Loading summary
Transcript95 lines
- [00:00]
Nad Chishti
Like people can do things that they never could do before. They're doing things that they could never even imagine before.
- [00:04]
Rid
It's the fastest growing startup in European history. What the heck is that like, as the sole designer, the way that we.
- [00:10]
Nad Chishti
Think about things and the way that I kind of work is I'm trying to challenge myself across both individual velocity, but also team velocity. And so for me, what that means is as a designer, I'm an enabler.
- [00:22]
Rid
You're just in this unprecedented little collection of companies where you're not the only young rocket ship even. Everything's moving so fast. All eyes are on this suite of products.
- [00:33]
Nad Chishti
We basically built this sort of design tool version first, had an existential breakdown, deleted half of it, and then shipped this kind of simpler version afterwards. The eventual goal will be to have something where you have as fine grained pixel level control as you can get from a fully fledged design tool. Where I'm less certain is will the shape be design tools as we know it? I think there's an opportunity to declare a lot of what we've got used.
- [00:57]
Rid
To as legacy, but it's addicting. You know, it's just fun to try to solve the next problem and then the next problem, the next problem.
- [01:03]
Nad Chishti
Now I just generally we will design maybe the first state in Figma and then punch out to Lovable and then just make it interactive from there. And so I'll kind of jam with the AI to work through like live prototypes.
- [01:15]
Rid
Welcome to Dive Club. My name is Rid and this is where designers never stop learning. This week's episode is with Nad Chishti, who's the first designer at Lovable, which is the fastest growing startup in European history and has pretty quickly become my favorite way to explore ideas in code. So we're going to get a little behind the scenes and see what it's like designing at a rocket ship startup. And all of the ways that tools like Lovable can help designers become builders and impact the future of the practice. But I also want to start this episode by learning more about the beginning of Nad's Lovable journey because he shares some really great advice for people who are interested in becoming founding designers.
- [02:00]
Nad Chishti
I was basically hacking around with LLMs in my spare time as like more of a hobby, you know, kind of got infected with the cure, I guess the same as the rest of the world did with ChatGPT. But I was super curious about what I could use them for in design and kind of at the time I was working at a scale up that was working on kind of secure messaging and we had really, really good traction in public sector and we had to do all this kind of design work around things like accessibility and contrast ratios and meeting different accessibility standards for different platforms and different environments. And it was all quite rewarding, but a little bit grueling, I think, for the team. And so I started to build these little utilities using LLMs where I could do things like give an accent color to them and then use computer vision models to then create like a tailwind color scale from like a brand color or something like that, and then do like a cross check of what are the contrast ratios when these different color combos are working and stuff like that. And kind of started building these little design utilities. And then I just got completely bitten by this bug of like, wow, this just actually feels like this is what the future is going to be like, rather than us having to kind of manually do everything ourselves. And so I started experimenting with that and then that led me to an open source project called GPT Engineer, which was a project made by Anton, who's one of our founders, where he had basically started experimenting with LLMs for kind of the same reason, but in completely in parallel over in Sweden, he was the CTO of a YC startup, really loved what he was doing, but he actually got quite frustrated because he thought that all of his engineering peers were being too unimaginative with LLMs. So he would be able to see like, I don't know, five, ten years into the future and he'd be thinking, most code in the world is going to be written by LLMs and people would say no to him and sort of tell him he was wrong. So he got really frustrated and he put together a proof of concept called GPT Engineer, which was basically a command line tool where you ask the AI to build something, if it doesn't know what you mean, it asks you a question back and otherwise it just builds for you. He built that and then overnight, well, not quite overnight, that became one of the largest, most popular code gen projects on GitHub. And so that went from zero to like 52,000 stars on GitHub.
- [04:16]
Rid
Wow.
- [04:16]
Nad Chishti
And so yeah, I basically found that project, started playing around with it, then reached out to Anton, did some advisory stuff to begin with. So like a bit of contracting and a little bit of like, okay, let's go from like zero design to some design. But then flew over to meet the team in person, sort of since then, basically just decided to go all in.
- [04:33]
Rid
Just quick context, how much of a technical background do you have as a designer?
- [04:37]
Nad Chishti
I would never call myself an engineer, but I've always seen it as a, almost a professional responsibility to sort of really understand like my materials. And so I've just always hacked together front end. And I've always kind of strived to be technical enough that I can have a high frequency, high bandwidth conversation with the people I'm working really closely with. And so I can go quite deep actually on things like technical architecture, but always in a way that kind of relates back to design. And so I would say engineering minded in the abstract and sort of. I, yeah, and I can communicate very well with engineers.
- [05:13]
Rid
It's cool because you're the perfect type of person that then gets superpowers from a product like Lovable and you get to create that future. So I would imagine it's quite fulfilling right now.
- [05:21]
Nad Chishti
100%. I feel very fortunate with sort of my, my kind of shape and skill set and sort of where, where kind of all of this is going. But I also think it's a bit of a correction in some sense as well. Like as designers we know that form follows function and that they're as important as each other. But I feel like in the digital design world we just kind of obsess over form and so now at least with AI we can sort of widen back again and kind of shape both sides and also be way more cross domain and way more cross functional.
- [05:49]
Rid
Real quick message and then we can jump back into it. So here's the thing, the last few prototypes that I've made haven't been in figma. Instead I'm using Lovable. And honestly, it feels like magic to create real software without touching a single line of code. I mean, you could literally build whatever you can come up with and it's good. Like I'm genuinely proud of the prototypes that I'm making and developers can't believe how quickly I'm able to bring my ideas to life. So this is your wake up call. Don't stay stuck in rectangle land. I mean, I promise lovable is way easier than you think. And I'm having more fun designing right now than I have in a long time. So head to Dive Club slash Lovable to start building today. That's L O V A B L E. As a designer, I'm always talking to people, team meetings, design crit, user interviews. So it's super important to capture the ideas and the feedback that I'm getting. And that's why I never ever, ever, ever, ever have a conversation about design without Running granola in the background. It's like Apple notes, but it transcribes my meetings for me. So when the meeting ends, granola enhances the notes I've written and I can even ask questions or get tailored summaries for from the call. I mean, it's very quickly become a staple tool in my design practice. Every single designer should be using this. And if you want to go to the secret link, dive club slash granola, then you and your team can get three months free. That's dive club slash G R A N O L A. Okay, now onto the episode. Okay, so let's talk about lovable now. So roughly, like 10 engineers every day there's a new AI advancement. It's the fastest growing startup in European history. What the heck is that? Like, as the sole designer, really fun.
