Building AI Tools for Roblox Creators

Host Devin Becker sits down with Nicolas Vizioli (Founder of Lemonade) to unpack what “AI coding for UGC in Roblox” actually looks like in practice, ranging from how Lemonade plugs into Roblox workflows to why Roblox is a uniquely interesting target compared to broader “vibe coding” for apps. Nicolas shares early results, where the product is (and isn’t) competitive with Roblox’s native tools, and how AI-assisted development has changed over the time he’s been building in this space. They also zoom out to where AI fits across UGC platforms, what impact it’s already having on Roblox creators, and what needs to happen, both technically and culturally, to reach the next phase of AI-powered UGC game development.

We’d like to thank Heroic Labs for making this episode possible! Thousands of studios have trusted Heroic Labs to help them focus on their games and not worry about gametech or scaling for success. To learn more and reach out, visit https://heroiclabs.com/?utm_source=Naavik&utm_medium=CPC&utm_campaign=Podcast

We’d also like to thank Neon – a merchant of record with customizable webshops optimized for conversion – for making this episode possible! Neon is trusted by some of the biggest names in gaming and can help you sell direct without the typical overhead. To learn more, visit https://www.neonpay.com/?utm_source=naavik 

This transcript is machine-generated, and we apologize for any errors.

Devin: Hello everyone. I'm your host, Devin Becker, and today I'm delighted to be joined by Nicolas Vizioli, founder of Lemonade. Lemonade is an AI coding platform built specifically for Roblox game creation, and today we're gonna discuss the intersection of AI and UGC development for the biggest platform Roblox. So just to start things off, can you give us a quick overview of your background and origins of Lemonade, Nicolas?

Nicolas: Sure. Thanks for having me, Davin. My background comes from gaming. Since I was a kid, I did Minecraft servers very, very young. I had the servers like True. I, I built servers mostly for my friends back when I was 12. And the servers that I built, like started growing, like getting spread between my school. And then I quickly realized that I could start making money with these Minecraft servers that I had. And then that's when I got like rat pill into the UGC gaming industry, and kept doing Minecraft servers for many, many years. Eventually had one of the largest servers in Latin America. We had a few thousand concurrent users, working after that with Alex from Vex Games. They're now like the, the largest Roblox startup. And before Roblox, they actually started with Minecraft servers as well.

So, I helped Alex for a few years and was building those games on Minecraft. And after that, I, I just move it to this big gaming company called Wildlife Studios. They, I, I joined it as a PM intern, work at, in a few games inside of the company. And then I moved to Europe to work in a, in a new UGC gaming app that was trying to actually compete with Roblox. It was called Soba. Raised a good seed round. At that point, that was 2022, and, and yeah, I just learned a lot about the platform angle. I was, I was serving creators and, and was a creator myself as well for 10 years. So that's when I started getting a lot of these ideas of what to do next. And that's how it connects to, to the vision that we have right now for beauty on top of Roblox.

Devin: Nice. So, I mean, to get into a little bit of detail, how, how does Lemonade specifically work with Roblox and like what does the, the overall workflow look like?

Nicolas: Yeah, so we are a coding agent connected to Roblox Studio. So, we know that like all this, there's like a whole generation of kids that are just starting to get their feet wet.

They never could make games before they, they always saw like this dream game ideas. They always wanted to do that. And making games was just incredibly hard, right? And that's what we are helping right now. So, we are helping those kids make their first games and that's the, the very first product that we have.

Devin: So why are you targeting coding specifically for Roblox as opposed to like the other parts of the UGC game creation?

Nicolas: Yeah. When you analyze the, all the creative outlet that there is involved to making a game, you can see like you have to do in the past. You had to like mess up doing UI creation.

So, you had to build a UI, you had to do game design, you had to do the map building, the 3D asset generation. And then, you had also like this beast that was coding and it's just extremely complicated to learn and you had all this friction to go through it. And yeah, when we started like thinking about what the piece inside of game development we wanted to tackle first, so like being very narrowly focus, making sure that we take a space and we really nail it. Coding was very obvious and I think like in, in the very beginning of the company as well, we were exploring this idea maze on top of Roblox. We were realizing that a, a lot of those kids that make Roblox games that we're making Roblox games after AI started like getting more important, they were using ChatGPT and they were going to ChatGP and asking like, hey, make me a script. They were copy and pasting this script inside of Roblox Studio manually, and they were doing this process like hundreds of times. So, like as we were interviewing these users, they, we, we could see like this pattern repeating and repeating over and over, and that was early 2025.

And then it became very obvious for us that like, okay, coding is already a very evident use case is definitely one of the hardest things in the entire like pipeline of making games and was just like, okay, let's, let's jump in, let's try to nail this, this space first. And right now, we're starting to expand slowly, starting to expand into other areas like UI development, UI generation.

That's very interesting to us as well. And if, if you're looking into Roblox, for example. 50% more or less of the, of many games are purely UI. It's just like the 2D UI. You join the game, you see an inventory UI, you see a setting UI, a leaderboard, and using like AI to code these UIs right now programmatically, they do a good job.

