How a solo founder used Codex and ChatGPT to launch a fashion brand without engineers | Yana Welinder

0:00Normally I would hire a technical team, like engineers. I didn't, right? I sort of just came to Codex and asked it to build the website. The idea is to use AI really anywhere in the process where that makes sense. It's literally my technical co-founder.

0:15Yana Welinder:There's so much you couldn't do before, practically from a cost perspective, even from an execution perspective, that is now totally possible. And so you can like unlock your creativity in a way that wasn't possible before. It really does unlock so much creativity. A lot of my designs start from a hand-drawn sketch, but the other piece of this is I sort of developed the fashion prompt that's behind it, and it describes a lot of sort of what goes into garments. So it has like the silhouette, the proportion or the volume of the dress, like kind of like the fabric, how it flows, how it behaves, the construction details, how it moves, even how it sounds.

0:57The other piece that is still unsolved and I'm sort of still banging my head against the wall is to get it to create patterns based on my design and there I'm kind of running human skin AI in parallel so I am working with human pattern makers codecs and just saying who's going to get to making my thing fastest

1:16Yana Welinder:Welcome to How I AI. I'm Claire Veva, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I have Yana Wellander and she is building an AI native fashion startup. And she's going to show us how AI can intersect art, creativity, and real world production, and why computer use plus software means SaaS really isn't dead, at least not yet. Let's get to it. This episode is brought to you by Merge. Building an AI product is one thing. The hard part is everything around it. Connecting to the tools your team and customers rely on, letting agents take action with the right permissions, and keeping everything reliable and cost efficient once you're in production.

2:01Yana Welinder:Most teams end up piecing that together themselves. So instead of building the product you actually care about, you get pulled into integrations, permissions, routing, and all the infrastructure underneath. Merge is the infrastructure layer for production AI. It connects to thousands of tools, gives agents secure ways to act inside them, and optimizes model routing and spend without you building or owning any of it. OpenAI, Dropbox, and Ramp already use Merge to move fast and build AI right. Visit merge.dev slash howiai to start building for free. Yana, thanks for joining How I AI. I'm an art and fashion girl.

2:43Yana Welinder:You know this. There are like five of us AI, art, and fashion girls on Twitter. And we all find each other. But I am one and I love what you're working on. So immerse us in this new thing that you're working on. And then we'll talk about how you're using AI in this really unique fashion. Cool. Yeah, I'm so excited to be here. Thanks for having me. I am building this AI native fashion brand. And the idea is to use AI really anywhere in the process where that makes sense. So obviously heavily in the design and production process, but also it's literally my technical co-founder. And so I that's that's what I use it for.

3:25Everything.

3:26Yana Welinder:And can you show us like it's probably hard for people to conceptualize what like an AI powered fashion brand looks like. Can you just like show us a little bit of kind of like some of the stuff that you're working on and then we can get into how it actually how you actually got there. So this is Yana Bana, the fashion brand. And you can kind of see like everything here is built with the eye. And so you have some of the different garments that I designed. And I'll show later that like different ones start from different, like from different inspiration, from different points. And so oftentimes I start from a sketch.

4:02You can see that when you hover over some of these. So I start with a hand-drawn, humanly, manually, you know, old-school hand-drawn sketch. And then I use AI to turn that into different types of fashion collateral and kind of technical specs and everything along the line to ultimately get to a garment. And I kind of use AI for all the things to visualize it, to create photos, to create videos of some of these garments. A lot of them kind of allude to different like technical, you know, computer things in a lot of ways, because I feel like that should be really part of the theme. It should be obvious that that what it comes comes from.

4:44And so the fabrics will use a lot of kind of the punch card, like computer punch card patterns and things like that so that you can really see that. than the other way in which it sort of appears. As you can see, for example, for this like post keyboard t-shirt, which I'm wearing myself right now, it also is alluding to the fact that now we are not going to be using keyboards and a lot of this stuff. But can we now give it a second life, essentially, and make sure that it's like obvious the world we live in and the world we're entering.