- [07:33]
Nad Chishti
I guess, like first of all, like, there's definitely stressful moments or like, you know, moments of being underwater, but overall energy giving rather than energy taking. And like that's, I think that's the most important thing because if that, if that wasn't the case, everything else would be more difficult. But super high paced internally, we and culturally, we put a very, very high emphasis on maximizing learning above everything else. The way that we think about things and the way that I kind of work is, I'm trying to challenge myself across both individual velocity, but also team velocity. And so for me, what that means is as a designer, I'm an enabler. The way that I see things is that design decisions are happening all of the time. Like everyone in every single team, everywhere is making decisions that in some way will resolve into user impact. At the end of the day. My job is to enable kind of higher quality decisions across the board rather than making all those decisions, decisions myself and then waterfalling them onto the team. What that means in practice is for us, a lot of the engineers are carrying things end to end, like as much as possible. I'm basically kind of guiding them. It's less so much about, here's the perfect design that will exist in the abstract on a Figma canvas and then we go and create it. And more so about, okay, let's align first of all on what problems we're going to solve. The engineers have a lot of latitude on how to solve those and then we pair up on the best user experience along the way.
- [08:51]
Rid
It makes sense. You're basically removing yourself as a bottleneck when you're operating at a level of velocity that is required in this type of industry, in this stage of the company.
- [08:59]
Nad Chishti
Even when I've been in larger teams, I've found this to be a healthy operation as well. Because, first of all, it's not that designers have the best ideas. Unfortunately, the very, very best things happen from collaborating and also come from the most unexpected places. And so I've always tried really hard to avoid this sort of feeling of waterfall or that things are either designed or they're not designed, when the reality is that if people can update the products, it's always getting designed by someone.
- [09:27]
Rid
I'm sure there's somebody listening right now that's like, well, how do you ensure the right level of quality in the product when engineering, in theory, could take smaller things end to end? Everything's kind of being shaped all at once. And especially as the first designer, I don't know if you've ever experienced this. I've sometimes felt this, like, fear of pushing something to prod that isn't up to my bar, because I know, like, it's never going to get prioritized. Like here, everything's moving too quickly, where that thing might be cemented for a full year as the product roadmap grows.
- [09:59]
Nad Chishti
I think about this as almost like a deficit. And so I think about quality as debt. I'm never thinking about quality being this bar that needs to be met. It's more so this. This almost this deficit or this feeling that can go up and down for sure. There's features that go out where we're in debt, and so we need to pay off that debt in future. But, yeah, but I see it as this sort of living thing where create debt and we pay it off, and it's just this constant, this constant moving cycle. It also means that we can translate those conversations internally to things like technical debt, and it becomes very, very easy to then advocate for paying off some of this design debt alongside technical debt.
- [10:35]
Rid
You've done the founding designer role multiple times now. So before we get into the weeds of how you work at Lovable, I kind of want to stay a little bit higher level and tap into your perspective as someone who has been in this situation multiple times. And at least for me, every time I start with kind of the blank canvas. As the first designer, it's this opportunity to take everything that I've learned, all my past experiences, and figure out the right things that I want to tweak or the ways that I want to do differently. And I'm curious if that resonates and if there are certain ways that you're taking advantage of this blank slate as a designer. At lovable.
- [11:10]
Nad Chishti
I really love working with founders. And so, like, founders are great because I think it takes a lot of conviction to sort of go from something just never existing or not existing at all to like, okay, this is actually going to exist out in the world. And as a first designer, I think you sit in this intersection of founders and the market, and so what you're doing is just sort of trying to tap into this raw ambition, raw conviction, and kind of make it understandable for everyone else. And there should be this sort of healthy push pull of, you know, there's things that just exist because that was in the original vision of the team or individual people or whatever. And there's other things where you get completely led by the market. And it's more so about, oh, we were completely wrong about this. But here's these. All these other amazing things that take you by surprise. I think what I find repeatedly interesting is sitting between these two and like, and having its healthy push pull between them.
- [12:03]
Rid
Any advice for someone who's interested in designing at startups that they could kind of pull from or tap into some of your learnings for how to succeed in that environment where you're sitting in between kind of the market and the founder and everything's moving so quickly.
- [12:16]
Nad Chishti
Be insanely curious, Learn extremely quickly, don't fall in love with your ideas because they're going to be wrong and just iterate. And every single startup trope you've heard of, like, talk to your users, talk to your customers, build what people want, just do that like on repeat, and everything else will kind of fall out of it. I think the biggest enabler for me has been constant learning. Learning both about users, the market, like how your product's doing where it's failing, but also learning about people as well. I think designers actually have such a superpower in anyone that has any kind of research discipline. The fact that we get taught and we learn how to talk to people, decode them into goals, desires, fears, just apply those research superpowers to absolutely everything. Like, apply it to talking to a finance person about how their finance operations are going, or the reporting process is like, whatever, but just go around the entire team or the entire org and just pretend it's a user research problem. If you do that on repeat, I think there's actually almost nothing that can't be solved.
- [13:16]
Rid
I love that because it's even great advice for how to interface with a founder too. Treating them like a research project, helping them navigate the weeds of their own mind and all of the ideas and untangling things. Something that I've kind of picked up from a lot of these conversations is that a trait of a great first designer is being effective thought partner for that founder and helping them even sequence and think through all of the ideas. You know, because there's a million ideas, all of them are good. Okay, well, how do we make sense of the right ones in the right order and what good ideas to ignore in the early stages?