Like the visuals are not there yet. Quite sloppy. Right? And that's like another space that we're slowly starting to expand from coding right now is like UI generation. Being very, very focused on those places first and expand from there.

Devin: That seems like a good expansion from there. Just 'cause obviously the UI is what drives a lot of the interactivity in these games and therefore like the actual code. So having those two tied together seems like a good way to make sure that things make sense, especially for a lot, a lot of these game developers that are, that are younger, may not have a lot of experience doing UI. So, like that, that seems like a pretty natural expansion from there. Overall though, like, how does Lemonade sort of compete with what Roblox is already providing?

Nicolas: Yeah, so that comes precisely on the, like the defensibility side that we are focusing right now. Like we have a very. Intentional core audience that we are focused on. Like for us it's really important to target this first time developers. And you can imagine that Roblox as like this huge company, even though they have these initiatives, like to do the Roblox assistant, they're now launching the Roblox MCP integrations.

They have to be very agnostic actually with doubts that they're serving. So, they're like trying to help kids turn developers, trying to help like developers that exist in the platform to build even better games. And I think for us, like a lot of, a lot of it comes from like being very intentional to the, the audience that we're serving, again, first time developers, making sure that the installation pro process is extremely easy for them.

So, the way to install our coding agent right now in Roblox is just. It's simply like a plugging side of Roblox Studio. You go in the marketplace and you're like few clicks away, and then you use the interface in the web. It's a website, and then we have like all this initiatives focus on product development.

And UI is one of them. Like we, we recently built this feature that you can build like UI just by prompting. So similar to like startups, like lovable V zero, you could go to the website, you prompt, you see the UI in the website, and you can interact with the UI from within the website. And that's something, we launched it recently.

So, like we have all this like differentiability, like trying to differentiate ourselves by being like product that's very unique to us, and that's not gonna be easily replicated using Claude code or Codex or any integration that you have. There, there's actually like an interesting topic here.

Like for us, we, we've seen like this, the paradigm of coding agents changing a lot over the last year. So, like it was relatively complicated to build a coding agent, like beginning of last year, middle of last year. And right now, it's actually fairly, like fairly easy to like do an agent, do the loop and play around with agents yourself.

So, for us, like we think coding agents are getting super commoditized and a lot of the defensibility is actually gonna come through like this. Product features, features that are very like the have this layer of like word of mouth being very intentional. Like how does, how do we really surprise users after they use this feature?

So, they tell their friends and we gain distribution after that. And also, like focusing a lot on branding and this, this modes that, that we think are durable. But like coding agents actually, um, especially intelligent is not our focus. Definitely. I'm happy to share more about this. I have a lot of thoughts, but it's definitely not what we're thinking right now.

Devin: Nice. Definitely, definitely stuff you've thought about for the future there as obviously Roblox is going to be trying to expand that themselves, so it sounds like you guys are maybe a little more focused on user experience than they are perhaps, which is, which is good given the audience, right?

Like, but I mean, kids are, kids are very smart. Their, you know, their brains are still growing, but they also like, may lack a lot of experience that game developers will have. So, it's a little bit different audience. Whereas Roblox is, tools will be interesting to see if they gear a little bit more towards some of those game developers moving into the space as opposed to their, their specific, like younger audience. So, I'm, I'm really curious to see how that expands. But I'm also curious, how are you making sure that Lemonade understands Roblox, like, that it stays current with the documents and stuff? Like do you feed it the, the docs that Roblox provides? Do you actually like, give it extra bits of information that you know, like how do you make sure that it understands Roblox.

Nicolas: Yeah, we have all these layers of knowledge specific to Roblox embedded inside of our tool, behind the scenes. So, the developers, and, and that's particularly good again for like this first time developers 'cause they, they don't have actually the time to go to Claude code and be building their own like, skills of knowledge.

So that's, that takes time. Right? So for us, like we handle all of that and we had this like since last year. And one thing that's important to, to realize as well, like it's one of the, the like realizations we had recently is like you, you don't wanna be competing with intelligence when it comes to this coding agent layer 'cause like every single time you, you have to like work on the model harness, you have to improve your tool. You're gonna be working like marginal improvements. Like maybe you improve the agent 5% here, 10% there. And it then is like it's marginal, right? And almost the next model, like the next release comes from the labs, they usually like eat all this improvement that you had.

So, for us, we're trying to be like very, very intentional to actually leave our bottom act to bet intelligence. So yeah, as we do the basics, like in terms of Roblox knowledge, we already covered that. Like how does the models get even better? We don't do much work here to like improve the harness aside from the foundation we already built and we're much more, more interesting again, building this product experiences that are domain specific to Roblox, that other coding agents are not gonna deliver simply because they don't focus on Roblox.

It's like Claude Code, like Roblox is such a small market for them and, and through that we can like, develop a better experience for the audience that we're targeting. So, like for first time developers, how do we teach them what a core loop is? Right? So, you, you imagine a kid joining the, the platform, like they don't even know what game design is.

So, we have to like retain them. We have to make sure that they have guard rails around their first prompts so that what they're building actually connect and ties to, to the pieces, the mechanics that they're doing sequentially and all these like tiny details around the experience and not so much on the intelligence layer.

