're gonna be dropping something. I don't want to spoil it too much. We're gonna be dropping something on the video side as well. And, but yeah, all, all AIs, I also, I also kick off a lot of research tasks, like long horizon research tasks. Yeah.
24:00 Claire Vo? So one of the things I want to call out from a nano banana perspective or podcast is I've used nano banana to turn every conversation. I think we're now at a hundred and eighteen workflows. Every AI workflow that we talk about on the podcast gets its own, pretty consistent nano banana infographic. And so I just think there's just such undervalued use cases in both idiot, image and video gen. And I'm about to take this and turn them all into little mini videos.
24:26 Speaker 00 We also created a really awesome, I don't know if we've written about it yet, we're gonna publish on the blog post. We have an OG image, like an open graph card, Twitter card generator that we use internally. That combines more traditional rendering techniques, but also image generation. So a bottleneck in our team was sometimes literally like, can we get that social card? To get the announcement through the door. And so now we, we've also sort of automated and agentified that. Every day we're basically asking ourselves, how can we build an agent that takes over a task that we were previously given to a person? And typically, the person that was working on that task is now the one creating the agent. So something we said at the beginning is, we want V0 to be really awesome for you all to create agents,
25:11 Speaker 00 not just traditional web applications. So that's basically the roadmap of the product.
25:17 Claire Vo? So I have to say, my favorite, so that's your favorite use case. My favorite use case of your use of V0, which I don't know if you're prepared for me to have this much knowledge about what you vibe code, is your agent-to-agent chess game. My kids are obsessed with this. They think it's because they got the AI chessboard. And now they're like playing chess at various levels.
25:39 Speaker 00 By the way, I learned a lot. So it was really cool. Like during the holidays, I'm kind of a visual person. So the chess AI thing has been done before, but I imagined this sort of, imagine like ESPN is broadcasting a final of a chess match and they're going over the shoulder of each player and showing the chessboard, obviously in 3D. And so I figured, could V0 generate 3D code, right? Could it render with 3JS and things like that, a live chess match? And could I have two AIs battle it out? And so you could open in V0-chess-match.russell.app.
26:24 Speaker 00 And the other thing, the other thing, I wonder if I am SEOed or not.
26:30 Claire Vo? You were number one. Good job.
26:32 Speaker 00 Yes.
26:33 Claire Vo? A little terminal core over here.
26:35 Speaker 00 So terminal core, of course. But so what I did is I started streaming the thinking tokens of the models. Apologies to Google in advance. We're using a very old model of theirs that is really cheap, but they're losing 2205. At least they got five in. So you can see the thinking tokens of the models. This is combining all of the Vercel AI infrastructure. It's using a workflow. So the game could run forever. The game could literally run forever or until I run out of tokens.
27:06 Claire Vo? AI gateway.
27:07 Speaker 00 AI gateway, of course, because we can change models. Like we could see like Brock versus, you know, whatever. What dropped this week? When 3 Max thinking? But also I learned chess incidentally because not from these guys, these guys are kind of dumb. But you can see how it thinks through what piece to move. And it says, oh, no, because if I move it there, I'm gonna get F. So I need to do this. So this is a fun V zero created during the holidays.
27:35 Claire Vo? Yeah, so I need a kid core version of this. Um, I also want to see how much these models are spending to beat and lose.
27:42 Speaker 00 Well, that's a beautiful thing about the AI gateway is that we kind of report, you know, for this prompt, how much it costs you with this model, et cetera. But see, so this is GPT open source, which is actually pretty decent and pretty cheap. So.
27:57 Claire Vo? Great. And then so on this talk, so that's my kid's favorite, your V zero. I don't know if they have a favorite, my V zero.
28:04 Speaker 00 It's popular with kids. I also got another parent reached out to me and say like, oh, this really inspired us and we're gonna use V zero together to create more things.
28:11 Claire Vo? My kids, uh, D A U on V zero. Don't worry about it. So this is my second question, which is, what is the last thing you built with your kids that was really fun?
28:20 Speaker 00 So the other day I brought them all to the office and what we started vibe coding is, so now we want to do things that are more like physical AI, like bring AI to the real world. They think it's the next frontier. And so at the office, we have a thing called Vesta board, which is a board where you can basically render things in the real world. And I think I really broke their, their brains that day. Not all of them, because I brought four of them and one was on his iPad, not paying attention. It was almost like bringing them to Sunday school, for what it's worth. Uh, but two of them were like, holy crap, you can type in code and then you can change the real world? So I kind of taught them the concept of an API. Uh, and yeah, all of that coded and I, I took one of the nannies too, and she was mind blown.