- [13:47]
Nad Chishti
I think it comes with time, but I think once you have a good amount of trust and a good amount of gel, you start to build a bit of, like, intuition around what are the really noisy ideas where these are probably just never going to work versus, like, what are the. That we should entertain a little bit, because there's probably one aspect or one shade of it that could have a completely outsized impact.
- [14:05]
Rid
If this works, can we double click on that piece? Because you're in an interesting place now where, yeah, that's like a universal part of being a startup designer, but you're also designing in a space where you're kind of just betting on a massive amount of technological breakthrough which will change the entire industry. And so my sense is you're probably kind of straddling these two worlds of what's possible today versus where this all might go. And how does that impact the way that you explore and test out different ideas, even in conversation with a founder?
- [14:37]
Nad Chishti
I think, again, like, it all comes down to learning. What I think about and what we think about as a team a lot is just how do we maximize our learning in the shortest scale possible? What that means is, like, lots of rapid, scrappy experimentation, lots of being willing to be wrong and just putting things out there to kind of see what sticks. Where we have failed actually has been when we've tried to be too visionary. And so there's been a couple of projects or a couple of angles where we've worked on a problem and we've thought, oh, okay, the models are going to do this in like six months time. And actually, in some cases, you've listened too much to the foundation model providers where they've kind of said like, oh, these things are on the horizon. So therefore, you should be thinking about building in this way for like nine months time or whatever. Whenever we've gone down that route, we've had suboptimal results. Whereas whenever we've really reduced our iteration cycles, really, you know, spoken deeply to our users, really shipped small, small pieces first and, and kind of built iteratively from there, we've generally Kind of come to a good outcome. I think that was true pre AI, that you should always be scoping things down to the smallest version possible. I think it's still true. I think there's obviously going to be still big bets and especially when there's a huge step change in model capability, you need to be ready for that. But again, even learning with a new model, I think you should approach that very iteratively of starting small and then building up slowly from that.
- [15:58]
Rid
I want to go really deep into how you work and maybe we could use the visual edits feature that you just released as kind of a window into what day to day is and how you work through different ideas. Maybe we could start all the way at the very beginning when presumably you've identified this broad opportunity space. How were you then as a designer exploring and bringing clarity to what that could be?
- [16:24]
Nad Chishti
We had this kind of deep, fundamental philosophical belief that the best AI engineer or the best product of our kind of shape would almost feel like a WYSIWYG tool. It would be like instant feedback. The same way that if you, I don't know, draw a rectangle on a canvas in Figma, it's just there instantly at, I don't know, 120 frames per second or whatever your screen is refreshing at. And we wanted that to feel, we wanted our product to feel like as instant as that. Like since day one we just sort of felt that it's going to promote being able to build the best products and some of our competitors didn't think like this at all. So like obviously super famously like Cognition launched Devin and they just went full blown agent of like, oh, actually LLMs can write code. Instead we're going to visualize like a desktop and sort of you're going to fire something over to this engineer and it's going to spend four hours processing things and then come back or whatever. There's obviously two extremes between a WYSIWYG tool and that, but we were always trying to figure out where do we sit along this scale? And every single time we indexed more back on instant feedback. We never regretted it day one. We always wanted to have the core experience to be as rewarding as possible, as fast as possible. Visual edits, they were never really, it's not like they were like a roadmap item that needed to be prioritized. They'd kind of just always been on the horizon since day one because it just felt intuitive to us that you'll always want to directly manipulate software. And so that's Kind of why we did them when we built them. I mean, we actually built two versions of them almost. So the very, very first version that we built, our ingoing hypotheses was that design tools have solved a bunch of problems. And really what we're adding uniquely is the ability to collaborate with AI and manipulate the outcome in a known environment. The first version that we built was actually super familiar to anyone that has used Photoshop Sketch Figma insert design tool here over the last 20, 30 years. So we had a Layers panel where you could browse all of your layers. We had a properties panel where you could inspect things and then manipulate them, all the good stuff. But we had this moment where we realized that actually these things haven't really moved since the 90s. The very first version of Photoshop had a Layers panel in like, I think 1992. And so we started to sort of ask ourselves from first principles, like, why, why haven't things evolved? And we thought there was a good reason for, like, previous shifts. Like, you know, if you look at like desktop to web, it kind of makes sense. Like you're still at a desktop computer, so a desktop interface makes sense. But what we realized was that actually now with AI, we think we can move forward, like genuinely forward rather than iteratively. And so what we did is we actually, we deleted the Layers panel because we realized that, like, who cares about layers? I think the fact that there's even such a debate amongst designers about, like.
- [19:09]
Rid
Who names or naming or not, it's.
- [19:12]
Nad Chishti
Like, that's such a leading indicator that.
- [19:14]
Rid
Like, don't delete my group. 1427.
- [19:17]
Nad Chishti
Yeah, exactly. So we, yeah, we built a layer panel, we got rid of it. It. We built more styling, we got rid of it even down to. So I'm quite technical, so I don't know. I know flexbox quite well, for example. And so in a tool like webflow, I'm quite at home if I want to be like, oh, use, justify between at this responsive breakpoint or whatever. It gives me more control. But we just had this revelation. We were like, who wants to learn flexbox? Like, who wants to sit down and be like, oh, I'm going to ingest all of this crazy domain knowledge in order to just create something that I like and create something that I want other people to like. So we basically built this sort of design tool version first, had an existential breakdown, deleted half of it, and then shipped this kind of simpler version afterwards. The simpler version basically linchpins on. We're trying to find this tension where, like, when do you want to manipulate things directly versus when is it actually just better to use AI? And so we're trying to find these moments or these key interactions where natural language is superior versus when natural language is inferior. Most of the design process was indexing around trying to find those lines.