I think that we we're, yeah, that's, that's the operational level we have for right now.

Devin: Interesting. I, I, I'm curious too, like, uh, both how, sort of model agnostic you are and like whether or not you kind of have to lock it to specific models. Meaning like, you know, hey, if a new model comes out, you gotta test it first, and stuff like that.

But also, I'm kind of curious about what you said around these people maybe not understanding game design stuff and I'm thinking like, oh, like a new user. How are they gonna prompt this? How do they know what to prompt? Do you provide any guidance or like how do you, how do you help people get the prompt ball rolling?

Especially for kids that are new to, obviously there's kids that are gonna be like, oh, I use AI all the time for school and things like that. But then there's people who are like, I don't know how to prompt it's, it's like this art science kind of a you just blank white page sort of thing.

Nicolas: Yeah, a hundred percent. This is one of the hardest and most like complex things we're having right now is like dealing with this user intent coming from kids, coming from young teenagers that don't even know how to articulate what they have in mind. So, we have like this whole layer of like agents and routers behind the scenes that like try to deconstruct what is the meaning of the user.

Like when they, when they say that they wanna build a game, let's say like they have their favorite games, like Grow a Garden for example. So, like when they prompt a mechanic, they're like, oh, I'm trying to build a farm mechanic, and we have this layer. We understand like that their favorite game is already grow a garden 'cause we do have an integration with Roblox and we can pull the data to see what are, what are the user favorite games. Then we, we start to collect like this data around user intent that helps us understand what the user is trying to build, even if they don't express with the right words what they're trying to, to like exactly make right.

And yeah, we're being like very, that, that's one of the biggest challenges we have right now is just like decompressing and deconstructing user intent and making sure we collect a lot of data points that are external to the prompting layer. So, we help the user like get to, to the dream game they wanna build.

And in terms of models, like we're being a hundred percent agnostic right now. So we build our own evolve pipeline and evolve tasks under the hood. And every time, like a new model drops, like, yesterday, Opus 4.7 just launched. Like we, we run the eval immediately. Like we measure, we have like specific tasks for Roblox, so we know like, oh, make me a punch mechanic.

And then we have an agent that joins the Roblox studio. He tries the mechanic. And we see like, what are the mechanic works or not. So, we have like, have many tasks like that and then we can measure like performance across different models and, and very fast see which one is good for each kind of like different space, like which is better for physics UI.

And then we just provide this to users like we we're very like agnostic to, to the models we serve as long as they're good to, to the user.

Devin: Nice. Well, I mean that makes sense considering like you never know these days you have, like for example, what happened with Open Claw and Claude, where suddenly Claude is like hey, no, you can't use Open Claw anymore. And that was like the main platform, you know, model that I was using. So obviously there's a situation like, you know, that potentially they could just be like, sorry, like you can't use Claude anymore. And so, it's good that you have these other tests running 'cause it does seem like building on top of models is always a little bit risky in, in the current world.

And being agnostic definitely helps. So having the evals seems like a smart way to like always be looking out. So, like for example, if, if Gemini suddenly was better or if Codex was suddenly better, you'd be able to switch pretty quickly because you'd have the evals kind of tell you that.

Nicolas: Yeah, exactly. We, we can see high level, like what are the models that are doing better edge at each different time. This is actually like a strategy very similar to Cursor. Like if, if you look into the Cursor, the way that they operate since the very beginning of the company, it took them a long time to start like doing post-training experiments and they were just like providing what was state of the art from the labs.

So they, they were giving like Sonnet Opus when he launched like Gemini, like all these models, all these different models that the user could select themselves. And only now they started like experimenting with post training and it, it's very, it's funny 'cause it's like very, a very specific layer of models.

It's like the cheaper version, given that the AI labs are like, they're leaning towards, like pushing the frontier and not actually, like, not shipping or dropping so many, like expensive and super, sorry, cheaper models anymore. So, for Cursor, it's good for them to like post a cheap model, student intelligent versus competing with like the frontier that the labs already provide very well.

And for us it's the same thing. Like we're not experimenting with post-training our own Roblox coding model yet, even though we have a lot of data and we like have the data label and yeah, it's always interesting to think like when you start collecting this data, how you can like make sure you have the entire trajectory of the data you're collecting 'cause that's like this raw data, it's the most valuable piece of data you can have. And after that you can have like human humans annotating the data and you can do all these experiments on top of it. So yeah, that's, that's the way we think right now is like not doing post training yet. We wanna intentionally have intelligence as, or bottleneck, 'cause the models are gonna keep getting better here.

And as long as we have a very strong foundation of evals under the hood, we are gonna be good 'cause then we can flip the models very fast and just make sure we're providing the best experience and like whatever works best right now for the users.

Devin: On talking about the users, I, I understand you have quite a number of users already. You've run game jams for this and things like that. What are some of the, the more noteworthy results that some of the people have made like some of the things maybe from the Game Jams or anything that, ideally stuff that surprised you that people were able to pull off, or that helped maybe even shape the direction that you took?

Nicolas: Yeah. We started building this a year ago, and the beginning was very like zero to one, doing things that don't scale. So, it was like very manual reach and growing few hundred users every month. And we saw a spike coming a few months after in August. So that's when we got like our first few thousand users.

