Guillermo Rauch, founder and CEO of Vercel, advocates for a 'trust but verify' approach when using AI agents, emphasizing that developers should personally verify AI outputs by testing them as novices, using adversarial validation with multiple AI tools, and maintaining human oversight for critical decisions. He demonstrates this philosophy through his daily workflow, where he uses agents like d0 for metrics analysis and email triage, but always manually reviews final outputs and maintains a 'creation over communication' mindset, believing that building real products is more valuable than extensive verbal or written discussions.
Deep Dive
Prerequisite Knowledge
- No data available.
Where to go next
- No data available.
Deep Dive
The Man Who Built a $9B Dev Platform Thinks You're Overcomplicating AI | Guillermo RauchAdded:
This is a clear instance of a CEO actually adding value even though it's marginal.
>> Hi, I'm Jules and this is Show Me Your Stack, a series where we're interviewing your favorite techies to understand what their day-to-day tech stack actually looks like. Today we're interviewing GMO who is the founder and CEO of Versel.
>> This is Show Me Your Stack.
>> One thing about G, he loves to hack.
>> He loves to hack. benevolently only good hacks.
>> I actually love reverse engineering taking things apart >> is that to sort of identify the holes in that system as you take it apart.
>> Something that I focus on a lot is trying to understand what's true about the world.
>> Yeah.
>> If someone tells me like this framework or this tool is really successful, popular, etc. I try to understand like is that so like can I go out into the world and see how it's being used? I have an attitude of like trust but verify with what I hear.
>> So are you always first person verifying things or >> I try to and and because I have agents that can do the work for me and I can say send my agents outl >> into into the world and I do that not because I don't trust you but because >> you can say it.
>> I I actually don't trust her.
>> I want to verify technology from an enduser perspective. I want to try it out. Like I'm the first person to ever use this technology like where I pretend to be a novice.
>> Yeah.
>> I click things that are not meant to be clicked. People sometimes like don't look forward to my product reviews.
>> When I first came to San Francisco, mobile and cloud were like blowing up much like AI is blowing up today. M >> I don't know that we had so many billboards dedicated to the it took a lot of reconfiguring of your priors and your mind of I now have to think more about mobile and if you succeeded in doing that this massive market opened up to your company and so now people have to do that for agents >> so to me there's a lot of elements of deja vu deja vu deja vu >> one of the The most magical parts of early versel days was the ease in which a developer could spin up a UI and create an interface which is like so ironic that we're now here craft interfaces.
>> I think we need to now think about what is the equivalent design philosophy but for building agentic products. The new interface for agents is going to be natural language and conversation. So, WhatsApp, Telegram, >> Versel just announced the chat SDK to help developers build agents that have interfaces in all of the messaging platforms. I think UI this is still going to be important that you can dive deep into the things that the agent looked into. Let me read those logs. The models continue to improve. More and more of the world will be the agentic interface. M >> so I I still think a lot about like more and more of our company runs on our internal agent. Right now it's called D0 >> D0 >> V0 and D0 >> unfortunately a little too close.
>> It's going to get renamed soon.
>> What are the interfaces that are going to be most important to us in our day-to-day? you were asking about like what what are some apps that I use and I believe that in the fullness of time and this is what Verscell is enabling. I'm going to be able to go to any application and it's going to be agentic and AI native for applications that are not fully AI native yet. I can do command shift space brings up raycast AI. I still use the terminal a lot by the way. I use clot code and okay >> I I use this for automating some things on the operating system side.
>> How are you actually operating as day-to-day?
>> Dere is a big part of it. I have a bunch of channels where I get periodic reports of company metrics. I also can ask the zero for bispoke questions. I also shared on X recently. Every Monday I get the brain dump. The agent does basically like a business analysis. It looks at our metrics. This is what happened to total requests on the platform. This is what happened to total compute on the platform. This is what happens to all tokens on the platform. Agents are really good at spotting trends.
>> Okay. So, walk me through this is how you're also reading your email. Yeah.
>> How does that work? you you no longer use a Gmail superhuman interface.
>> I I still use it from time to time. One of my predictions that is actually I'm stealing it from Nikita X. He mentioned that the spam problem is going to become more and more insurmountable because of things like open claw. It's very hard to notice if some post on social media is coming from a person or some agent.
>> So if you were to write me an email right now, how would you do that?
>> Writing doesn't happen that often.
Although I will say that for example I can say here summarize these actions I just took and send them to Valerie on Slack. I have the Slack MCB wired up.
>> You are not in Slack writing these messages yourself.
>> Well I am I am most of the time. I am most of the time.
>> Every Versail employee is twice when they receive a message.
>> Uh it found my EA.
>> Yeah.
>> Right. And and by the way I think it discloses it. So let's let's open it.
>> She's going to be like aren't you in an interview right now?
>> So perfect. Right. So, here's a summary of what I just knocked out. Um, >> so cool.
>> It's so impressive how in the weeds you are still as a developer. Obviously, you've always been a developer. You love building side projects, but this still occupies a lot of your time.
>> Well, the funny thing is, is this developing? G from 10 years ago would be like, "No, man. It's an IDE or using Vim." Like, I'm a huge Vim user and whatnot, but I haven't really had the need. I use nano banana a lot in grog to take an image of something and very quickly prompt to do something else or to give an idea to the teams. I think creation really replaces a lot of the more bespoke ways that we used to communicate. I really believe that a real link and a real product is worth not a thousand words, it's worth 1 billion words. We've been talking about it and and I always say like whenever we catch ourselves talking, we should be vzeroing.
>> Why? Why are you chatting on Slack?
>> Yeah.
>> Get get busy building.
