Vibe coder Lazar Jovanovic: How to plan before AI ships slop

1. 0:00 – 4:53

   Introduction to Lazar and professional vibe coding

   1. LJLazar Jovanovic0:00

      I'm the first official vibe coding engineer at Lovable.

   2. LRLenny Rachitsky0:03

      You're at the top .1% elite level of vibe coding. It's a dream job for so many people.

   3. LJLazar Jovanovic0:08

      It became a job by building in public. You don't need a company to hire you, you can hire yourself as a professional vibe coder first.

   4. LRLenny Rachitsky0:15

      You've never coded, you don't [chuckles] wanna look at the code?

   5. LJLazar Jovanovic0:17

      Coding is gonna be like calligraphy. People will be 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.

   6. LRLenny Rachitsky0:25

      These Venn diagrams of engineer, designer, PM, used to be very separate, now they're converging.

   7. LJLazar Jovanovic0:29

      AI, regardless of your background, is an amplifier. If you don't know what you're doing, you're just gonna produce garbage faster.

   8. LRLenny Rachitsky0:36

      Feels like an emerging core skill is learning clarity in the ask of the AI.

   9. LJLazar Jovanovic0:41

      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 wanna 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 100% of my time today on good judgment, clarity, quality, taste. [upbeat music]

   10. LRLenny Rachitsky1:08

       Today, my guest is Lazar Jovanovic. Lazar is a professional vibe coder. He gets paid to vibe code 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 also spent a bunch of time on Lazar's best advice as an elite vibe coder for getting the most out of AI tools. He's got a bunch of really interesting and useful frameworks I have 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 Replit, Bolt, Gamma, n8n, Linear, Devon, PostHoc, Superhuman, Descript, Whisper, Flow, Perplexity, Warp, Granola, Magic Patterns, Raycast, ChatPRD, Mobbin, and Stripe Atlas. Head on over to lennysnewsletter.com and click Product Pass. With that, I bring you Lazar Jovanovic, after a short word from our sponsors. This episode is brought to you by Strella, 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 wanna 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. Strella 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. Strella's AI moderator asks real follow-up questions, probing deeper when answers are vague, and surfaces patterns across hundreds of conversations, all in a few hours, not weeks. Product, design, and research teams at companies like Amazon and Duolingo are already using Strella for Figma prototype testing, concept 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 Strella. Run your next study at strella.io/lenny. That's S-T-R-E-L-L-A.io/lenny. Today's episode is brought to you by Samsara. 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 checkout flows. Samsara 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 Samsara's technology protects them. Samsara is solving complex problems at the intersection of hardware, software, and edge AI, and their AI doesn't just detect events, it reasons about the intent and answers questions like: Did that truck driver brake abruptly because they were distracted, or was that a heroic act? If you want to ground LLMs in messy, real-world telemetry or solve edge AI constraints at a planetary scale, Samsara wants to talk to you. If you like playing with enormous datasets, moving fast, and working in small teams, come help build the technology that makes the physical world safer and more efficient. Visit samsara.com/lenny to learn more. That's S-A-M-S-A-R-A.com/lenny.

2. 4:53 – 9:26

   What a professional vibe coder actually does day-to-day

   1. LRLenny Rachitsky4:55

      [upbeat music] Lazar, thank you so much for being here, and welcome to the podcast.

   2. LJLazar Jovanovic5:00

      Thanks for having me, man.

   3. LRLenny Rachitsky5:01

      Okay, so I had Elena Verna on the podcast. She's Head of Growth at Lovable. She mentioned that she works with a professional vibe coder, you. I had so many questions, I almost wanted to, like, go on a tangent with her, just try to understand this role. Instead, I asked you to come on the podcast. Uh, there's so much I wanna talk about. I wanna 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 wanna get into what you've learned about it being successful using all these AI tools, because this is your job. First, I wanna 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?

   4. LJLazar Jovanovic5:47

      Well, as you said it, like, it's the-- it's a dream job, right? I get paid to do what I would have done anyways, right? It's the best job in the world. I get to use tools like Lovable every day-... to push projects to production, whether for internal or external use. Those could be ranging anything from, like, different templates on marketing side, sales side, or whatever, or they can be as deep as, like, building some internal tools with a lot of integrations and connections and whatnot, right? So the surface area that I cover is pretty wide across all departments, 'cause it's such a flexible role, and it complements so many things, right? It, it's, it's an ideas role. A lot of people have a lot of great ideas, but they don't know how to build them, and, 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.

   5. LRLenny Rachitsky6:43

      And one thing that's really interesting here is 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, and, and it's, like, sort of a product, level products.

   6. LJLazar Jovanovic6:55

      Yeah, definitely, like, some of the stuff that I've shipped that are public are, like, when we launched our Shopify integration, most of the, if not all the templates that users were remixing were built by me, right? So stuff like that, or, like, the merch store, 'cause we wanted to obviously prove the concept that, hey, Lovable and Shopify just works. It's so simple, anybody can do it. I vibe coded our merch store, so all the merch, including this shirt, that people were buying online, uh, they would've bought it, well, from a store that was built by me. But then on, again, on the internal side, we, we wanna track a lot of things. Like, one of the, the cool things that we wanna, uh, build now, for example, is, like, feature adoption matrix. Like, if, if we build a feature, how many people are actually using it and 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've 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, I'm in that position of, like, build versus buy, I, I'm, I'm in the build boat, uh, so to speak. Yeah.

   7. LRLenny Rachitsky8:09

      And then who do you report to? Are you kind of this rover that helps wherever, or are you with a, with a specific team?

   8. LJLazar Jovanovic8:15

      I, I'd say probably closer to the former, right? Uh, I've started in growth, right. El- Elena brought me on, uh, early on, and, you know, to, to co- 'cause she has so many great ideas, and, like, she just needed s- somebody with the right type of mons- 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, or, or anything, go to market or whatever. But then, obviously, the... when you're able to ship fast, everybody needs that in an environment that we, as a company, are now living in, which is we're the fastest-growing startup 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 for enterprise team. But I'll, I'll- I'm, I'm working on some community tools as well right now, as we speak, so I'm a little bit all over the place, but I kinda thrive in that environment, where, like, I'm given a rough concept, a rough idea, and I'm just tasked to bring it to life, uh, as soon as possible.

   9. LRLenny Rachitsky9:18

      Okay, I'm hoping with this chat we create a lot more Lazars, and I wanna get to the career path, how you got to this, and what it takes to actually become a full-time

3. 9:26 – 12:24

   Why non-technical backgrounds can be an advantage

   1. LRLenny Rachitsky9:26

      vibe coder. But I wanna start with, because you do this full-time, you're, you're at the top 0.1% elite level of vibe coding. You're doing this full-time. They hired you [chuckles] 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, that help you be really good at, at this job?

   2. LJLazar Jovanovic9:51

      The first understanding that I had very early on, even though I-- just in full transparency before we begin, I don't, I don't have a technical background. I never wrote a single line of code in my life. Almost, like, I've, I've, you know, written a couple of console logs manually, and that's about it, right? So, like, I, I'm very much lean onto AI assistance.

   3. LRLenny Rachitsky10:10

      Let me actually follow that thread, 'cause 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 this space.

   4. LJLazar Jovanovic10:20

      Yeah. Yes, I, 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. Um, 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, why is that not possible," right? And then people that are technical start explaining you, "Oh, well, you know, it's React, it's different stack, it's this," you... And people like me, including myself, 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 desktop applications on Lovable. Again, something that shouldn't be possible, it simply is, right? Our community manager, Whitney, at one point she was, like, building this presentation deck for, 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 vi- 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, 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, like, that's just the, the pursuit that I have in my mind, uh, that has helped me, among other things that we'll chat today, I think, to excel in this role that, that I have at Lovable.