And after that, like, because we were pretty much the first agent on top of Roblox to make Roblox games, the growth was vertical. So, like we have been growing very steadily. We, right now we have almost a hundred thousand monthly active creators actually. And, and yeah, like it's very fulfilling for me to see like all these kids turning creators be being able to like, finally, finally have this dream games and turn them into reality.

And for some of them, which is actually our mission in the company, like the reason we call ourselves lemonade is because we wanna help teenagers. Make their first dollar online. So, we're trying to build like the Lemonade stand for the next generation. We think Roblox is the best place to get started.

Right now, it's like massive, too many users, and we do have users right now that are already making money with the games that they built with Lemonade. Like last month we had a user that, that but game and made over $20,000. So, like, it, it was like a complete first time developer. Like the, the user never built a game before, was completely done using AI.

And, and yeah, this shows like the potential of course, like this is a, this is like long tail text stream example, but it does show the, the potential of focusing and like you, you don't need to, like an AI is expanding all this, the, the things that were complex before, like designing, doing UI, as I said before, like you a, a single person can do that right now.

So, if as long as you have the free time and you have the curiosity to explore, there's a lot of you to, to collect from, from doing, doing that on Roblox right now.

Devin: Is this kind of helping people sort of accomplish what Roblox is sort of issue wants to enable? Kids to be able to sort of make money off of games and make games and things like that.

And now, enabling that a little bit easier, I think for some people that were kind of scared off by the coding side of things. I'm kinda curious though, like, you know, we're talking about zero to one and things like that sort of working from scratch. How well does this sort of platform work with, like, let's say I already had a game, or let's say I just bought a game from someone.

I'm like, I don't wanna read through all that code and try and understand it. Could I use this with an existing project? Is it gonna be able to at least understand enough of the code to be able to make modifications, things like that?

Nicolas: Yeah. Even though we focus on, again, first time developers, you're able to connect like any, any existing game, from Roblox into Lemonade. So, like we, you can do that for sure, like you can do live ops. We have users that have been working on their games for many weeks already, so that's possible. And, and yeah, it's just like, for us, it's not the audience that we are focused at right now, but it is, it is something that you can, like, you can have your code base and connect and like keep making a game from there.

Devin: The live ops part sounds kinda interesting, especially like, I, I just thinking of, obviously that's a new concept for a lot of the, the young developers and the idea of like, hey, I wanna keep this going long tail, I need to actually like update my game. Maybe they don't think of it as live ops. There's like updates, you know, people want updates.

So, it's really interesting that it can help enable that because that's something that could be difficult. Especially for newer developers. So definitely interesting there. In general though, like, what are some different ways, I mean, live ops was a great example that you see AI fitting into like UGC development, not, not just mean Roblox, but just across game development 'cause this is something that I think is gonna matter, to this current generation coming up more so like obviously we've had our generations of UGC and mods and things like that. This definitely seems like a time when, especially with Enable or AI enabled stuff like you guys are building, that this is like a big opportunity.

So how do you see that across the whole sort of UGC game development ecosystem?

Nicolas: When it comes to AI, we see like AI coming pretty much in all the fronts in terms of like everything you can do in gaming. So, you can do like the asset generation or the sound generation, the map building as well. One of the reasons why we decided not to, to touch map building early on was because we saw the Roblox actually like doing an extremely good job here. Like they have this own internal motto that Open Source called, called Cube 3D, and yeah, they have been focusing on that, doing a super good job there and it's coming out different fronts. To be fair, I think like one of the, one of the coolest ones we have been seeing is like on Roblox specifically, if you open the, their website and you go to see the games in the homepage, most of the thumbnails there are AI generated already. So, like you see those kids like it, it, it's at the very top of the funnels, like the very first impression that you have of a game.

The thumb and even the, the game name for sure. Like a lot of kids are using Dutch like refiner game name, like making sure he has the best hook. So, it's coming every single from, and yeah, it's super, I'm, I'm actually like very curious about the things that are gonna be explored from now on. Like, there's a couple of areas that if you're underserved still, one of them is like AI first games on top of Roblox.

Like that's not super evident. So, like that, that does feel like an under explored space. Like we don't see that many games using AI chat bots or like any kind of AI visual generation on top of Roblox. And that's an area that I think like there's, yeah, again, an opportunity to explore. And something that I'm also like very curious, and we think very actively about this for Lemonade, is how do we solve user liquidity?

So, in terms of when you think about the desire of that someone has to make a game, it's often one of the biggest desires. Is that like the social recognition, the social status that comes from, from building your own creation. Roblox does, does that super well 'cause they push the algorithm, the discoverability is very sharp to get players in front of your game if the game is minimally good.

But for people that don't, that perhaps wanna make like a multiplayer experience and need, like user liquidity, people online, I think those like AI characters are, they're gonna start like, becoming extremely good to the point. Like they, they resemble actually a, a real human. And you do have the same, the same feeling of like, you're playing a game with a, a, an extremely intelligent agent that does give you the feeling that like he, he's your buddy for real.

