Getting paid to vibe code: Inside the new AI-era job | Lazar Jovanovic (Professional Vibe Coder)

I'm the first official vibe coding engineer at Loveable. You're at the top.1% lead level of vibe coding. It's a dream job for so many people. It became a job by building in public. You don't need a company to hire. You can hire yourself as a professional vibe coder first. You've never coded. You don't want to look at the code. Coding is going to be like calligraphic people. Oh my god, you wrote that code. That's so amazing. It's going to be so rare that it's going to become an art. These are the end diagrams of engineer designer PM. You used to be very separate now. They're converging. AI, regardless of your background is an amplifier. If you don't know what you're doing, you're just going to produce garbage faster. It feels like an emerging core skill is learning clarity in the ask of the AI. I like to use the Aladdin and the Genie analogy. You rub the lamp, a genie comes out, I'll grant you three wishes. The first wish is I want to be taller. Genie makes me 13 feet tall because I was not specific. AI just don't understand what do you mean when you say, you know what I mean? So you need to be specific. I'm optimizing a 100% of my time today on good judgment, clarity, quality, taste. Today, my guest is Lazar Yovanovich. Lazar is a professional Vibecoater. He gets paid to Vibecoater all day and build internal and external products. This conversation is going to blow your mind in so many ways. This is not only a really interesting new career path for people to consider, if you listen to what Lazar shares, it's also a really important glimpse into where things are heading for tech roles. I found myself thinking more deeply about the future of product management and engineering and design during this chat than I have in a long time. We'll also spend a bunch of time on Lazar's best advice as an elite Vibecoater for getting the most out of AI tools. He's got a bunch of really interesting and useful frameworks I've not heard anyone else share that will immediately level up your success using all the latest AI tools. This conversation is going to expand your mind in so many ways I cannot wait for you to hear it. If you enjoy this podcast, don't forget to subscribe and follow it in your favorite podcasting app or YouTube. It helps tremendously. And if you become an insider subscriber of my newsletter, you get over 20 incredible products for free for an entire year, including a year free of lovable and replad bold gamma NADL linear Devon postdoc superhuman de-script with profloproplexity work granola magic patterns rakek etch f your demobinant stripe Atlas. Head on over to liniesnewsletter.com and click product pass. With that, I bring you Lazar Yivanovich after a short word from our sponsors. This episode is brought to you by Strela, the customer research platform built for the AI era. Here's the truth about user research. It's never been more important or more painful. Teams want to understand why customers do what they do. But recruiting users, running interviews, and analyzing insights takes weeks. By the time the results are in, the moment to act has passed. Strela changes that. It's the first platform that uses AI to run and analyze in-depth interviews automatically, bringing fast and continuous user research to every team. Strela's AI moderator asks real follow-up questions, probing deeper when answers are vague, and services patterns across hundreds of conversations all in a few hours, not weeks. Product, design, and research teams are companies like Amazon and Duolingo are already using Strela for figma prototype testing, constable validation, and customer journey research, getting insights overnight instead of waiting for the next sprint. If your team wants to understand customers at the speed you ship products, try Strela. Run your next study at stralla.io slash Lenny. That's strilay.io slash Lenny. Today's episode is brought to you by some Sara. If you listen to this podcast, you know that we spend a lot of time talking about building things that sit on a screen, onboarding funnels, mobile apps, and check out flows. Some Sara is building products for the physical world. First responders racing to emergencies, truck drivers, carrying critical supplies, construction workers, building our cities and data centers. These are people who put everything on the line, every single day, and some Sara's technology protects them. Some Sara is solving complex problems at the intersection of hardware, software, and EJI, and their AI doesn't just detect events. It reasons about the intent and answers questions like, do that truck driver break abruptly because they were distracted? Or was that a heroic act? If you want to ground LLMs in messy real world telemetry or solve EJI constraints at a planetary scale, some Sara wants to talk to you. If you like playing with enormous data sets, moving fast and working in small teams, come help build the technology that makes the physical world safer and more efficient. Visit somesara.com slash Lenny to learn more. That's S-A-M-S-A-R-A.com slash Lenny. Lazar, thank you so much for being here and welcome to the podcast. Thanks for having me, man. Okay, so I had Elena Verna on the podcast. She's had a growth at Loveable. She mentioned that she works with a professional vibe coder. You. I had so many questions. I almost wanted to go on a tangent with her to try to understand this role. Instead, ask you to come on the podcast. There's so much I want to talk about. I want to talk about just this career path and just how you got into it, how other people might get into it. Where you think this is all going, this whole vibe coding thing. Also, I want to get into what you've learned about it being successful using all these AI tools because this is your job. First, I want to just start with understanding this actual job. Just like what is it that you do, day to day? You're basically being paid a full-time job to vibe code. Incredible. What are you responsible for? What are you doing day to day? Well, as you said, it's a dream job. I get paid to do what I would have done anyways. It's the best job in the world. I get to use tools like Loveable every day to push projects to production, whether for internal or external use. Those could be ranging anything from different templates on marketing side, sales side, or whatever, or they can be as deep as building some internal tools with a lot of integrations and connections and whatnot. The surface area that I cover is pretty wide across all departments because it's such a flexible role and it complements so many things. It's an idea. A lot of people have a lot of great ideas, but they don't know how to build them. Or they just don't have the bandwidth to. And that's where I step in today to make sure that these ideas come to life fast and with quality and security that they should have in order to be available for users in production. I wouldn't think that's really interesting here as it's both internal and external tools. A lot of companies have someone building a bunch of internal tools using AI, you ship stuff that's actually public and it's like sort of a product, Loveable products. Yeah, definitely. Some of the stuff that are shipped that are public are when we launched our Shopify integration, most of the, if not all, the templates that users were remixing were built by me. So stuff like that or like the merch store because we wanted to obviously prove the concept that, hey, Loveable and Shopify just works. It's so simple, anybody can do it. I've I quoted our merch store. So all the merch, including this shirt that people were buying online, they would have bought it from a store that was built by me. But then again, on the internal side, we want to track a lot of things. Like one of the cool things that we want to build now, for example, like feature adoption matrix. If we build a feature, how many people are actually using it, adopting it? Like, and that's a pretty custom build, right? We have a very custom stack, we're building custom features. There's nothing out there that I could just pick off the shelf and build or adopt faster than I would have built it myself. Like at this point, I'm at a stage where like, if it takes me an hour or two hours to set up like a big enterprise account somewhere, I'm just gonna build it myself faster. So, you know, I'm in that position of like, build versus buy, I'm in the build boat, so to speak. Yeah. And then who do you report to? Or are you kind of this rover that helps wherever, or are you with the winnest specific team? I'd say probably closer to the former, right? I've started in growth, right? Elena brought me on early on, and you know, to come because she has so many great ideas and like she just needed somebody with the right type of mindset and velocity and ownership to just take them away, build them up, get them into production, whether they're like based on education or anything, go to market or whatever. But then obviously, when you're able to ship fast, everybody needs that in an environment that we as a company are now living in, which is where the fastest going start up in history. So every department needs a Lazar now or yesterday. So now I'm like shifting a little bit, I guess into some of the go to market roles and even building some again, internal tools or enterprise T, but I'm working on some community tools as well right now as I speak. So I'm a little bit all over the place by kind of thriving that environment. We're like, I'm given a rough concept, a rough idea, and I'm just tasked to bring it to life as soon as possible. Okay, I'm hoping with this chat, we create a lot more Lazar's, and I want to get to the career path, how you got to this and what it takes to actually become a full-time bike-coder. But I want to start with, because you do this full-time, you're at the top 0.1% elite level of bike coding. You're doing this full-time, they hire you to do this as a job. I'm so curious what you've learned, what are some pro tips that you've developed for being successful with AI tools, lovable and also just more broadly? What are maybe two or three things you've learned that help you be really good at this job? The first understanding that I had very early on, even though just in full transparency before we begin, I don't have a technical background. I never wrote a single line of code in my life, almost like I've written a couple of console logs manually and that's about it, right? So I'm very much lead onto AI assistance. Let me actually follow that thread, because that's such a good point, and something that when we were chatting earlier, you pointed out your feeling is, it's actually an advantage to not have a technical background when you get into the space. Yeah, I honestly feel that it is, because people like me don't know that they are not supposed to be building XYZ, and that's how we actually are able to build it. Let me give you an example. Like six, seven months ago, somebody in our community was like, oh, I wish lovable can build Chrome extensions, right? And then folks that are not technical, were like, well, why is that not possible, right? And then people that are technical start explaining you all, well, you know, it's a react, it's different stack, it's this, and people like me, including us, we just go in to lovable and like build me a Chrome extension based on this app. And I was able to do that with lovable. There were people that were able to build desa applications on lovable. Again, something that shouldn't be possible, it simply is, right? Our community manager with me, at one point she was like building this presentation deck for something, she's like, would it be cool if this was a video, right? And then she just prompted her way into building a generating an actual video inside lovable before that was available. Now that's a feature. Now you can prompt lovable to do it, but back in the day when she did it, even I thought it was impossible. I never tried it. So I think that's the advantage that we have over people that are technical. We just come into this completely unbiased and very positively delusional, which