- [20:23]
Rid
Did you actually ship the full layer panels to even like a beta, or was it just internally you had this sense that this is not the direction.
- [20:31]
Nad Chishti
That we should go for that one specifically? That was internally. That was like, we, we built it and we used it and then we slept on it and then we woke up the next day and we were.
- [20:39]
Rid
Just like, no, I want to keep going even deeper because even within this new, smaller, contained ballpark of like, okay, we don't want the full layers panel, but we still want to find the right level of affordances to give users to make these more precision changes. What were some of the things that you were wrestling with as a designer, even figuring out how to implement that version?
- [21:03]
Nad Chishti
The word that the team got really bored of hearing from me was progressive disclosure. And so we were basically just trying to figure out what do we show and when and how do we do it progressively. Where we landed was basically a single panel where first of all, the feature is like almost invisible. If you're not a designer and you are never going to care about like manually setting a color palette for your app or whatever, you probably won't even notice that the button exists in our interface. And that was very deliberate because actually not everyone is a designer as well. And so, and a lot of our users as well are people building apps for the first time. First of all, the entire feature is completely hidden. And secondly, it gets more progressively complex once you drill down into more advanced properties. And so that was most of the work was figuring out, okay, like, how should we be progressive over time.
- [21:50]
Rid
Do you have any thoughts on where this could go or are you viewing visual edits as a building block for any future explorations? How are you thinking about that?
- [22:01]
Nad Chishti
The eventual goal will be to have something where you have as fine grained pixel level control as you can get from a fully fledged design tool. Where I'm less certain is will the shape be design tools as we know it? I think there's an opportunity to declare a lot of what we've got used to as legacy. That's, I think, where we'll probably experiment a lot more. It's where we'll probably get a few things more wrong before we get things more right. It's where Perhaps people might feel a bit more frustrated because this thing's just plainly missing. Like if you do want to name a layer, you can't just one click go. But I think with maybe like a one or two year view, I think it's the right thing to do rather than just sleepwalking into assuming that we need the tools of the past in the future.
- [22:41]
Rid
It's not just the tools of the past, though. Like, you're in a really fascinating space and I basically never ask about competitors on this show, but I think I am going to ask you if that's okay because, I mean, you're just in this unprecedented little collection of companies where you're not the only young rocket ship even. Everything's moving so fast. All eyes are on this suite of products. So how do you think about the right level to even pay attention to what's happening around you as a designer at one of these companies?
- [23:11]
Nad Chishti
It's really fun, as in, like working in tech in this space right now is as fun as, you know, if I feel as energized as I did when I was a kid, like doing this for the very, very first time. So that's really, really great. What's less great is it can be super distracting. Like even just, I don't know, even just scrolling over Twitter whilst having a coffee or like, whatever. There is, like there are thousands of things that can suck you in. That's a bit of a personal battle. So I've had to like, up my, I don't know, my phone lives on, like, do not disturb 247 because my life is better that way. I try to time box a lot for anything that could be a distraction, but it's super energizing. Honestly, it feels like, and I can only say this with hindsight, but it felt like things got a little bit stagnant. Like we kind of had mobile and obviously that was a huge shift. And then, you know, as a designer then we started to think about starting cross platform and things like designer ops. But we kind of understood SaaS, right? It was like, of course there was going to be new SaaS companies, but it was what it was. It's like, okay, deliver some value, charge people for it on a recurring basis, more or less. And now everything's changing and I think that's awesome. And so, yeah, ultimately it's a super fun, super energizing.
- [24:27]
Rid
Do you have any beliefs or hypotheses about the future of the state of design tooling that you're kind of working backwards from as a Design.
- [24:35]
Nad Chishti
I think the same way that developers have their own development environments. Like if you look at ides, the I stands for independent. And the reason why every development environment can be independent is because code is interoperable, right? It's like you can have your source code store it somewhere. Developers can pick and choose how they want to work individually per device even, and everything just works. And I think the future of design will be really, really similar. I think there's going to be multiple winners. Like I don't really see there being like there'll be one AI design tool that will win. Likewise, I don't even see it. The incumbents are the best positioned I can imagine almost niche tools for niche purposes, depending on whether it's motion or doing more detailed color work or using shaders or whatever it might be. But I think now with LLMs, code can be the source of truth rather than design files. And I think that's going to enable this interoperability and therefore design tools being able to work independently but contribute to the same source.
- [25:31]
Rid
I think it even goes back to some of the emphasis on learning and curiosity that you were talking about earlier. Like it's the first time in so long that there's a real fracturing of the market and maybe we're inning one and I think we are. But gosh, I mean all we talked about was Figma for a long time, like many years. And I do believe that they're going to make some kind of a play. And you know, we have config here in a couple months and everyone has their ideas of what that could look like. But the fact is there are a lot of really interesting niche tools and a lot of different ways that designers can visualize their ideas now, which, which is very exciting 100%.
- [26:06]
Nad Chishti
And I think also niche tools should be stellar braided. I think in tech, especially in venture capital, the name of the game is always who's going to win and it's always who can get majority market share. But especially now with AI, now that we could write software cheaper, I think we should be celebrating the fact that we can create more single purpose tools that can focus on one problem and doing that really, really well.
- [26:29]
Rid
Have you played with Unicorn Studio? Out of curiosity. That's the perfect example of a niche tool for me where it's no code web and there's not that many people tinkering with it, but the people that are, are just making the most incredible output on Twitter is obviously like where I'm seeing it. And it just, I look at Something like that. And I'm like, man, I'm so excited for the long tail of tooling.
- [26:51]
Nad Chishti
So I haven't played around with it. So for the uneducated, like what's the, like what is it? And like what, what should I do? Like what should the first thing I do be if I, if I play around with it?