And he, he knows the entire game, like end to end and I know Roblox, like is, is exploring some, some side of that internally, but like that's one things that, that one of the spaces that we have on Lemonade that perhaps we can build games that come with bots, like those intelligent characters attached to the game itself.

And then we are like helping users, helping creators not only with the creation part, but also if this feeling like they wanna have, have like liquidity, user liquidity. They wanna have the social character with you through, through like the user journey and yeah, that's, that's another thing that's super interesting to me.

Devin: Nice. Well, I think we'll definitely see a lot of that happen, probably faster than we expect. But I, I am kind of curious, since you've been doing this for a little bit in terms of building this out, how have you seen AI coding specifically for game development? Evolve during this time that you've been working on it?

Because I think, I imagine, I don't know exactly when you started, but I imagine when you started it was pretty different than how it is now, just with how rapidly things have changed for coding. Especially like I, I heard a lot of people, you know, saying that like before December last year, coding was one way and then after it's like world's different.

I mean, have you seen like a, a lot of evolution, like what have you seen kind of tr especially for game development, because I know that's usually talking app development. I think game development's a little bit different.

Nicolas: Yeah, on our field, like coding, coding agents, which is again, is like con, it's connected to game development because of the programming side.

I think we recoded our architecture over five times over the last year alone. So we have been doing that all the time and we can like act, we can very clearly see that the paradigm is changing like every three months and we have to keep adapting so one of the, the things that's happening, like we, we were just discussing this internally this week, is that this, this like flow of like, you plan your task first and then you deconstruct the task into many smaller pieces.

So, you have like a separate agent to planning and then you have a separate, another agent to executing this flow is actually starting to like vanish right now because like with, with the model capabilities we have that they can do like long horizon tasks better, they're more intelligent. You kind of like don't need a planner agent anymore. You're able to put like the planner inside of the executor and like actually share the entire context with a single agent. And it's funny too to realize this 'cause like that, that was literally like the paradigm for the past year and a half, two years. Like everybody had plans like the plenary steps and one of the bets we have is like this is gonna start to converge again. Like before you had to separate context and now it's starting to converge back to like consolidating context in a single agent. And it's very like, it's fun and at the same time chaotic to be working with this 'cause we have to keep like adding new layers on top of our technology and in parallel we have to like keep s sculpting and taking things out at the same time.

So, yeah, that's one of the observations we have. It's like very, very chaotic to be working with it right now. But if you're in, yeah, if you wanna keep like building the agent, the best agent possible, you have to keep like refining it all the time. And that's why we did like recode it up the, the agent, we have so many times already.

Devin: Interesting. And, and I, I mean, talking about this whole planning paradigm and things like that, I'm kind of curious, one of the things we've seen especially trend for a while is this idea of using markdown files to keep memory as opposed to say that database or something like that. You know, Open, Claude is big about that.

Claude Code is big about that. Is that something you guys are leveraging as well to kind of keep track of things, to remember stuff obviously like keeping things, everything in context is kind of expensive to do. So, like, are you guys architecting similar, like to file marked on stuff or?

Nicolas: Yeah, we have a similar architecture. This is actually an, like an area that we want to put more time on right now, but yeah, we, we do have like this memory bank that the, the project of the user is like the constructed and we have all the information inside of like different areas of the project and the, the agent can like pull this information selectively as, as it, it's doing the generation.

So, this is your good to do and, and again, with like context windows for, for models, for example, getting much larger and more formatic. You don't have to be spreading like how your context within like dozens of files anymore as, as happening in the past. We're seeing the same thing that I just saw, like we're seeing like the, the context converging into fewer places and the agent is able to, to pull the context from, from fewer places right now.

Devin: Cool. Well, I mean, I imagine we'll see that evolve somehow. There'll be a completely new paradigm or some other way of doing ma memory management and context in the future as a, especially since the context stuff tends to lead to higher costs, despite the window increases. So interesting to see.

I'm curious though, like, most of the time when you see talk about vibe coding or AI coding, it's very app focused. I am curious what you've seen different about game development specifically 'cause you know, a lot of people talk about coding game development, you know, very vaguely. You don't see a lot of details. What have you seen that's like really different about it?

Nicolas: Yeah, I, I think if you like looking at the fundamentals be behind like vibe coding an. And vibe coding a game. I think like both of them have different purposes. At least that's, that's the thing that comes top of mind. Like if you're, if you're trying to vibe code an app, it's very likely that the app has a specific utility that you want to get out of using.

It could be like a financial app that you just wanna like check your savings, for example. So, like you have this final goal that's very specific, very clear, and you just wanna get there. Versus in contrast. With gaming, I think the, the experiences like the entertainment is, is the goal, right? Like you're, you're playing something and you're either like trying to escape like reality and just like get your time sucked inside of the game you know that very well, like with, with the game design tricks and, or you're like trying to like socialize, like how do you reengage with your friends or how you meet new friends online. So, there's like these different purposes behind games and also in, in the action as a creator, the go of games. And that's something that we're doing internally.

Like we, we have this core principle that we don't try to one shot games like Zero Shot. We, we see all this like AI game platforms that they try to go like from prompt to game in like five minutes. And that for us is not fun actually. Like if you understand what a game actually is that the joy comes from the process, right?