5:20Yana Welinder:And I just want to pause because when I first saw this, I was like, what a fun like little art project. Like I once made this like I vibe coded this app, which was Anthropic as an anthropology website because I thought it was very funny. But you're actually bringing these designs to life. Like you are actually wearing this keyboard shirt, which is super cool. And so what you know, I hear a lot of people who are in the creative fields be really fearful of AI because I think it is like displacement in a lot of ways. Like let's let's all be honest here. There's like videos and sketching and all sorts of stuff that AI can do.

5:57Yana Welinder:And yet, if you step on the other side of this like post-keyboard future, there's so much you couldn't do before, practically from a cost perspective, even from an execution perspective, that is now totally possible. And so you can like unlock your creativity in a way that wasn't possible before. So I want you to show us step by step kind of what goes into creating a garment like this, creating and imagining a design like this, and then actually getting it to production and getting a website like this up. I think you're absolutely right that it really does unlock so much creativity. A lot of my designs start from a hand-drawn sketch.

6:39But the other piece of this is I sort of kind of developed this technical, it's essentially a stack, but for the purpose of visualizing what it looks like, I have this sort of set up as just like the fashion prompt that's behind it. And it describes a lot of sort of what goes into a garment. So it has like the silhouette, the proportion or the volume of the dress, like kind of like the fabric, how it flows, how it behaves, the construction details, how it moves, even how it sounds. I can show in one of the pieces, it kind of has this really interesting kind of sound as you're walking in the dress.

7:25and I take all of this and put it together in essentially kind of when we, if we take it out of my flow, you can see that it's at the core of it, there's sort of this prompt that we could take and plug into chat GPT. And oftentimes when I'm working with this, I will also have an actual sketch of what I want and I sort of am then defining this in addition to the sketch, but just for the sake of us kind of playing in real time. I just thought it'd be cool to just use prompts to start with. So here we have a sharply tailored waist defined jacket with exaggerated shoulders and blah, blah, blah, right?

8:09So now we're putting this in. Oh, I should have told it to make an image, but maybe figure out to do that. Yeah, there we go. Sometimes it's smarter than you think, even on instant. And so now it's going to generate an image. And oftentimes this will give me kind of like a product project photo but usually what I then want to do with this is to then take it to kind of the next level and I will have very specific types of like collateral that I want to get out of it so once we have this ready I will ask it to generate a Vogue style runway photo oh there we go so this is kind of like the product photo of this so it has these exaggerated shoulders the waist a lot of kind of the stuff that I asked it to.

8:53And if I had a specific sketch, it would really adhere to my sketch much more so than what was in the prompt. But then if we go to here, we say, like, now make it into a Vogue style. Can you tell that I normally do not type anymore? And so I usually just use voice for all these things. It's just like so hard.

9:16Yana Welinder:It's easier for our podcast guests um when you use voice because they don't have to imagine what you're typing so she's you know you're typing make it into a vogue style photo of a model walking down the runway in this outfit and so then i kind of just like iterate on this and there's um i go to to photo um that's a runway photo then i go to like a influencer photo and you kind of see this from a lot of different angles and also iterate on it based on kind of what you're seeing. Now make it red, make it shorter, make it longer and all those different things. But I usually just start from a specific point and then iterate from there.

10:02Yana Welinder:I have a question for you, which is why ChatGPT and why ImageGen2 as the model you're using? There's a lot of ImageGen models out there. Why that particular one? Yeah, so I've done a lot of experimentation with lots and lots of different image models. And what I found was ultimately Nano Banana and Image 2.0, really Image 1.5 was already pretty good at this, are the best at following visual directions. And often I'm not doing this. Usually I'm sort of, as I mentioned, I'm mostly giving them a sketch that I want them to turn into a picture. and what image 1.5 did better than Nada Banana and images Chachupiti images 2.0 does even better is it really well follows the sketch.