   5. LRLenny Rachitsky12:02

      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, uh, this, like, teetering slop that will collapse someday 'cause you don't know, you know, system architecture, you don't know if this is gonna scale, all those sorts

4. 12:24 – 14:42

   The importance of self-awareness

   1. LRLenny Rachitsky12:24

      of things. So coming back to h- 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 how to avoid those sort of things, and what you do when you get stuck is, is one example.

   2. LJLazar Jovanovic12:36

      I, I'm happy that you mentioned, like, those, those limitations. I have some other ones that I wanna bro- bring in, but let's address this one first, which is of the most important one, and that is, you have to be self-aware, right? I, I didn't come into this... Yes, I am delusional, as I mentioned, in the sense that I, I just don't wanna accept something's not possible, but I'm also we- well aware that I need to be better in order for it to become a reality from my own point of view and my own sake. 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 anyway. So, like, very early on, I started leveraging chat mode, and, uh, to this day, I can say I spent 80% of my time in planning and chatting, and only 20% in executing the plan, 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, to, to this. I've tested and, and played around with all the tools, obviously, but, like, whether somebody's doing it in Cursor or Cloud Code, doesn't matter where you are, the problem remains the same. Y- you need to be clear on what you want to do, and you need to know what you're doing, 'cause 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, in, in LLMs and AI these days, and I, I understand that there may, may be some people that, that are not as confident

5. 14:42 – 17:43

   His “genie and three wishes” mental model

   1. LJLazar Jovanovic14:42

      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 wanna tackle, tackle on next, right? The first one being that the, the-- there is a limitation when you work with LLMs, so that's, there's a machine-level limitation, and there's a human-level limitation, right? The first one is, there's something that, that is known as the context memory window, right? And for non-technical people, I like to use the, uh, Aladdin and the Genie analogy when I explain, right? It's, it's very simple. Everybody knows the storyline. You, you rub the, the lamp, a genie comes out and tells you, "Okay, I'll grant you three wishes." Not 3,000 wishes, not three million, just three at a time, right? To me, when I translate that 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 it 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 100,000 tokens, for example. So when you make a request, a part of those tokens is, AI spends to read stuff, another to browse the web, another to, uh, 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, uh, analogy of the genie and the Aladdin. I ask 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, I'm a dysfunctional human being, right? [chuckles] 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, so I have 36 years of experience of human, uh, 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 h- is how to combat that part, and I think, you know, because I can't control the first part, which is the token memory window, the quality of the LLM models, you are 100% in control of the latter, and that's what I, I wanna dive into, uh, today as well, and just try to teach people, okay, if I'm the malleable part, how do I, how do I fix that part, right? I think that's the, the key lesson here.

   2. LRLenny Rachitsky17:41

      This is so helpful, and s-

6. 17:43 – 21:46

   Developing taste and judgment in the age of AI

   1. LRLenny Rachitsky17:43

      I love this metaphor of the genie. The, this 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?

   2. LJLazar Jovanovic18:07

      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, um, 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, 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 AI tools, first thing that I knew was, like, I don't know how to code, right? 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... Why-- 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 it's like at-- once you figure out that we solved for the how, which is use AI assistant or rapid engineering, call it whatever you want. You can call it vibe coding if you want to, but, like, we solved for that. Now w-we gotta solve for everything else, and everything else is what matters: good design, good taste, good user experience. Like, w-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, I think that the, the core skill there to work on and develop today isn't, again, coding, although I have nothing against traditional engineering, and, and I'll, 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, I'd honestly say no. Like, y-you're, you're optimizing for the wrong skill set. We won't be rewarded in the world 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 I'm deliberately exposing myself to people and resources that I nee- know I need to consume to level up. And then a lot of it just comes from building as well. You know, if we're honest, like, it's a muscle. Everything is a muscle you need to practice. You need to see what's possible, and, you know, though, that's where some of the techniques and mindset shifts that I wanna also use an opportunity today to ingrain into people's minds later down the call may be, uh, useful.

   3. LRLenny Rachitsky21:09

      Uh, so, okay, so what I'm hearing here is, uh, because coding is now essentially a solved problem, I love that you don't look at the code. You don't even... Like, you've, you've never coded. You don't wanna look at the code. You don't care about what's happening there. That instead, you're watching this agent output. I wanna actually ask you 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 we're- and I wanna hear how you actually do that, what you do there. 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

7. 21:46 – 29:30

   The parallel project approach for better outcomes

   1. LRLenny Rachitsky21:46

      and more important. And on the taste judgment side, you shared this concept. That's something Guillermo Rauch, uh, shared on... in, in 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 flow. Here's a great, uh, I don't know, website. So I li- I li- I, I really like that advice. It's so ac- so actionable. Okay, I just gonna- I'm gonna spend more time with stuff that's great to inform my, my taste and judgment. And then on the clarity piece, uh, I wanna... Let's actually talk about that. Just what do you, what do you do there to be clearer with Lovable and other AI tools to help it build the right thing?

   2. LJLazar Jovanovic22:22

      This is the first mindset, mindset shift that I wanna put into people's minds, right? 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, right? Just talk into it. Lovable, specifically, I don't know about the other tools, has a really cool voice function. You click it, you just dictate the hell of it, and just press Send, right? Don't even wait for it to finish. Open a new window. Again, lovable.dev. In here, you're like: "Okay, n- as I was brain dumping, I think I found a good thread, right? I think things are getting clearer. So let me start another project, now with more clarity, more deliberability." Like, I know which features I want, which pages I want, and maybe I can even find a good reference. Maybe I can go on Mobbin, maybe I can go on Dribbble, maybe I can go wherever, get a good screenshot, get a good animation, and attach it, 'cause most of these tools accept files as a part of the input. So, like, you have the second project started. Now things are even more clear. Now you, you, you expose yourself to quality, and now you're like: "Well, what if I, what if I found a template that actually is already out there? Why reinventing the wheel? I'm building a platform that somebody else built. Why not expose AI to what quality looks like, right?" So what I'll do is I'll, I'll go to and find a library, 21st dev or, uh, um, or a .build, or, like, 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 communicate in code the best. If you wanna get pixel-perfect results, just give them code. It w- it will interpret it better than your English or Spanish or whatever, uh, language that you use, uh, in these tools. So that's the third way. You're like: "Okay, now I'm even more deliberate. I'm not, I'm not even, uh, uh, going as, as wide as, like, giving it vague concepts. I'm giving it code snippets. Like, 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, uh, an, an, an empty piece of paper, or maybe a- maybe chatting just with ChatGPT, but not taking action. I think taking action is so, so cheap these days, and free, by the way. Like, all the tools I mentioned have free plans. Like, most times, you, 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 co- cost anything either, uh, or doesn't incur additional cost, except for builder credits. You're gonna get three, four, five, six different concepts that you can compare. As you're comparing them, clarity just keeps coming. Like, and things get better and better to understand, and you're also solving for one big problem that you mentioned. You used, uh, the term AI slop, and I like it, 'cause a lot of people, when they say AI slop, they don't refer the, uh, cl- uh, beautifying the code, but beautifying the design, right? 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. 'Cause a lot of people obsess over the concept of, oh... When I give them this, this hack, they're like: "Oh, but that, doesn't that cost more?" I'm like: "Yes, upfront, it may cost a little bit more. In the long run, if you really wanna 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 from a point of better clarity and better refinement process," right? So, like, that's the first step of solving for clarity. There are more, right, which is the s- the, the, the second layer, but I, I assume you may have some questions on this one.

