Software Supernova: Lovable's "Superhuman Full Stack Engineer" to Transform Idea to App in Seconds

In this episode of the Cognitive Revolution, founder Anton Osika and AI engineer Isaak Sundeman from Lovable.dev, discuss their AI coding platform that allows users to describe software in natural language and have it built by AI. They delve into the nuances of using AI for full-stack engineering and the future of human coding. During the episode, they demonstrate building a product comparison app, discussing the integration of AI, backend functionalities, and handling complex API interactions. They also talk about the challenges and opportunities in UI design, the role of AI in improving user experiences, and the potential future impacts of AI on software development. The conversation touches on the phenomenal growth and scaling of Lovable.dev, their strategies for managing context and dependencies in large codebases, and their vision and roadmap for the future of AI-powered application development. Checkout lovable here: http://lovable.dev SPONSORS: Oracle Cloud Infrastructure (OCI): Oracle's next-generation cloud platform delivers blazing-fast AI and ML performance with 50% less for compute and 80% less for outbound networking compared to other cloud providers. OCI powers industry leaders like Vodafone and Thomson Reuters with secure infrastructure and application development capabilities. New U. S. customers can get their cloud bill cut in half by switching to OCI before March 31, 2024 at https://oracle.com/cognitive NetSuite: Over 41,000 businesses trust NetSuite by Oracle, the #1 cloud ERP, to future-proof their operations. With a unified platform for accounting, financial management, inventory, and HR, NetSuite provides real-time insights and forecasting to help you make quick, informed decisions. Whether you're earning millions or hundreds of millions, NetSuite empowers you to tackle challenges and seize opportunities. Download the free CFO's guide to AI and machine learning at https://netsuite.com/cognitive Shopify: Shopify is revolutionizing online selling with its market-leading checkout system and robust API ecosystem. Its exclusive library of cutting-edge AI apps empowers e-commerce businesses to thrive in a competitive market. Cognitive Revolution listeners can try Shopify for just $1 per month at https://shopify.com/cognitive CHAPTERS: (00:00) Teaser (00:56) About the Episode (03:57) Introduction and Guest Welcome (04:21) Overview of Lovable.dev (04:53) Building a Product Comparison App (05:19) Starting the Coding Process (05:46) Defining the App's Functionality (08:21) Setting Up the Backend (13:20) Future of Software and AI (Part 1) (17:40) Sponsors: Oracle Cloud Infrastructure (OCI) | NetSuite (20:20) Future of Software and AI (Part 2) (23:44) Challenges in AI Development (Part 1) (32:48) Sponsors: Shopify (34:07) Challenges in AI Development (Part 2) (39:08) Integrating External APIs (54:01) Helping Out and Initial Fixes (54:18) Progress with Documentation and API Updates (55:21) AI Analysis and Product Comparison (57:33) Building AI Applications: Challenges and Solutions (59:02) Understanding AI Agency and User Experience (01:24:27) Scaling and User Growth (01:29:03) Future Directions and Hiring (01:30:55) Final Thoughts and Advice (01:32:06) Outro PRODUCED BY: http://aipodcast.ing

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Over time, AIs are going to read our minds, basically, or they're going to be extremely good at predicting what we want in a given situation. Historically, we have switched overnight after a new model comes out because we tried out and say, okay, this is a better model. We don't use just one LLM. We do smart routing and we use from Gemini, OpenAI and Anthropic. And soon, I imagine, potentially from DeepSeek. When you're connecting to external APIs, as you said, Nathan, it's often more things that can go wrong. And that's where you need to have a system that's good at debugging itself between the different components that are interacting. The most important thing is that you have a product that predictably works and like works in an intuitive way.

• 0:40Speaker 00

  And making an agent work intuitively and like in a nice way, it takes a lot of iteration. If you're currently working without AI, then I think you're really disappointing your employer or your customer, your clients.

• 0:57Nathan Labenz?

  Hello and welcome back to The Cognitive Revolution. Today, we're simultaneously releasing the first two parts of a series we're calling Software Supernova, with the makers of new and stunningly fast-growing full-stack AI developer products, Lovable and Bolt. Each episode explores in its own way how AI's rapidly improving coding capabilities are beginning to tangibly transform the software industry by expanding the space of what can be built, changing how professional software developers work, and making it possible for people to create software without ever learning to code. My guests in this episode are Anton Osika and Isaac Sundeman, founder and AI engineer at Lovable, online at lovable.dev, which describes itself as "your superhuman full-stack engineer"

• 1:43Nathan Labenz?

  and promises to take users from idea to app in seconds. Headquartered in Stockholm, Sweden, Lovable has achieved extraordinary growth since launching in November, reaching $9 million in annual recurring revenue in just their first two months in market, thus becoming one of, if not the, single fastest-growing European startup ever.

• 2:04Nathan Labenz?

  In this hands-on episode, we weave a discussion about Lovable's vision for the future of software, their product philosophy, and some of the opinionated choices they've made to maximize user success rates, including their SuperBase integration for database functionality and authentication, their approach to error message handling and debugging, and their extremely novice-friendly user experience for handling API keys, all together with a live demo in which we actually use Lovable to build a large language model-powered product comparison application. I think the audio version should be fine for most listeners, but if you want to read all the prompts and see the product in action, you can visit our YouTube channel for a version that includes a screen recording. As you'll hear and perhaps see, while we do encounter some friction along the way,

• 2:47Nathan Labenz?

  in the end, we are able to create a neat little AI app not just once, but twice. The first time iteratively over a dozen or so interactions, and then on the second go, with a few lessons learned in just four prompts. All with Cloud 3.5 Sonnet, I should note, as we did record this episode just prior to the recent release of O3 Mini. The upshot is that today, non-coders with a bit of AI savvy and willingness to retry when needed can create basic full-stack applications on their own without writing any code. And of course, new models will only continue to expand the scope of possibility. This represents a massive democratization of software development, and considering that so many of the resulting apps will use AI to do things that traditional software never

• 3:30Nathan Labenz?

  could, a low-cost path to AI transformation for many millions of businesses. As always, if you're finding value in the show, please take a moment to share it with friends, write a review, or reach out via our website, cognitiverevolution.ai. We always welcome your feedback and suggestions. For now, I hope you enjoy this unique look at AI-powered software development with Anton Osika and Isaac Sundeman of Lovable, online at lovable.dev.

• 3:59Nathan Labenz?

  Anton Osika and Isaac Sundeman, founder and AI engineer at lovable.dev. Welcome to the cognitive revolution.

• 4:07Speaker 00

  It's great to be here. Thank you. Thanks, Nathan. I've been listening to your podcast and I love that you cover everything and I get smarter every time I listen.

• 4:15Nathan Labenz?

  Well, thank you. Very flattering. That is definitely the goal is to learn as much as we can and hopefully be a little smarter about what's going on in AI. So you guys have been on quite an exciting journey lately. Lovable online at lovable.dev is an AI coding agent. I would classify it as, you can tell me if you have a different high level label for it, but it's one of these new AI full stack engineer. Yeah. So it's one of these things where you can show up and say, hey, I want a piece of software created for me and just describe what you want in natural language and then have the AI run off and try to build it for you. And so today, what I thought we would do is kind of a little bit of a departure from

• 4:59Nathan Labenz?

  our usual format, but you know, have the normal conversation, try to understand what you're building and your vision for the future and you know, how soon you think human coding becomes irrelevant, if that ever is going to happen. And then at the same time, actually, you know, kind of go in the background, partially in the background and actually try to build an app as we go. And I think that'll be a very, you know, informative two track experience. So I guess Anton, you and I'll be primarily talking and I think you'll be kind of primarily coding in the background. So I guess maybe let's start with just kind of a little, we'll get you running on the, on the programming and this will be on the video feed. You know, we can just be kind of following along with you. You can, you know, we can stop and interject anytime and share developments.

• 5:43Nathan Labenz?

  And then Anton and I will kind of just, you know, continue with sort of big picture stuff while you're moving forward. A simple app that I had an idea for that I think we are going to try today is just a product comparison app. Basically, say you've got a couple of links to a couple of products online and you want to get a good comparison of those two products. Feed them both into an app and have the app come back and tell you what matters about this kind of product and how these products compare on that dimension. And I'm sort of thinking of this as an AI-driven comparison, right? So it's not something that would be fully programmatic or formulaic, but where there's a little bit of dynamism in using

• 6:25Nathan Labenz?

  the AI to determine what sort of comparison even makes sense for a given product. How's that sound?

• 6:32Speaker 00

  That sounds good, I think. I hope so. Like, what type of products do you want to use this for?

• 6:39Nathan Labenz?

  Well, I think what's so interesting about AI products in general is how open-ended they can be and how flexible, you know, they can be. So I guess my initial idea was like, any products, you know, a very like live example right now this week in my home is that our washing machine has broken and we need to replace it. And so my wife is like, you know, going on to review sites and the wire cutter and Consumer Reports and, you know, trying to figure out which one should we get? Obviously, you know, capitalism has provided us with a huge number of different options, but we don't even really know what matters, right? We've never bought one before. We've never thought about it. If you think about what you do today, if I think about what I do today, I first sort of feel like

• 7:24Nathan Labenz?

  I have to go out and educate myself generally about a product category, like what are the dimensions that matter? But that process of identifying those dimensions is, you know, where the bulk of the cognitive work seems to be going. You know, do I want, for example, a front loader or a top loader in my washing machine was not a question I had considered at all before. And I had to first like educate myself to even get to the point where I realized that, okay, that is an important dimension of this comparison. So I feel like if the AI was really serving me well, it would flag for me like, okay, here are the main things that people find to be important about these products that you may not even be aware of

• 8:06Nathan Labenz?

  yet. And then here's how they compare. But sort of creating the comparison framework and then populating it is sort of what I imagine we would have loved to have had these last couple of days.