29:05 Claire Vo? Well, that is.
29:06 Speaker 00 I'm teaching everyone how to vibe code.
29:07 Claire Vo? That is, you and I, we're like twin stars here because while you have the Vesta board, which is pretty big, I have this like tiny, like thirty two by thirty two pixel fake little mini computer that my kids and I are like, vibe coding, a little screens on, a little games on. So I completely agree. Take it off the screen for many reasons. If you have kids.
29:26 Speaker 00 Yeah.
29:27 Claire Vo? Put it in the real world and you can do some. Fun stuff and blow their mind.
29:29 Speaker 00 The idea of like sending a packet and responding to it. And the beautiful thing about VZ and things like this is like you're literally speaking English to the computer. So I think if you can teach them that they can express their thoughts and desires, then they can make anything happen.
29:44 Claire Vo? Okay, important question. Are you teaching your kids to type?
29:46 Speaker 00 That's a tough one because I was, when I grew up in Argentina, my dad got me this soccer game. He tricked me. I thought, oh, he's getting me FIFA or something cool. No, he got me a soccer typing game.
29:59 Speaker 00 So to score, I had to type really fast. And that's how I learned to type really fast. But nowadays, like they're kind of getting really into the, the speech to text thing. I need to find that hack where like, oh, I got you Roblox and it's not, it's just typing.
30:12 Claire Vo? So I, I, I'm tricking my youngest right now. We have a Switch. And I really don't play Ocarina of Time for people that were born when that game came out a million years ago. And the only reason I let him play it is it's like 99% just reading.
30:27 Speaker 00 Nice.
30:27 Claire Vo? And so I'm like, you can play this very slow paced game. It's a game. It's really just going NPC to NPC and reading two sentence phrases.
30:35 Speaker 00 So we played a game like this with my kids during the holiday break. It was basically like a puzzle math game that looked like a game. And that inspired, so okay, good and bad. The good was the game was like really educational. The bad was like it was like ad ridden brain rot slop. And so it's like, okay, huge opportunity for someone to create a game platform. You can combine all of these models. You can do image generation for the assets. We're about to drop something insanely cool, text to SVG. There's models that now produce really, really high quality. We're gonna share re-craft models through the Versale AI gateway.
31:15 Speaker 00 So you can create assets that are beautiful, game ready, scalable in high DPI screens, whatever, iPad. And so I really, I, I, I see the future of really high quality content at our fingertips and getting rid of all this slop.
31:32 Claire Vo? Yeah, well, um, I, you know, my, my future roadmap releases are not as confidential as yours. And so I am in the back of my mind. Working on like Mama Claire's dojo for crack little hackers.
31:42 Speaker 00 Nice.
31:42 Claire Vo? So maybe someday and deployed on obviously Vercel. Okay, last question. Do you, when you're frustrated, prompt AI the same way I have seen you prompt in Zoom chat? Which is, explain. How do you, how do you, how do you, yeah, question mark. Like, what do you do when it's not giving you what you want?
32:02 Speaker 00 So I, I do think that what we, we're dropping now is gonna help you so much for the moments where, like, I mean, let's be real. You can get stuck with AI, right? But now that you can essentially have this full, like, let's call it escape hatch, right? Like, you can, if you want, you can clone the repo and keep cooking on your local machine. Or if you need some, someone else to help you, this is fundamentally a collaborative medium. That's the thing that GitHub unlocked for the world, collaboration between engineers, designers, marketers. And so I, I foresee that a lot less people are gonna get stuck, frankly. The models also keep getting smarter. Skills is gonna help you a lot as well. So I'll give you an example. We are always adding new frameworks and new capabilities. And next year is getting more powerful and the AI SDK.
32:48 Speaker 00 Now that we have skills for those that we're gonna preload into V0, the model itself is not gonna get as stuck as easily. Cause now it has more resources to like, figure out how to solve that problem. Another thing that I've done, it actually used it for this project. So there's a lot of subtleties about this, this 3D thing that I didn't know anything on 3D. So whenever I would get stuck, I would ask other models. I think it was something about the way that, and kudos to the awesome soul, the, the gentleman that open sourced the 3D. So I got it from a sketch fab and he didn't design this for creating a game or anything like that. So all of the pieces were stuck together.