I think you have to have, when working with AI tools, you have to come with this delusion that absolutely everything is possible until proven wrong. And that's just the pursuit that I have in my mind that has helped me among other things that we'll chat today, I think to excel in this role that I have at lovable. Two of the, I think concerns, maybe traps people that don't have a technical background fall to in theory is one is, if you get blocked, it's not obvious how to solve a problem. And two is just, are you building like this like teetering slop that will collapse someday? Because you don't know, you know, system architecture, you don't know if this is going to scale all the sorts of things. So coming back to what you've learned about how to be successful and build successful products, talk us through just things you've done and things you've learned for a head of a way, those sort of things. And what you do when you get stuck is what example. I'm happy that you mentioned like those limitations, I have some other ones that I want to bring in, but let's address this one first, which is the most important one. And that is you have to be self-aware, right? I didn't come into this, yes, I am delusional, as I mentioned, in the sense that I just don't want to accept something's not possible, but I'm also well aware that I need to be better in order for it to become a reality from my own point of view, in my own sink. So I understood very early that coding is not the problem that we're solving for, here that the problem we're solving for is clarity, right? Like the output that AI can do is much faster than human output anyways. So like very early on, I started leveraging chat mode, and to this day I can say I spent 80% of my time in planning and chatting and only 20% in executing the play, actually, right? I'm optimizing for the right kind of speed. Most people optimize for the wrong one. That's the first lesson that I learned literally on day two, because I just, I came into lovable, that was my first exposure to this. I've tested and played around with all the tools, obviously, but like, whether somebody's doing it in a cursor or a cloud code doesn't matter where you are, the problem remains the same. You need to be clear on what you want to do and you need to know what you're doing, because these are still just tools. Yes, AGI is coming, but it's not there yet. So like until it's here, you're still steering the ship. In order for you to steer the ship, you kind of have to know the instructions, right? And the best way to learn is by building, but treating these tools almost as technical co-founders and educators and learning while doing, and religiously reading the agent output, not the code output, I don't care about the code. Like the syntax is not of my interest. It's what the agent tells me then that matters to me. I put a lot of trust in LLMs and AIDs days, and I understand that there may be some people that are not as confident as I am. I just feel that the models today are good enough for me to trust in their syntax output. However, I'm concerned about the agent output and because of the two limitations that I want to tackle on next, right? The first one being that there is a limitation when you work with LLMs, so that there's a machine level limitation and there's a human level limitation, right? The first one is there's something that is known as the context memory window, right? And for non-technical people, I like to use the Aladdin and the GD analogy when I explain, right? It's very simple. Everybody knows the storyline. You rub the lamp, a genie comes out and tells you, okay, I'll grant you three wishes, not three thousand wishes, not three million, just three at a time, right? To me, when I translate it into working with AI, that simply means, hey, I can only make so many requests within a request at a time for AI to be able to listen, understand what needs to do, scope it, do the research, read, like take all the actions, all the inputs and ingredients that it needs to produce a high quality output, right? So that's the first part, understanding that there's a limit and it's denominated in tokens. Maybe that's gonna be different a year from now, but today, there's a token limitation, I'll take an arbitrary number of a hundred thousand tokens. So when you make a request, a part of those tokens is AI spends to read stuff, another to brands the web, another to think, and then another to execute the code, right? Then there comes the second limitation, which is you, me and you, humans, which is, let's go back to the analogy of the genie and the Aladdin, I asked the genie for the first wish and the first wish is, I wanna be taller and guess what happens? Genie makes me 13 feet tall. All of a sudden, I can't sit in the car, I can't get into my house, I'm a dysfunctional human being, right? Because I was not specific, right? Like, so the part that we need to optimize for today, it's gonna get better, but today it's still not there yet, is that, AI just don't understand what do you mean when you say, you know what I mean? Like you do, when I tell you that, we as humans, we have, I'm 36, I have 36 years of experience of human, living as a human to know what you mean, but AI doesn't have that, right? So you need to be specific, you need to provide references, you need to provide the right context. So what I've learned is how to combat that part and I think, you know, because I can't control the first part, which is the token member, Wingdoll, the quality of the LLN models, you are 100% control of the latter and that's what I wanna dive into today as well and just try to teach people, okay, if I'm the malleable part, how do I fix that part, right? I think that's the key lesson here. This is so helpful and I love this metaphor of the genie. The piece about clarity is such a thread I've been noticing across people that have been successful using AI tools and it feels like an emerging core skill is learning how to be, learning clarity in the ask of the AI. Do you have any advice or anything you do there to help be better at being clear with what you want? Yeah, so first of all, you need to be, as you said yourself right now, you need to be good at understanding what clarity means and how to translate it. In my terms, clarity means understanding what tasteful looks like, what's good enough versus what's world class, what's magical. And I developed that through something that I heard from you, you mentioned before, which is exposure time, right? Making sure that I'm exposing myself to content and to people and to relationships or whatever that are gonna help me to level up in that domain. Again, it goes back to self-awareness. Like I knew when even before I joined Lovable, I was like, okay, even before I started using Lovable or any of the tools, first thing that I knew was like, I don't know how to code. So my first thing was like, oh, I can build, wow, amazing. But a week later it was like, oh, I can build, but I'm not fast enough. So I optimized for speed. So I was like, oh, I can build and I can build so fast. And then two weeks later, I, my development cycle that I'm in began and it's still ongoing, which is, wait a minute, should I have I even built this in the first place? Cause like at once you figure out that we solved for the how, which is, you AI assistant or rapid engineering, calling whatever you want. You can call it vibe coding if you want to. But like we solved for that. Now we got to solve for everything else. And everything else is what matters. Good design, good taste, good user experience. Like when you think about who you're building stuff for, with these tools, you're building it for humans. Humans are emotional beings. And we all make our purchasing or any kind of decisions on an emotional basis, right? So I think that the core skill there to work on and develop today isn't again coding, although I have nothing against traditional engineering and I'll say later why I'm actually a big fan of it of elite engineering. But like people like me, people watching that are like, should I start learning how to code? If you haven't done it yet, I'd honestly say no. Like you're optimizing for the wrong skill set. We won't be rewarded in the word of AI for faster raw output. We will be rewarded for better judgment. So I think that better judgment comes with, again, to go back to your question, like, how are you solving for that? How are you solving for this? Well, it starts with exposure, so deliberately exposing myself to people and resources that I know I need to consume to level up. And then a lot of it just comes from building as well. If we're honest, it's a muscle. Everything is a muscle. You need to practice. You need to see what's possible. And that's where some of the techniques and mindset shifts that I want to also use an opportunity to date and graze into people's minds later down the call, maybe useful. So what I'm hearing here is because coding is now, essentially a self problem. I love that you don't look at the code. You don't even, like, you've never coded. You don't want to look at the code. You don't care about what's happening there. That instead of you're watching this agent output, I want to actually ask about that. But what I'm hearing here is the areas you are investing in building in yourself is at the front end, clarity around what it is. And I want to hear how you actually do that. We do that. You have a really cool system there. And then there's like the taste and judgment of knowing is this the thing I want. It feels like those are the two sides now that are more and more important. And on the taste judgment side, you share this concept to something Guillermo Rausch shared on our conversation. This idea of exposure, time exposure hours, being exposed to great stuff. Here's a great user experience. Here's a great onboarding club. Here's a great, I don't know, website. So I really like that advice. It's so action. OK, I'm going to spend more time with stuff that's great to inform my taste and judgment. And then on the clarity piece, let's actually talk about that. What do you do there to be clearer with Lovable and other AI tools to help it build the right thing? This is the first mindset shift that I want to put into people's minds. If you just have a vague idea, let that be your first version of the project. Open, cursor, lovable, whatever it is that you're using. And just input a brain dump prompt. Just talk into it. Lovable, specifically, I don't know about. The other tools has a really cool voice function. You click it and just dictate the hell of it and just press send. Don't even wait for it to finish. Open a new window. Again, lovable.dev. In here, you're like, OK, as I was brain dumping, I think I found a good thread. I think things are getting clearer. So let me start another project. Now with more clarity, more deliberately, like I know with features I want, which pages I want. Maybe I can even find a good reference. Maybe I can go on Mavin. Maybe I can go on Dribble. Maybe I can go wherever. Get a good screenshot. Get a good animation. And attach it. Because most of these tools accept files as a part of the input. So you have the second project started. Now things are getting more clear. Now you expose yourself to quality. And now you're like, well, what if I found a template that actually is already out there? Why re-enointing the wheel? I'm building a platform that somebody else built. Why not expose AI to what quality looks like? So what I'll do is I'll go to and find a library, 21st then, or that build, or whatever places which allow me not to export screenshots, but export code snippets. Because guess what? Even though English is the number one programming language, lovable and all other tools still communicating code the best, if you want to get pixel perfect results, just give them code. It will interpret it better than your English or Spanish or whatever language that you use in these tools. So that's the third way. You're like, OK, now even more deliberate. I'm not even going as wide as giving it vague concepts. I'm giving it code snippets. I want this exact design. I want this exact type