- [26:59]
Rid
So that's the thing is it's like, it's so art forward because it's just open ended WebGL where you can create these really, really detailed 3D motion effects and then it exports a format that you can embed as like a framework component, for instance. And so like one of the things I helped with is like making this 3D moving or. But it's all controlled in code, you know, it's not a video file. And so it just, it raises the ceiling for what you can do with like these kind of crazy visual details, maybe in a similar way that something like Rive would for animation. And I just get, I'm tooling nerd. So this is just like a fun time to be someone who does spend too much time scrolling on Twitter. Getting distracted.
- [27:39]
Nad Chishti
Cool. You've added one distraction to my list.
- [27:42]
Rid
Speaking of distractions, actually I do want to get nerdy for a second here because I was looking at your roadmap and I saw MCP in the Next up column, which is one of those kind of buzzwords that you're seeing all the time on Twitter now. And I don't know, I'm sure other people that have come across it feel the same FOMO that I do. So. So do you have the ability to explain what that might mean or what it might unlock for designers in the future?
- [28:10]
Nad Chishti
MCP stands for Model Context Protocol. And in typical computer scientist fashion, it's a terrible name. We are terrible at naming things. Generally all it is is it's just a standardized way for models to talk to other things. If you're building with AI, you'll be able to integrate MCP and anything else that integrates MCP will just be able to interact, operate. And so we're using MCP right now, something that we're cooking up at Lovable, where we'll be integrating with MCP servers on things like Stripe as well as things like Web Scrapers as well as Supabase, which we use for building Full Stack applications, where because we've done one integration with mcp, Lovable will just interoperate with all of these things really, really well. And so what we'll see is we'll go from this world of like, I don't know, LLMs being little silos where they have their own history, their own knowledge and that's kind of self cont. Then separately, one particular SaaS platform being its own silo over there as well to just all of these things being able to talk to each other. So that's the dream, that's the pitch. Pretty bleeding edge though. And I think there's also a lot of promises being made that actually maybe aren't quite being met yet. And so we'll see where this goes. But, but it's super exciting.
- [29:22]
Rid
Can we talk about the Supabase piece for a second? Because that was actually my aha moment with Lovable was when I could just connect it to a database, talk to the database and make changes without to get into the schemas or really understand how anything's actually working behind the scenes. What was that like designing that integration and even more broadly creating interactions that try to simplify and demystify some of the technical things that are happening behind the scenes. How do you figure out where that line of abstraction versus control exists for users?
- [29:56]
Nad Chishti
We integrated Supabase because we wanted to enable people to create full stack applications. And so before Lovable existed there was like multiple options to create like a landing page, a static website, whatever. Super difficult to create like a real working application. We looked at a bunch of different options and we really, really liked what Superbase was doing. And so it's a bit of a no brainer to use that or to enable people to use that for a backend. In terms of how we designed it, we basically shipped the simplest, smallest version of it that we could and then we did two different things after that. The first thing is we added to it very, very slowly with a bunch of, of like user onboarding calls. We had it in private beta for a while and then we would onboard people into it one by one and then just simply, just like classic iterative product development. One thing that really surprised us actually with all of this was that people are really willing to go on a like quite a long self education journey with these tools. And so I think like classical thinking has been this whole sort of don't make me think and sort of like reduce friction. Reduce friction. But what we're seeing is that people are very stimulated. People can do things that they never could do before. They're doing things that they could never even imagine before. And actually what's happening is that as soon as people get a taste of like, wow, I can actually do this for Myself, they're willing to go on this entire self education journey of let me learn what about databases? Even like, I don't know what one is. Like, I'm going to Google what is a database and then I'm going to sit on YouTube for like two hours learning about what like a managed backend is or whatever it might be. In terms of where we landed, we had these early indicators that people felt very empowered by being able to create full stack. And we also had this early indication that people were willing to educate. And so in the end we actually cared less about what is the technical abstraction and what is jargon, because jargon is quite individually dependent depending on your domain knowledge. And so I think we struck an okay balance so far of kind of just explaining what it is and the value of it and then trying to hold your hand at sort of key moments. But I think we can do a lot more. We're kind of riding the middle at the moment of just like trying to be a little bit technical, but not too technical technical.
- [31:58]
Rid
It makes sense what you're saying about like the getting a little taste because that's was my experience. Even reflecting back on the journey, it's like you get so much value and you're, you're so interested in that first like 10 seconds, like the first time you generate anything, you're like, holy smokes, that was crazy. Let's do it again. And right away you're very motivated to keep going, I guess. And I don't know, like I blinked and the next thing I'm like reading Twilio docs cuz I want to hook up the API, you know, like, I had no intention of doing this, but it's addicting. You know, it's just fun, fun to try to solve the next problem and then the next problem. The next problem.
- [32:31]
Nad Chishti
I think fun is the word. Like we, we think a lot about flow. As designers, we know this, right? Like, you know when you're in flow and you know when like you almost lose all concept of time. One of our kind of driving philosophies is just trying to figure out what promotes and what detracts flow. When we think about things that way, it's actually quite surprising how many technical concepts or how many technical abstractions, you know, might initially seem like they're, they're quite domain specific. But if they're promoting flow and if they're empowering you as you build, it's still fun. And so that feels like a good outcome for us.
- [33:02]
Rid
You talked about promoting flow speed to Feedback. It's clear that you do have these philosophies as this team that are guiding you. And so are there any other that we have not talked about that are kind of serving as like a North Star for you as a designer?
- [33:16]
Nad Chishti
One thing we talk about a lot is clock speed or this idea of clock speed. We think that we build the best products by learning as much as possible always. And we think we learn as much as possible by kind of having an uncomfortably high clock speed, like individually and as a team. And so we try to challenge ourselves on how long do we take to make a specific decision or does communication need to take as long? Like, rather than arriving at a conclusion and being like, let me sense check that with someone else and put in a meeting for next week. What stops you from making a 10 second version of that decision on the spot instead? And so we challenge ourselves on clock speed a lot. I think that's paid dividends when it comes to our overall learning on our capabilities and what we can build. It comes with the kind of trade off that sometimes that can come in the face, that scrappiness can come in the face of quality. But so far that's basically given us a super powerful product that people love with really, really great fit. Where I'd rather have the sort of quality challenge of quality can always be better and with some fit rather than the other way around.