33:32 Speaker 00 It was almost like you had 3D printed it and the pieces were stuck together with the board. And so I, obviously I want that sweet animation that when the model decides it moves the piece, right? And so I had to ask a lot of questions to other models about, hey, teach me what's going on with this 3D thing. How do I, how do I reason about it? And then I would copy what another model tells me and I would toss it into V0. So another thing that you can do when you get stuck is you she can't see it here because it's only for me. But there's a debug button. And what the debug button says, I asked B zero, hey, give me debugging tools. So that I can visualize the mesh of the 3D model. I can visualize, I can turn the textures on and off.
34:16 Speaker 00 And so the the AI itself can help itself. It can give you tools to debug problems, which is kind of meta, but try it, try it and it's going to work well for you.
34:26 Claire Vo? Okay, so you you ask an expert, which is another model.
34:29 Speaker 00 That's right.
34:29 Claire Vo? And you find out the right question to ask. Well, this has been very fun. Thank you for showing us a little bit behind the curtain of how you use V zero, all the new stuff. Some of the ways you use it in your personal life and fun projects. We love to see it. So you have this new V zero, you have this room full of people. What do you want from them? What what can they do for you?
34:48 Speaker 00 I mean, get busy shipping. So try it out, give us feedback. We will fix it very, very fast because we're going to be eating our own dog food. And yeah, share the things that you built with V zero.
35:02 Claire Vo? Oh, we have a question back here. Oh, I love it.
35:04 Speaker 02 So I had a question. Thank you for sharing like the feedback process, how you loop in terms of like from ideation to like production, like during that process, do you do any like product market fit? How do you validate that what you're trying to build is actually like useful or impactful for like your ecosystem?
35:23 Speaker 00 Yeah, super hot of the presses, new sort of mental model that we've been using internally. There's a customer zero and a customer one. Customer zero, we like to be ourselves. We it's like the Rick Rubin, the confidence in our ability to know what's good, whatever. Like we like our taste. We've been around the block for a while. We want to, we have ideas of products that we would like to see out there in the in the universe. But customer one is also really important, like a closed design partner, Claire Voe.
35:54 Claire Vo? Oh.
35:54 Speaker 00 Claire V zero. Claire and our our CPO are constantly texting.
35:59 Claire Vo? We're on a text chain, yeah.
36:00 Speaker 00 She she texts bug reports, she texts things she needs. So having that group of design partners, enterprise companies, individuals, community members, people that slide into my XDMs. So it's you always wanted that pressure test of of the world. And for skills, it was that, you know, people telling us, hey, like, why does Opus 4.5 kind of know the latest next year's but not really? And how can we embed your best practices? So that was kind of like in in our backlog, like we were thinking about that problem for a while. But then it also became really concrete. We were like, OK, how would we go about distributing and discovering these skills? And so sort of the idea became very complete. And that's where a tool like V0 really helps you.
36:43 Speaker 00 Because when you want to extract it out of your mind, you can just V0 it. And so pretty much what you see today, it started with like four or five V0 prompts in a conversation with our VP of Design, who then took it away further and made it actually good and and our our CTO and our and our product leader.
37:02 Speaker 03 So you mentioned about BMs. Is there a possibility of having React Native in V0?
37:08 Speaker 00 So what you saw today is if you if you if you feel the covers of how V0 is built, it's built on a bunch of Versale infrastructure that you also all have access to. The the virtual machine that we use to run that next year's preview is called Sandbox. So the Versale Sandbox is a very powerful computer. In fact, what's actually making agents really capable is not that they're perfect, is that they have a computer at their disposal in order to solve every any problem. So the reason we showed you a glimpse of how we work internally with V0. The reason D0 is so good at data analysis is that it has a computer where it can do research, it can write Python code, it can run it, it can make a lookup to Snowflake,
37:51 Speaker 00 it can search the web, it can come back, it can fix the it's like it's like a four or five minute process, right? And so these computers are very powerful general purpose computers. You could imagine them running React Native, you could imagine them writing other programming languages, they can obviously already write Python and run it. And so the sky's the limit from that perspective.
38:11 Claire Vo? I have a question on that topic. Is there going to be a point at which V0 is going to help you build those agents?