of functionality. So that's your third project. And then by the time you do all of these three, you're already at a level of clarity that you wouldn't have if you just sat with an empty piece of paper or maybe chatting just with chat GPT, but not taking action. I think taking action is so, so cheap these days. And free, by the way, all the tools I mentioned have free plans. Like most times you would be able to do this without spending any money at all just by starting multiple projects. Because guess what? That doesn't also cost anything either. Or doesn't incur additional costs except for builder credits. You're going to get three, four, five, six different concepts that you can compare as you're comparing them clarity just keeps coming. And things get better and better to understand. And you're also solving for one big problem that you mentioned. You used a determined AI Slop. And I like it because a lot of people, when they say, AI Slop, they don't refer beautifying the code, but beautifying the design. This process that I just mentioned actually gives you four or five different design options. And in the long run, save you massive amounts of credits. Because a lot of people obsess over the concept of, oh, when I give them this hack, they're like, oh, but that doesn't cost more. I'm like, yes, upfront, it may cost a little bit more. In the long run, if you really want to finish this project, you're actually saving hundreds of credits and maybe even hundreds of dollars, not to mention the amount of days, simply because you started for a point of better clarity and better refinement process. So that's the first step of solving for clarity. There are more, which is the second layer. But I assume you may have some questions on this one. Questions and also just wow, this is such a great. It shows you the power of having someone come into this world without an engineering background. This advice of just build it five times in parallel. Ask AI to try all kinds of stuff. Like this is not how someone that has been a software engineer or a PM or designer would approach stuff. So your advice here, which is so fun, is as you're getting started with a project, just run five different approaches at it to start. One is just brain dump. Here's what I'm thinking. Here's this general idea. Like use whisper flow or use the built in mic. And then two is, okay, now I have a general idea. Let me try to type it out, like actually thinking through the prompt. Three is, let me find a mock design somewhere online. The sites you suggested were mob and andribal. Those are the two that you go to. Yeah, most of them. Okay. And then the fourth, these are all in parallel. It's great. Is find like actual code template that looks similar to the thing you want to build, download like the zip file basically and put attach it or is it just HTML and CSS? Is that kind of anything? Anything you got. Cool. Yeah. Okay. And then cool, here's the prompt here. Make me what I want. And what I love is there's two wins here. One is just it helps you clarify the idea as you see the tool build it. Like, oh, no, that's not what I mean. Let me try it again. And then two is you're pointed out. You can pick the right direction so that you're not locked into your first design and first architecture to your point. If you then spend all this time trying to fine tune design and direction, it's like all these tokens are being lost. You could have just started over. This is so great. Someone may think, okay, of course, you're just getting us to spend all these lovable tokens. This is what a lovable person would tell me. But what I'm feeling is this is where you could save the most money because if you get a correct in the beginning, you save so much work trying to get it back to where you wanted to go. I'm million percent that I'm actually saving people. Like, I'm actually going against what I should be saying. If I was thinking about lovable design, I would be like, no, no, just try to fix it in perpetuity. But that's not... We're not in business of doing that. We're in business of empowering anybody to build anything that they want. And then, you know, it's my personal mission that resonates with me because if there wasn't lovable, I would have never built anything potentially in my life. And I don't think that that would have been a fun life to live. So, you know, I guarantee people, I've tested this framework with many people and everybody. It's telling me the same thing. I open her. So simple yet unintuitive, as you said, even though for me, it's kind of... I don't know. As you said, I attributed to a non-technical background. To me, that was the first thing that I would do. Like, I just did it. I never thought about it. Like, oh, I'm developing this amazing hack. I was just like, I'm waiting all this time for these agents to finish. I met as well as start another project and another one and another one. And it's also a productivity hack. Like, that's what people ask me like, wow, how do you ship so many things? I'm like, I never built just one project at a time. I built five or six. I have six lovable tabs and I just switched between them. And that's the next hack that I want to talk about if you allow me, which is the question in return is the obvious one, which is, how do you context switching? Like, you talk about context so much yet you're a keep switching between apps. How do you manage to do it and do it in a way that's productive? You're not produce bad code or bad product. And that's how I solve for that LLM problem. Again, the Aladdin and the magic clamp and all that, which is if there's a limited token window, how do I make it dynamic? And why do I mean by that is this? If you just go and you prompt and you prompt and you prompt and you prompt, you'll realize that no matter what tool you use, the memory just isn't infinite. By the time you reach message number 10, 15, 20, 30, 40, snippets of early messages sort of get lost in the translation because agent is optimizing for speed. If it had to read the entire conversation and the entire stream of requests that you made, developing anything viable or large would be impossible because it's just like consuming a lot of time and a lot of memory and a lot of tokens. So again, something that I just figured out very early on as I was building was like, okay, if it can't remember things, my job is to provide it with reference. So let me tree lovable or any other tool as an engineer that I suppose should be providing perpetual context as the project goes. And you can do that in many ways, but the most efficient way that I found was like, I would do the four parallel builds. Like let's continue off of that example. Very quickly after you've built hundreds of projects like I did, you see the winner. Like the winner is so obvious, it's not even a competition. You maybe do want or more to prompt to calibrate it and when you're like, okay, the winner is here. At that point, I either ask the tool that I'm using or I'll maybe let's say go to Chadgbt or whatever and ask the LLM to produce a series of PRDs. What PRDs are for, again, people that are not familiar with the terms there are project requirements documents or for me, I call them like sources of truth, right? What needs to be true for this project to be successful from a couple of perspectives. I usually build something that I call a master plan. It's basically a compass saying, here's what we're building, right? It's like talking to a human. I really treat lovable like a human being. So it's like, this is what we're building. Then I build an implementation plan, which is this is how we are going to build it. This is the sequence, right? It's very important to me, again, going back to quality, taste, human nature. I need to define, because I'm still working with a system that is not emotionally intelligent yet. I need to define how I want the app to look and feel. So another PRD that I build is design guidelines. And then finally, something that just circles it all around, which is like, okay. When we know how things look and we know how we're building it, how does the user journey look like? Right? I use the registers and then what? And then when they register and do that first step with the second step and with the third step and what not. So I built at least four PRDs, right? And then when these are built, I read them. That's the planning, chatting part. Like that's where I'll spend a lot of time now on. When I kneel down that first design, I'll spend an entire day if I need to. Just planning this part out, like documentation and breaking things down, because that's how I'm setting the course. Like everything's going to be dependent on this particular part of the process. When I'm done doing that, I build one final document, which I call either plan.md or tasks.md and that md part is, you know, mark down, basically I'm just using markdown format because I've learned that AI likes to read markdown. And what that serves as a source of truth on like actual tasks and sub tasks that it will need to execute to get to the finish line, right? And then there's the final, final layer, which is depending on what tool you use, called code or cursor have what's known as rules.md or agent.md, which you're basically doing with rules or agent files is, you're letting the agent know how you wanted to behave and what it should focus on in the long run. So you don't have to repeat yourself with every prompt, right? So, in loveable, there's a, there's a separate menu for an app in your project settings where you can define project knowledge and usually what I'll say, hey, read all the files before you do anything. Like don't do anything before you read all the priorities, read tasks.md to see which task is next, then execute on that next set of tasks. And when you're done, tell me what you did and how should test it. And that's where that conversation about, I religiously read the agent output comes into play. I've told the, I gave the agent everything, all the tools and resources that it needs to succeed. I give it the rules, I give it the docs, I told it what to do with them. And at that point, I'm just sitting and reading. All I don't prompt anymore. And from that point on, I can switch as many windows as I like. My prompts have become perceived with the next task. I don't need the context. I outsource that and delegate that to the agent. The agent needs context and I need to make sure that it's dynamic. I need to make sure that I'm regularly updating the documents from time to time so that we shift that token window. It uses it, how it uses it over time. But I'm not prompting. I'm not interrupting the flow. Yes, I'll go in test, maybe put a prompt in here or there. But that's how I can build five projects simultaneously and never lose the productivity part, which is again, as I said. I do this today manually. Call me to talk three months from now. An agent will do this for me. I'll be out of job pretty much. That's why I don't optimize for this skill at all. Like I'm using it today to bypass the shortcomings of human nature and LLMs. But I'm optimizing 100% of my time today on good judgment, clarity, quality, taste, good copy, good fonts, like people don't talk about fonts at all that work with AI. They're like 60% in my mind, maybe even more in how your outputs go look like. That's my obsession. Like I don't obsess over these things that I'm talking today because I know what's coming. Like the agents are gonna get better. The models of it get better. They're not gonna need me to extend the context. They're gonna do it themselves. So for me, the skill that I optimize for is the one that requires better decision making, rather than better output or better alignment. Oh my God, there's so much here. This is so awesome. Okay, so essentially what's happening here is, you start a project, try a bunch of stuff, pick a direction that feels most correct. And once you have a set direction, you spend essentially a day not building, but working with this AI agent to plan. And then, and why I wanna talk about that. And once you have the plan, then it's, and it's amazing that you could do stuff like this with what people, some people