- [34:19]
Rid
Is there an example where you've prioritized clock speed and just pulled the trigger on a decision versus turning it into this debate interaction?
- [34:26]
Nad Chishti
Honestly, probably every major feature that we shipped, so the visual edits for example, I mean, for sure we had this philosophical debate on layers, panels and let's see if we have a shot at making these legacy. But it was also like, okay, there's one path where we simmer on this for days to weeks more. There's another path where we just remove it from the conversation and we can get new feedback uncomfortably fast. And so I guess we're trying to embrace that uncomfortable part of uncomfortably fast.
- [34:59]
Rid
I feel some conviction because I've been using the word simmer a lot lately as I work on a new product. Let's talk about your personal process a little bit more. When are you reaching for lovable in your own design journey?
- [35:12]
Nad Chishti
So in general with design, I always start kind of big to small. And so I'm very much like, okay, like hierarchy first information within that and then content design. And then, then once I'm happy with content, then lay it out. And so in terms of my design process, I Try to ask the big questions first. I try to figure out what I want from a content perspective. And then depending on what the feature is, I'll either reach for Figma to figure out the best way to lay out the information, or if it's interactive. Like these days, I just go straight for Lovable. I think where I was getting frustrated by design tools was just the whole pool noodling of needing 500 art boards with the most perfect sort of orchestration in order to build what I wanted. Whereas now I just generally will design maybe the first state in Figma and then punch out to Lovable and then just make it interactive from there. And so I'll kind of jam with the AI to work through, like live prototypes.
- [36:07]
Rid
Can you talk a little bit about what jamming with the AI looks like for you? And any lessons or tips that you've picked up along the way to help designers become better at prompting?
- [36:15]
Nad Chishti
I would say treat AI as a creative partner. It's surprisingly good in any other creative discipline. Like, experimentation is always good. Like actually a of structure is where you find, you know, where you find novel solutions. And so rather than thinking, okay, I need to have the perfect structure and the perfect idea and I need to sort of translate that for this AI to then execute on what I think is in my head. Just be like super open and like just jam with it the same way. I don't know if you're like a musician and you're just jamming with someone, just go for it and things will just happen. Like a photographer doesn't try to manipulate light perfectly. They set up shot and the shot is in the right direction, but nature provides some light and the photons bounce around in an unexpected way. And then at some point something beautiful happens and that's when you're like, okay, I've got it. And just treat designing with AI the exact same way. I'd say, obviously you need to exercise your own taste and you need to apply your own filter on everything that happens. But I'd say don't expect it to be perfect and don't try to be perfect, just go with it.
- [37:16]
Rid
Do you have an example of when collaborating with AI took you to a place that was a little bit unexpected, but it turned out pretty awesome?
- [37:22]
Nad Chishti
Happens all the time with content design, I'd say. And like, sometimes the hallucinations are actually really, really great for this as well, especially with like naming features. So definitely more on the content design front. I'm trying to think if there's anything interesting on the visual or interaction side. Yeah, actually one, one thing that I'd really recommend, like anyone to do is pick up a. Pick up like an AI powered design tool, like a tool, like lovable, and actually just feed it different art styles. Build a UI that you like. It's going to look probably a little bit vanilla to begin with, but as soon as you start to think about adding personality, actually just ask it to style things for you and almost act like an artistic creative director and go crazy because these models are trained on the entirety of human knowledge. And so if you say something like make it more art deco or make it more Bauhaus or whatever, don't stick to the UI styles that you see on Twitter of, I don't know, glassmorphic or whatever. Like think of anything visual and they do a surprisingly good job just treating it as a creative collaborator. Not just on the functional parts, but everything else. It can be super rewarding.
- [38:29]
Rid
I love that. You're totally right. There's a lexicon of adjectives that relate to UI and I almost exclusively use those when I'm interfacing with AI about like a set of visuals. That's such a great piece of advice. Just breaking out, like, I can say anything, I can say anything and it's going to generate something. So I might as well use that as a way to break out of the box of what I'm capable of imagining. Imagining.
- [38:52]
Nad Chishti
When we were working on, we didn't ship any of this, but when we were working on like auto generating color scales, like, I was feeding in a lot of. I'm a big, like cinematography nerd. So I was feeding in like a lot of stills from some of my favorite films and some of my favorite cinematographers. And so you could even be like, I don't know, like, build a UI and then be like, hey, like, here's a shot from like, like my favorite, like Wes Anderson flick. And like, let's make this feel more Anderson. And like, it does a surprisingly good job.
- [39:18]
Rid
How much of a role as a designer at Lovable are you playing in shaping the interactions that users are having with the AI? The specific words that are coming out, any like system prompt stuff versus the interface itself. Is that part of the role for you?
- [39:30]
Nad Chishti
I started out on the interface side, so of course, like the first problem to solve was like, let's put together, like our UI that people are going to interact with. But you kind of quickly realized that, I don't know, setting the line height of the AI response isn't really designing AI, like what people do when it kind of is. So yeah, for sure. Like we have, we have a. It's pretty, I'd say it's pretty meritocratic internally in terms of the way that we build our AI. Everybody in the company can edit like how it thinks and how it works. Actually most people in the company contribute to it and even non engineers. And so one of the people who works on our support, like they're contributing to the core AI like all of the time. And they're sort of closing the loop from what would typically be a customer service problem to just feeding back to the AI to just improve things on the spot. And we have that feedback loop there as well.