   3. LRLenny Rachitsky26:31

      S- questions, and also just, wow, this is so [chuckles] such a great... Uh, 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. [chuckles] You 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 a general idea." Like, use Whisper flow or use the built-in r- uh, 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," and the sites you suggested were Mobbin and Dribbble. Those are the two that you go to?

   4. LJLazar Jovanovic27:20

      Yeah, most times.

   5. LRLenny Rachitsky27:21

      Cool.

   6. LJLazar Jovanovic27:21

      Yeah.

   7. LRLenny Rachitsky27:21

      Okay, and then the fourth, [chuckles] and these are all in parallel, it's great, uh, is: find, like, actual code template that looks similar to the thing you wanna build. Download, like, the zip file, basically, and put- attach it. Or is it just HTML and CSS? Is that kind of what-

   8. LJLazar Jovanovic27:36

      Anything.

   9. LRLenny Rachitsky27:36

      Yeah, anything. Got it.

   10. LJLazar Jovanovic27:37

       Anything works.

   11. LRLenny Rachitsky27:37

       Cool. It's just like-

   12. LJLazar Jovanovic27:37

       Yeah.

   13. LRLenny Rachitsky27:38

       [chuckles] Here you go. 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 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. Uh, this, 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 I- what I'm feeling is, this is where you could save the most money, because if you get it correct in the beginning, you save so much work trying to get it back to where you want it to go.

   14. LJLazar Jovanovic28:27

       A million percent. That, I'm actually saving people. Like, I'm, I'm actually going against what I should be saying. I- if I was thinking about Lovable's, I would be like: "No, no, just try to fix it in perpetuity," but that's not-- W- we're not in business of doing that. We're in business of empowering anybody to build anything that they, they want. And then y- you know, i- it's my personal mission that resonates with me, 'cause if, if there wasn't Lovable, um, I would have never built anything potentially in my life, and I don't, I don't think that that would've been a fun life to live. So, um, you know, I, I, I guarantee people, like, I've tested this framework with many people, and everybody is telling me the same thing. Eye-opener. So simple, yet unintuitive, as you said. Even though for me, it's kind of... I don't know, i- i- as you said, I, I attribute it 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," it... I was just like: "I'm waiting all this time for these agents to finish. I might as well start another project, and another one, and another

8. 29:30 – 36:56

   Creating dynamic context windows with PRDs

   1. LJLazar Jovanovic29:30

      one." And it's also a productivity hack. Like, that's when 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 switch between them." And that's the next hack that I wanna talk about, if you allow me, which is, then the question in return is the obvious one, which is, how are you context switching? Like, you talk about context so much, yet you're keep switching between apps. How do you manage to do it, and do it in a way that's productive, you're-- and not produce bad code or bad product? And that's how I solve for that LLM problem. Again, the Aladdin, and the magic lamp, and all that, which is, if there's a limited token window-... How do I make it dynamic? And what 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, right? By the time you reach message number ten, 15, 20, 30, 40, snippets of early messages sort of get lost in the translation because agent is optimizing for speed, right? 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 treat Lovable or any other tool as an engineer that I'm supposed to 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- you've built hundreds of projects like I did, like, you, you, you see the winner. Like, the winner is so obvious, it, it's not even a, a competition. You maybe do one or more two prompts 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 ChatGPT 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, they are project requirements documents, or for me, I call them, like, sources of truth, right? What sh- 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 gonna build it, and 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 when we know how we're building it, how does the user journey look like, right? A user reg- registers, and then what? And then when they register a- and do that first step, what's the second step, and what's the third step, and whatnot? So I build 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 nail 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 gonna be dependent on, 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 .md part is, um, uh, you know, a Markdown. Basically, I'm just using Markdown format 'cause I've learned that AI likes to read Markdown. And what that serves as a, it 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, CloudCode or, or, or Cursor have what's known as rules.md or agent.md. What you're basically doing with rules or agent files is you're letting the agent know how you want it to behave and f- what it should focus on in the long run, so that you don't have to repeat yourself with every prompt, right? So in Lovable, there's a, there's a s- separate menu for that in your project settings, where you can define project, uh, uh, 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 PRDs, read tasks.md to see which task is next, then execute on that next, next set of tasks. And when you're done, tell me what you did and how I should test it." And that's where that conversation about, "I religiously read the agent output," comes into play. I've told the a- I gave the agent everything, all the tools and resources that it needs to succeed. I gave it the rules, I gave it the docs, I told it what to, to do with them. And at that point, I'm just sitting and reading. All- I don't prompt anymore. At, from that point on, I can switch as many windows as I like. My prompts become, "Proceed with the next, next task." I don't need the context. I outsourced that and delegated that to, to the agent. The agent need c- 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, it uses and 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, p- people don't talk about fonts at all, that, that work with AI. They're, like, 60% in my mind, maybe even more, in how your output's gonna 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 are gonna 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, is the, the one that, that, like, requires better decision-making rather than better output or better, uh,

9. 36:56 – 44:43

   Why elite vibe coders focus on planning, not coding

   1. LJLazar Jovanovic36:56

      alignment.

   2. LRLenny Rachitsky36:57

      Oh, my God, there's so much here. This is so awesome. Okay, so essentially, what, 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, well, 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 fe- may, some people may feel are not in- sophisticated tools that can build incredibly powerful things. Like, you can do a lot of this with tools like Lovable, like, have plans and rules and MD files. Like, you know, 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 have what- you get it going. And a key part of this, the, this three wishes rule, is really important. The reason you're doing this in a, in 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, uh, 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?

   3. LJLazar Jovanovic38:12

      It is, yes.

   4. LRLenny Rachitsky38:13

      Okay.

   5. LJLazar Jovanovic38:13

      'Cause, again, i- if... Let's say you didn't do this. Let's, let's hypo- let's talk about you ignoring this, and you're like: "I, 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, you're not i- referencing files or architecture at all, you're just describing the issue. Here's what's gonna happen. Any tool, Lovable or Cursor or Plot, whatever tool you, you, you talk about, is gonna do this. It's gonna be like: "Okay, let me start investigating," 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's- it can read 20 files. But what, what happens when you have... I, I, I'm just building a project right now that has, like, 60, 70 edge function- functions, right? What happens then when I say, "This broke," and there's no reference which edge function does what? Guess what? Lovable's 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, an LLM expert in the comments may say that I'm wrong, but this is my best guess as a non-educated person, the f- 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 h- 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, to an extent, I, I, I will say that's true. It's your fault, my friend. You did not provide any clarity or context to this tool. You just used its raw power and dug a deeper hole with your... spinning your wheels into the, into the mud, right? And, and, you know, obviously, I think we're heading into a world where AI is more honest than obedient, and say: "Hey, I only partially fixed this. You know, I- you did not give me enough of a context," right? The bigger mistake that people make then is, like, they trust the tool fixed it. They test, they see it didn't, 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 tr- it, it, do that's- it, 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, but that's... I- if you ever read, like, a stream of ChatGPT's thinking i- in thinking models, you see exactly what I mean. Like, 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, I just fell for the, the, the worst trick in the book." I, 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, my advice for people is, like: Yes, vibe your way for fun, and v- vibe your way, uh, whil- while you're prototyping, 'cause that's the exploration part. I love that part. But when exploration is done, please, please, please, use referencing, documentation, uh, uh, use all the agent files that you can, 'cause the, that, 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.