may feel are not, and sophisticated tools that can build incredibly powerful things. Like you can do a lot of this with tools like Lovable. Like how plans and rules and MD files, like a lot of people may not think, may not know that. And so the idea is, okay, spend all this time planning because again, that'll save you a lot of time down the road. And then only once you have a plan, you get it going. And a key part of this, the three wishes rule is really important. The reason you're doing this in a large part, beyond just being really clear about the plan, is this idea of one task at a time keeps the agent's context window small so that it doesn't lose track of where it's at. That part seems important, right? It's like do this thing. And then, okay, cool, now do the next thing, right? Yes, yes, because again, if, let's say you didn't do this, let's, let's, let's talk about you ignoring this, you're like, I just wanna vibe my way. Okay, great, no problem. You work, you work, you work. At one point, something breaks, right? You haven't documented anything. There's not, there's no reference points. You report a problem. You're not referencing files or architecture at all, you're just describing the issue. Here's what's gonna happen. Any tool, lollable or cursor or plot, whatever tool you talk about is gonna do this. It's gonna be like, okay, let me start investigating it. And then your code base gets bigger and bigger and bigger and bigger and bigger. Like when you, when you first start, you have like 20 files, it can read 20 files. But what, what happens when you have, I'm just building a project right now that has like 60, 70 edge functions, right? What happens then when I say this broke and there's no reference which edge function does what? Guess what, lovelable is gonna read all of those. And it's gonna consume 80% of the token allocation on reading to get clarity, leaving only the final 20% for thinking and executing. What I'm guessing, and I can't prove this, I know all I'm expert in the comments may say that I'm wrong, but this is my best guess as a non-educated person. These tools are very obedient and very agreeable. They're gonna lie to you. They're gonna tell you that they fixed the problem even though they didn't. They're just gonna try to make you feel happy and say, yes, I found what the problem is and I fixed it. When a lot of times when they don't, people blame the machine. And to an extent, I will say that's true. It sure fault my friend. You did not provide any clear to your context to this tool. You just used its raw power and dug a deeper hole with your spinning your wheels into the mud. And obviously, I think we're heading into a world where AI is more honest than obedient and saying, hey, I only partially fixed this. You did not give me enough of a context. The bigger mistake that people make then is like, they trust the tool fixed it. They test, they see it, then they get mad at it, start cursing and yelling as we say. And then it gets even worse because guess what? Another bad trait of AI is, it's best not to hurt your feelings and never say you're the dumb one. It says, no, I'm the dumb one. So it focuses, in the next request, instead of focusing on reading, it spends another 30% of tokens trying to come up with an apology, right? Again, I'm not educated, if you ever read a stream of chat GPT's thinking in thinking models, you see exactly what I mean. When I insult it, I see that the first message is, okay, the user is mad, so I need to think of ways how to reduce their anxiety or whatever, I'm like, oh, man, I just fell for the worst drink at the book. I made it spend the most scarce resource, which is those tokens on thinking how it should address my anxiety versus focusing on the actual problem. So my advice for people is like, yes, vibe your way for fun, and vibe your way while you're prototyping because that's the exploration part, I love that part. But when exploration is done, please, please, please, use referencing, documentation, use all the agent files that you can because that token allocation is so scarce. Like, it's gonna get expanded over time. Things are gonna get cheaper faster, but right now it's still so valuable and precious. You really need to make sure that they are allocated in the right direction. This is hilarious. I think the genie metaphor is so good here. Just thinking about this genie is, you're trying to be clear about what it is you want. And if you're just like vibe, you know, vibe wishing, it'll do the wrong thing. So the advice here is, be as, give it as much context about what you want it to do as possible. And these files, we'll talk about right after this, but the idea here is just like, laser, show the point, the laser, where you want it to fix the problem. Don't just assume it'll go figure out because it will and it'll try really hard to and it'll waste all your tokens, it'll fill the context window. And I remember at one point you mentioned before this recording that because it starts to run out of space in the context window, it just like the solution ends up, it doesn't actually work that hard on figuring it out in the end because it's spent all this energy on reading and thinking. And then it's like, okay, here, the last second here's a solution. I think it just picks the first thing it thinks it's broken. And that just again, this is me completely uneducated, coming into the conversation and just thinking out loud. That just might got feeling in the way I think logically about it, which is, hey, if it consumes most of its window and knows that it's running out of it, maybe it's aware that it's running out, maybe it isn't, but either way, I've had the experience anecdotally to where like, my request is unclear. I feel it takes the easiest fix in the book, just the easiest versus the other way around where I'm like spending so much time finding a right file, referencing that file, like really putting in the effort of hand holding it in dark, maybe giving it a flashlight and then saying, here's the problem. I think that this is the problematic file and then it's like, oh, yeah, you're right. And now I'm gonna actually fix over and over and over. And I've seen that because again, all I do is read the output. Agent makes me learn how to use it. By some people read, I don't know what people read, but all I read is the output. Like I don't read the code and it's slated on the road because like I know that it can do that much better than I can. Again, I feel if there's a good quote I've read, I can't, I'm, I apologize to the author because I can't contribute it off the top of my head, but it's like the ceiling on the AI isn't the model intelligence. It's what the model sees before it acts, right? So that's the ceiling right now. Like what do you, when are you exposing, we talk about exposure time for humans. What are you exposing your agents to as well is as important, if not even more important before it makes code edits. Yeah. Coming back to these files, I think this is really important. So let's think about just like what's like the MVP for someone that wants to do this better. You listed all these kind of files, these MD files essentially that you're building over the course of a day before you start actually building the thing you had design guidelines, the user journey tasks, agent, MD, rules, MD. Say you wanted to just like move one step forward and be better at the stuff. What are the files you create and then what do they roughly look like? What's inside these files? Yeah. So the master plan is the first one, which is like it's a 10,000 foot overview, right? It really high level explains the intent that I have with this app. And this is master plan that MD is at what you call it? Yes. Yeah, master plan.md. And it's like, it's really just like, hey, this is why I'm doing this. This is who I'm doing it for. This is how I want them to you feel. And a lot of times in the master plan, I will reference the other priorities. I'll be like, the design needs to feel modern and slick. But for exact parameters, consult and read design guidelines, dot MD, right? So I'm using just a master plan as like this high level overview, right? To get the agent into, oh, okay, yeah. We are building XYZ, right? Then there's the implementation plan because there needs to be some order. If you just like dump stuff on top of each other without any order, you're never going to get to the finish line. And this is tasks that MD is at what you call it. No, that's the implementation plan. I call it implementation plan. Yeah. And implementation plan is kind of in service of the future tasks.md. If that may, all of these files are in service of building tasks that in the, when you build tasks.md, then the rest is almost irrelevant. It's just a basis for you to build tasks to execute, right? The implementation plan is kind of the first layer, which is again, higher level overview. It doesn't go into the depth of like, how to get there. It just goes into the explaining of like, oh, well, if we're building this, I think we should start with the backend. And we should start with tables and then later authentication. And then after that, we're gonna bring in the API. And then after that, we're gonna do this. It's like, again, just think of it as having, I'm an ideas guy. I'm sitting with a technical guy. It's me and you, we're building our startup. You, I know you're a software engineer by background. And I'm telling you my idea. I'm giving you the master plan. And you come to me back and you're like, okay, if you wanna do this, it's doable. Here's how I would order it. Like you have a roadmap. You're not, you didn't open your linear and started writing features and RFCs and whatever. You're just high level talking about the order of things. And then me and you, again, as two co-founders, we talk and say, okay, well, if we agree on this, like, how should this look like? How should this feel, right? Let's describe it high level, but now, because I use AI, I can go a little bit deeper. And that's where I like to see lovable or any other tool. Chat GPD is good at it. I even have my, I'm built like custom GPD. So if people wanna start somewhere before they even get into any tool, they can go to chat GPD store. And for GPDs and just type lovable base prompt generator or lovable PRD generator and find those that I built and just like, brain dump in them that get these files as output, right? So I like to see some elements of CSS in design guidelines, because you know, you, with design is a little bit, it's a little bit tricky. AI is sometimes over creative. So I, that's where I'm doing a little bit more technical steering, right? And then finally, it's just the user juries. Just like, if we know how things look like, if we know how they feel, if we know what we're building high level, like high level, just very high level again, how do people navigate? What are some of the features in there, you know, and stuff like that? And then tasks that it gets into the nitty gritty of like, oh, if you want these user journeys and you want the backend built first, here's a set of tasks that I need to do. Like it just takes that as an input. I'm just making the tool do the, do the, you know, that gritty work that humans used to spend so much time on. Like, I feel like with, with these tools, we're all becoming product managers on steroids, you know, like we're just leveraging AI, but like good product manager, I think are not compensated for writing good PRDs, they're compensated again for good judgment, right? Somebody else can do the writing, you as a, as somebody who directs and builds this product, you need to know again, what, what, what's going to be useful, what's going to be tasteful, what's going to be something that actually moves the needle. I will say one thing though, just because I put so much emphasis on like, oh, you need to acquire taste, oh, that doesn't mean you should build. You get better at this by building actually. So everybody listening to this should like literally go and build something today. One, two, three, four, five projects, test all of these tools, because that's how you get to clarity, not just by reading, but