• 8:19Speaker 00

  Let's see if we can ship an MVP and then iterate. I think that's always the best. It starts super simple. So I guess let's go. I'm thinking the first part is to just get up like some core data input into the system and then feed that into an AI and see if we can hook all that up and how long time that would take. I would do just like we want to, you want to put, so one workflow is you say, I want to buy a dishwasher. Which ones should I compare? But let's be more to help it out and say, I want to put in a few URLs of these different dishwashers and compare them. Does that sound reasonable?

• 8:58Nathan Labenz?

  Great question. I don't have a super prescriptive idea in mind of exactly what the user experience should be.

• 9:05Speaker 00

  It's cheaper first version.

• 9:07Speaker 02

  There are also like some of the things that you can think about when you create your product within Lovable is that you can't think more overarchingly what tools and APIs we should use. Like for example, there is this Perplexity API that will automatically search up things for us. So that could perhaps.

• 9:24Speaker 00

  That could be super useful. But let's start with like, we have a constraint as much as possible to see if that works out. And we just get the UI up. So first type out, we first type out a prompt where we say, I want the UI to kind of do, let me put in URLs of products. And then there's some information about those products should be shown and the AI should help guide us through what's important to consider. Maybe generating a product comparison table. So let's go with this prompt. So we test create a product comparison tool that uses AI, create the UI and the flow is something like the user put in product URLs. Products, right.

• 10:07Speaker 00

  URLs and input fields. Nathan, do you think this is good? What do you want it to do once you put in the fields?

• 10:17Speaker 02

  Should we have like a button called analyze or like compare?

• 10:19Speaker 00

  Yeah, let's have a button, analyze button. Sounds good. And then we have analyze.

• 10:27Speaker 02

  A button that uh when pressed will uh scrape the websites. And get the data and then call upon, then call G P T.

• 10:43Speaker 00

  Let let's take that later, let's call.

• 10:44Speaker 02

  Yeah, yeah. But let's start with a really nice UI.

• 10:49Speaker 00

  So it's like it's try typing out the prompt here that is like has a few typos and things.

• 10:53Speaker 02

  Yeah.

• 10:54Speaker 00

  Uh and I think that the typos, they don't matter, the A I understands perfectly. But the formatting and the sequencing of what you ask in what order, that does matter quite a lot. So like be and being being very specific about when once you have an application and you want to change it, being very specific about in the prompt, in your prompt is very important. And what what we're seeing now, feel free to ask any any questions, Nathan, I think that's more fun. But what we're seeing now is that the the A I creates a plan for what to do, a bit about the like first it plans out the design. And and then it generates what we think is the best practices in terms of a web application.

• 11:33Speaker 00

  Uh like most software today is actually web applications, so so that's what what it's doing, it's uh React code. And uh now it's spinning up the the first UI version of of this. And yeah, I guess like here you can add a few product URLs and click compare products in the.

• 11:52Speaker 02

  Yeah.

• 11:53Speaker 00

  Then now now you're getting a Swedish version of washing machines because Google is adapted to where where we are at right now. But let's pick that one.

• 12:01Speaker 02

  Okay, so I guess the idea is.

• 12:02Speaker 00

  Let's compare the same one, yeah.

• 12:04Speaker 02

  Yeah. Let's let's take take something else, here's this different one.

• 12:09Speaker 00

  Yeah, and this should work for like Amazon or any URL, right? But let's let's see.

• 12:14Speaker 02

  And then we would press.

• 12:15Speaker 00

  What happens if we press compare?

• 12:16Speaker 02

  Yeah, so nothing should happen right now because we haven't actually connected the backend or anything. So, yeah, analysis feature is coming. I love how it gives you the little heads up.

• 12:27Speaker 00

  Notification.

• 12:30Speaker 02

  Yeah, and.

• 12:31Speaker 00

  So yeah, so let's hook up the data input and then we need a backend. So the backend is needed when you have something that requires like external data, AI features and so on. So the way we set up a backend is that we rely on our wonderful friends over at the uh Superbase, which has like a backend as a service that covers all your needs. And then usually I guess you would be logged in here, but now.

• 12:57Speaker 02

  Yeah, now I need to log in.

• 12:58Speaker 00

  One click, one click, get the backend set up.

• 13:02Speaker 02

  Yeah, let me, let me log in real quick.

• 13:04Speaker 00

  Do you want us to clarify anything on what's happening there, Nathan?

• 13:10Nathan Labenz?

  Well, let's maybe start with a like big vision and then, you know, we can kind of meet maybe in the middle. We've got the very low level, like we did our first prompt, we're connecting into Superbase. What do you think is the sort of big picture future of software? Like, where is this all headed? Because I feel like we have this sort of like competing narratives right now around the future of software. And I always say my crystal ball gets real foggy more than a few months out. So what do you think is the medium term future of software? You could maybe take that from like a user standpoint, you know, a developer standpoint. Are there still developers? Does anybody just sort of speak software into existence?

• 13:54Speaker 00

  My biggest prediction here is that when I was super young, I started coding and started creating computer games. And that's been like a superpower to understand the world and communicate about technology and to make things come into existence. But much less than 1% of the world's population has that superpower. And with AI, the 99% are going to be empowered to create, solve problems with software and edits and improve software. Like everyone is going to be able to use a version of the software that they prefer. That's customized work, improved to them. And that's changed and how fast it's going to be because AI is much faster than humans at writing code.

• 14:40Speaker 00

  Is going to result in some kind of Cambrian explosion of really high quality software and just human creativity is going to be unleashed at a much larger pace. I think that's going to be the biggest change. And then you can talk about how that affects the current workforce building software. And that's a bit more complex, but I think that's the biggest obvious change in my eyes.

• 15:07Nathan Labenz?

  I guess one big question I still have about that, though, is like with this example that we have, right? If I imagine a future where AI is sort of continuing to advance and it's like achieving the promises that, you know, are sort of, everybody sort of seems to believe that it's about to achieve. It seems like we have lots of reasons to think, you know, capabilities are not done improving.

• 15:29Nathan Labenz?

  Then will there be like any UI in the comparison process of products in the future? Like, I could imagine a much different thing entirely where I just asked the question directly, right? And maybe this is sort of a fault of like the example app that I proposed, but in today's world, we like need these dedicated UIs because we don't have a like general purpose interface to the world's, you know, information, let alone reasoning.

• 15:55Speaker 00

  I've been hearing this generative UI thesis a lot on like, oh, we're not going to have software, just going to have AI. And then there is some general like interface to all of this AI. I'm confident that that's not going to be the whole answer. And there is a very simple reason for that. And it's that us as humans, we prefer when things are predictable and the same. And more so that the software that we're in, the products that we're interfacing with has a UX that has been tested by many other humans. And it's something that humans can understand easily. So if you have an AI that always generates like a new type of interface with context dependent on where you're at, then it's going to be different every time potentially.

• 16:40Speaker 00

  And it's going to be different for your grandmother and yourself. So you cannot kind of explain, oh, this is how the software works. I'm pretty sure that we're going to like have a standardized like people are going to use the same software, the same UX always, most of the time, because that's just easier for us humans to get used to, build up the muscle memory of how do I use Slack, how do I use my email client and so on. And the exact UX is something that is super hard to nail, like it takes so many iterations of making a product lovable. That's why we call it lovable. It takes so many iterations and now with AI, you're going to be able to go through those situations and really nail like what is the right UI for what this

• 17:23Speaker 00

  software is supposed to do. So that's why I don't think generative UI is going to come in and just wipe out everything else. But there's definitely going to be much more generated components and like these parts of the parts of software that is powered by AI that pulls in the right context, depending on what you're trying to solve for right now.

• 17:43Speaker 03

  Hey, we'll continue our interview in a moment after a word from our sponsors.

• 17:48Nathan Labenz?

  Yeah, I feel like I agree with that to an extent, at least where I'm kind of like, part of what we're doing here will have a little bit of a generative UI component to it because part of it, because we're going to have, I mean, even and even in just in this product comparison idea, there's going to be sort of the dimensions on which a product will be compared are not hardcoded, right? So even just like the table, how many, you know, what are the sort of fields of comparison is like, you know, that's sort of gener, you know, dynamic or generated UI writ small. I agree that when it comes to like power software that people spend a lot of time with, you know, your like Gmail or whatever,

• 18:29Nathan Labenz?

  like I would not want to have a Gmail experience that I log into and it like gets, you know, the UI is regenerated every day on the fly. And it's like, well, where was I know, I know where things are in today's world and I want consistency. And there's probably just no reason to recreate that all the time. People do want, I hear you on all that stuff. At the same time, though, I do have a sort of different vision that competes with this too, where I'm like, you know, if, if we're imagining a world of abundance in the future and we sort of say, okay, well, what do the people that have the most abundance today do? And would people in the future state of abundance like to try to do the same?

• 19:13Nathan Labenz?

  Or would they do something different? Like, you know, how does Elon Musk buy a washing machine today? I think the answer is he basically says to someone on his team, or maybe at his level, it doesn't even come to his attention, you know, that the washing machine is broken in the first place. But if it did, he would just say, okay, find the best one and buy it and install it. And let me know when it's done, right? There's a sort of, I don't even want to think about this. I just want to delegate the entire task and then come back when it's installed. Or maybe somewhat sort of that, like, tell me what I should do. And then maybe I'll review it and approve and we'll go from there. So I do sort of wonder if my future is mediated by UI at all in some of these scenarios?