>> Get to Vzero. I love our documentation, but it's overwhelming. So, let let's actually open it. I was telling uh our designer of like, hey, like let's actually make it real. And within two basically vzero shots, I now have a new version of documentation. This is a clear instance of a CEO actually adding value even though it's marginal.
I prefer to do this >> which doesn't take me that much time than give a bunch of unstructured feedback on Slack or meetings or whatever, >> right? When you already have a clear idea of what you want.
>> So, it's like I asked Vzero, build me like 20 different progress bars that resemble classic video games.
>> Gosh, I love this.
>> And by the way, came up with the ideas, too. This is not an original G idea.
This is an original G's agent idea.
>> I invited the agent to augment my idea, which is something that I also recommend. A little bit of like ego death. Don't try to overly complete the idea because you're not that smart.
>> How he starts the prompt. I am dumb. I am not that smart. Let's see what I did.
Please fix my ideas.
>> What was really So this is where I was giving the agent a lot of feedback.
>> How far are you going to go back with the agent in like tweaking these little by little changes? It depends on how much time and how obsessed I am with the problem.
>> I created tooling that allows me to count how many keystrokes I entered into a given day.
>> Is this a reflection of your productivity in a day? I >> I tend to think so. So, let's look at the data.
>> The month of February.
>> It's all fake.
>> Oh, what?
>> It's all fake. So, I actually have it sharted by computer. So, it only has the last few days of data.
>> Let it be known he was working in Q1.
Feb 26. It was my hottest day.
>> Nice. The Coachella of coding.
>> That's right.
>> I do think that prompting well is an art >> of sorts because sometimes I found success by saying agent, let's both take a deep breath. Let's reset the approach altogether. It's not unlike managing humans. When I inst a a G soundboard, >> one of the >> I'm going to make an example. Now, >> one of the key things is why is this so slow? Why? Cuz I know how fast it can be. This is why understanding systems, understanding the raw materials, understanding networking and like the bigger like higher level concepts is really good for the prompter because then you're not sending your agent into a dead end and you're not wasting tokens chasing something that's not fundamentally possible, right?
>> Yeah.
>> We launched for cell cues and I wanted to tell the world about how it's different. I cooked with the agent on a couple things. One, I asked you to visit our documentation and compare it to the other products. I combined the research task. It created the dimensions for me and then I also made it beautiful so I could screenshot it and post it on the X platform the everything app. Before I post it, I adversarily checked with a bunch of other AI tools. You can create like a consortium of agents to like judge your work and then I also uh work with the humans with the humans on this one >> and then yeah and then sign off. You're like, I'm optimistically trusting the AI, the agent, to perform tasks on my behalf, to do this research, but I will always, always, always check.
>> Yeah. The the ultimate check that I've always loved to do, I check the final product. The final product has to be great.
>> This episode is brought to you by Vzero by Vurcell. Vzero by Versell is like your favorite coding agent, but on the web and no setup required. Whether you're technical or not, take your ideas out of the group chat and into production. It's not just a vioder, but an agent builder where you can prompt, build, and ship in minutes. Every prompt becomes real deployable code connected to your stack. It's never been easier to create a new landing page, deploy your next app, or build your first agent.
Visit vzero.app to go from idea to production in seconds.
One of my predictions for 2026 is that we're going to generate so much software as a collective. So, you have to decide, all right, what are the battles that I'm going to pick? That's why we have a lot of really cool things that just meant to stay internal. They're highly custom to how we work at Verscell. We don't want to pollute the world with noise and like, hey, here's 20 other new things for you guys. There's also an app called Timeless. This is another app we built internally that allows me to whenever I spot a bug, I can press a command and dump a few of the last few seconds of screen recording and document the bug for my teammates.
>> Oh, interesting.
>> So, if something happened in the past that I wasn't happy with, you can go back. You can go back in time.
>> What is an essential part of your non-digital stack?
>> Due to being on a time crunch, I spend a lot of time on Pelaton. Oh, >> I guess it's digital in some fashion.
>> Digital thing is still a digital thing.
>> My non-digital thing is digital.
>> How do you handle task management?
>> Don't I try to memorize the most important things? The reason I do this is if something is so important, >> how is it falling out of your top of mind? Why do you need to write down a reminder?
>> I feel like my memory has deteriorated so dramatically because of AI use. Like I rely so much on the tools to be my memory system.
>> For me, it's not so much memory. I think what's going to deteriorate first is the hard thinking cognitive skills cuz you don't use those brain paths. Do you feel like any of that has deteriorated for you yet?
>> I think so, actually. But I've leaned more into the massive diversification of tasks and delegation that I can do. It's been a good tradeoff.
>> Oh, no.
>> Yes.
>> Thank you so much.
>> That was super fun.
Related Videos
The #1 Reason Your Top People Keep Leaving (How to Fix It)
Entreleadership
470 views•2026-05-29
What Happens After A Motorcycle Dealership Shuts Down?
FastestWay.1
374 views•2026-05-29
The Evolution of DSP's Pokemon Unpack-ack-acking Grift
Toxicity_Unmasked
2K views•2026-05-29
Help re-structure my finances, I want to buy a house, save and invest
JennNxumalo
2K views•2026-05-29
Asian Paints Q4 Results: Revenue Beats Estimates, 5 Key Takeaways For Investors
NDTVProfitIndia
111 views•2026-05-29
Trying to Afford Vancouver on a Single Income | $2,550 Mortgage
chelseaspursuit
308 views•2026-05-28
Are you busy but still feeling broke?
TaraWagner
305 views•2026-06-01
7 Nigerian Stocks That Could Explode Because of Dangote Refinery IPO
femiakinwale9269
478 views•2026-05-29