also by doing as well. Here's a puzzle for you, what do open AI, cursor, perplexity, versel, plat, and hundreds of other winning companies have in common? The answer is they're all powered by today's sponsor, WorkOS. If you're building software for enterprises, you've probably felt the pain of integrating single sign-on, skim, R-back, audit logs, and other features required by big customers. WorkOS turns those deal blockers into drop-in APIs with a modern developer platform built specifically for B2B SaaS, whether you're a seed-stage startup trying to land your first enterprise customer, or a unicorn expanding globally, WorkOS is the fastest path to becoming enterprise-ready and unlocking growth. They're essentially striped for enterprise features. Visit workOS.com to get started, or just hit up their Slack support where they have real engineers in there who answer your questions super fast. WorkOS allows you to build like the best, with delightful APIs, comprehensive docs, and a smooth developer experience. Go to workOS.com to make your app enterprise-ready today. I'm imagining people hearing this, may start to feel like this is so much work. I just have to sit here and create all these rules and figure out all these little details. Like in one sense, it is in another sense. This is like you spend a few hours, maybe a day planning, and then you have AI build this thing that would have taken somebody weeks months, right? It's like the amount of investment to achieve this thing is absurd ROI. Also, this shows you just what professional wipe coating looks like. Everyone imagines wipe coating. You're sitting here, typing stuff, and going, do this, good. If you want to actually build something really great that moves the needle, as you said, that solves people's rules problems, that lasts that scales. This is how you do it. If you really want to do this as a job, and also if you want to build things that are really great. Yeah, and they'll get me wrong. There's obviously a ton of alien prototyping. There are a lot of people maybe watching this that are like, okay, I want to use lovable at work, but I can't or whatever. There's different reasons there's maybe you're in healthcare or finance, or there's something regulatory that just prevents you from pushing to production. Like building for the sake of pros, I think is one of the best use cases. We, our motto for 2020 file was demo don't memo, which is like, instead of writing all these documents and talking and sitting on meetings with your engineers, trying to get your vision as a marketer or a sales guy in the office across, go into lovable and build the prototype in 30 minutes, and just hand it over. And I have a real job that I held before lovable. That's exactly what happened. Like this time, last year, I needed something built enterprise grade, really, and lovable and myself were not there yet to build it at that point, but I had a team of engineers that I worked with. I built the prototype in four hours, and they actually were able to replicate it six to seven months later into production with connecting all the pipes and everything, but like, if I had to describe it, I would say it would take me at least a week or two, just to get the words out there. I just sat and built it in four hours, and that's like lovable January last year. This lovable today, January 2026, is like ages ahead with functionalities. It's so much better, it's not even a contest, right? So I think now, what are stage were like, for instance, there's, I'd say at least to best of my knowledge, at least half of S&P 500 companies have people working in them that are using lovable to some extent, right? And we have a lot of enterprise companies that are actually on enterprise plans with lovable that are creating super meaningful projects. Like, I'm not gonna name names, but like leading right shared companies of the world, reading telecommunications companies of the world, leading companies of the world, many, many aspects, healthcare, finance, like are actively with their teams using lovable, and it's always the same feedback, which is, yes, we may not be able to push to prod, but like, our marketers are no longer waiting for engineers, are people in got a market or sales or HR or whatever roles are now just confidently building internal stuff for us to manage our expenses or manage employee onboarding or like, there's so many use cases like that where like you're seeing lovable and other tools for that matter being used to push things into production. Yeah. Let's help people do this workflow that you're describing with all these MD files. Do you think you could share after we record this, just templates, like simple templates of what these files look like for people just to look at and copy? I would literally go to chat GPT, as I said, and bring dump into it in my just type lovable, GPT, lovable PRD generator. You'll see my name there, right, and that I'm the author. Go in, bring dump, it will ask you a couple of questions to get clarity and just produce four files for you, and you can just go ahead and upload those. Yeah, cool, we'll link to that. So it's not just here's a bunch of files that go talk to this thing, it'll generate the right files for you and then you plug that into lovable or other tools. Yeah, it's trained, don't it? It's trained to think like I do, so yeah. Oh, amazing, okay, that is perfect. By the way, I want to talk about like how you unblock yourself because there's a whole other series of tips you have there, but I just want to reflect, it's so interesting how one, you're kind of from first principles, under learning how to build product as a PM, as an engineer, as a designer, and you're kind of figuring out a workflow where AI is helping fill in all the gaps that you don't have for as an engineer, as a PM, helping you craft PRDs and design. So I think that's so interesting, just it's interesting that these functions still work and are necessary now, it's you and AI help create all, this basically is triad that's always existed, product manager engineering and design, and something I've always thought is that, there's this question of which background will be most valuable in this future, is it a PM, is it an engineer, is it a designer? My mind has always been the PM function is, like their job is, clarify, figure out what to build, clarify what to build, be really clear about the requirements, figure out what success looks like. It feels like that's where the skill is most needed. There's also a design component of like, make this look awesome, and it feels like that's gonna be an emerging, the value of that being really good at design and taste and judgment is only gonna go up. Before we get to things you've learned about unblock yourself, because a lot of times, things don't go in the right direction, there's a bug without being in the general, what do you do? Before we get there, is there anything else you wanted to share around just like tips for being successful? If we measure success in the right terms, again, AI as you pointed out, regardless of your background is an amplifier. So, if you don't know what you're doing, you're just gonna produce garbage faster. One thing, again, I just wanna double down on is, in the old world, good enough was good enough, right? Because even producing good enough was not easy, right? 10 years, 15 years ago, just producing was more than plenty, more than good enough. You built a SaaS, who cares how it looks like it works, it does stuff, oh my God, I'm so much more productive. Today, if good enough was here, let's visualize it for people. If this was pretty bad, could be better, mediocre, good enough, world class. If this was the gap between good enough and world class, well guess what, the gap is now this, because everybody produces good enough with AI. Absolutely, everyone does it. So now, learning and optimizing for how do I produce world class and magic is the key lesson to take away today. As you pointed out, I think PMs are the winners of AI today, because they bring clarity. If I was a betting man, as they say, I bet that the next class that wins our designers, because we're training these tools to be more clear, to be better, to make better technical decisions. I don't think we will train them just yet to be, make better emotional decisions. And I think design is all about emotion, and that's where the level of the skill up needs to come. That's the biggest level up. If you ask me like, oh, what is the main thing you figured out when you joined LUMB. What's the biggest personal up skill? Let's like working with Felix, Nad, Abbey, all of the people that are designers, just really what moved and shifted the needle for me. I'm like, oh, so this is how world class looks like. This is what it takes, right? I always use the analogy of like, I wanted to steal one of their designs and bring it into my level of projects. So I went into Figma and I was like, let me just take this background, like I can just put it in there. I went in and realized that what could be interpreted as a pretty simple or rather simple gradient took 50 different layers to produce. So I clicked on that component and I was like, oh my God, this is not three colors, this is 50 colors. And not just 50 colors, 50 colors with different gradients of levels of opacity. So I was like, oh, okay, well, and that's the big disconnect that I've had all along. So like, again, if I'm answering your question directly, I'm like, okay, what are some of the other tricks? What are some of the other things? Design, guys, just expose yourself to exquisite designs, follow Felix from lovable. He has an amazing newsletter like, and to teach you how to, and learn how to prompt for a good design, learn about design styles. I didn't know what Bale House meant or glass morphism had no idea. So I built an app as well for that, lovable. I was like, I needed to build an app to learn these styles. So now it's public, anybody can see it. It's like some UI style.lovable.app. I don't know what it is. It has like 18 different styles and prompts to replicate them. So like, learn what good design means, learn all the design styles, learn how to prompt to get them is probably what I would optimize for at this stage. Well, we're on this topic. What's your sense of just engineering as a function? Do you feel like there will be a future where software engineers are still thinking? Do you feel like that goes away based on your experience? It never goes away. We will need elite engineering more than ever. Like, cause let me tell you this, in a world where everybody builds and everybody's building everything, who's doing the maintenance, right? Taining code bases, scaling code bases, maintaining projects. You know, they're still gonna be a thing, definitely. And obviously, AI's gonna be good at this, but again, that requires a different level of skills, right? It's one skill to build something. It's a completely different set of skills to expand it, extend it, and maintain. And not to mention that, either world where everybody's building, infrastructure suffers, right? Like, we know all know and experienced like CloudSlayer went down two or three times in the last two or three months. The whole internet goes down. Elite engineers are the ones fixing this. Lovable experiences, massive amounts of influx of new users, infrastructure they are suffers. Elite engineers are the ones building the infrastructure to hold the fort, right? So like I think we're gonna need a lot of people with really good skills of like, hey, who actually builds the world that needs to support billions of builders now? Cause everybody's gonna wanna learn how to build stuff. Like, how do we teach them? How do we maintain everything that they need? The hostings, the security, the email, the connectors, the APIs, the what-nots. Like, so I think there's gonna be room for it. But I'm also on the boat of people like, if I had an 18 year old brother and he asked me what should I do, I would tell him, hey, go become a plumber. You know, don't go and get a CS degree, you learn a good trade, you know? Cause the new generation of millionaires in the US are actually electricians and