   6. LRLenny Rachitsky42:04

      This is hilarious. [chuckles] I think the, uh, 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, uh, 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 real, uh, right after this [chuckles] but, uh, the idea here is just, like, laser- show the- point the laser at 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 i- because it starts to run out of space in the, in the context window, it start- it just, like, the solution ends up... It doesn't actually work that hard on figuring it out in the end, 'cause it spent all this energy on reading and thinking, and then it's like, "Okay, here, I'll... At the last second, here's a solution."

   7. LJLazar Jovanovic42:59

      I think it just picks the first thing it, it thinks it's broken. That just, again, this is, uh, me completely uneducated, coming in, into the conversation and just thinking out loud. That's just my gut feeling and 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 the right file, referencing that file, like, really putting in the effort of handholding 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, the output. Agent makes me learn how to use it by... Some, some people read... I don't know what people read, but I, all I read i- is the output. Like, I don't read the code, and it's later down the road 'cause, like, I, 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, I apologise to the author 'cause I can't attribute 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, what 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.

10. 44:43 – 50:57

    Creating MD files to guide AI development

    1. LJLazar Jovanovic44:43

       Yeah.

    2. LRLenny Rachitsky44:43

       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 file- 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, uh, agents MD, rules MD. Say you wanted to just, like, move one step forward and be better at this stuff, what are the, what are the files you'd create, and then what do they roughly look like? What's inside these files?

    3. LJLazar Jovanovic45:12

       Yeah. So the master plan is the first one, which is like, it's, it's a 10,000-foot overview, right? It, it, it really high level explains the intent, uh, that I have with this app, you know-

    4. LRLenny Rachitsky45:23

       And this is masterplan.md, is that what you call it, or?

    5. LJLazar Jovanovic45:24

       Yes. Yeah, masterplan.md.

    6. LRLenny Rachitsky45:26

       Okay. Okay, great.

    7. LJLazar Jovanovic45:26

       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, to you feel," and a lot of times in the master plan, I will reference the other PRDs. I'll be like: "The design needs to feel modern and slick, but for at exact, you know, parameters, consult and read design guidelines.md," right? So I'm using just the master plan as, like, this high-level overview, right? To, to get the agent into, "Oh, okay, yeah, we are building XYZ," right? Um, then there's the implementation plan because, you know, there needs to be some order. I- y- if you just, like, dump stuff on top of each other without any order, um, you're never gonna get to the finish line. Um-

    8. LRLenny Rachitsky46:11

       And this is tasks.md, is that what you call it?

    9. LJLazar Jovanovic46:12

       No, that, that's the implementation plan.

    10. LRLenny Rachitsky46:14

        Implementation plan.

    11. LJLazar Jovanovic46:14

        I call it implementation plan. Yeah.

    12. LRLenny Rachitsky46:15

        Okay.

    13. LJLazar Jovanovic46:16

        An implementation plan is kind of, uh, in service of the future tasks.md, if that make... All of these files are s- in service of building tasks.md. 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, uh, explaining of like: "Oh, well, if we're building this, I think we should start with the back end, 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 a... 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, right? 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, you're not- you didn't open your Linear and started writing features and, and, uh, RFCs and whatever. You're just high-level talking about the, 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, 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, like, I, I like to see, uh, um, Lovable or any other tool. ChatGPT is good at it. I even have my... I've built, like, custom GPT, so if people wanna start somewhere before they even get into any tool, um, they can go to ChatGPT store and for GPTs and just type Lovable base prompt generator or Lovable PRD generator, and find those that I built and just, like, brain dump in them, and then get these files as output, right? So I'll, I'm, I like to see some elements of CSS in, in design guidelines 'cause, you know, you... With design, it's a little bit, it's a little bit tricky. AI is sometimes overcreative, so I, uh, that's where I'm doing a little bit more technical steering, right? Um, and then finally, it's just the user journeys. Just like, if we know how things look like, if we know how-... uh, they feel, if we know what we're building, high level, like, high level, just very high level again. How do people navigate? What, what are some of the, the features in there, you know, and stuff like that. And then Tasks.md gets into the nitty-gritty of like, "Oh, if you want these user journeys, and you want the back end 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 managers, I, I think, are not compensated for writing good PRDs. They're compensated, again, for good judgment, right? Somebody else can do the, the writing. You as a, as somebody who directs a- and builds this prod- product, you need to know, again, what, what, what's gonna be useful, what's gonna be tasteful, what's gonna 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, you..." That doesn't mean you shouldn't 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, 'cause that's how you get to clarity, not just by reading, but also by, by doing as well. [upbeat music]

    14. LRLenny Rachitsky49:57

        Here's a puzzle for you: What do OpenAI, Cursor, Perplexity, Vercel, 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, SCIM, RBAC, 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 start-up 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 Stripe 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

11. 50:57 – 56:50

    Why prototyping still matters

    1. LRLenny Rachitsky50:57

       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've taken somebody weeks, months, right? Like, the amount of investment to achieve this thing is absurd, the ROI. It... Also, this shows you just what professional vibe coding looks like. You know, everyone imagines vibe coding: "I'm just sitting here, typing stuff, go and do this, good..." If you wanna actually build something really great that moves the needle, as you said, that solves people's real problems, that lasts, that, you know, scales, this is, this is how you do it, if you really wanna do this as a, as a real- as a job, and also if you wanna build things that are really great.

    2. LJLazar Jovanovic51:48

       Yeah, and don't get me wrong, like, there's, there's obviously a ton of value in prototyping. Like, there are a lot of people maybe watching this that are like, "Okay, I wanna use Lovable at work, but I, I can't," or whatever, you know. There's, 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 prototyping i- is the, one of the best use cases. We-- o- our motto for 2025 was, uh, "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. Like, and I have a real, like, 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 have- 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, with connecting all the pipes and everything. But, like, if I had to describe it, I would say it took me- 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, u- ages, ages ahead with functionalities. Like, i- i- it's so much better, it's not even a contest, right? So I think now, we're at a stage where, like, for instance, there's... I, 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 c- creating super meaningful projects. Like, uh, I'm not gonna name names, but, like, uh, leading rideshare companies of the world, leading telecommunications companies of the world, leading, leading companies of the world in 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. Our, uh, you know, people in go, uh, in go-to-market, or, or sales, or, uh, 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, uh, and, and other tools for that matter, being used to, to push things into production, yeah.

    3. LRLenny Rachitsky54:39

       To help people do this workflow that you're describing with all these MD files, do you think you could share, uh, after we record this, just templates, like, simple templates of what these files look like for people just to look at and copy?

    4. LJLazar Jovanovic54:51

       I would literally go to ChatGPT, as I said, and brain dump into it. In my- s- just type Lovable GPT, uh, G- uh, Lovable PRD generator. You'll see my name there, right, and, and, and that I'm the author. Go in, brain 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, and upload those. Yeah.

    5. LRLenny Rachitsky55:14

       Amazing. Cool. We'll link to that. So, so it's not, it's not just: here's a bunch of files. It's go talk to this thing, and it'll generate the right files for you, and then you plug that into Lovable or other tools.

    6. LJLazar Jovanovic55:22

       Yeah, it's-

    7. LRLenny Rachitsky55:22

       Uh

    8. LJLazar Jovanovic55:22

       ... trained on... It's trained to think like I do, so yeah.

    9. LRLenny Rachitsky55:25

       Oh, amazing! Okay, that is perfect. By the way, I wanna talk about, like, how you unblock yourself, 'cause there's a whole other series of tips you have there, but I just wanna reflect on... It's so interesting how, one, you're kind of from first principles, unders- 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, and design. So I think that's so interesting, just this... It's interesting that these functions still work and are necessary. Now, it's you and AI help create all this, basically, this triad that's always existed: product manager, engineering, and design. And something I've always thought is that, uh, 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 I feel like that's gonna be an emerging, uh... That the value of that, being really good at design and taste and judgment, is only gonna go up.