• 19:56Nathan Labenz?

  Or if I just say to like a general AI, my washing machine broke. Like, find me a couple of good options. Tell me what the pros and cons are and I'll make a call. And then you go online and buy it.

• 20:08Speaker 00

  Yeah. I mean, can I spin on this? On the topic of like the AI would know, or in the Musk case, his colleagues, whatever, they know what he wants. And that, I mean, that transfer, I think, is the only important thing in the future somehow. Like transferring what the human wants, desires in this very moment to a different system. Yeah, and transferring the information to the user. And over time, AIs are going to like read our minds, basically. Or they're going to be extremely good at predicting what we want in a given situation. So then that, those UIs, those elements where you need to say like, oh, I don't care about the front loading, whatever, you don't need to do that because it already knows what you want.

• 20:52Speaker 00

  On the displaying information to the user, like which might be less important as well in the future. That there we're going to have the most, at least some level of standardized UI components. But yeah, I'm not saying this is not going to happen. I'm just saying there's going to be some parts that are going to be.

• 21:10Nathan Labenz?

  One question I've had, I wonder if you have a take on, as I've tried, you know, all sorts of things like this. And I've definitely made it my business to go and try a wide range of products. I've been a longtime fan of Replit. I've used Cursor pretty heavily in recent months, building an app.

• 21:29Nathan Labenz?

  It always seems like the DevOps portion, the ability to actually deploy to a machine and get things working in a way that is exposed to the Internet, always seems so hard relative to that initial code. Like so many experiences I've had, you could say, oh, give me this UI. You get something pretty decent, you know, that like looks more or less what you had in mind. And then you're like, you know, why is this, you know, I have a dependency that's missing, what's going on? Or this thing is not building or whatever. You know, I'm not sure what's going on with these port forwarding situations. All that stuff seems like very hard for the AI. Do you have a theory for why one is so much more difficult than the other?

• 22:11Speaker 00

  Yeah, totally. I mean, the software engineering gets very hard when you have like different things that have to connect them. The more components that have to kind of be wired up and connected to each other in the right way makes it exponentially more error prone. And the way to handle that in like how we, how we approach it as well is to limit those choices as much as possible and say like, okay, no, if you're going to deploy something, you can only use Superbase for the, for your backend functions and for your database. And if you're going to add payment, there's a very clear happy path for that. And it goes like this, we generate the button for you to go out to Stripe

• 22:52Speaker 00

  and get your account set up there or just grab your API key, key comeback. And then the payment is like almost guaranteed to work. If you just let an LLM, like an large language model, if you're using Cursor, that's much less opinionated, but still like amazing tool, then it's going to sometimes, it's going to generate different pieces of the software that haven't been fine tuned so that they were, are guaranteed to work really well together. And then at some point, it's going to, you're going to run into a problem and the AI is going to have a hard time recovering from that problem.

• 23:28Nathan Labenz?

  So do you think this is a technology wave that creates like consolidation across different technology stacks and potentially like core providers? Like it seems like everybody I noticed, for example, in their original generation, it was Tailwind CSS. It seems like that's become a, you know, community favorite, if not standard. And it seems like it's kind of a standard in most of the code gen experiences. And I would imagine like, you know, for payments, I don't know what you're using, but I would expect that like Stripe is probably a leading candidate that has, you know, lots of great documentation and so on.

• 24:05Speaker 00

  Yes.

• 24:06Nathan Labenz?

  Is there sort of a shelling point effect where everybody ends up using the same core components?

• 24:11Speaker 00

  I think so. I mean, there is already a shelling point among, among human developers where Tailwind is like the shelling point. It seems like now, or at least according to most people, and large language models accelerate that because like it's much easier, one is much easier to learn these new best practices. As a human, if I don't know Tailwind, it takes a long time for me as a human to learn it. The LLMs, they just instantly spit it out and it works. And secondly, the LLMs are much better at the very popular choices because they have much more training data there. So there's some convergence for sure. But I'm also excited about that. There are going to be technological innovations, like

• 24:54Speaker 00

  Tailwind might not be the end all. There might be better ways to style components. Facebook came out with something like a few months ago, I think. If this gets adoption, then all the AI tools are going to just like overnight, maybe switch over to this new shelling point.

• 25:09Nathan Labenz?

  Yeah, that's a really interesting possibility. I've been kind of interested in that idea at the level of the AI providers too. You know, are we entering into a race dynamic either between countries perhaps, or between leading companies? And what are the incentives there? Is there any way for people to sort of? Coordinate to proceed with responsible caution? Or are they going to constantly face this like, got to go faster to beat the other guy incentive? And one of the questions I've been wondering about there is like, how easy is it for everybody to switch when a new model comes online?

• 25:51Nathan Labenz?

  And one thing I did notice in lovable, which is distinct from say a cursor, is like in cursor, I just have a dropdown. I can choose what model I'm using in the background. And so now all the developers get to choose. With lovable, I don't know what background model I'm using. And so you are choosing. And I guess I wonder like, how easy is it for you to switch? And which dynamic is better or worse from the standpoint of the developers and the racing dynamics? Like if all the developers can switch, not all of them will. But it's like, it can happen, you know, super quickly. You guys would have more of a process, but you'd be switching on behalf of like all your users. So yeah, I'm interested in how you think about model choice and switching.

• 26:36Speaker 00

  Yeah, historically we have switched overnight after a new model comes out because we tried out and say, okay, this is a better model. We don't use just one LLM. We do smart routing and we use like from Gemini, OpenAI and Anthropic. And soon I imagine potentially from Deepsec.

• 26:53Nathan Labenz?

  And maybe Kimi, don't sleep on Kimi.

• 26:56Speaker 00

  Yeah, but we do have a model selector for us, like an admin feature. So we can do some selections. And what I think, but I don't think that's the right user interface for a user. Because like if you have a selection and you don't know how to have all the context, then you're more likely to make the wrong decision. What we're planning to roll out is that you can, I mean, the default to be the fastest chain of large language models. And then if that doesn't work, it goes into showing that in the UI and letting the user have some type of control and a deeper kind of analysis of the problem with larger and slower large language models.

• 27:38Speaker 00

  So I think that's the right approach and not be specific about which chain of models are running here. That's too much information for the user. Yeah, I mean, we make sure that we can switch out models super fast and then know if that's a better or worse user experience.

• 27:54Nathan Labenz?

  In the future, you expect to? Be able to incorporate new models really quickly, but it doesn't sound like the activity on lovable is going to be like a winner take all contest because you're already subdividing the queries and figuring out where they should go. And so a new model will at most take a bite out of other providers' usage. Seems very unlikely from what you're saying that there would be a new model that would just dominate everything and take all of the activity from one day to the next.

• 28:25Speaker 00

  Yeah, we'll see. Of course, I guess it's all about moving like everything is about having a team that just can just execute super, super, super fast and move the fastest here. And it might turn out that one model just dominates everyone else in terms of price and performance.

• 28:42Nathan Labenz?

  DeepSeek does seem like they have a strong contender all of a sudden. Do you have like a sort of rundown, you know, a cached thought on like how the OpenAI's Anthropics and Geminis compare to each other today? Is there like a shared understanding on the team of what's best for what?

• 29:01Speaker 00

  Yeah, yeah, sure. Yeah. And to your point there, like DeepSeek is open source and that makes it much easier to have low level control and train your own model, at least for maybe the majority of fast use cases, just train your own model and use that as default. I see that happening for us quite soon. The difference is now Claude 3.5 is still overall like the best one. It's very, it's fast, it's very good at coding, it's good at reasoning, and it works the best most of the time. And then if you look at wanting to speed and low costs, then the Haiku is actually quite expensive compared

• 29:40Speaker 00

  to 4.0 Mini. And the best one that we're switched over to for the smallest calls now is the Google's Fast Model, which is also like really performant and fast. And yeah, so for Open, but the final win for OpenAI is that their reasoning models are good when like the AI gets stuck and you want to get out of that and do take a lot of information about like kind of in an uncommon situation, reason from first principles, then OpenAI's reasoning models are still the best ones.

• 30:15Speaker 03

  Hey, we'll continue our interview in a moment after a word from our sponsors.

• 30:20Nathan Labenz?

  Yeah, I feel like that echoes what I've experienced when doing this sort of model choice manually. You know, it always varies a bit, but I would say if I want to do like a new feature on an app, and I'm working on this app that is designed to help people create even more so than curate because oftentimes it is synthetic data that is being used, just really high quality examples for use in few shot prompting or potentially even fine tuning, but some sort of AI automation context, you know, you have some task, routine task that you want to automate. First, and honestly, the most critical step most of the time is get together a small number of examples that demonstrate what you want,

• 31:04Nathan Labenz?

  and that you can sort of stand behind and say, yes, this represents a job well done. I found that not too many of the LLM ops apps really help with that. There's many things that help with like monitoring your performance and logging everything and running standard evals, but just getting to like a half a dozen or 10 really high quality examples for your particular task. I haven't seen too many things that help with that. So I decided I was going to make one kind of as an exercise.

• 31:31Speaker 00

  To me, like, why do you, what do you use those examples for? Did you compare this vibe check the output on different LMS or yeah, something else?

• 31:40Nathan Labenz?