Like you're iteratively building mechanic by mechanic. And the process is the fun. It's not like the final product. And, and also like games, you could have like this final piece kind of in your mind, and you can imagine how the game is gonna look like. But the process of making a game is also very fractal.

So, like you, as you build it, new things start emerging new ideas start taking shape. And I think that's the joy, like for, for us, we're being very intentional. Like if someone goes to Lemonade right now and, and try to prompt, make me steal a brain rod, if they literally prompt, prompt that we, we don't, we don't let the user generate anything.

Like we return, like some options to the user. Like, hey, these are mechanics that exist inside of steel brain rod, which one do you wanna start first? Right? So, we have this guard radio to make sure that we keep. The process as the main thing, as the, the main joy and just allowing the user from, to build from there. That's something that, that we think about a lot.

Devin: Well then, you definitely bring up something that's really important. I think it's the, the one shotting versus the iterative process, right? Game development is extremely iterative. As much as people would love to just like plan and, and just produce straight through, that's not really how games work, right?

Whereas apps generally can a bit, right? You have your spec, you generally are producing it. You can maybe iterate a bit, but usually that's at the end when you're adding features as opposed to tuning, tweaking, iterating. How are you guys supporting that iterating process?, Like you mentioned a little bit of it, I'm, I'm really curious how that that works, that iterative loop, because let's say I, I, you know, I, I tell it what I want, I get it and I test it.

Is, is the tool then, like, trying to be like, hey, how did that work? What do you wanna change? Or is it more like just whatever you wanna do next? Do you wanna add something? I, I'm curious how you get sort of guiding or supporting that iterative process, uh, differently than like, something that Claude Code would be doing.

Nicolas: Yeah, high level for us, like we're trying to understand all the abstractions that are required to make a game, and then we're, we have these agents that like, build these abstractions. Like they, they kind of like help the user get their, uh, again, our focus right now is just coding and UI, but we are gonna expand to other areas, like we are gonna expand to asset generation, to sound generation.

These things are definitely in the plans. And also, we have like all these capabilities for a single person to be like a full game alone. Then I think for us is like, just becomes understanding the user intent. So, like making sure we have the intent of the user, like the final goal or like the, the thing that they had in mind when they, they started prompting kind of like have this in place and help.

Placing guard rails through this journey so the user gets there so they don't like derail and start making com something completely different than what they wanted initially. And out of the center they have a frank sty and when they see they cannot like even publish the game. Right? So even though it could be a fun experience for, for the creator, I think for us it's really, really important to help them finish and publish.

So, we have like specifically on the product we have a few guard rails to like, when we build a mechanic, we send back to the user like, hey, are you happy with this mechanic? Or do you wanna add it or refine it? And then the user kind of like a human in the loop step that the user has to review what they just did.

We also have like, something that we're working internally now is like, how do we have all this core loop architectures and how do we make sure that as the user builds the game iteratively we have, we can recommend mechanics coming next that tie to the core loop. Or perhaps like just the mechanic sequence that the user is, is building so far so we can finally close a loop and help them build something that's playable.

That's another thing that, that we are doing to keep the gures and keep helping the user get to a final game. Yeah, that's, that's partially like, that's a few ways that we think about it.

Devin: Interesting. Yeah. Like it, it is just really interesting that, that the harness parts that are not just the coding, right?

The parts that are like helping users go through this game development process and sort of learn it. Eventually it becomes like a mentor as well, right? Like where you're almost like working with a, a, a mentor to develop a game, go through the process. And the nice thing I suppose is you can also then implement like best practices and other things that sort of help them.

Better do a good job, like you said, trying to help them finish the game or, or stop them from just going on all these tangents, like that's, that's scope creep, right? There's always a problem for game development, so anything you can do to help nip that in the butt early seems like a good idea.

Nicolas: Something that we're really interested, interested as well, is how do we help those users monetize the games again, in, in the mission that we have as a company, helping those creators earn their first dollar online. Roblox is an extremely healthy ecosystem to do that, honestly. So as long as you have something fairly unique and you put like this granular taste, like you keep you, you build a game in a very novel way, Roblox is gonna, like, the algorithm is gonna help you find players for your game for free.

Like you don't wanna even have to spend anything. And that's very, very distinct from the gaming industry itself. You don't find this like super easy on chain. Like if you wanna crack growth in machine, on machine, you have to do like all this like wishlist, growth hacks. And it's like completely different.

Even if, if I come back to my time, which was a Minecraft, you had to like find the server IP and then you had to like put that in the server list. So, discoverability was very, a huge pain and that that layer like Roblox really, really nails it. So, with this solved, how do we help the users finish and actually make money with the games?

And there's a lot of strategies here. Like as, as the user is finishing the game, how do we can, how can we help them add perks to their games? How can they sell like in a purchases, subscriptions, and all these things that we can have an agent that is like there almost as a buddy for the user. And yeah, helping them like achieve these goals.

Ultimately just being very fulfilling for us. That's, that's how we started, like, making money online through gaming and that's what we wanna do with our kids right now.