12. 56:50 – 1:00:53

    Why “good enough” is no longer good enough

    1. LRLenny Rachitsky56:50

       Uh, before we get to things you've learned about unblock yourself, 'cause a lot of times, you know, things don't go in the right direction, there's a bug. Without being an engineer, what do you do? Before we get there, is there anything else you wanted to share around, just, like, tips for being successful?

    2. LJLazar Jovanovic57:03

       If we measure success in the right terms, again, um, AI, as you pointed out, regardless of your background, is an amplifier. So, you know, if, 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 i- i- i- in the old world, um, good enough was good enough, right? Because even producing good enough was not easy, right? Ten years, 15 years ago, just producing was more than plenty, more than good enough. You, you built a SaaS, who cares how it looks like? It works, it, it does stuff. Like, "Oh, my God, I'm so much more productive." Today, like, if, if good enough was here, let's say... Let, let's, let's visualise it for people. Like, if this was, like, pretty, 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, 'cause everybody produces good enough with AI. Absolutely everyone does it. So now, learning and optimising for: How do I produce world-class and magic, is the, 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, a, a betting man, as they say, I, I'd bet that the next class that wins are designers. 'Cause 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, like, the level up, 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 Lovable? Like, what's the biggest personal upskill?" Let's say, like, working with Felix, Nad, Abby, uh, a- a- all of the people that are designers, just really what moved and shifted the needle for me, and like: "Oh, so this is how [chuckles] world-class looks like, and this is what it takes," right? I, I always use the analogy of, like, I, I wanted to steal one of their designs and bring it into my Lovable project, so I went into Figma and I was like: [lips smack] "Let me just take this background, like, and just put it in there." I went in and realised that what could be, uh, uh, you know, 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 colours, this is 50 colours. And not just 50 colours, 50 colours with different gradients of levels of opacity." So I was like: "Oh, okay, well, that..." And that's the big disconnect that I've had all along. So, like, um, again, if you, if I'm answering your question directly, of 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, from Lovable. He has a, an amazing newsletter, like... Oh, and to teach you how to... And, and learn how to prompt for good design, learn about design styles. I didn't know what, uh, Bau- Bauhaus meant or glasmorphism. Had no idea! So, like, I built an app as well for that in 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 uistyle.lovable.app, I don't know what it is. Like, 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, uh, i- is probably, uh, what I would, what

13. 1:00:53 – 1:05:14

    The future of engineering in an AI world

    1. LJLazar Jovanovic1:00:53

       I would optimize for, um, at, at this stage, yeah.

    2. LRLenny Rachitsky1:00:56

       While 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 a thing? Do you feel like that goes away, based on your experience?

    3. LJLazar Jovanovic1:01:05

       It, 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, w- who's doing the maintenance, right? Maintaining code bases, uh, scaling code bases, maintaining projects, um, you know, they're still gonna be a thing, uh, uh, definitely. And obviously, AI is 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 it. And not to mention that, in a world where everybody's building, infrastructure suffers, right? Like, we all know and experience, like, Cloudflare 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 there 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, w- 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, the security, the email, the connectors, the APIs, the whatnots? Like, so I think there's gonna be room for it, but I, 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, not... "Don't, don't go and get a CS degree. Learn a, learn a good trade," you know, 'cause, uh, the new generation of millionaires in the US are actually electricians and plumbers and whatnots, right? So it's like, uh, you know, i- i- it's a balancing act, I'd say. I don't know. Like, I, I do still think that good engineers with, with good sense of, like, um, understanding where the future is going, are always gonna be needed, and, and scarce.

    4. LRLenny Rachitsky1:03:08

       Such an interesting question. I think to your point, there's definitely gonna be- people need to keep building the machines that power all this stuff. Will we need engineers to build the actual products, the, the, the application layer? That's, that's the question. Like, is everyone gonna be like you? Is everyone gonna be... Are designers just gonna be all we need?

    5. LJLazar Jovanovic1:03:27

       Everybody's gonna become a, an engineer, and, and let's, let's, let's then then... Let's speak to that end, like, I'm an- I feel like I'm a, I'm a rapid engineer. Like, I, I'll re- I'll refer to myself as a, as a rapid engineer in, in a year from now, 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, whatever you wanna call it? They... AI writes all the code. I, I, 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 fine printing, like, on a, 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, it already is, in a sense. Uh, m- most elite vibe coders rely on AI. Again, it's an amplifier, right? So I think, um, everybody becomes an engineer in, in the, in the world of the future. A designer, a PM, uh, uh, e- everybody is a, a, an, a forward-deployed engineer, or an AI assistant engineer, or an LLM engineer, or a vibe coder. The term is irrelevant. We're all using LLMs for raw output based on good judgment or bad judgment.

    6. LRLenny Rachitsky1:04:54

       Oh, man. Essentially, these Venn diagrams of engineer, designer, PM, they're all- 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, but it's fun to pontificate.

14. 1:05:14 – 1:14:27

    What to do when you get stuck: his 4x4 debugging workflow

    1. LRLenny Rachitsky1:05:15

       I wanna get back to when you get blocked. Speaking of elite engineers, uh, thing 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, um, network issue. What do you do when you get stuck? Do you have kind of a workflow you go through of unblocking yourself?

    2. LJLazar Jovanovic1:05:37

       Yes, great question, and, uh, absolutely true. Like, no matter how good of 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, if you have it on your car, you're gonna get yourself out of the mud much easier than, than, uh, the other way around. So, uh, in that sense, four different ways to debug. Attempt one of each only once, and I'll explain why in the end. Um, first one is, again, every tool is different. I'll, I'll reference Lovable's workflow, um, 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, uh, have this little button usually, which is, uh, uh, called Try to Fix. So your 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, the problem persists. And sometimes even the problem persists, but Lovable's agent's unaware that it persisted, so there's no more Try to Fix button. Lovable thinks everything's working, but in reality, it isn't, and the, the culprit there is usually you're using a third-party integration. You did not give enough context to Lovable where, what 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 aware- awareness layer. And what I do there is I go in, very simply, open the preview sandbox dev environment of my app, whatever, try to run the, the, the function that's broken, right-click, read the console log, right? Every, 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 l- layer into the equation." It writes the console logs, you rerun it, guess what? Now you have a full history of everything that was happening. You copy that, you paste it inside your chat. 99% of the time, that's enough. That's, that's already enough. AI's like, "Okay, got it. Found it, fixed it," right? But then there are 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, OpenAI, right? What I do is, like, any, any build that I do, I will export it to GitHub. Like, Lovable allows you to own your code, Cursor as well. C- 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, I, you know, used Codex since beta, like, I import it in there, and then I'm using an external tool. So I'm, I'm like, i- in the first try, as, uh, if you remember, like, I used the tool and I was like, total vibes, I'm, I'm relying on the tool, right? In the second try, I used myself as the awareness, uh, uh, facilitator. In the third one, I'm using an external tool a- 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, good model." I just don't know its agent well enough. Like, I don't wanna go and, and, 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. Uh, it's an old w- w- uh, workflow that I had before Codex and before Cloud Code, which is... There's a tool called Repomix, which allows you to, like, compress every, all, your entire code base into a single file. You download it, and then I upload it to Claude, just Cl- regular Claude or ChatGPT, and I'm like: "This is what I'm building. Read it, and, 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 'cause your team just can't handle it, right? And then the fourth one is, is usually the best one, 'cause a lot of 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, you had a bad prompt. You, you, you premised your request in the wrong way. You just don't wanna admit it, or you can't remember that you did, but it's your fault. So again, in Lovable and in the- all these other tools, you can revert back. There's version control built into Lovable, Cursor, Cloud Code. You go and say, "Okay, I tried these three things. I'm just gonna take three steps back, and I'm gonna think about my prompt a little bit more." Take a couple breaths, go for a walk, have some coffee, come back with a clear mind and try again. 'Cause 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, 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, 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?" 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, you ne- we all need to be aware and realistic. These tools are so good at, at doing things the right way if they are used the right way. It's always our fault. It's a hun- I say 90%, but honestly, it's 100% our fault, right? 'Cause 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 it the right way. For me, as a non-designer, I don't know any of the terminology, like, none of the headings and whatnots, and I still don't know it to this day. So when I'm, I'm-- I struggle with prompts, a lot of times I use chat mode to help me craft a good prompt. I mean, anybody can do this, too. If you are just stuck, it's 10:00 pm, and you don't know what to ask, switch to chat mode, brain dump, and be like: "Help me draft a better prompt. Help me prompt you better."... and let the tool e- effectively prompt itself. A lot of times you're gonna solve your problems by not introducing them at all with, with bad inputs, so.