  Yeah, that's part of it. I just find kind of the great examples are kind of the heart of any automation project, right? You first have to understand what is it that we want? Usually there's a team involved. So like, can we all look at these examples and agree that, you know, this is what we want as a team? Just getting clear on that, you know, that's more of a social challenge than a technical challenge, but it's an important challenge in practice for many automation purposes. And then, yeah, once we have those, like which model can even just on a few shot basis, you know, imitate that. Part of what the app does is it also tries to help fill in the reasoning process that converts the inputs to outputs. Obviously now, you know, reasoning chain of thought type of stuff

• 32:25Nathan Labenz?

  is like all the rage, but a few months ago, and even still, I think people kind of sleep on how important that is because often what they have in their business is The inputs and outputs, you know, whatever they want to automate responses to customer service tickets or whatever, right? They have like the message received from the customer and then maybe they have the message sent back to the customer by the agent. But what they generally fail to capture and maybe they have like documentation in policy format or something like that. But they very rarely have any sort of chain of thought that connects like, okay, this is what the user sent. And, you know, now I'm thinking about the deep seek, okay, the user is asking about this, right? And then working through all that stuff until you finally get to an output, that stuff typically does not exist.

• 33:09Nathan Labenz?

  So part of what my little app does is tries to help fill that in, you know, saying, okay, well, here's the output and it came from this input. What is the likely chain of thought? Help people iterate on that so that they can see something, you know, because people have a hard time writing this stuff down. So show them something, then they can react to it and say like, that is what I do, or that's not what I do. And they can iterate toward hopefully a chain of thought that represents the way they really think about it. And then from there, yeah, test out different models, you know, maybe graduate to fine tuning. I'm not planning to commercialize this app because I don't think it's a very monetizable thing. It's like, it's the sort of thing you don't necessarily use all the time. And it stops actually at the point where you have enough examples that you can take it somewhere else.

• 33:53Nathan Labenz?

  Like we're not gonna, I'm not gonna run fine tunings for you or, you know, be your like middleware of any sort. It's just like you get to the examples and you could export them to a prompt format or a JSONL format or, you know, whatever.

• 34:06Speaker 00

  Did you, did you build this app in with lovable?

• 34:09Nathan Labenz?

  I didn't know I was, I, I've been, it's been a slow burn. So I'm not even sure if you guys had launched, uh, maybe you can tell the timeline of launch and how you've scaled. I think, I think I started on it before you were an option.

• 34:23Speaker 00

  Yes, yeah, we, we launched the 21st of November, we launched like lovable. And, um, since then, the product has, like, that's when we also launched, like, we have built out everything with the backend functionality, which is a huge part of the unlock. And, uh, yes, since then, we've just been scaling like absolutely crazy and spent most of time keeping up with that. But I'd be happy to show you some of those, show some of those parts and get back to the product comparison tool.

• 34:55Speaker 02

  Yeah, yeah. So I I had to log into Superbase again. I hit rate limits, or not rate limits, but I had too many Superbase projects that I had created. So I had to, yeah, I had to fill that. Okay, so I pressed the Superbase button now. I connected a Superbase project to our Lovable project. And we can see that we also, we get this message that automatically is sent to the Lovable AI when we do that.

• 35:19Speaker 00

  What where are we at now? We have the UI and we're supposed to try comparing two products. And we need to fetch the data from those, from the websites of the products we're comparing somehow. So I think then the the right thing is just to ask the AI, like, how do I connect the script data from an external URL?

• 35:38Speaker 02

  Create data from an external URL.

• 35:42Speaker 00

  And you don't have chat mode enabled here, but that's.

• 35:45Speaker 02

  But we could, we could enable that.

• 35:46Speaker 00

  Yeah, you can usually, you can, you can decide.

• 35:48Speaker 02

  Yeah, so we have this chat mode feature which allows you to chat with the AI. Opposed to, um, just tell, like, if you only want to chat with AI and you don't want the AI to code. You kind of want to pan out things before actually writing any code. Then you can enable this feature right here in Labs where we try out new features. If you go back into the project. You will see that we have this little toggle right here. So now we can go on chat only mode. And now we can ask this question and now the AI will actually give us some guidance. So how do I scrape data from an external URL? So then we just send that.

• 36:25Nathan Labenz?

  Yeah, a couple interesting things here while it's thinking. One of the questions I had written down, I hadn't realized this feature was there, was. What do you think about like getting the AI to sort of coax more of what you want out of you? You know, when I first kind of prompted and when you first prompted, it was like, here's what I want. And then it just kind of immediately hauls off and is like, all right, we're coding, you know, here we go. And I feel like if you were to, again, sort of compare and contrast this against like, what would the experience be? If I were Elon Musk today, right, it would be sort of a person answering back to me and be like, "Hey, okay, so yeah, Elon, I got a couple of questions for you about what exactly you want before I go start coding this."

• 37:07Nathan Labenz?

  This seems like a step in that direction, but I'm interested in your thoughts on the sort of potential for a Socratic interaction with.

• 37:14Speaker 00

  Yeah, there is a lot of things you learn by using a system like this. And we are like, when you become a super user of our tool or other AI tools, you get like 10x the value. So getting there the fastest is something that's a big part of building a product like this. And we haven't gotten that far. What you're seeing here is that it suggests click on this button to go to the super base API key

• 37:39Speaker 00

  or the edge function logs, for example. It gives you those information contextually. But the next steps are to interject some of these conversations like, "Okay, before we do that, let's go through a few of the things to clarify." And then it says, "I'm ready to build it now." "Does this look good? Does this panel look good?" Then we go back to execute. It's not like the most critical thing for the product. Like if you're really good at using it, if you use it a lot, then you can still get all the value without that, I would say. And now, this is an AI full stack engineer. But in the future, you're going to be talking more to like a CPT or Chief Product Technology Officer. That's how I see it, or also like Chief Design, Head of Design.

• 38:22Speaker 00

  And then it should be doing even more of those things, right? Like what technology choices, like suggesting things with the product. And I'm super excited about seeing how all of this evolves for us and for others building in the space. What you're seeing now in what Isaac is doing on the prompting side is that it said, "Okay, let's use Firecrawl." Firecrawl is that super popular way of fetching data from the internet. And then it says, "I'm going to need your Firecrawl API key. Go to this URL." And then it opens an input box where you just paste your API key. So. You have to like, we don't manage your fire crawl billing. It fire crawl is free in the beginning, but then it costs money later on.

• 39:05Speaker 00

  But you're fully in control as a builder with Lovable that way. And then now it is do trying to do a scrape request. And like when you're building yourself or when you're building with air for that sake. You often run into errors. So that's what we're seeing here. There's some kind of errors and you can click try like. We're seeing some of the error part of the logs here. Now we've we've got an access from Superbase so that we can get the error logs from the backend. So that's going to be launched. That's going to be a game changer to build this. Build with backend endpoints, which is what we're doing here. But right now, Isaac has to manually open the edge function logs in Superbase and paste the errors from there.

• 39:48Speaker 00

  And so there's a bit of a complexity here.

• 39:51Nathan Labenz?

  So is this a new feature that there? Because it's something I'm also very much on the lookout for is people building for AI users as opposed to building for human users? And if I'm understanding you correctly, this is maybe an instance of this from Superbase where they in the past were kind of like. Well, of course, it's going to be a human developer, so they'll just come to our site and look at the logs and understand the logs and whatever. And now you need more programmatic access because you're actually trying to directly feed that into a language model.

• 40:23Speaker 00

  Yeah, I think we've been driving most of Superbase's new signups. At least in the past, I think that might still be the case. And they are like, oh, wait, we have to start building for exactly what you're saying for programmatic access to everything. And I know that others who are building similar products to Superbase are also like, we're going to be agent first. In terms of building for a world where software and all of these things are managed by agents, not by humans.

• 40:48Nathan Labenz?

  I definitely have this experience too, where I find myself being like a glorified copy and paster, you know, is sort of a lot of what I'm doing between things. That's also been the case even in just. We kind of got sidetracked from this earlier, but we were talking about like different models and what happens when there's an error and OpenAI can. You know, with the O1 series can kind of help reason through things. I found myself quite often using like ChatGPT Pro to.

• 41:16Nathan Labenz?

  You know, make my plan or like diagnose, how should I think about this feature at a high level?

• 41:21Speaker 00

  Yep.

• 41:21Nathan Labenz?

  Have it give me instructions and then I'm like pasting instructions one by one into another UI, AI UI and having it, you know, like implement the plan step by step. So it is funny how much of the actual watch over the human shoulder, they're spending just like pasting, you know, stuff back and forth between systems and that definitely seems like the sort of thing that's going to get smoothed out.

• 41:45Speaker 00

  Like that, that's a big part of the, what you're seeing with Lovable is, is collecting, like the hardest part or the most important part in the beginning of building a large language model app is context management and knowing like, do we need information from this source for this, from this other source, from our knowledge database and from like the history of what the user has done. And if you're very good at not managing that context, it becomes much easier for the workhorse of the coding, in our case, like Claude, to take the right decisions. And yeah, that I think that's, we, we have spent a lot of time on that. And that's why, a reason why it's just more reliable than other tools that at least according to the people that I know who have, who run comparisons among, among all of them.

• 42:28Nathan Labenz?

  I did enjoy how you had the, and this maybe also kind of gets to who you're targeting in terms of users and what you're seeing in terms of, you know, the kind of background of people that are using the tool and what level of knowledge they have coming in. But I did appreciate how along the way, there are these sort of prompts to say like, I'm not going to tell you go somewhere else and find the place to do this. Instead, like you give me the API key here, I'll put it where it needs to go. Uh, I thought that was like quite nice and definitely a notable step toward, you know, anybody being able to do this sort of thing.

• 43:05Speaker 00

  Yeah. But Isaac, do you want to go to the edge function logs and see like what was exactly? Uh, so. So here it says, I already clicked that one. The, and this is what, this is what's not yet in production at least fed into the AI system, but that should of course be fed into the AI system. And what does it say exactly? So I think we can just copy paste all of this into the. Yeah, let's just do that. And then go back to the, to that. So this is what you're saying, like now we're doing the copy pasting, this is going to be completely automated and then we wouldn't have gotten stuck at this point at all. Sure. Yeah, let's send that.