plumbers and what-nots, right? So it's like, you know, it's a balancing act, I'd say. I don't know, like I do still think that good engineers with good sense of like, understanding where the future is going, are always gonna be needed and scarce. Such an interesting question. I think to your point, there's definitely gonna be, people need to keep building the machines, that power all the stuff. Well, we need engineers to build actual products, the application layer. That's the question. Like, is everyone gonna be like you? Is there gonna be designers just gonna be all we need? Everybody's gonna become an engineer. And let's let's let's then, let's speak to that end. Like, I'm an, I feel like I'm a rapid engineer. Like, I'll refer to myself as a rapid engineer in a year from up, because vibe coding is just coding in 12 months from now. And even today, we spoke about this before, like how many elite, elite engineers are publicly admitting they're no longer hand coding or manually coding, we're gonna call it. They, I write all the code, I use the analogy here of like, coding is gonna be like calligraphy. You writing code is gonna be the equivalent of like, you write, you find printing like on a canvas and people are like, oh my God, you wrote that code? That's so amazing, it's gonna be so rare that it's gonna become an art, right? It's not gonna be, it's gonna be commoditized completely. Like, it already is in a sense. Most elite vibe coders rely on AI, again, it's an amplifier, right? So I think everybody becomes an engineer in the world of the future. A designer, a PM, everybody is a forward deployed engineer or an AI assistant engineer or an LLM engineer or a vibe corner, the term is irrelevant. We're all using LLMs for raw output based on good judgment or bad judgment. No, man. Essentially, these Venn diagrams of engineer, designer, PM, they're used to be very separate now, they're converging and people with a specific, with deeper PM, engineering, design background are gonna, like they can all do the same thing essentially. All the roles are converging. What a, what a time to be alive. And it's so hard to predict exactly how this all goes, but it's fun to pontificate. I wanna get back to when you go block. Speaking of elite engineers, things that there's like in the, in reality, you're still writing code using these tools. Sometimes code goes, things go wrong. Bugs are introduced, there's a weird database thing, there's like some network issue. What do you do when you get stuck? Do you have kind of a workflow you go through unblocking yourself? Yes, great question. And I absolutely true. Like no matter how good a plan you have in place, you're gonna run into problems eventually. And I have like a small little framework that I call 4x4, just again, analogies, right? 4x4, if you have it on your car, you're gonna get yourself out of the mud much easier than the other way around. So in that sense, four different ways to debug. Attempt one of each, only once, and I'll explain why in the end. First one is, again, every tool is different. I'll reference Lovable's workflow, which is when something breaks, Lovable's agent is smart enough to say, hey, I made a mistake. It will label that message in orange and have this little button, usually, which is a called try to fix. So you agent basically admits it made a mistake. You click on a button, and most times when it's a smaller issue, it corrects the course, fixes it, no problem, right? Now, there are situations, obviously, when the problem is a little bit deeper than that, right? You click to try to fix, but the problem persists. And sometimes even the problem persists, but Lovable's agents are not aware that it persists. So there's no more try to fix button. Lovable thinks everything's working, but in reality, it isn't. And the culprit there is usually, you're using a third-party integration. You did not give enough context to Lovable where to observe and what to see. So it can't see that the problem exists because Lovable, cursor, Cloud Code, you name it. All these tools are good enough today to fix any problem they're aware of. Again, awareness is the key here, right? So when they're unaware of it, there comes the second part, which is, okay, I need to bring the awareness layer. And what I do there is, I go and very simply, open the preview, sandbox, dev, environment of my app, whatever, try to run the function that's broken. Right-click, read the console log, right? Every browser allows you to just go and read the console log and a lot of times it will record. Stuff, if it doesn't, you can prompt any tool and say, hey, I don't think you're seeing the problem. So instead of me yelling at you, let's find it together, right? I think it's a problem with XYZ. I want you to write console logs in relevant files so that we can monitor every step along the way. Let's just bring awareness layer into the equation. It writes the console logs, you rerun it, guess what? Now you have a cool history of everything that's was happening. You copy that, you paste it inside your chat, 99% of the time. That's enough. That's already enough, he has like, okay, got it, found it, fixed it, right? But then there's situations when even that's not sufficient. So you're like, okay, I need to go even deeper. And that's where like code reviews and evaluations come into play. My go-to tool today for that is codex, open AI, right? What I do is like any build that I do, I will export it to GitHub. Like, lovable allows you to, when you're code cursor as well, all of these tools allow you to have a copy of the code that you can export to GitHub and then import it into wherever you want to. So I use codex since beta, like, important in there. And then I'm using an external tool. So I'm like, in the first try, if you remember, like I use the tool and I was like total vibes, I'm relying on the tool, right? In the second try, I use myself as the awareness of a facilitator. In the third one, I'm using an external tool as a facilitator, which is like, I'll either connect to codex and chat with codex to then fix the problem in lovable, right? I don't allow codex to make code changes for me. A lot of people will say, why don't you? Like, it's a good model. I just don't know it's agent well enough. Like, I don't want to go and use a tool that I don't know how to steer. So I use it only for diagnostic purposes. And I'll also do it manually. It's an old workflow that I had before codex and before cloud code, which is, there's a tool called repo mix, which allows you to like, compress every, your entire codebase into a single file. You download it and then I upload it to cloud, just cloud regular cloud or chat GPT. And I'm like, this is what I'm building, read it. And this is the problem that I have. These are the console logs again. It's almost like having an external consultant at that point. Like, you're hiring help elsewhere because your team just can't handle it, right? And then the fourth one is usually the best one because at the time when there are problems, it's my fault. Like, no matter how your ego is big guys that you're watching this, it's your fault. Trust me. You had a bad prompt. You premised your request in the wrong way. You just don't want to admit it or you can't remember that you did. But it's your fault. So again, ill lovable and in all these other tools, you can revert back. There's version control built into lovable cursor, called code. You go and say, okay, I tried these three things. I'm just going to take three steps back and I'm going to think about my prompt a little bit more. Take a couple of breaths, go for a walk, have some coffee, come back with a clear mind and try again, because guess what? AI is just writing code very fast and sometimes it stumbles on a very small rock and it only happens then and never again. So you just gotta make the same request again. And usually that just fixes the problem. It's just a snag. It's a syntax error. It's something's minute, right? And then I do the final thing, which is this and this is the key one, actually. When the problem gets fixed, I go into the chat mode and I ask lovable, I say, okay, I needed to do four different things to fix this. How can you help me learn how to prompt you better? So that next time I have a problem, we do it in one go. In 99% of the time, I get such a great answer that I don't have the problem of not knowing what to do next time, right? Like again, we all need to be aware and realistic. These tools are so good at doing things the right way if they are used the right way. It's always our fault. I say 90%, but honestly, it's 100% awful. Because they're good enough. It's just that I'm not dynamically shifting token allocation. I didn't reference the right file. I didn't say the right way. For me, as a non-designer, I don't know any of the terminology. Like none of the headings and what nots, and I still don't know it to this state. So when I struggle with prompts, a lot of times I use chat mode to help me craft the good prompts. Wait, anybody can do this too. If you are just stuck, it's 10 p.m. and you don't know what to ask, switch to chat mode, bring them and be like, help me draft a better prompt. Help me prompt you better. And let the tool effectively prompt itself. A lot of times you're gonna solve your problems by not introducing them at all with bad inputs. So. Oh my God. Everything you share so interesting. I just wanna keep digging. So just to reflect back the sequence and then I wanna follow up with another question, the sequence you go through when you get stuck, which is gonna happen to everyone. One is just ask the tool to try to fix it and oftentimes it's telling you, something is wrong. Can I fix it for you and you're like, please fix. Sometimes that'll work. Two is work on adding more debugging messages to the console log and this advice I love of just ask it to add more debugging lines to its own console log to help see what's going on. And then you can ask it, okay, now that you're looking, watch, look at all the output of your console log see if you can help find the problem. And then step three is go to Codex, which is so funny. And I hear this a lot. Codex is like the most elite engineer as an AI. Karpathi tweeted this once that, and we had the head of Codex on the podcast too, by the way, that she's like, anytime I have the most gnarly bug, I just go to Codex, let it run for half an hour and it solves it unlike any other tool author. And so it makes sense that that's where you go. So the idea here is you point codex to your code, you show it all the console, all output logs, tell it what the problem is and just have it go, figure it out, sweet. And then this final step is so great. And this is where I want to go. They, which, use this as a learning opportunity. So that next time you solve the problem more quickly or avoid it completely. So what you do there is you ask the agent, okay, here's what happened. What can I do? What could I have said? How could I have prompted you better to have gotten this immediately solved? Yeah. And then even more, even deeper than that is like, once you go through this conversation, you're like, okay, let me eliminate myself again completely on the equation because I won't remember to prompt you better two days from now. Put this into rules, put this, what we just learned into rules.md, because I am making you read the rules every time anyways. So you might as well just record it there. So I'm not going to prompt you better. You're just going to learn that I'm stupid and you're going to prompt yourself better, right? Again, just eliminate yourself and move the context. You solved 99% of the problems with AI today. So idea here is help it build its own brain and rules and wave thinking based on problems you're in and too. So great. Okay, so I want to come back to this point. You've made a couple times which is so interesting. This idea that you watch the output of the agent to learn what is going on. There's something I've seen other people Ben Tossel who I think is a factory now share this recently. He's also basically by coding all the time. He was brilliant at no-code tools before. Now he's all about by