    3. LRLenny Rachitsky1:13:05

       Oh, my God, [chuckles] everything you share is so interesting. [chuckles] I just wanna, I wanna keep digging. So just to reflect back the, 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?" [chuckles] 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, which is so funny, and, uh, and I hear this a lot, that Codex is, like, the, the most elite engineer as an AI. Karpathy tweeted this once, that... And we had the head of Codex on the podcast, too, by the way. Uh, that he'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 out there." 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.

15. 1:14:27 – 1:15:35

    Helping agents learn from their mistakes

    1. LRLenny Rachitsky1:14:27

       Sweet. And then this final step is so great, and this is where I wanna go. They- which you 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?"

    2. LJLazar Jovanovic1:14:52

       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 out of the equation, 'cause 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, 'cause I- I'm making you read the rules every time anyways, so you might as well just record it there. So I'm not gonna prompt you better, you're just gonna learn that I'm stupid, and you're gonna prompt yourself better, right? Again, just eliminate yourself a- and, and, move the context, you solve 99% of the problems with AI today.

    3. LRLenny Rachitsky1:15:29

       So the idea here is, uh, help it build its own brain, and, and rules, and way of thinking based on

16. 1:15:35 – 1:19:08

    Why watching agent output is more important than code

    1. LRLenny Rachitsky1:15:35

       problems you run into.

    2. LJLazar Jovanovic1:15:36

       Yeah.

    3. LRLenny Rachitsky1:15:36

       So great. Okay, so, so I wanna come back to this point you've made a couple of times, which is so interesting. This idea that you watch the output of the agent to learn what is going on. This is something I've seen other people-- Ben Tossell, who I think is at Factory now, share this recently. He's also basically vibe coding all the time. He was really into no-code tools before, and now he's all about vibe coding. And he shared... Basically, like, he's learning how things, how coding works, and learning how systems work by watching the agent output. And this connects to something Michael Turrell shared, the CEO of Cursor, when he was on the podcast. He had this vision of Cursor 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 it's, what it's thinking, and then what you tell it back. So essent- essentially, it's English in a conversation, which is... Like, it's not even pseudocode. It's interesting that that's where it feel, feels like things are heading. The layer over code is just its thinking and your conversation with it.

    4. LJLazar Jovanovic1:16:41

       Yeah, yeah, exactly. I mean, um, again, in a, in a way, I really optimize for, for good judgment, and part of good judgment is, it comes from, again, learning how these tools work. Uh, you need to know what's possible. We talked about it, and I, I know I may sound, sound contradictory sometimes, right? But it, it's because, as you said, it's so interesting, the world we live in, that things contradict to each other. It's an advantage not to know what's possible, but then at the same time, you cannot be completely, uh, oblivious to, uh, something that's like a, a, a factual thing. So let me talk about a failure of mine that came from being delusional. Um, back in the day, when OpenAI, um, uh, started, uh, uh... Or better say, released image generation natively in the app, right? So you could go to ChatGPT and be like: "Gen- generate an image of XYZ." The whole world exploded, like, that was, like, the biggest thing ever. Obviously, first thing that comes to my mind is, like, I wanna build a Lovable app. I just wanna build a wrapper, and I wanna 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, uh, brute force my way into making this work, instead of just waiting for another week, 'cause 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 i- when it was impossible, impossible. Like, so, um, I think again, you know, uh, uh, i- it's just a matter of really learning what's possible through communicating with the agent layer. 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, they have reasoning and thinking capabilities. So that's why I'm so invested into that conversation, 'cause a lot of times it will tell me, "Hey, what you're trying to do is just undoable at the moment because of XYZ." So, like, I always use those, uh, uh, as a learning opportunity, and I just level up most by-... being in chat mode, uh, for planning and learning purposes. And, and because it just, again, develops your clarity, your judgment capabilities, uh, rather than coding

17. 1:19:08 – 1:22:55

    The incredible pace of AI development

    1. LJLazar Jovanovic1:19:08

       capabilities. Yeah.

    2. LRLenny Rachitsky1:19:09

       The other point you made here, uh, 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, vibe coding, is just they had all these workflows, all these files, and then Cursor adds them, Lovable adds them, and-

    3. LJLazar Jovanovic1:19:27

       Yeah

    4. LRLenny Rachitsky1:19:27

       ... it's, like, sad. Oh, shoot, I had this cool workflow, and now... But on the other hand, it's like, okay, now it's just doing all these second focuses on this.

    5. LJLazar Jovanovic1:19:32

       A year ago, a year ago, if we had an interview, your mind would be blown. Stuff that I had to do as workarounds to, for, to, 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, I was teaching people, like, I have a YouTube channel, a little bit appreciated, but, like, there's a, there's a, like, a seven-day learn how to vibe code with Lovable series that I did in March, completely obsolete. Like, it- 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, it just works, right? So, um, that's why, as I say, like, um, uh, i- 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? Took us about 200 years to build it. When it got to-- when, when engines got built and put... cars were put on the roads, I, I think that 90% of horse population was, got eradicated in the US within 20 years. The person that tweeted 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 evolve it into, into something else," right? So, you know, I, 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, 'cause 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, uh, doing spreadsheets. Like, uh, nobody... May- 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 gonna be paid to think longer and ponder longer, because the longer idea simmers and gets broken down, the better, 'cause building it is gonna be an instant, right? It's gonna be like this. It's just a matter of you having so much clarity around it, because guess what? If a tool is super powerful and you give it a wrong input, the output's gonna suck as well. That's why, like, I've never become good enough at Claude Code, I feel, 'cause I don't start my projects with enough clarity, and the tool is so powerful that, like, I just misdirected completely from the get-go, and I was like: "Oh, shoot, this is not what I wanted to do." So that's why I, I still f- uh, see myself being good at, like, using tools that are, uh, uh, a little bit on the exploratory prototyping path, um, uh, more than, like, on the path that, you know, uh, elite engineers would use, for example.

    6. LRLenny Rachitsky1:22:53

       I love your optimism and excitement about this

18. 1:22:55 – 1:28:30

    Why emotional intelligence will become more valuable

    1. LRLenny Rachitsky1:22:55

       stuff. I think for a lot of people, say, they're current software engineers, PMs, designers, there's a lot of fear about the future of their careers. Are they gonna be relevant? Will I- will my software engineering skills disappear? So to follow the story 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?