- [40:21]
Rid
It's not the first time I've heard it where people on support or growth teams are contributing back to the core system prompts. And I think it's a really interesting trend where I was kind of mentioning this earlier. Companies fall into two buckets right now. You have companies that are adapting to AI and you have companies that have been birthed from AI and AI and its capabilities are at the center of how they work and how they operate, how they think. Think. I'm wondering how much that resonates and if there are other examples where you can kind of point to the way that the org operates at Lovable that is distinct and unique from what you've experienced in the past.
- [40:58]
Nad Chishti
Every bit of kind of people infrastructure that we've got used to creating. Like I think it's up for challenging like in general and like I don't, I don't mean to be like too alarmist with that. It's just the like the reality of kind of what, what I'm seeing and not, not just across Lovable as well by the way. Like there's other companies also much larger that are kind of doing this sort of AI first pivot and kind of seeing this as well. So like in Europe, like Klarna quite famously is doing this and also Intercom as well have been pretty public about doing this kind of pivot. I think entire functions can collapse and merge, which is really interesting. At my last company we had so many people that sat between product and customers where they were almost just different flavors of the same problem. So we would have product managers and researchers and solutions architects and pre sales engineers and account managers and this kind of laundry list of people where the job was like know the product and know the customer, but solve a different part of different parts of this flow. And so like that's like a really good example of like, okay, you could Collapse almost all of that down to either one function or like, very few people. And I'm seeing that across the board, like entirely. And so we have the benefit as a new company of like, rather than having to pivot to the new world, we can just start. But I for sure think it's the future and kind of where things are going.
- [42:15]
Rid
Hey, it's Rid. I'm constantly asked about my favorite product, so I want to take just one minute and give you a quick rundown of my stack. Destin is how I ship design changes without having to code. Framer is how I build my websites. Genway is how I do research. Jitter is how I animate my designs. Play is how I design and prototype mobile apps. Visual Electric is how I generate all of my imagery. And Raycast is my short shortcut every step of the way. Now I've hand selected these companies to partner with me so that I can do these episodes full time. So the best way by far to support the show is to check them out. You can find the full list@dive.club/partners. Okay, now on to the rest of the episode. How does the value proposition of design shift in that new world?
- [43:04]
Nad Chishti
I mean, the obvious thing that everyone says is that, you know, like, taste is going to be paramount. I think that's 100% true. The other thing that I find really interesting, and I've, I've thought about this for years and I'd love to get your perspective as well, is I find it interesting when different industries use the term design in different ways. For example, I'm a huge Formula one nut and I love like motorsports and I also love like aerospace. The chief, most engineer in those industries is the chief designer. And so like, why is it that all of these other industries, like being a designer, is just so fundamentally different to being, you know, what we call a designer in tech. And so I think we'll see more of those, more of that merger. And so I think design and engineering is quite an obvious one that actually in a lot of ways I think they are two sides of the same coin. And so now with that of AI, I think that can merge in sort of very, very new and exciting ways as well as, you know, cross functionally in other ways like say design and product management. For sure.
- [44:01]
Rid
Yeah, that was the piece that I was going to add on where even going back to what you were talking about in the very beginning, where you're sitting in between the founder and the market, that's design at a very high level. It's Positioning as design? No, how do I want to design the shape of the entire product offering? And how does that fit into the different opportunities that I'm seeing? And I'm excited. In a world where, yeah, we can even further increase the speed of iteration and more people will capable of shipping and getting something out the door. That part of design is exciting to me too, where it's like the very strategic, strategic product level design, market level design. It's exciting to think about.
- [44:39]
Nad Chishti
Yeah, 100%. And I think it's all to play for as well. At the moment. It's maybe like easy to forget that tech is quite young. Like, we've literally gone from like static websites in the 90s to like Web 2.0 to like, here we are. And there's a lot of like, management practices or a lot of like company structure. Things that we just sort of made organically. The way we've arrived at organically isn't because it's the most optimal design. It's just because it's kind of just what happened. It's. And I think the other thing that's really easy to forget is that one of the reasons why I love tech is that there's almost no barriers to what you can do. But the other side of that is that we also end up with bad managers. Like, frankly, like, we end up with people who are like, not trained or they maybe like shouldn't be in that position. And this also extends to founders in a lot of way as well. And so it means that we build functions and entire companies around quite imperfect or suboptimal small structures as well. I think all of it's up for play at the moment. Whatever we've considered like, traditionally of like product design and engineering and these formal lines between them, like, I think we can blur, if not eradicate as much as possible.
- [45:43]
Rid
Can we speak to someone who's listening, who is excited by everything you're saying? Conceptually it makes sense and yet there's still this chasm that they're having to cross to figure out, like, how does a tool like lovable fit into my everyday workflow? Working at a company that, you know isn't pushing the boundaries of AI, they're probably still working on that SaaS. And it's like, okay, like, but, but where does a tool like lovable sit into my process? And how can I even think about using it to push my craft forward?
- [46:12]
Nad Chishti
There's also the reality that it might not, might just not be the fit as well. So there are other tools. So for Example, we don't support importing. If you have an existing application, you can't bring that in and then edit it. But what I would say is coming back to this idea of like constant learning. You learn so much by shipping and so end. And so if you are non technical, as in you're not an engineer who can develop, build, deploy, maintain full stack applications, you can do that now for anything you want. And so just even the sheer act of solving something that feels like a small problem to you, you can build it, you can ship it, you can give it to people and you can learn from it. And that in itself I think is incredibly rewarding. You're going to learn things and you're going to reveal more about yourself. Even I would encourage people to play with it from that perspective. It's just, and don't even if you're not, I don't know, commercially minded, even if you're not thinking like, oh, I want to start my own startup or I want to do X, Y and Z just it for fun. Like the same way that you would, I don't know, make a loved one like a home cooked meal. Just make, make a loved one an app and just, just see what happens.
- [47:17]
Rid
I started making birthday cards in Lovable. I made one for my dad where it's like I, I can deliver it, I print, I make a QR code code and like that's the card and then you scan the card and then it's a custom website with like little fun little animations and it's like, why not? It's fun.
- [47:33]
Nad Chishti
And do they like them as well?