10:57In fact, it follows the sketch sometimes a little bit too precisely and so you get something that doesn't look like fabric anymore and you have to kind of be like, no, no, no, no, no. You got to like, it's got to flow. This is kind of why I have this very detailed kind of prompting where I tell it how the fabric should flow because otherwise it can get into the mindset of, oh, she really wants it to look like paper, you know. But the flip side though, with all the other image models that I've tried is that they will make it look beautiful and realistic, but it will look very, very different from my design.

11:30And obviously when you're designing fashion, you need it to look new and different. You don't need it to look like the most similar thing that's walked the runway some other time. And that's usually what you get with a lot of other image models.

11:43Yana Welinder:What I love, and if you can go back to your prompt flow, what I love about this is this is just, okay, so people are going to be like, I'm not a fashion designer. I don't have any use for this. What I think is the takeaway here generally for folks is write down your process and write down what a definition of complete or good is. You and I, you know, we're product ladies. Like product people. Yeah, it's a stack. We were like official product ladies. And you need a spec. Like your prompt is a spec. And so if you can put into the effort of saying like, what makes a really good garment? Like what makes a really good photo?

12:21Yana Welinder:What makes a really good illustration? And come up with like five things that you can define for the prompt. You can get a really good output of AI. And then what I love, my friend Zach says, what's good for AI is good for humans. Like, let's just say you had you were going to have a human sketch this out or build this. This is the exact information they would need as well to do a good job. And so whether or not you're doing like fashion illustrations or coding, right, like this at the spec, the PRD matters, people like the spec matters. And so getting forcing yourself to sit down and be a little bit more precise is going to get you that exact outcome that you that you want.

13:00Yana Welinder:And, you know, to be honest, I think that jacket's pretty, pretty rad. I would, I'd wear it. This episode is brought to you by Jira by Atlassian. The teamwork graph in Jira delivers 44 % more accurate agent results with 48 % less token usage. That's a huge difference when working with AI coding agents like Quad, Cursor, Codex, or Copilot. The hardest part of shipping with AI isn't the code. It's the context. What's the right ticket? What did the spec say? What got decided in Slack? The Teamwork Graph pulls all of that from across your entire stack, from Jira and Confluence to GitHub, and feeds it directly to your agents before they write a single line.

13:42Yana Welinder:You assign the work, the agent gets everything it needs, and a PR surfaces when it's ready. No digging, no context switching, no broken flow. Same team, smarter agents. Try it free at jira.dev. that's j-i-r-a dot d-e-v i love it so you've created this this image i i also love this idea taking like a core image and iterating it through like runway photo influencer photo like you know standalone catalog like photo product product shot what do you do next like what's the next part of your flow? So a lot of what I do is kind of iterate on it. And so I have this like, you know, change the color, change the, you know, change the fabric.

14:34And so I have kind of a lot of these different ways to do that. But then the next piece really comes to kind of like, what is the production process? And the production process is going to be very different depending on what I'm doing and so um to give you an idea from one of these so for example I had this uh dress that actually did not come from a sketch it came from I had this one day where I was just being bombarded with Ruth Asaba's um artwork in different places like I went to I went with my son to this like like kids event and there was an exhibit across the street that I like accident like we were just early so we went and watched it and we're like at the SF MoMA and there's like a permanent exhibit there uh he had a piano recital and the church had one of her pieces hanging like literally almost above my head and I was like I keep I don't know and so and so this was this is literally from my phone so I didn't have a sketch right normally I start with a sketch but in this case I was like you know make a photo of a model walking down the runway in a dress inspired by Ruth Asaba's loop-wired sculptures.

15:44And it was important that it had a beige undergarment because otherwise ChatGPT will not, like, it's like, no, you're trying to make me make nude pictures and I don't do that. Very artistic nude picture. No, I don't do that. Actually, I think even here, I tried to make it to remove the sculptures in the background. And I was like, we're sorry, this violates our nudity guidelines, right? This happens all the time. I have to tell you.