    2. LJLazar Jovanovic1:23:32

       Yeah, emotional intelligence, for sure. Just understanding human nature, real-life stuff. I think we're all gonna get so tired of everything fake: fake images, fake posts, fake profiles, fake this, fake that, fake videos. Everything is becoming fake and AI-generated. I think humans just craving humans naturally are gonna wanna do live stuff more. So anything human to human is gonna be a big thing to skill up on, understand the dynamics. Anything regarding math, uh, i- if it's a math problem... I think P- Peter Thiel said it recently, like: "People that just do math stuff, you know, AI is gonna come for you." Like, anything that's very deterministic, meaning X input equals Y output, and it's pretty clear the, the line is pretty clear, AI, AI's got, got eaten, 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 gonna become good. So if we translate it again to a s- specific skill, I'll say it again, good design, really good design, great design. Like, how, how... And when I say design, that's images, fonts as well. Copy. Copy is a big one. Like, we all now, we're, 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's AI and what isn't in, like, three seconds, and we're only a couple of years in. So, like-... really good copywriting is gonna be a very good skill to have, 'cause people are just gonna know after three, uh, words or three sentences that it's AI-written, and even I don't read AI output anymore. I, I don't like just seeing it. I want raw, that raw human experience. So I think human skills... I, I don't even know how to describe it, because I don't, I don't think we're doing an awesome job, uh, putting g- labels onto what humans are good at natively, but I think we will. I think we will describe job descriptions better. Um, we, we will have, like, uh, a human-first engineers, I don't know, or human designers, or I, I don't know how to describe those roles, same way how, uh, Karpathy, uh, coined vibe coding. I was vibe coding before he did it, and I didn't know how to call it. Like, I started vibe coding in July of 2024, and I think he, uh, uh, he coined it in 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, 'cause there was no name. It was like, "Oh, I'm just using AI to, to, to do this for me." I'm, I'm... I don't know, whatever. So yeah, I think we're gonna reinvent some of the, the terms, roles, and whatnot, but, uh, uh, stuff that's like human to human is here to stay. Stuff that's like, I think, like, oh, you're, you're just doing... You're, you're m- you're a middle manager, you're a middleware person that's just translating stuff. Um, and I can use that analogy again. Translators are gonna die, people writing jokes, comedians, are not. G- AI is never gonna be able to write a good joke, never, never, never. It just doesn't have that layer, that just doesn't understand what's funny. Like, if you ever try to use AI to write jokes, like, they're awful. They're always gonna be awful. But if you use AI to translate things from one language to another, it's very good at it. Like, AI is gonna replace translators, it's gonna replace most journalists, because it does good research, it can write good copy, whatever, not, not elite journalism. It's not gonna be able to replace all the writers. It's gonna amplify great writers that can train AI on how to write books. So, like, somebody who's a amazing writer is gonna 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 being replaced, zero, and that's just my personal belief. Like, AI's never gonna write good comedy. It's impossible. And like... So try to find your analogy in your industry. Like, I just gave you one for, uh, writing skills, so to speak. So writing jokes, super good skill to have. Um, translating, uh, I'm sorry to say, but, like, you're not gonna have a job for much longer. Like, uh, you better find something else to do. Um, but yeah, that's, that's how I look at it.

    3. LRLenny Rachitsky1:27:57

       The, the comedy piece is interesting. I had one of the founders of a, the data labeling company, I don't know if it was Mercoor or maybe Surge, and he said that, um, I think it was Anthropic hired a bunch of National Lampoon comedy writers, uh, to help them train models, and so they're working on it. I'm so... I, I love the strong prediction you made. I'm so curious in a year to look back and be like, "He was completely right," or, "Nope, they got that one, too."

    4. LJLazar Jovanovic1:28:23

       I'll be wrong on 95% of the things I said today, three months from now.

    5. LRLenny Rachitsky1:28:27

       [chuckles]

    6. LJLazar Jovanovic1:28:27

       That is the only thing I can say very, very confidently.

19. 1:28:30 – 1:30:10

    How to become a professional vibe coder

    1. LRLenny Rachitsky1:28:30

       Mm-hmm.

    2. LJLazar Jovanovic1:28:30

       Yeah.

    3. LRLenny Rachitsky1:28:30

       Mm-hmm. That seems right. [chuckles] Okay, so speaking of 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?

    4. LJLazar Jovanovic1:28:50

       Well, my personal path and personal journey was anything but linear, right? I, I've done so many things in l- in, in life, like, um, blue-collar jobs, worked at, even at Subway while I was studying and stuff like that. Like, um, I'm, I'm an engineer by trade, but not a software engineer. I'm a forestry engineer, so no coding, but still-

    5. LRLenny Rachitsky1:29:09

       Wow

    6. LJLazar Jovanovic1:29:09

       ... engineering is engineering, I feel. You still develop certain set of skills doing that.

    7. LRLenny Rachitsky1:29:14

       Mm.

    8. LJLazar Jovanovic1:29:14

       Um, I waited tables a long time, so you develop some human skills. You understand what people like, what they don't like. Like, I've, again, blue-collar jobs, like, teach you hard work and, like, it's... As I said, the path was not linear, but I feel almost like a Slumdog Millionaire, the movie storyline, which is like, everything that happens to the character brings him into a position to be able to answer the qui- the questions in the, in the quiz better. I have- I feel the same way of like, I've 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's something we haven't touched upon at 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? Like, and at, get attention, which is kind of s- it is the most scarce resource, and it will be even more scarce. But, like, going back

20. 1:30:10 – 1:37:03

    Why building in public is the fastest path to opportunities

    1. LJLazar Jovanovic1:30:10

       to the vibe coder role, if somebody's, like, saying, "Okay, well, I have, I have a pretty diverse background, too, and I'm vibe coding," and, like, "how do I... How does this become a job?" Well, for me, I feel like it became a job by building in public. I did chat with Elena once, only once, so, like, "Why me? There are so many good vibe coders out there. How did you pick me out of the crowd?" And I think, you know, obviously, you know, she gave me a couple of reasons, but, like, to translate it into, like, a, a, a, s- one concept, it was like I was building in public and sharing. I, as I said, I made a YouTube channel, and I, I shared all the failures and all the knowledge, all the projects that I was building. I used social media a lot, like LinkedIn was my go-to, 'cause I, I just have that type of-... cadence. Uh, as you can s- see, I, all my answers are very long, and X doesn't, doesn't cut it for that. Like, you need very, y- y- you know, you need to be very, uh, to, on, on, on point to be successful at X, so I'm not. So I guess, you know, it's just, like, build in public, share your knowledge, give away all the secrets. Like, there are no secrets whatsoever. Uh, if you're sitting on a good concept, you're missing out, so just share it immediately if you figure something out. That, I recognized that, um, very early on. And, you know, just like I think a lot of people participate in hackathons these days, I wanna encourage people to do them. Like, find those, those opportunities locally to connect with other builders. Lovable is hiring across the board. Check out our op- open positions. It's as easy as that, right? Like, just apply, really. Find companies that, that are hiring, and, and hiring in, in different roles. And I've seen people do something, I'm gonna give people a, a secret away. [lips smack] A couple of hires stood up by not sending resumes, but sending Lovable apps. They built Lovable apps to show what they're... Why they're a good fit for a role. And we, as Lovable employees, will always open an app that uses lovable.app domain. Always. If you send me a DM, send me a Lovable app. Don't send me anything long, send me an app that tells me what, what you want from me, or how do you see us collaborating and working together, right? So there's people finding creative ways to get in front of eyeballs of decision-makers like Elena, right? And, um, I, I mean, skill-wise, again, w- we're just rec- uh, repeating ourselves here, but I think it's important to repeat it as many times as possible: really develop good judgment, right? Really, uh, understand, in a deeper sense, how, uh, how things translate w- when vibe coding comes into play, right? There's a company out there, I, I'm not gonna name them, but, like, um, that uses Lovable religiously. It's gonna be one of our main case studies, actually, where, like, they a- actually hired vibe coders before Lovable did. Like, I'm the first official vibe coding engineer at Lovable, like, with that title, but I've met people in companies where they hired them before us, people that are just vibe coders, people that just understand that speed matters, [chuckles] right? It still matters a, a lot to be fast. And, like, there's a company out there with three vibe coders full-time, all they do is, like, translating the old, uh, code base into, uh, uh, o- onto Lovable. This is bringing everything, their CRM, CMS, everything. The, all the tool sets that they have, and they needed, s- there are people now actively just migrating everything, everything over. There's S&P 500 companies that are, like, putting Lovable in, in job descriptions, too. Like, saying, "Hey, Lovable scares, uh, skills are, you know, um, recommended, i- in the recommended tab," right? So yeah, to, to, to, to go back to the how to become vibe coder professionally, well, you don't need a company to hire you. You can hire yourself as a professional vibe coder first. I think the reason why it... I clicked with Anton and with Elena, and everybody else, because I was already doing it. Like, all, all I did, I just changed the, the, the, the vehicle, but I was already doing it professionally before I got hired. So that's kind of the, the, the key. Like, uh, do the job you, you, you would've done anyways.