- [47:34]
Rid
Oh yeah, it's great. It's totally unique, totally unique. It doesn't even take that much time, you know, but it's just a fun way to be creative. I, I've started lowering the bar basically for what I can make and I, I, I made like a, my first foray into Supabase was a Super bowl betting game where I asked like 20 questions for the most popular super bowl prop bets. And then everyone filled it out and then it would generate like an, a dynamic leaderboard and you could see who got the most questions right and we could all watch together and refresh on the page and it's like, it was amazing. Like I would have never been able to do that before. It took me probably two and a half hours and it was some of the most fun I've had in months.
- [48:12]
Nad Chishti
And I love, I love those two examples as well because I'd actually blocked this out of my memory. But Going back almost like 10, 15 years, I used to send greeting cards online to people because that was a fun thing, but they were always riddled with ads. They were horrible. And so, like, it's so good. But now you can just build something completely bespoke, it's yours, and we just don't have to think about that.
- [48:33]
Rid
All right, so we were touching on some of the, like, AI native or everything's up for grabs. How are you then reacting to that as someone who's, you know, you kind of have this blank slate of a design org to assemble. How does that impact the types of design designers you're looking for, the traits that you want to prioritize, and even the way that you dream about how you all might work in the future.
- [48:57]
Nad Chishti
So I think one of the things that's unique at Lovable is that we hire probably more generalists than companies do. Generally, we actually most of the team. Well, maybe not most of the team. A good portion of the team is ex founders, I'd say. One thing that the entire team has in common is that everyone's really high agency. And so generally people have had, like, I don't know, slightly unusual backgrounds in some way, shape or form. And so, for example, Henrik, who runs our social media accounts, he kind of got into social media because he used to run an Instagram account for the Office, like the US Office, that went completely viral. Hundreds of thousands of followers. He started, like, monetizing it as like a teenager with like, merchandise and stuff like that. And so he just, like, really deeply understands social media and has this kind of maverick streak about him on the design side, like, where we're basically thinking about things the same way of, like, hiring people who are like generalists, very high agency, don't necessarily think too much about, here's the constraint of the box that I fit into. And also in some way have this kind of maverick streak of just figuring things out for themselves.
- [50:03]
Rid
I love the culture of former founders. Like, that's about as fun as it gets in terms of just like generalists. Everybody's wearing all the hats. We're all just figuring this out together. I gotta imagine this probably makes for a fun place, place to work.
- [50:14]
Nad Chishti
The nice thing is that especially as a designer, design is not waterfall here. So it's not like, here's the perfect designs. I've thought through every single edge case. Here you go. It means that we can collaborate and calibrate on kind of the most important parts, which is what problems are we solving and why and what's the overall philosophy and really nail out more of the happy paths together. So that's super rewarding in itself, but also just working with a lot of high agency individuals. Everyone's just super smart and super driven. And so the opportunity again for learning is just huge, which is great.
- [50:47]
Rid
Any other challenges or considerations that you're experiencing when designing for AI products specifically that maybe someone who's not in this type of field would be unaware of?
- [50:58]
Nad Chishti
Yes. I think one of the things that really, really surprised me is that there's a completely kind of symbiotic relationship between the end user, the model, the context that the models have, and also how you build around the models with the actual architecture of your own application as well. And this needs to work really, really well across the whole stack. And so for lovable users, if you're trying to add a new feature to your app, the way that we handle that is through one entire code path and one entire model path, which is really different to if you're trying to fix a bug. One failure would be if we treated these things as technical problems, where it's more like, oh, the AI engineers are going to figure out what context the AI models will have in these specific instances. And wherever we've succeeded, it's actually been a user experience problem. It's been, okay, what is the user trying to do in that exact moment? What is their goal even before they launch the app? How are they breaking down tasks in terms of how big they are or how small they are, and how are they navigating through that? I think the best AI products that I've used or the best solutions really nail this marriage of user goals to the individual implementation. And so I was really surprised at how symbiotic all of that is. And so actually, whilst we had a wait list, so we had a waitlist for around six to nine months before we did our kind of big public launch. We did like three major RE architectures where we almost deleted the entire app and started out again. And it's because we weren't kind of happy with the core user flow and this sort of core flow that users were going through as they were iterating on their apps. And we couldn't just edit the UX on one hand and think about AI on the other. We had to think about these things completely together.
- [52:40]
Rid
We've covered a lot of ground. Any parting ideas or advice or learnings that you want to leave people with who are interested in how you all are working as a team, or even just what it's like to start to tinker and explore with AI, I'd actually.
- [52:56]
Nad Chishti
Love to learn from others as well. And so I think there's so much up for grabs right right now that there's a few key products out there that are doing really amazing work. And I'd love to sort of figure out which are the best AI products out there right now and, like, what is getting everyone else excited. Anything where there's like an interesting intersection of, like, users can actually behave in a different way now, thanks to products existing.
- [53:17]
Rid
We'd love to hear about anything that's already on your list that you're taking inspiration from.
- [53:20]
Nad Chishti
I think Granola's a really, a really, really interesting one because the thing I love about Granola as well is that the UX is so minimal. It's like four or five small decisions made really, really well and then that just empowers a bunch of different use cases. And it also forces you to change in a lot of ways. Like, Granola's turned how I think about note taking, like, upside down. And I think actually historically, like we've always said, like, reduce friction and sort of meet users where they are, whereas with AI, we kind of need to invert that. And it's not about meeting people where they are, it's about giving them superpowers. And so Granola is one of those tools where I feel in a lot of ways like I have super house.
- [53:58]
Rid
Well, I've definitely felt that about lovable too. I mean, even just like using the mobile site in a cafe, like, it just has become the new game that I play on my phone. So I appreciate all of the work that's went into it and you taking the time to share a little behind the scenes with us today.
- [54:13]
Nad Chishti
Great. I know, yeah. Real pleasure to meet and to talk.