• 43:42Speaker 00

  Hopefully this should. So when you're connecting to external APIs, it's as you said, Nathan, it's often more things that can go wrong. And that's where you need to have a system that's good at debugging itself between the different components that are interacting. And now we're interacting with the browser is interacting with Superbase that in turn is interacting with the fire crawl, which is kind of fetching the data for us.

• 44:08Nathan Labenz?

  One other question I had going back several rounds in the exchange with the AI was, I forget exactly what you typed, but it was like, what's the best way to scrape product information?

• 44:20Speaker 00

  Yep.

• 44:21Nathan Labenz?

  And yeah, so what's the best, how do I scrape data from an external URL? So I found it in my general use of AI that, and I think this is starting to change a little bit with the reasoning models, but certainly pre reasoning models. I've developed a practice of trying to be super neutral with my language. Because especially in an area where I don't know super well what the right answer is. I'll often find that unintentionally I can bias the AI in a particular direction. So for example, there scrape, right? Seems like it with almost all the models up and at least until like the sort of O one series.

• 45:06Nathan Labenz?

  My use of the word scrape would naturally send the AI down a path of like, okay, we're scraping. And then in a lot of tools I've seen, actually, I really like the idea of trying to default to like the best in class tool like a fire crawl. So that you're not kind of recreating scrapers from scratch. But I've had many experiences where. It'll be like, okay, we're gonna write a Python scraper and you know, then it'll like make a sort of bare bones like we're, you know, we'll use the requests library to like go get the HTML and then we'll like use beautiful soup and you know, whatever. And next thing you know, you're sort of lost in scraping hell.

• 45:47Speaker 00

  Yeah.

• 45:48Nathan Labenz?

  And it's like, man, there's way better things out there to do this. So I like the idea, first of all, that you're sort of, seems to be kind of curating in the background, like these are the production grade tools that we trust that you can tap into immediately. So you're not kind of recreating stuff from scratch. I also wonder if you're like in more general, do you have like a list of sort of, these are the tools that are like on that sort of fire crawl level that we know and trust and we're gonna kind of try to route common needs to those best in class tools?

• 46:22Speaker 00

  Yeah. So we have like a list, we have, if you go to lovable dot dev slash integrations, there is like the, the ones that we default to and we're adding, I think maybe not everyone is here, but we have for emails, we have resend for payments, Stripe. For AI, it defaults to OpenAI or Anthropic if you ask for that. If you want to, I can have that generate images that's run where, and I'm not sure we launched it yet, but we have using a replicate for various like AI, a lot of other plateau.

• 46:54Nathan Labenz?

  Models galore, for sure.

• 46:56Speaker 00

  Yeah. Yeah. And I think there are many people that request us to add there. There's like people that reach out from large tech companies that want us to use them as a default provider for both for the backend parts and for some like for payments, for example.

• 47:15Nathan Labenz?

  That's cool. I think that is really smart. Going back to just kind of the language and sort of the user potentially.

• 47:23Nathan Labenz?

  Mistakenly like leading the AI astray. I've started to see with the reasoning models occasionally, they will come back to me and say, I understand what you're trying to do and why you're trying to do it this way, but I actually recommend a different approach. Like in this case, it, you know, it might say instead of scraping, you should, you know, use a commercial API that can get product information for you or whatever. Do you have any sort of strategy for kind of questioning the assumptions of the user to make sure they're not like going down sort of the wrong path?

• 47:55Speaker 00

  That's, that's, yeah, we should have that. Like now we rely on people really knowing their shit and like, or being, being fast learners and figuring out errors. Like in this case, I will definitely be like, okay, now maybe we had the problem and I will restart from scratch. I would just like, okay, let's restart from scratch. And because then you can instantly quickly learn like, how do you make this work reliably? And in the future, you mean, we want to of course be much more Socratic and be like, okay, this is the situation. We, I think you're asking for this, but it doesn't really make sense. Potentially you're like, what do you mean exactly? And that's going to be a big level up for most users. I'm surprised that this didn't work absolutely instantly.

• 48:41Speaker 00

  So what we're seeing is we're getting an error, we're getting a bad request. And now I, I mean, most non-developers have a hard time understanding this, but it is possible that that's human going in and saying, okay, um, there's something about the connection here, here, here not working. And it says like, oh, review the API documentation. I don't think we need to do that. It says unrecognized keys. Maybe something changed in their, in their API, but we're getting 400 errors. If I ask try to fix, it will pass the, pass in use this logs. It will not use our super base logs. Right. You need at least two products to compare. Okay, sure. Let's do it.

• 49:24Speaker 00

  It'll scrape enough products for comparison. That's, that's clear at least. And while, while it's running, I'll check the super base logs to see if there's any more details there.

• 49:37Speaker 00

  And yeah, what you can of course do if you're a developer is like you spin up a nice UI. There's a lot of best practices that are like spun up for you Stripe and so on. And then at some point, maybe you want to do edit the.

• 49:50Speaker 02

  Seems like it was successful.

• 49:52Speaker 00

  Unknown product, unknown product. I think the problem here is that I'm not scraping washing machines. Do you have any washing machines?

• 49:56Speaker 02

  Yeah, I do it on another tab, but it's going to.

• 50:01Speaker 00

  Let's take two of the same washing machines. Here we go.

• 50:12Speaker 00

  So I had to click, try to fix that. I'm so happy I could help you out.

• 50:15Speaker 02

  You were trying to do it. Why didn't? Okay, that's serious.

• 50:18Speaker 00

  Amazing. So then what you what you say is just like it just says unknown product. Make sure to show.

• 50:27Speaker 02

  It it seems like we're making progress now, so I think it successfully script the links now. And I I think like one thing that I did is I included the documentation on Firecrawl. And that's one thing like these L L M's are are not up to date. If if, for example, Firecrawl updated their docs, their API, the lovable might use the old documentation and then you might have to include that within the the context. Now, in our native integrations, we actually stay on top of all of that stuff. So that will essentially always work. Um, but in the case where we want to pick an arbitrary API and use it, then then it will not necessarily work if the API has been updated. Now, like I I guess the lovable AI doesn't actually know what to display right here. And I think we will have to use.

• 51:11Speaker 00

  Yeah, no, that's true. That's true. We should have to process that. Processing it through the through and through an AI model. But I mean, this is very standard. Like, okay, so you get something, you'd be like, okay, something, the API works. Now we have to update the UI to handle the API response. And that's what we're doing, what it's doing now and writing a local. Let's see.

• 51:30Speaker 02

  Yeah, there we go.

• 51:31Speaker 00

  There we are. Yeah, we will. Yeah, so we're seeing that. We're seeing them. But let's now an AI analysis of them. And Nathan, do you have any preferences on what you would so what you would want to compare? Given where the UI is at right now?

• 51:46Nathan Labenz?

  Yeah, I think maybe I want like a two part analysis that at first is like, what are the most relevant factors to like, you know, consumer satisfaction with this product type? And then.

• 52:01Nathan Labenz?

  Present those in sort of a head to head way. You know, and they could be like key features. It could be, you know, common problems like. But you know, that front loader, top loader thing is a good example where I was just never really thought about that before. And then when you start reading the wire cutter on washing machines, you know, it's like, okay, well, the first thing you're going to need to decide is do you want, you know, front loader or a top loader? And by the way, if you have a top loader, then you definitely can't stack them on each other. So, you know, do you have space for two side by side or do they need to stack? It's sort of this like, what should I even be thinking about? As the relevant dimensions? And then show me what they actually are.

• 52:44Speaker 00

  So let's ask that. I'm saying let's send all these products to the AI and it should be in a short format. Give you three important features to consider. And as a recap now, what we have is you can enter products, you can get data. And now we're going to send the product data to an AI model to say, what should we consider? And then as a step after that, probably list the differences among those dimensions as a table or something like that.

• 53:14Speaker 02

  Yeah, but that's really interesting that like some of the dimensions of certain products, we don't even know, right? Like you didn't even know that that was a relevant thing to look for in dishwashers. So yeah, I think that would be a really cool thing that dimensions will actually be suggested by the AI to us. And to create that table, we'll want to get a structured response from one of these AVMs, right? And that's totally possible using function calling. And Lovable knows how to use that. So I think that's probably the next step that we have this response.

• 53:45Speaker 00

  And I just want to clarify, like for an application like this, it's, I would say for a pretty technical person, you can very reliably build this entire application and then for a technical person. If for people who are less technical, for a simple application like this one, with some patience, you can, you will be able to succeed in building it, but you will run into problems with at least 50% probability, you'll be frustrated if you're not technical. And with maybe 10% probability, it will take a shit ton of time. Like you will really like get feel like you're getting stuck and that's, but and it's a bit random, like for in some cases you're lucky, in some cases you're less lucky.

• 54:30Speaker 00

  So just like this, this type of application is something you can definitely build with the current version of Lovable. And this is as bad as it's ever going to be.

• 54:42Nathan Labenz?

  Yeah, it's funny. This has just been, how long were you building before you launched two months ago? I think we're talking on exactly the two month anniversary of your launch.

• 54:49Speaker 00

  So the company has been, we started the company a bit more than a year ago. And then we went through a few different iterations. We went down like their agent hole or agent route, which has some advantages, but we came to some realization on the UX why agents is usually a very bad UX and made it much more focused on speed and like the fastest possible way of to get the result back to the user.

• 55:14Nathan Labenz?