16:13Yana Welinder:Quick side. You know what? If I showed up to a date with my husband in this gown, I do not think he would be through. I don't think he'd be like, ooh. It's not quite the erotic. Exactly. It's not nudity. It's not, you know, it's not torn. But here we are. And so this one, right? And I think that a lot of garments you would do, like some garments I will drape, right? Like on the model behind me. Or some garments go into, they become, you create a kind of a pattern. And I have different, some AI processes and some non-AI processes that I've done for patterns. But this garment is previously unmanufacturable.

17:01And so what I, and I ended up kind of taking this and also creating a video of it. This is kind of like, you can see a little bit more of what it looks like. But the next step for this particular garment will be to take it and 3D print it. And particularly these kind of big ball pieces will need to be 3D printed. And so I then went onto Codex and had it help me create CAD files for these balls. So I first prepped it and had it like, I was like, okay, so I made that into sketch. Then I made these pieces into kind of more sketch illustrations. Then it didn't do well. It still didn't do well. We had a bunch of back and forth.

18:00Eventually, it started doing something that was a little bit more similar. I had to do, this is a really, really long process. And then ultimately, I had it using computer use, go and build this in 3D software so that I could create like an.tl file and send off to 3D prints. So that's the process for this particular garment, sort of to 3D print it.

18:22Yana Welinder:I have to, again, like I have to pause because if we're just talking about the creative like generation process, again, this is now a garment that would have been previously like almost inconceivable to make. not just because it was it's difficult to construct but even if you were like of course we could 3d we could 3d print that before ai we could 3d print it after ai that like tedium of creating the cad models was so onerous that like even getting to the point where you could execute on it is is really hard and so i just think this moment of like unlocking the previously impossible whether the impossible was technically impossible, or if it was just like practically infeasible is super important.

19:09Yana Welinder:The other thing that I love, bless computer use, and like codex plus computer use, love you so much. Because I can just be like, I don't need to know how to use this software. Like you go use that software, you do whatever you want. I've gone through this like trough of despair of like sass is dead maybe like we're never gonna touch a website again you know what like agents are really good at pressing buttons so like a software is back for but agents are going to use it it's very very kind of like interesting shift i'm seeing i think that that's a great point and one one fascinating piece is that a lot of these things like for actual end product like a CAD file, Codex, as amazing as it is, is not great at generating a final CAD file if you ask it to do it on its own.

20:00But if you use, yeah, if you use computer use and have it go and do it in a piece of software that's designed for that purpose, and I have both for like actually for 3D printing. And there's a, there's a, uh, uh, fashion, um, uh, software called Clo, um, that I've used as well. And it generates this, like, like it generates patterns and it, and it then fits them on the 3D model. And, and I tell Codex to go and use this software that I haven't learned how to use myself. And it does such a great job at something that it itself couldn't do. So it's sort of like fast in combination with Codex works so well on a lot of these things that don't, and I'm sure it's just a matter of time, but that's where we are today.

20:45Yana Welinder:And I want to do it today. I don't want to wait. I don't want to wait like a year. Yeah. I love it so much. Okay. So you like generate an idea. We've sketched it. We've created images. We've even started to prototype the construction of it. How are you getting something built? And maybe not the gown, like maybe this like keyboard shirt that you're wearing. Like, how are we actually getting this manufactured? Yeah. So for something like that, what I've done, and I do this a lot, is I will go and now this same tool becomes my research assistant. And I ask it to identify, like, you know, find 10 U.S.-based custom apparel manufacturing companies that are similar to the one that I liked, but I want to see if there's other ones.