38:16 Speaker 00 Oh, absolutely. So the main the main idea of this chess thing, it's cute, but I mentioned the workflow. So it's actually tricky for me to say this program is going to run forever in the presence of network or compute failures. So in fact, like, you know, we're doing this live and just randomly came up with the idea. The reason I had confidence that demo was going to work is that if an LLM provider is down, or a function called dies, or times out, or whatever, the workflow engine of our cell will say, we're doing live, we're going to try it again, and we're going to try it again, and we're going to try it again. What we're going to help you do is create those kind of workflows from within V zero. A lot of
39:01 Speaker 00 agents need that kind of reliability. For example, you send a message from Slack, and you say, at player GPT, go and spec out this PRD for me.
39:12 Claire Vo? Yeah, it's called at chat purity. It is running on workflows and
39:15 Speaker 00 Yes, we didn't rehearse this.
39:17 Claire Vo? Yeah, so we do have, we do have, I feel the pain on, on agents where workflows are really helpful because they give you durable overtime execution. You can retry things, things can fail, you can do them sequentially, you can do all sorts of things. And so I do think the ability for you to build that on the backend is very helpful for, even for applications that don't have the same kind of UI that you would have it.
39:38 Speaker 00 Totally. Because some are, some are very visual, and some are going to be more headless. Like, some are going to be background agents that are doing work for you. In fact, the world is excited about the artist formerly known as Claude Bot, Mold Bot. I don't know what Mold Bot means, by the way.
39:55 Claire Vo? Well, crustaceans, this is how you know you have kids in like elementary schools, crustaceans like lose their shell, so they molt. Yeah, it's like a snake.
40:04 Speaker 00 Yeah. Got it.
40:06 Claire Vo? And then emerge to steal your bank account.
40:09 Speaker 00 But, so that's a beautiful example of the background thing, right? Because you text it, and it does a bunch of stuff for you, and then a response. So that, that's the kind of thing that we want you to be able to build with V zero, where it's going to use workflows, it might use sandbox, and it might be more, I think Mold Bot is like super general, it can do anything, can even hack your computer. But I expect a lot of really cool agents to, to work that way. Like, you just WhatsApp them. Yeah, and we'll, we'll help you build those with V zero.
40:40 Claire Vo? And the last thing I actually deployed on Vercel was my live Mold Bot conversations. If you want to see, well, it is terminal. I, well, I, I shut the computer and walked away. I did not enjoy my, it was an interesting experience. You can smash that subscribe button if you want to watch it. But I did, I did deploy to Vercel a terminal view of my conversation with Moldbot. So you can go, it's like, it's quiet.
41:07 Speaker 00 Moldbot confessions.
41:07 Claire Vo? Yeah. Oh, that's exactly what it is. Yeah, it's real scary.
41:10 Speaker 00 That app.
41:11 Claire Vo? Great. Maybe one more question?
41:12 Speaker 04 Oh, wow. What an honor. First of all, thank you so much for hosting the event. Thank you so much for the new V0. I ship a lot with V0. My co-founder is using Cursor and now we have like a mutual compatibility.
41:24 Speaker 00 We're so back.
41:24 Claire Vo? Love it.
41:25 Speaker 04 There you go. And so I wanted to, again, I'm also a V0 ambassador. There we go. Let's go. I wanted to ask two questions. Number one, a little bit different, but when do you think so V0 has really democratized the ability to go from prompt to UI, UI that works and UI that satisfies like the prompt that the user created? When do you think that paradigm is going to happen within consumer in genuine UI? I see that your team has been playing with a bunch of different libraries, different ways to create that. When do you think that switch is happening? And then the second question, when can I write a prompt and then deploy to the App Store?
42:05 Speaker 00 Yeah. So on the, on the first question, sometimes you're going to want like a flash V0. So we're playing with ideas around generative UI where an agent might decide to render something and think of it as like spontaneously creating the UI code and then rendering it right away. You're not actually creating a code and an application and deploying it. You just want to make it happen. So we're doing a lot of research on like, what would that look like? So it's another tool that we can give agents. On the App Store question, you've seen some of the stuff that we've been doing with V0 iOS app, React Native Skills. A long held dream of ours has been to really democratize pushing to the App Store like
42:48 Speaker 00 you would push to the web. And everything here is like sort of using that same, those same ingredients, React based deployment platform, just deploy with one press of a button and whatnot. So yeah, don't want to promise any timelines, but definitely something we want to do.
43:04 Claire Vo? Thank you. Thanks, everybody.
43:08 Claire Vo? Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.
Previous How this PM uses MCPs to automate his meeting prep, CRM updates, and customer feedback synthesis | Reid Robinson (Zapier) Next How to build your own AI developer tools with Claude Code | CJ Hess (Tenex) Page updated October 31, 2026 · transcript and summary are machine-generated