  I mean, I think people have very different ideas of what an agent is, or you know, they mean very different things when they talk about agents.

• 55:21Speaker 00

  Yeah.

• 55:22Nathan Labenz?

  And the way I think about agents as opposed to say intelligent workflows is that an agent in my mind is something that has at least a certain amount of delegated decision-making authority. Whereas, you know, if I make something in a Zapier type framework where it's like one step follows the other, maybe some of those steps are AIs, but like the prompt is prescribed, everything is kind of happening sequentially, one step after another. I would say that's like low, that might be intelligent, but it would be low agency if like every, you know, step is sort of fully planned out. Whereas here,

• 56:02Nathan Labenz?

  I think this is actually like higher agency for the AI than most product experiences. Cause here there is like a decent amount of the AI sort of interpreting what you're saying and, you know, making sort of dynamic decisions about exactly how it's going to go about it. So how do you understand agency and what do you mean?

• 56:23Speaker 00

  I mean, the agency, I think, is a bit of a different, is like goal oriented. But but agent in L L M setting is like the agent does one action and then it looks at the result. And then it does another action, then it looks at the result and very open with a very open ended loop. I think in most cases, if you want to do what you're asking for, like a reasoning steps and so on, you can do that without that kind of open and that very open ended loop. You can design the chain of L L M calls in an intelligent way. But the problem is with if you do it in an agentic way, which has the benefit of being more general, is that it's very unpredictable how long time it's going to take.

• 57:03Speaker 00

  And that the unpredictability from a user standpoint, especially if the system is not hundred percent reliable, if it's unpredictable and not hundred percent reliable, is a very shitty experience. So you want to get as far away as possible from that. And then, once you're at the like the far as as fast and as reliable, then you can start making it take more than one, just one step over L L M calls. But I'll just look back to the product now. So we can see the two products now and them compared, like what we should look at load capacity, steam cleansing technology. Okay, I don't know if that's a top grade priority, but that's apparently what the A I says is the priority. So you could do some better prompting at making sure it looks at what's most important and energy efficiency. That makes sense.

• 57:47Speaker 00

  Let's take to other products, like what would you consider buying, Nathan, apart from a dishwasher? Let's do headphones. Let's do headphones. So we do Bose and J B L here. And now we're still just going to see the like what's good to consider for for headphones in this case. But the next step would be for it to list like why you should use X over Y. And I guess we could just write the pros and coms list for both of them for now. We should consider sound quality, battery life, comfort and fit. So for next prompt, I imagine we could write something like let's just prompt the A I system to also list the.

• 58:31Speaker 00

  How the two different, all the products compare along these dimensions as a nested bullet list or something like that. Does that make sense?

• 58:40Speaker 02

  Yeah, yeah, I think so. Ask like another step then.

• 58:42Speaker 00

  Yeah, I would do the same step for just for.

• 58:44Speaker 02

  Same step, okay. And then instead, uh, dimensions, compare how the two products compare with each other.

• 58:58Speaker 00

  It's not limited to two products.

• 59:00Speaker 02

  Oh, yeah.

• 59:03Speaker 02

  Of the products with each other based on the features listed.

• 59:08Speaker 00

  Yeah.

• 59:09Speaker 02

  Make this happen in the same AI call.

• 59:14Speaker 00

  Yeah.

• 59:16Speaker 02

  Okay, let's send that.

• 59:17Speaker 00

  Maybe this is going to be a killer application when we're done. I guess.

• 59:21Nathan Labenz?

  Next, not too far downstream from this would be then starting to pull in like customer review highlights potentially as well. I'm just kind of, you know, my vision for the product is evolving. I'm kind of imagining like

• 59:35Nathan Labenz?

  a sort of advi- the first step is like the advisor layer. That's kind of, you know, I'm coaching you on what you should be thinking about. Second step is like, now here's an objective tale of the tape. And to some extent, that's kind of informed by like, the product pages typically have these sort of like spec, you know, things, but of course, they're all formatted differently and it's hard to, you know, even just in simple things like the size of the washing machine. Wait, how wide was that other one? And, you know, is this one wider and whatever? And then a third section that I could imagine would be just like, what would past customers have to say about this? And is there anything that they're bringing to the fore that the product pages themselves didn't mention?

• 1:00:19Nathan Labenz?

  You know, when we may or not get there, you know, in this session, but with all three of those things, I think you would have a pretty useful little tool.

• 1:00:25Speaker 00

  A hundred percent. I, I think what I'm also excited about here would be, the first step is just, I'm just looking for dishwasher and then it pre fills some of the, like the products to analyze.

• 1:00:38Speaker 02

  Um. Yeah, yeah, that's cool too.

• 1:00:41Speaker 00

  And we got an error now, I don't know what was that?

• 1:00:44Nathan Labenz?

  Yeah, it was.

• 1:00:46Speaker 00

  Maybe we're out of quota for our APIs. So I mean, if you're impatient, you just click to fix. But I don't know why we would have a new error here. So I would read the logs in this case and be like, if you show logs up there, we can try to understand. Like, why did it suddenly have an error? So it had bad gateway and that's fire crawl site. So if there starts with 500, it's not our fault. It's actually a fire crawl. So now it's trying to fix it on our side. We can't do that. But we can try again.

• 1:01:16Nathan Labenz?

  Hopefully it'll prove transient, yeah. Going back to the agency thing, while we're debugging this, if I understand your understanding of agency correctly, what would make this more agentic, but you think is not a great experience is if, for example, encountering this error, then it just took the next step on its own to try to resolve the error.

• 1:01:39Speaker 00

  Yep. That is a very reasonable thing to do, right? But yeah, there's a few reasons we don't do that. We don't unleash it like that for now.

• 1:01:48Nathan Labenz?

  Yeah, so tell me what they are. Because I feel like, having tried a bunch of these different experiences, another one that's obviously gone through cycles of hype and counter hype and whatever over the course of the year is Devon. And in preparing for this, I did an experiment with a similar, you know, little project, right? I loaded up multiple of these sort of coding agents or assistants or whatever, creating products. And with Devon, I did have a weird experience where, because it just keeps working, right? In the background.

• 1:02:19Speaker 00

  Yep.

• 1:02:20Nathan Labenz?

  I was rotating between them. I would like, look at the state of one of the products, give a next direction, like we're doing here. But then I would just tab over to the next one. And when I would get to the Devon tab, I did realize, I have no idea what's going on. This thing has been working continuously in the background. And in some ways, that's like very appealing. But in other ways, when I get there, it might be on like, iteration 87. And I have no idea what the current state is. So it's like very hard in that moment to be like, what are you even working on? Like, what's working and what's not working right now? Where are we? And I did, I did find that to be weird. So it kind of led me to a sense.

• 1:03:01Nathan Labenz?

  But then here, I also do think, as you said, that, you know, certainly be reasonable in some cases to like. Take that next step, or, you know, another thing that we're looking at here a lot is like just literally pasting in the URLs and running it again. And so to some degree, I also think like, especially with, you know, something like Claude computer use, starting to be a thing. Part of me is like, could I sort of have like limited agency? Like, I don't necessarily want this thing to run forever and run up a bill or, you know, drift off into some state that I have no idea where it's at. But I kind of would like it if it sort of took my one prompt, tried to do it, tried to use the product, you know, and head Claude, computer use like face, face, go.

• 1:03:45Speaker 00

  That is coming up, the computer use part. There, I mean, my, my point, this thing, many of these things you can, I, I think you saw Isaac just used the selector to use chat mode. And there is a pre, this is not public available, but there is an agent mode there in the, in a selector, which is only available if you're, you have like an admin account like Isaac has. So these things are things that people like us experiment with. The, the most important thing is that you have a product that is predictably works and like works in an intuitive way. And making an agent work intuitively and like in a nice way, it takes a lot of

• 1:04:26Speaker 00

  iteration, a lot of iteration. And we haven't, we haven't made it work in a kind of reliable, nice way. But I think we're going to be there very soon. It's something, it's not, yeah, it's one of the things in the coming few weeks that's going to be on the top of the roadmap.

• 1:04:40Nathan Labenz?

  Yeah.

• 1:04:41Speaker 00

  And what you saw here, so the product works now. If you look, we have the two headphones compared, and it says the key feature to consider is sound quality, noise cancellation, battery life. And then it runs a comparison. And here, like, we should continue to iterate to make sure that the AI always spits out a comparison in an easily digestible format. Here I think it says like, oh, this one is offering superior sound quality in a long paragraph. And what did you do, Isaac? Is you asked AI, what should we do next? And then it says like, oh yeah, do visual comparison improvements? We could just pick one of these, paste it in and ask AI to do it. And then it's, you know, what would you say, like, we're the CEO? And then there's, we just ask the AIPM, product manager,

• 1:05:25Speaker 00

  and then we decide what the software engineer should do out of those, these suggestions.

• 1:05:30Speaker 02

  Yeah.

• 1:05:30Speaker 00

  I think some of these are pretty good, like, reviews.

• 1:05:33Speaker 02

  I, I think it would look really good if we had like a table, like you guys talked about. And I, I think I'm gonna notch the Lovable AI now to use function calling from OpenAI just to make sure that we get that format of the response for the table. Because, yeah, in this case, we, we don't just want like a long chat response. We want a format of the response so we can render it in this beautiful, digestible way. So, yeah.

• 1:05:57Speaker 00

  But, but yeah, I, I think that was again a, a good rundown. Now, now we built this simple AI app and it ended up giving us a product that can provide value. If, if we had done this with everything logged in and set up from scratch, I would expect this to take five minutes. And we're happy to see people do speedruns of something like this.