21:34and then I just like there's a bunch of things I want and I kick off a deep research on extra high so that it's extra high while doing it in not in that way um and um and then and then I get back a bunch of things but usually so so for for a lot of my work I end up like I'm doing something else so I'm like I am kicking off this research and then I go and like drape fabric on on model or I do like I'm I'm on my sewing machine doing prototypes like I'm doing something else and so a lot of them kind of the next steps end up being via voice and so I like in this case I came back to and I was like well do you see the um because I'm talking uh apparel I've been using voice right like the apparel manufacturers that I asked you to find um now can you like put together the emails that I can that you can send off to them but like you may want to make sure that you get my my approval to do that and then i have and then i use browser uh used to let it go into superhuman and like set all of these up for me but i really want to click the send button before

22:44Yana Welinder:just to check its work again like something that is just so tedious and you know if if i was like you're you're you're much more diligent at this than i am but if i was like oh my gosh i had this vision we're gonna make we're gonna make these keyboard shirts they're gonna be amazing and And then I'd be like, how can I make it? And I'm like, oh, I have to like look up vendors. I would just practically give up because it feels so boring. But if you can get that work off to someone, again, like the next step and the next step and the next step. And then what you're going to end up with is this like incredible business.

23:16Yana Welinder:And so I just am like so inspired by people like you that take AI and create like a niche. and like can then take that and build out a business where maybe one wouldn't have been available or possible before. I just think it's super cool. Okay, so you're doing this vendor outreach. You're actually going to get this thing, this thing produced. Side note for all the cool girls out there. When they're ready, we all want one. Put me on the pre-order list. There actually is. I'm going to be that person, but you can pre-order it. Amazing. Perfect. Okay. And then last kind of flow you have is like, again, going back to like pre-orders and how to actually run this business.

24:04Yana Welinder:How are you using it to like be your technical co-founder in all this? that's I gotta say that that's probably like my favorite piece because this I mean apart from the fact that it is like there's so much AI in this but it's basically like an AI native like Everlane or something right like normally I would hire like a technical team like engineers I would have possibly have it I probably I probably wouldn't let's be real I wouldn't have a technical co-founder but like I could have had a technical co-founder I'm a solo solo founder girl like This is just my nature. It's the life. It's the life.

24:41But I would hire engineers. And I didn't, right? Like I had to build this website and I did it. And I sort of just came to Codex and asked it to build the website. There's a lot of pieces here that aren't just like a static website in that it like you can obviously pre-order things. and I could like add Stripe to it, which is like in prior lives have been like a tedious big exercise, but I can go back and kind of show you the Stripe flow. But adding that was just like, you know, a second. I had to create like databases to be able to like track votes as people are voting on these different governments.

25:24So I can decide, kind of figure out which are the most popular ones to bring to life. And so like I had to do that. in an earlier phase of this, I had to create a separate dashboard for me to track the votes in real time. And so I did that. Now I really just like, I just use voice and I'm like, oh, hey, how many votes do I have for this thing now, right? So like, why would I even have a dashboard? So I don't do that. But like, just to kind of show you like the Stripe flow as an example of like, yeah, I came here and I was like, oh yeah use browser to add stripe to my site it was like uh i don't know you're like i'm not signed in i'm like no you gotta sign in in my in my own in a browser i'm like no no no you got go to mine i'm already signed up there and then i was like yeah you gotta do it i'm like no you can do it you know it's like narco for it's like no no you can do it um and uh and yeah this is it and and then I had done um everything's uh added and now pre-order is live this is like a very very fast process and literally whenever I like need to change something about like the the process I can I can really just come here and just like list out all the things I want to I want to change and and it goes off and it finds the result project it um it's it has like finds the repository in GitHub and does all the things.

26:55I would say like this weekend, my son built his own websites using like chat GPT sites. And I'm sort of just like sitting there going like, do I, should I really like, do I want to migrate off of herself? Do I really want like, you know, like, is this, is this a whole new, like now, like now a nine-year-old can have his technical co-founder like do this or like build, build a company for him. Right. Like just, it's,