coding and he shared basically he's learning how things, how coding works and learning how systems work by watching the agent output. And this connects to something Michael Torell shared the CEO of Curse who he was on the podcast. He had this vision of Curse who are becoming basically what comes after code. What's the layer that we are adding on top of code where people don't need to worry about code anymore? And at that point it was like a year ago that we chatted and it feels like this is the layer is the agent conversation of what it's thinking and then what you tell it back. So essentially it's English and a conversation which is like it's not even pseudo-code. It's interesting that that's where it feels like things are heading the layer over code is just it's thinking and your conversation with it. Yeah, yeah, exactly. I mean, again, in a way I really optimized for good judgment and part of good judgment comes from again. Learning how these tools work. You need to know what's possible. We talked about it and I know I may sound contradictory sometimes, right? But it's because as you said, it's so interesting the world will live in that things contribute to each other. It's an advantage not to know what's possible, but then at the same time you cannot be completely oblivious to something that's like a factual thing. So let me talk about a failure of mine that came from being delusional. Back in the day when OpenAI started or released image generation natively in the app, right? So you could go to ChatGit and be like generate an image of XYZ. The whole world exploded. Like that was like the biggest thing ever. Obviously, the first thing that comes to my mind is like, I want to build a lovable app. I just want to build a wrapper and I want to build an image gen with lovable without thinking that OpenAI did not release an API for that just yet. So I spent at least a week trying to brute my force, brute force my way into making this work instead of just waiting for another week because a week later they had an API and I built this app in 30 seconds. The problem was that like I tried to do it when it was impossible and possible. Like so I think again, you know, it's just a matter of really learning what's possible through communicating with the agent player and lovable and all the other tools are agentic now, which means like they don't just write code. They can browse the web. They can read files. They have reasoning and thinking capabilities. So that's why I'm so invested into that conversation because a lot of times it will tell me, hey, what you're trying to do is just undo at the moment because of XYZ. So like I always use those as a learning opportunity and I just level up most by being in chat mode for planning and learning purposes. And because it just again develops your clarity, your judgment capabilities rather than coding. The other point you made here that I think is really important is that over time these tools will do more and more of what you do manually. I've heard this from other people that are doing this full time basically by coding is just they had all these workflows, all these files and then cursor adds to them, lovable adds to them and it's like sad. Oh shoot, I had this cool workflow now. But on the other hand, it's like, okay, now it's just doing all these second. A year ago, a year ago, if we had an interview, your mind would be blown. Stuff that I had to do as work around to address shortcomings. Like I built a very successful course on that with starter story. Like for a year, people were like, just, oh my god, you're the only guy in the world that knows this secret. Now lovable natively addresses 99% of it. I can almost say most of the stuff that I was teaching people were like, I have a YouTube channel all a bit appreciated, but like there's a, there's a like a seven day learn how to buy code with lovable series that I did in March. Completely obsolete. Like none of it is true. None of it is a problem anymore. All the things that I was like, oh well, this is missing and that is missing. It's not missing anymore. It's natively in the product. Like you don't have to work your way around it. It just works. Right. So that's why as I say, like, it's the, it's the horses analogy. I don't know if you heard of it. Like a lot of people are tweeting about it, which is like, we started building the steam machine in 1700s, right. It took us about 200 years to build it. When it got to when, when engines got built and cars were put on the roads, I think that 90% horse population was got eradicated in the US within 20 years. The person that we did this works at Claude code, right. So he was like, now when I translate it into AI, I was hired to do a job technical job, technical writer, whatever. I became obsolete six months later. Like humans did not get the 20 years that horses did. The guy that that is was hired to do a thing is like six months later, I need to reinvent my, my role. I need to involve it into into something else, right. So, you know, I think there's just an evolution that's coming really, really fast. But like a lot of people are scared when I'm just super excited because don't you see our roles are finally going in a direction where we're outsourcing what we hated doing anyways, right. Sitting in meetings, taking notes, doing spreadsheets, like nobody, maybe there are people that like that. But like most people don't we're just getting into a place where we're rewarded for what really matters like clarity, judgment, thinking we're actually going to be paid to think longer and pawn their longer because the longer idea simmers and gets broken down the better because building it is going to be an instant, right. So, it's going to be like this is just a matter of you having so much clarity around it because guess what if a tool is super powerful and you given a wrong input, the outcomes can suck as well. That's why like I never become good enough at cloud code, I feel because I don't start my projects with enough clarity and the tool is so powerful that like I just misdirected completely from the cat go and I was like, shoot, this is not what I wanted to do. So that's why I still see myself being good at like using tools that are a little bit on the exploratory prototyping path more than like on the path that, you know, elite engineers will use for example, I love your optimism and excitement about this stuff. I think for a lot of people say their current software engineers PM designers, there's a lot of fear about the future of their careers, are they going to be relevant. Well, I know my software engineering skills disappear. So to follow this thread a little bit, if you were to give someone advice on which skills you think will be most valuable slash where AI will take on more and more this kind of momentum you're seeing of where AI is filling in more and more gaps. What would your advice be of what you think people should focus on what will continue to be valuable in the future. Yeah, emotional intelligence for sure, just understanding human nature real life stuff. I think we're all going to get so tired of everything fake fake images, fake posts, fake profiles, fake this fake that fake videos. Everything is becoming fake and AI generate. I think humans just craving humans naturally are going to want to do live stuff more. So anything human to human is going to be a big thing to skill up on and understand the dynamics. Anything regarding math, if it's a math problem, I think Peter is still said at recent like people that just do math stuff, you know, AI is going to come for you like anything that's very deterministic, meaning X input equals Y output and it's pretty clear. The line is pretty clear as got you eaten for lunch, right, but if you understand how X to Y goes in human dynamic human relationship layer, I think that's where things are going to become good. So if we translate it again to a specific skill, I'll say it again, good design, really good design, great design, like how I say design that's images, fonts as well, copy copies a big one like we all now we're all going to do it. Now we're like two years into AI, I'll bet you me and you if people put 10 pieces of copy in front of us, we could tell what say I'm what isn't in like three seconds and we're only a couple of years in. So like really good copy writing is going to be a very good skill to have because she's going to know after three words are three sentences that it's AI written and even I don't read AI output anymore. I don't like just seeing it, I want to draw a draw human experience. So I think human skills, I don't even know how to describe it because I don't I don't think we're doing an awesome job, put a labels onto what humans are good at natively, but I think we will I think we will describe job descriptions better. We will have like a human first engineer's I don't know or human designers or I don't know how to describe those roles, same way how a Karpathi a coin vibe coding I was vibe coded before he didn't I didn't know how to call it like I started vibe coding in July of 2024 and I think he he coded it sometime in early 2025. So I was like doing it for seven months and I was teaching people how to do it for about three or four with courses and I didn't even know how to call it like because there was no name was like, I'm just using AI to do is for me. I don't know whatever. So yeah, I think we're going to reenwent some of the terms roles and whatnot, but stuff that's like human to human is here to stay stuff that's like I think like, oh, you're just doing you're you're a middle manager, you're a middleware person that you're doing. Where person that's just translating stuff and I can use that analysis get translators are going to die people write jokes comedians are not. AIs never going to be able to write a good joke never never never just doesn't have that layer that just doesn't understand what's funny like if you ever try to use the act to write jokes like they're awful they're always going to be awful. But if you use AI to translate things from one language to another it's very good. I like a is going to replace translators it's going to replace most journalists because it does good research you can write good copy whatever not not elite journalism. It's not going to be able to replace all the writers it's going to amplify great writers that can train AI on how to write books like somebody who's an amazing writer is going to all of a sudden write seven books a year instead of one. Right so that's that's dangerous if you're an average writer be careful. There's zero comedians be placed zero and that's just my personal belief like a is never going to write good comedy it's impossible and like so trying to find your analogy in your industry like I just gave you one for writing skills so to speak so writing jokes super good skill to have. Translating i'm sorry to say but like you're not going to have a job for much longer like you better find something else to do. But yeah that's that's how I look at it the comedy piece is interesting I had one of the founders of the data labeling company out enough is mr core maybe surge and he said that i think it was a ontropic hired a bunch of national lamp hoon comedy writers to help them train models and so. So they're working on it and so I love this strong prediction you made i'm so curious any year to look back and be like he was completely right or no they got that one too i'll be wrong on 95% of the things I said today three months from now that is the only thing I can say very very confidently yeah that seems right okay so speak your career so one interesting career option is to do what you're doing. As you said this is a dream job for you it's a dream job for so many people what what is the kind of your path to this job and what do you think it takes for someone to actually do this as a profession. Well my personal path and personal junior was anything but linear like i've done so many things in life like. Blue color jobs would fit even it subway while I was studying and stuff like that like i'm an engineer by trade but not a software engineer i'm a friend. So no coding but still engineering is