• 1:06:20Speaker 00

  But, yeah, as you can see, there is a lot of iteration. Now, plain English is the hottest programming language. It actually works in this case. But it still takes an engineer, a human supervisor that uses the QA at, at this point. So that's the state of things right now.

• 1:06:40Speaker 02

  Oh, here we go.

• 1:06:42Speaker 00

  Oh, wow, this is actually really good. One more prompt and you just nail it, yeah.

• 1:06:45Speaker 02

  Yeah. This is nice.

• 1:06:47Speaker 00

  Nice. And unfortunately, the AI is extremely politically correct. It just says everything. I can't decide, yeah.

• 1:06:55Speaker 02

  Well, we should do this with both the Lovable, see what it does. Is it gonna? Should I try? Try it, see what it, see what it says.

• 1:07:03Speaker 00

  Go for it.

• 1:07:04Speaker 02

  Okay.

• 1:07:06Speaker 02

  Bolt and Lovable, let's see if it's going to betray us.

• 1:07:12Nathan Labenz?

  This is also like a self-awareness.

• 1:07:16Speaker 00

  Oh, yeah.

• 1:07:16Nathan Labenz?

  Situational awareness test.

• 1:07:19Speaker 00

  Yeah. So this is not our AI answering. This is the. This is the.

• 1:07:25Nathan Labenz?

  It probably knows, right? In like a system prompt or something. It should have some clue as to who it is.

• 1:07:30Speaker 00

  Yeah. Okay, let's see. We got the images.

• 1:07:34Speaker 00

  Let's see. User interface deployment options and ease of use. No. Bolt one, two, or three. What? But that is not true. Actually, we do built in deployment options. So I would say this is this was great. And the interfaces are also the same. But that's what you get with AI.

• 1:07:52Nathan Labenz?

  I can definitely bet you the fact that the interfaces are quite similar.

• 1:07:56Speaker 00

  Yeah.

• 1:07:58Nathan Labenz?

  Okay, yeah, that's that is really. That's cool. I mean, first of all, we're an hour into trying this. How many iterations have we been through? Seventeen, it looks like, edit seventeen. One thing you mentioned earlier that kind of caught my ear, because I've also experienced this a lot. I'm trying to build up my own like coding with AI best practices is like, commit at every working state and definitely be prepared and be willing to roll back to a previous good known state. Find that, and I don't think we ever reverted in this experience. Maybe we can just kind of scroll through and look at what were the seventeen steps that we took. And this is not like a lovable comment.

• 1:08:44Nathan Labenz?

  This is more of a like me doing it with cursor finding. But once I get off the track, I have often found it really hard to get back on track. It seems that the the models are generally much better at sort of doing the thing, getting it to doing it right the first time versus like iteratively debugging. You know, it's I find a lot of times they kind of end up making a mess. They try things over and over again. They get kind of confused. They don't break frame well. So, yeah, any thoughts about kind of when to revert? How to know when to revert? One thing I have found somewhat successful is when I do revert, I'll sometimes take the error message that it was struggling to fix.

• 1:09:25Nathan Labenz?

  I'll grab that error message, go back to the last known state, edit my prompt and say, "By the way, last time we got here and you couldn't fix it, so make sure you avoid that this time." And that often does seem to help. But anyway, just kind of wonder what else you have experienced in terms of like, and it's way different, right? Because I think people have in general, when they have done the code, they have a lot of attachment to that code because it represents a lot of like their work. Whereas, you know, it should be much easier to just throw away whatever a language model has given you over like four rounds of prompts. But yeah, what else have you learned about kind of when to, you know, execute like a tactical retreat?

• 1:10:06Speaker 02

  I think I have some good takes here. So I kind of see it as a search tree, right? Like you kind of have this tree, you start off, you know, in the middle of it, and then you can go in different directions. And when you're trying to implement a particular feature, there are various ways of doing that. And sometimes certain features require certain subsets. So usually when a non-technical user gets stuck implementing a feature, it's because he has not correctly taken all of the steps in the right order. And that's why we recommend consulting with the chat-only, the chat-only mode. But I think if you have taken the steps in the incorrect order, then it is a very good idea to revert back. Because then you could just kind of, as you mentioned, you can include the error that you got when you

• 1:10:48Speaker 02

  actually got stuck. You have that score tissue, kind of that intuition of where things went wrong, and you can not just let AI to go in a different direction. And then even if you don't do any notching, there's still a probability that the AI will go in a different direction, just on its own, because of randomness, and then it's, then it might work. So I think it's hard to say exactly in which scenarios where you should revert. But if it seems like you went down a spiral, and it's hard to get up again, then it's a very visual way of saying it. But for instance, I think it could have been a good idea to revert. In our case, when we were starting with Firecrawler, and then maybe include some of the documentation instead. Yeah, Anton is now redoing it now with the...

• 1:11:33Speaker 00

  I figured I'll just see if I can do this in four prompts. Can I get your API key for Firecrawler?

• 1:11:38Speaker 02

  Yeah, absolutely.

• 1:11:39Nathan Labenz?

  So do you want to, you want to show your screen as you're doing this? You're on a different computer? Yeah, that's, that's maybe you can speak to her. Yeah, I think this is really interesting, too. I mean, this is sort of, humans end up in this spot where it's like, we've been coding this thing for years. We've got all sorts of technical debt. We've got like all sorts of, you know, kind of shortcuts or weird strategies that we use that we kind of wish we would clean up. And this is basically the AI equivalent of that, right? Like, we've been seventeen rounds. We're not exactly sure what weird little micro decisions might have been made. And now you're basically saying, okay, now I kind of know what I want.

• 1:12:21Nathan Labenz?

  Let me go back, take it from the top and see if I can do like a really clean version. Is it, that's basically the thought process you're going through? Yes.

• 1:12:28Speaker 00

  I mean, I, I think Isaac had like the burst unlock I've ever seen. So I figured, well, what's the more likely outcome in this case? I mean, sometimes you are unlucky, but this is what I did. I said, okay, let's add the two URLs and then let's add fire crawl script and with fire crawl. And now I'm going to ask it to send it to OpenAI and to answer two things. One, what features should be considered when making a purchase decision? Two, how do the two products compare?

• 1:13:06Nathan Labenz?

  So this will just be the second edit?

• 1:13:10Speaker 00

  That would be the, yeah, so how did this work, actually? I think we had these two baked into one edit. That's true.

• 1:13:19Speaker 02

  Have we connected Superbase on this project?

• 1:13:23Speaker 00

  No, Superbase is not connected in this, in this project, but that's why I wanted to do it like absolutely fastest possible way.

• 1:13:29Speaker 02

  Yeah.

• 1:13:30Speaker 00

  So if I would have connected to Superbase first, it would have put the scraping on the, on the base.

• 1:13:36Speaker 02

  But it's all right, because we don't hard core the keys now. Instead, we have this input field where the user would put in their own keys.

• 1:13:42Speaker 00

  Yeah, so we're skipping, we're skipping a step there.

• 1:13:44Speaker 02

  Yeah, so that's OpenAI key, that's the fire crawl key.

• 1:13:49Speaker 00

  So here.

• 1:13:51Speaker 02

  And that's very nice. So like Lovable seems to almost never hard code his. So even though right now we haven't implemented Superbase, it still understands that we probably don't want to hard code the API keys within the front end, right? So instead it just lets us add these input fields.

• 1:14:11Speaker 02

  And this will probably also be way less error prone, because now we don't have a complex system, right? Before we had this.

• 1:14:19Speaker 00

  Yeah, I don't know. I wish I connected Superbase. I was too, I was too quick to ask for fire call. But at least now we're going to show that this works in just a few prompts, I hope. So what it does is that it lets me enter the OpenAI API key here. I'm gonna make sure I don't leak the API key, hopefully.

• 1:14:40Speaker 02

  It's alright, I can just remove it that way.

• 1:14:42Speaker 00

  Okay, let's go. And if you're a bit technical, you can always look at the network logs here and see if we're getting a response from them. Okay, so here we have the websites. It's going to compare Lovable in this case. So then when I fetch from, I hope it's fine. Here we go.

• 1:15:04Speaker 02

  Oh, nice.

• 1:15:05Speaker 00

  So now we did it actually in three edits. So that's what I would expect, to be honest. And we compared, let's compare something really helpful.

• 1:15:19Speaker 00

  I'm also notoriously hard to scrape, so I hope that works. But this was a three prompt version of it. And back to your question was like, how much we can expect this to work? I think if you're good at using revert and so on, as you were touching on, then for any product that is, or any internal tool is one of our core use cases as well, where it's like one main feature, like we're creating one main feature here, then it should take a dozen edits or so. If you're adding many features, it takes hundreds of edits. But, and then it also starts becoming much harder, because you're noticing that like the AI doesn't handle large code bases as well.

• 1:16:01Speaker 00

  We, yeah, there's a lot of smart things we're doing to handle large code bases, but it doesn't handle large code bases as well.

• 1:16:08Nathan Labenz?

  Yeah, that's, I mean, I'd be interested to hear more about that to the degree that you want to share it. I mean, what I have been doing on my own is just taking literally my whole code base. Like my little app that I've mentioned a couple of times is roughly a hundred thousand tokens. And with AI's help, of course, I had it, you know, just write a little script to put that all into a single file, kind of like your L O Ms T X T, except it's not docs, it's literally just the source. And then, you know, paste that into chat G P T and ask a one pro like, figure out a plan, you know, here's all my code, like figure out a plan for whatever. Now, obviously, that's going to run into limits.

• 1:16:50Nathan Labenz?