Devin: Awesome. Well, hopefully it has that effect as Roblox in general seems to have done quite a bit of that. I'm curious though, like just, just recently even, like, you mentioned, you know, the, the AI thumbnails and things like that. What do you think overall the impact has been on Roblox from AI, not just, you know, Lemonade, but just AI in general, but also what you've seen from Lemonade. Like what is it, what is it? I mean, is it taking over Roblox in general? Is it like, like really growing the amount of games on there? Like what is, what has the impact been?

Nicolas: On the, on the Roblox side, like what we observe externally is that it's very clear that one of the priorities of the company is safely. So that's one area that they're heavily using AI and they're, they're fairly like doing well with the moderation, especially as the models are getting cheaper and like open source right now, which is like you can run your own model and Roblox is doing that I think it's an area that I do wanna double down like here. Again, connected to discoverability. The main piece to gather your game, discover is having a great time. Nao is having like a great, a great game description, so that's how the algorithm can pick your game besides the game metrics. And yeah, if like, by simply opening like the homepage and Roblox right now, you're gonna see like a bunch of AI generated thumbnails or some flavor of it.

Like I, I, I should think there's, there's a mix that you need to put, like taste. Of like a real human on top of the eo, like there's a lot of termino that, that have like manual. You, you draw everything manually. But Termino is definitely like a way that that's very present right now in the platform.

And in terms of Lemonade, we have like dozens of thousands of games published yet using our tool already. And the thing that we are like exploring right now is actually like back to the product. Parts that we were discussing, like how do we make sure that the user finishes a core loop? How does the user has a gameplay that's a bit more connected, right?

Like, so it, it really gives a real chance for that game to work out, and that's like one of the things that we are working next and are super excited about.

Devin: Nice. Well, I'm, I'm excited to see like, the impact, I mean, obviously not everyone's a fan of AI, uh, in general, but I think if it can enable people to, to join game development, like I know we've had these sort of indie moments before in the past, but they've always been kind of difficult for people.

It was always a, a, an audience that was very kinda small and really dedicated and opening this up obviously is not gonna be good for everyone. We're gonna end up with, you know, a mix of, of quality of things here, but I think, uh, overall like generational benefit will be good. , We'll see if Roblox still ends up being the platform of choice for that forever, but what do you think overall, the sort of future for AI UGC game development looks like?

And I mean, even keeping in mind, who knows if GTA six will have modding stuff or whatever, like, like the intersection of AI and UGC in general. What do you think that looks like over the next few years in terms of where we go from here?

Nicolas: Yeah. Our opinion is very, I think like we, we were very opinionated when we started doing what we have right now.

For us, we think Roblox is gonna keep being a parallel in gaming. So, we think that, we saw this last year already, like how the success and like Roblox getting back to the spotlight. But I think they're doing like a few things that do feed more advantage to them back to like this discoverability thing, like being able to publish a game and have actual users trying it, that's rare.

Like it's not super easy to, to find distribution, purely relying in the algorithm so you don't have to spend much time like doing marketing and all of that. So that's very rare and unique for Roblox. We like the way that they're like planning their roadmap. Things like related to that as well. It's, I, it's important that the platform has this possibility of success through making real money.

So, they have the Roblox, this economy side of it. So, all these things like Align, it really make us believe that Roblox is gonna keep consolidating. And that's partially right. Why, like we don't really look so much into other UGC gaming platforms. There's a, there was a lot of like hype around UFN and I think they, they should have so much to prove themselves.

And, and even like GTA six, like, let's see what UGC comes out of the, out of the game. We, we are excited and we, we wanna see what they have. But right now, like all of our eyes and like all of our focus is going to Roblox and we, we are really batting that it's gonna keep growing. And in terms of the technology, like.

For ai that, that we are really excited for game development. I think it comes back to the points I said before, so like user liquidity, if you understand why someone is making a game, there's a feel like human desires connected to, you know, like the, the social recognition, social status status is definitely one of the, the largest ones.

So, if someone is able to fix user liquidity inherently as the platform, that's a very interesting play and, AI first games. Again, it's something that is stew and explore, especially on Roblox, so that there is a lot of opportunities to exploring AI first content. And I think we're gonna start have seeing more of this come out through the year.

And just like the, the fundamentals, like nailing distribution, is something important for the platform and. Yeah, I think like that, that those, those are some thoughts that come top of mind.

Devin: So, I'm curious then, like, having seen all this progress and the things that have worked out well and the, the direction things are going, what do you think is missing or really, really needs improvement just in game development using AI like that?

At least in, from your perspective? What of, what Lemonade does, that maybe is either lacking in attention or just not quite there yet, especially an area like that maybe has just been problematic to deal with.

Nicolas: It is funny to think about this 'cause it's like, I think a lot of the areas are like literally improving so fast and like having this substantial improvements.

So, we are benefiting from like different tailwinds coming to us. I think like the, the thing that comes to mind is like map building. I should think a lot of it, it's very hard to, it's very hard to build a map granular detail through a text prompt. You imagine like you have to say the positioning, the axis, like of which object you want to be, and then you have to detail each object.