    2. LRLenny Rachitsky1:34:18

       What a mind-expanding conversation. I love just how passionate, and excited, and motivated you are about all this. It feels like there's so many people out there right now that are so burnt out, I don't know, disillusioned, scared, and you're the opposite of that. You're just leaning into this, just taking advantage, taking... N- You're not sure where it's gonna go, but following the path.

    3. LJLazar Jovanovic1:34:38

       Yeah, and I, I don't wanna interrupt you, but, like, it's, it's, it's because, like, look, um, Lovable specifically isn't a company. Y- you can talk about it as a company. I don't see it as a company, it's a, it's an idea, i- it's a mission. It's, it's, it's something s- more powerful than the Internet, in my mind. Because, like, uh, Internet allows us to consume, Lovable allows us to build. And, and in our nature, in 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 me, it's just, i- 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 gonna be a software engineer or that I'm gonna be building, but, like, life wasn't as simple as that for me. Like, uh, uh, i- i- it was very, very, uh, complicated. And honestly, the last 5 to 10 years, I gave up on that dream, almost. I, I, I thought I'm never gonna build anything. Like, I've tried, I've, I've, I've 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 36, like, 30 years later, I, I feel like, again, like that, that kid. Like, I dream every day. Like, I... It's, it's amazing what this enabled us to do. And I... Anybody that's scared, like, just try it. Y- it, it switches from fear to excitement immediately, because then you see what's possible firsthand. Just go in, build something, build anything, and the, the fear goes away. You, 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.

    4. LRLenny Rachitsky1:36:45

       I think a big part of this is just stop listening to this podcast, go just do stuff, 'cause you actually-

    5. LJLazar Jovanovic1:36:49

       Immediately!

    6. LRLenny Rachitsky1:36:49

       ... try, try to, right? [chuckles]

    7. LJLazar Jovanovic1:36:51

       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.

    8. LRLenny Rachitsky1:36:58

       ... All right, bye everyone. Okay, I'm just joking. But let's, but let's- we, we shall wrap it up.

21. 1:37:03 – 1:42:29

    Final thoughts on focusing on quality over tech stack

    1. LRLenny Rachitsky1:37:03

       Um, I'm gonna skip the lightning round just to keep this episode shorter. Before we wrap up, is there anything else other than just go build some stuff, anything else you wanna say? Anything else you wanna leave listeners with? Otherwise, we'll let, we'll let you go.

    2. LJLazar Jovanovic1:37:15

       Yeah. Uh, tech stack doesn't matter anymore, right? It doesn't matter. Like, people obsess over, "Oh, is this written in HTML? Is this written in React?" Is... It doesn't matter. Like, it never mattered, but now it 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, 'cause otherwise you're just gonna end up in a crowd with millions and millions of others. But at the same time, if you don't know what magical 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. Le- read the agent output. Learn how it's thinking so that you know what's possible, but then also go and get inspired. Follow good designers on X. Find tools where great designs are produced, and follow their creators. There's a tool where w- where I'm following just the, the actual person that built it, 'cause he, he, uh, publishes videos almost daily, 40, 50 minutes long, of him designing. I wanna see how a world-class designer does it. I wanna see him talk to the tool. I wanna see him prompt, and that's how I learn to become better at it. So again, exposure time. Just 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 end are you using, which front end are you using. That doesn't matter. Quality, taste, design, that's all you need to optimize for in the future that's ahead of us.

    3. LRLenny Rachitsky1:39:12

       Lazar, this, uh... I think we're gonna leave a lot of li- a lot of minds buzzing [chuckles] 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 wanna reach out, maybe ask some follow-up questions, and how can listeners be useful to you?

    4. LJLazar Jovanovic1:39:39

       Awesome. Yeah, uh, so, um, I mentioned it already, LinkedIn is probably the best place, uh, to find me on. You know, I'm very responsive there. Um, if you wanna follow me, I hope to re-engage my YouTube channel a little bit more. I think I have a, a, a lot of cool tips and tricks that I, that I wanna share, and teach people how to, uh, use Lovable and, and just vibe coding in general, and level up. And on how people can, uh, be useful f- to me, well, you know, I, I'm very passionate about making sure that everybody experiences what I've experienced that day when I got my first prompt in. I envy the person that is gonna try Lovable for the first time after watching this episode, 'cause the feeling is just unmatched, o- of you going from a consumer to a builder. But in that process, there's gonna 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've been better in that experience, especially if this is your... Y- you just watched this, a- and you're like, "I'm gonna do it. I was on the fence, and I'm gonna do it." If something breaks, if something doesn't connect and relate, I need to know what that is. My job is 100% to empower you to build the best work of your life, right? Um, and, uh, you know, and I need to say this, too, 'cause a lot of people may be inspired, uh, not by building or, or using Lovable, but, but, but rather building Lovable. Come join our team. Again, we're hiring across so many things. I think a lot of people should feel inspired, because I h- I, I hope that the energy that I bring to the table will resonate. This is how it feels working at Lovable. 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 ab- about a problem today, and you s- you're like, "Man, I, I think I can solve it," come join us. Help us build and shape the future of software development.

    5. LRLenny Rachitsky1:41:52

       Incredible. And, uh, what's the site? I m- I imagine it's just a link on Lovable's website to find the, the open roles.

    6. LJLazar Jovanovic1:41:57

       Yes.

    7. LRLenny Rachitsky1:41:57

       We'll link folks there.

    8. LJLazar Jovanovic1:41:58

       Yeah.

    9. LRLenny Rachitsky1:41:59

       Incredible. Lazar, thank you so much for being here.

    10. LJLazar Jovanovic1:42:02

        Appreciate the opportunity.

    11. LRLenny Rachitsky1:42:03

        Bye, everyone. [gentle music] Thank you so much for listening. If you found this valuable, you can subscribe to the show on Apple Podcasts, 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 lennyspodcast.com. See you in the next episode.

Episode duration: 1:42:30