  So I've started to try to first like modify my script that creates the single file. And, you know, we don't really need like the CSS classes, you know, or we can like skip these various things. So it sort of adds a bunch of regular expressions to the script that prints the single file. And that'll save me like 20% of the token. So then it's okay, cool. Now I can, you know, do a couple more features till I hit the limit. But I'm like, obviously, you know, big code bases are like way bigger than a hundred thousand tokens. So what have you learned about managing context? Are you doing like dependency tree type of stuff? Yeah, curious as to what you've found to be successful.

• 1:17:28Speaker 00

  I mean, there's some things that really give you a bang, a lot of bang to the back for the back. And how we do rag, like we do agentic rag is the, is one of the key kind of differentiators for why our product is very good. But even, even as the code base grows, so I can't go into detail, but being just being smart about agentic rag get you very far.

• 1:17:52Nathan Labenz?

  Okay, well, that'll be a little, I'll have to go on a little side quest to figure out exactly what.

• 1:17:57Speaker 00

  I mean, you can try to reverse engineer it as well. I'm looking to be more open about this. This is a big part of it, like what were it's strong. And we're building out many more areas. But yes, let's, we got this error from where like in the last session here, just seeing how does the product work that we built? Where the error was the open A I couldn't handle Amazon websites. There's too much text on the Amazon website, so.

• 1:18:24Speaker 00

  The AI set the max number of characters to four thousand.

• 1:18:27Nathan Labenz?

  I think my guess is that this is going to not have the information. That's kind of what I ran into when I was messing around with this myself a little bit. If you just like truncate, you get a lot of just like header script kind of cruffed garbage. So I was, I was thinking, you know, how, but that does get tough. That's where I was kind of like, man, hopefully fire crawl can like maybe solve some of that nonsense for me.

• 1:18:53Speaker 00

  Yeah, but I think it did solve that. Yeah, I think it did solve that quite well. Do we get a response here? Oh, is it doing it crawling here? No, I hope, I hope not. So it does, it does like it, it picks up the title. It picks up the text like in a nicer format. And now I don't know if we're like, how, I don't know how we're using this different data. Normally like if to use our product model to its full potential, you often want to paste in like the, the payloads from the, the API request because they are not fed currently, I think. By default, that is not fed into the LLM. As you see, there's a lot of data here, but then it would be better at picking this, this one up.

• 1:19:37Speaker 00

  I think we're doing something in the background. Why is that? I do like a little bit of history here.

• 1:19:45Speaker 02

  Oh, we got a response.

• 1:19:45Speaker 00

  Okay, we got a response. So we have a lot of, yeah.

• 1:19:50Speaker 02

  And I think it's the analyzing. So we're waiting for the LLM to.

• 1:19:53Speaker 00

  So it's not the fast application that has been built here by the AI, but it's giving us.

• 1:19:58Speaker 02

  Okay, it says it's completed.

• 1:19:59Speaker 00

  Oh, no, I refreshed or I think I pressed back.

• 1:20:02Speaker 02

  Oh, no.

• 1:20:03Speaker 00

  I'm sort of.

• 1:20:06Nathan Labenz?

  Okay, cool. I think this has been really good. It's really interesting. Smart rag is a takeaway of, you know, something to think about more for sure.

• 1:20:15Speaker 00

  Yep. Management, it is a subset of smart rag and that's like, that's really like one of the core pieces of this.

• 1:20:23Nathan Labenz?

  Just in kind of a couple, you know, wrapping up sort of questions. Where are you guys at today? Like, who are your users? You've scaled like remarkably fast. I've seen tweets to the effect of, you know, one of the fastest growing, if not the fastest growing, you know, European startup ever maybe. So what's that story like over the last couple of months?

• 1:20:43Speaker 00

  Yeah, so I mean, since we launched, we just continuing to grow. If you analyze, I take it over a year, it's one million dollar revenue per year. So now we're actually at nine million and that's faster than from like in eight weeks. So that's faster than any other company like launching from Europe. That from my research is it's the fastest. And more importantly, we have hundreds of thousands of users. And whenever we post something online, people are, it's full of comments of people who are just like blown away by what they can do with our product now. And there's a lot of love. Yeah, our users are the people who are paying, they're using it every other day.

• 1:21:28Speaker 00

  So there's a lot of positive aspects. What we're doing going forward is to make this valuable also to teams that collaborate. And you can actually see that on my screen that I'm sharing here. Like this is, this is not a launch, but we're going to make it much easier for people who collaborate to use our product for that. So that's a bit of a snapshot. But what's much more exciting than that is the AI becoming more reliable, being able to do more debugging itself and launch agentic mode that you saw here as well. That's in the works.

• 1:22:05Nathan Labenz?

  So I wanted to ask also about edit code and publish that I see in the upper right hand corners, like those are, you know, maybe the less interesting things from an AI perspective, but they're obviously important for people that wanna even ship an internal tool, right? So what does that look like?

• 1:22:21Speaker 00

  We're deploying the applications on like on the edge with Cloudflare. And then it makes it possible to just like with one click, you have built your app and it's all in production. And this is running and it scales really well as well. So that's how our hard publish flow works right now. Edit code is actually more interesting than it sounds. I mean, you can edit it with any ID, like cursor, whatever. Here I'm just opening VS Code in the browser. And then if I edit, if I change something, let's see here, where then I can, it will synchronize. So then I will instantly see like, oh, a human edited the code from their favorite ID. And this is also a way to collaborate with the teams.

• 1:23:07Speaker 00

  And this is not us.

• 1:23:10Speaker 00

  GitHub is now slow is what I'm showing on the screen. But that's what we have made to talk about. I mean, there's some more very valuable features that you learn if you're a super user. One is that if you have a specific API, like the documentation for a specific API, you can just put that in the knowledge for this project that we're editing. And if you want to do changes experimentally, like if you're a developer, you use to something called branching, and that's something that's built into the product as well.

• 1:23:42Nathan Labenz?

  Gotcha. So you've got the basically kind of dual mode of you can do the full developer experience with your IDE. You've got all your obviously changes tracked on in a Git repo here, branching, et cetera.

• 1:23:59Nathan Labenz?

  How does your user base break down? I mean, it's probably all happening so fast, you may not even know. But like, how many people would you say that are using this are developers trying to move faster versus people who are like, I don't really know how to code, but I want to make something?

• 1:24:13Speaker 00

  I think we ask this question, like, how much coding experience do you have? And it's split evenly with 25% in like no coding to up to a bit and up to like a lot of coding experience. And we are all about empowering like the 99% of people that don't know how to code. And it's even more if we don't know how to do both front end and the back end. So there are more of users in that bucket. But the people who are technical, they get much further. They can read much more complicated things because they they understand a bit of like debugging. They understand what API calls, how that works and so on. So the theme we have in common about our favorite users are that they have a very entrepreneurial spirit.

• 1:24:58Speaker 00

  They are like high agencies, another way I like to put that. And so it's often founders and people, operators who are running their own business. So maybe it's an agency and they're like super quick to understand what's possible with the new technology. Like those are our favorite users today.

• 1:25:15Nathan Labenz?

  What do you think is going to move the needle most over the next couple of months? Is it just better models or anything else that you're kind of specifically tracking? And where do you think we get, say, over if you can, you know, see this far into the future? Where do you think we get over the course of 2025?

• 1:25:32Speaker 00

  Yeah, I mean, for us, like you mentioned DevOps and the infrastructure being the big bottleneck. And long term, you're going to be more of the infrastructure package in a very nice, quite opinionated way for AI, for the best AI models. And more of our smart algorithms that are putting us ahead of others today are going to matter less because the large language models are going to advance and advance and again, just keep becoming more intelligent. Our tricks on top of that are going to be less important. The things that do matter for us in the coming months is to add a few more. We try to assemble a team of the most highest talent density here in Europe, like absolute geniuses, the people creating the product, honestly.

• 1:26:16Speaker 00

  And that's what matters for us and making the team work really well together, figuring out what is the right abstractions, both on the UI and the UX, on the infrastructure of the code that's on the projects that are being generated and being smart with it, getting the most out of the large language models. So figuring that out as a team is really the key to win in any, building any type of AI product, I think.

• 1:26:38Nathan Labenz?

  Do you want to put out a call for what you're looking for and where? Are you guys all in Stockholm or is there a?

• 1:26:44Speaker 00

  They're hiring mainly for people who are up for relocating to be in an office, which is much, much more fun and want to solve really hard problems and be at the absolute epicenter of what AI is able to do right now. And we're paying top of market for the top talent.

• 1:27:05Nathan Labenz?

  Cool. Well, this has been fascinating. Anything else you guys want to touch on before we break?

• 1:27:10Speaker 00

  I think if people haven't tried these tools, then the best thing you can do for your career and for your friends and so on is to get your hands very dirty. That's like you're going to learn so much from using these tools, even if you don't have a business application today, you're going to learn so much. If you're currently like working without AI, then I think you're really disappointing your employer or your customer, your clients, if you're running an agency. So you should get on the train. It's a huge time saver.

• 1:27:47Nathan Labenz?

  Yeah, get hands on. That's always my number one advice as well. Cool. This has been really fun. I've enjoyed the peek into the product and I will definitely continue to follow your progress and I don't expect it to slow down. So keep up the great work.

• 1:28:03Speaker 00

  Thanks a lot.

• 1:28:04Nathan Labenz?

  For now, I will say Anton Asika and Isaac Sundeman, founder and AI engineer, respectively, at lovable, online at lovable.dev. Thank you both for being part of the cognitive revolution. Thank you for having us. It is both energizing and enlightening to hear why people listen and learn what they value about the show. So please don't hesitate to reach out via email at [email protected] or you can DM me on the social media platform of your choice.