engineering i feel you still develop certain set of skills doing that i waited tables a long time to develop some human skills you understand what people like what they don't like right i've again blue color jobs like teach you hard work and like it's as I said the path was not linear but I feel almost like a slum dog millionaire the movie storyline which is like everything that happens to the character. Brings him into a position to be able to answer the questions in the in the quiz better i have i feel the same way of like i'm done a lot of stuff last seven to eight years obviously spent in startups but doing everything but code writing like started in like community management social media again distribution matters a lot that something we have to put on and all like in a world when everybody's building. And there's roughly the same amount of consumers in the world how do you get in front of the the eyeballs right playing and get attention which is going to is this most scarce resource and it will be even more scarce but like going back to the back of the role if somebody's like saying okay well i have i have a pretty diverse background to an unbite coding and like how right how does this become a job well. For me i feel like it became a job by building in public i did chat with the lane of once only once like why me there are so many good bite quarters i did well how did you pick me out of the crowd and i think you know obviously you're she gave me a couple of reasons but like to translate into like. One concept it was like i was building in public and sharing i as i said i made a youtube channel and i should all the failures and all the knowledge all the projects that i was building i use social media like link thing was my go to because i just have that type of. Caners as you can see i all my answers very long and x doesn't doesn't cut it for that like you need to be very to on point to be successful at x i'm not so i guess you know it's just like building public share your knowledge give away all the secrets like there are no secrets whatsoever if you're sitting on a good concept you're missing out i just share it immediately if you figure something out that i recognize that very early on. And you know just like i think a lot of people participate in hackathons these days i want to encourage people to do them like find those those opportunities locally to connect with other builders loveable is hiring across the board check out our own positions is as easy as that right like just apply really find companies that that are hiring and hiring in different roles and i've seen people do something i'm going to give people a secret way. Couple of hires stood up by not sending resumes but sending loveable apps they build loveable apps to show what they're why they're good fit for a role and we as loveable employees will always open an app that uses loveable dot app domain always if you send me at the end send me a loveable app don't send me anything long send me an app that tells me what you want for me or how do you see us collaborating and working together right so there's people finding creative ways to get in front of. I was of decision makers like Elena right and i mean skill wise again we're just repeating ourselves here but i think it's important to repeat it as many times as possible really develop good judgment right really understand in a deeper sense how. How things translate when white code comes into play right there's a company out there i am i'm not going to name them but like that uses loveable religiously is going to be one of our main case that is actually where like. They actually hired by code is before loveable did like i'm the first official. By coding engineer at loveable like with that title but i've met people in companies where they hired them before us people that are just five quarters people that just understand that. Speed matters right it still matters a lot to be fast like there's a company out there with free by code is full time all they do is like translating the old code base into. On to loveable this is bringing everything there's CRMCMS everything that all the tools sets that they have and they needed there are people now actively just might bring everything everything over there's. S&P 500 companies that are like putting loveable in in job descriptions to like saying hey loveable skills skills are you know recommended in the recommended time right so yeah to to to to go back to the. How to become by code professionally well you don't need a company to hire you can hire yourself as a professional by put it first i think. The reason why i clicked with and time and with a lady and everybody else because i was already doing it like all i did i just change the the vehicle but i was already doing it professionally before i can hired so that's kind of the. The key like do the job you you would have done anyways what a mind expanding conversation i love just how. Passionate and excited and motivated you are about all this i feel like there's so many people out there right now that are so. burnt out i don't know disillusion scared. And you're the opposite of that you're just leaning into this just taking advantage taking not sure what's going to go but falling the path yeah and i don't want to interrupt you but like it's it's because like look. Lovable specifically isn't a company you can talk about it as a company i don't see it as a company it's a it's an idea it's a mission it's it's something. More powerful than the internet in my mind because like. It allows us to consume loveable allows us to build and in our nature and human nature is to build to create right and and the fact that there's a tool today that you can go into. And dump an idea in and and something comes out of it and somebody uses it and finds it useful to be it's just. It's the craziest concept ever it's my my only life's dream I had my first computer when I was six and I was convinced. My whole life that i'm going to be a software engineer or that i'm going to be building but like life wasn't as simple as that for me like. It was very very complicated and honestly the last five to ten years I gave up on that dream almost i thought i'm never going to build anything like i tried i tried to build with technical co founders like I just couldn't find alignment I was i just gave up on it. And I now like at thirty six like thirty years later I feel like I can like that that kid like I dream every day like it's it's amazing with this enabled. So I was doing I anybody that scared like just try it. It switches from fear to excitement immediately because then you see what's possible first hand just go in build something build anything and the fear goes away you should only be afraid if you're doing nothing if you're doing absolutely nothing yes. Be terrified by all means be terrified and then take a step towards doing something about it and trust me the leap is no longer as big as it used to be it's as big as. You come in and you just say what's on your mind and and just ship. I think a big part of this is just stop listening to this black ask you just do stuff you actually. Right. Right. Ideally people stop right now they've heard enough I gave them what I I gave them the best that I could just stop listening and just go. All right, bye everyone okay i'm just joking but let's we shall wrap it up i'm going to skip the lightning round just to keep this episode shorter. Before we wrap up is there anything else other than just kill build some stuff anything else you want to say anything else you want to leave listeners with. Otherwise will let will let you go yeah. Text tag doesn't matter anymore right it doesn't matter like people obsess over always this written in HTML is this written in react it doesn't matter like. It never matter but now matters even less the end user just wants a stellar experience we live in a world where anybody can produce good enough so. You you better start learning how to produce magic because otherwise you're just going to end up in a crowd with millions and millions of others. But at the same time if you don't know what magic looks like don't be discouraged to start building anything and start start from good enough and level up the best way to level up exposure time set aside more time on learning than building. Let read the agent output learn how it's thinking so that you know what's possible but then also going get inspired follow good desires on x. Find tools where great designs are produced and follow their creators there's a tool where where i'm following just the the actual person that built it because he. He publishes videos almost daily 40 50 minutes long of him designing I want to see how world class designer doesn't I want to see him talk to the tool I want to see him from and that's how I learn to become better at it so again exposure time just the deliberately set more time aside to learning than coding because you can code fast but you can code garbage fast as well as magic fast it's the same amount of time it's you and your input that matters forget about decisions on tech stack forget about which back and are using which front and are using that doesn't matter quality taste design that's all you need to optimize for in the future that's ahead of us. Was are this I think we're going to leave a lot of line a lot of minds busing after this conversation you blow my mind in so many ways what a fascinating topic conversation what a glimpse into the future what an interesting point in time i'm so curious just you know in six months where things are and revisiting this conversation. I really appreciate you coming on sharing all of this you're awesome. Where can folks find you if they want to reach out maybe ask some questions and how can listeners be useful to you awesome yeah so i mentioned it already lengthen is probably the best place to find me on you know i'm there responsive there i'm if you want to follow me i hope to reengage my youtube channel a little bit more i think i have a lot of cool tips and tricks that i that i want to share and teach people how to use loveable and and just vibe coding general and we're going to be able to do that. And on how people can be useful to me well you know i'm very passionate about making sure that everybody experiences what i've experienced that day when i got my first prompt and i envy the person that is going to try loveable for the first time after watching this episode because the feeling is just unmatched of you going from a consumer to a builder but in that process there's going to be some battles to fight. I want to reduce the amount of those battles and hurdles so if you can help me in any way message me what could have been better in that experience especially if this is your you just watch this. And you're like i'm going to do it i was on the fence and i'm going to do it if something breaks something doesn't connect and relate i need to know what that is my job is a hundred percent to empower you to build the best work of your life right and you know and i need to say this to. Because a lot of people may be inspired not by building. Oh using loveable but but but rather building loveable come join our team again we're hiring across so many things i think a lot of people should feel inspired because. I hope that the energy that i bring to the table will resonate this is how it feels working at loveable this is how it feels working with the best minds the brightest minds of the world. We're not number one by accident it's it's not a coincidence the best people are gathering and we we want you to be a part of it too so if. If the energy and the conversation resonates with you or if you heard about a problem today. And you you're like man i think i can solve it come join us help us build and shake the future software. Thank you so much for listening if you found this valuable you can subscribe to the show on apple podcast Spotify or your favorite podcast app. Also please consider giving us a rating or leaving a review as that really helps other listeners find the podcast. You can find all past episodes or learn more about the show at Lenny's podcast dot com see you in the next episode.