So, I don't think like the chat interface is super fluid to doing map generation. And I think that's an area that, that's gonna be fun to watch. Like you, how do you build like these complex maps and how do you keep the taste? It's possibly you're, it's gonna be the same as game development. Like you're gonna have to keep iterating many, many times until you get to the state that you want.

It's not gonna be something that you're zero shot and you're extremely happy and that was your dream thing. So definitely, I think like dispositioning of objects within a 3D map slash simulation. That's very interesting. And I, I think that's one of the reasons, like word models are in the spotlight more because they have like a different procedure or like the, the, the way that they generate everything is, is different than, than the, the, the LMS per se.

So that's definitely an area that, that I think there is a, a stronger bottleneck that we're keeping closer look at right now.

Devin: Yeah. It'd be really interesting to see if there ends up being like a sort of mainstream, like the Chat GPT equivalent of a world model that you can just use as a model to build things.

Because this doesn't seem like there's, you know, it's mostly these sort of demo tech demo kind of things coming out. There's not some sort of thing you can just use via the cloud or download to just build spatial things. So that is, that is an interesting problem. Building a game through text is kind of a weird idea, although people tend to do that with game design documents in a way.

Right? But then once you actually have to rubber hits the road and, and you actually have to have something that's playable in 3D, that does seem like kind of a weird. Way to go about it. I have seen like some attempts for like unity plugins and stuff to try and sort of populate things with like assets, but as you said, that fine grain detail sort of playability all those things need a certain amount of spatial conception that maybe might not be like existent in those sorts of things.

So that's an interesting approach. A couple last questions and it's real quick to just finish things off. Just, two quick questions. First off, favorite Roblox game?

Nicolas: Hmm. I'm, I'm not gonna go with the mainstream ones there. There's one that I play quite often. It's called Tank Game. It's like similar to Agario, you have to grind like you have your character. It gets bigger as you cue other players. I think that's a fun one and has gotten my attention for, for quite a, a long time.

Devin: Nice. What is the biggest issue you've seen in Roblox game development?

Nicolas: I think for us, connected to our audiences is to understanding what the audience means.

As we said before, like they don't know how to prompt well, and we have to do like how this work behind the scenes show, like understand user intent when they prompt like, oh, make me a single game. No mistakes, right? So, we have to do like the, we have to understand again and like put them back in the guard radio and like, hey, the jaw is not like one shot.

This like, let's go here step by step and we're actually gonna help you finish, but you have to keep with us. So, I think like the, the biggest prob problem is like, how do you get the user through this finish line? And at the same time, how does the user, like, doesn't derail and end up building like a Frank Stein and never finishing what they wanted initially.

So, all this, like connecting all these pieces and making sure the experience is very, very tied during the process has been the, the biggest challenge. But as well, like the, the most creative thing for us, like we, we come as game developers. We love doing this. It's been a lot of fun working to, to solve this problem for like teenagers to, to build their first games.

Devin: I'm sure it makes you think of game development differently when you have to kind of think of it from this perspective of how do I explain game development to someone else as opposed to just doing it myself? So, it's an interesting, interesting perspective, I imagine. Where can people find some of these games that have been made with Lemonade?

Is there, is it on the website? Do people need to join the Discord? Is there something you can search for in Roblox? What's the best way people to kind of experience some of the things that have been built out of Lemonade?

Nicolas: So, I think the best place for people to find us is definitely on Discord. We share all the games that have been built using our tool there.

It's discord.gg/lemonade, and yeah, it's growing a lot over 50,000 members. And that's where we are most active as well. So, like I definitely read all dms there and probably the best place you contact to me as well.

Devin: Cool. Awesome. Well, thanks, thanks so much for joining. I am really excited about this, this project in general 'cause I think it's, it's really cool to see something that empowers people to at least experience game development, even if they don't decide to do it for a career. I think it's a good way to get something hands on and actually experience. I, I'm looking forward to the day when we have game development classes using this kinda stuff and whatever in schools and whatever so everyone gets to get it, give it a try. Maybe Lemonade will be part of that. We'll see. But thanks so much for taking the time today. I appreciate it, Nicolas.

Nicolas: Thanks for having me, Devin.

Devin: Cool. Well, thanks everyone for tuning in and, and make sure to go check it out lemonade,gg and of course the Discord he mentioned. Lots cool stuff happening there, let always in motion, I imagine. And, and make sure you're, you're checking out, of course, Naavik Digest. And we also now have some new stuff around AI and gaming. So make sure you're checking that out. It just came out this last week, so make sure that you're up on that, on, on Substack and everything else. And in the meantime, catch you guys on the next one.

If you enjoyed today's episode, whether on YouTube or your favorite podcast app, make sure to like, subscribe, comment, or give a five-star review. And if you wanna reach out or provide feedback, shoot us a note at [email protected] or find us on Twitter and LinkedIn. Plus, if you wanna learn more about what Naavik has to offer, make sure to check out our website www.naavik.co there. You can sign up for the number one games industry newsletter, Naavik Digest, or contact us to learn about our wide-ranging consulting and advisory services.

Again, that is www.naavik.co. Thanks for listening and we'll catch you in the next episode.