Skip to main content
How I AI

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

32 min episode · 2 min read
·
Yana Welinder

Episode

32 min

Read time

2 min

Topics

Relationships, Startups, Design & UX

AI-Generated Summary

Key Takeaways

  • Prompt as product spec: Develop a detailed master prompt that defines every dimension of your creative output — silhouette, fabric behavior, construction details, movement, and sound. This reusable "fashion prompt" functions like a PRD: it produces consistent AI outputs and would give a human collaborator the exact same information needed to execute the work correctly.
  • Model selection for creative fidelity: ChatGPT's ImageGen 2.0 outperforms other image models specifically for design work because it follows source sketches closely rather than defaulting to aesthetically polished but generic outputs. For fashion design, sketch adherence matters more than photorealism — other models produce beautiful images that look like prior runway work, not original designs.
  • Computer use unlocks specialized software without learning it: Codex paired with computer use can operate industry-specific tools like CLO (fashion pattern software) and 3D modeling programs without the founder learning those applications. This approach generates usable output files — CAD files, pattern files — that Codex alone cannot produce through code generation.
  • AI as parallel vendor and research engine: Use deep research mode to identify and rank manufacturing partners, then chain directly into drafting outreach emails and queuing them in email tools like Superhuman for human approval before sending. This compresses vendor sourcing from days of tedious research into a background task completed while doing other work.
  • Pattern-making remains the unsolved bottleneck: Getting AI to generate accurate garment patterns from original designs is still unreliable. Welinder runs human pattern makers and Codex simultaneously, treating it as a race to see which produces the most accurate result fastest — a practical hedge strategy for any workflow where AI output quality remains inconsistent.

What It Covers

Solo founder Yana Welinder built Yanabana, an AI-native fashion brand, using ChatGPT, Codex, and computer use as her entire technical team — replacing engineers, pattern makers, and production researchers — demonstrating how AI enables a single creative founder to execute a full fashion business end-to-end.

Key Questions Answered

  • Prompt as product spec: Develop a detailed master prompt that defines every dimension of your creative output — silhouette, fabric behavior, construction details, movement, and sound. This reusable "fashion prompt" functions like a PRD: it produces consistent AI outputs and would give a human collaborator the exact same information needed to execute the work correctly.
  • Model selection for creative fidelity: ChatGPT's ImageGen 2.0 outperforms other image models specifically for design work because it follows source sketches closely rather than defaulting to aesthetically polished but generic outputs. For fashion design, sketch adherence matters more than photorealism — other models produce beautiful images that look like prior runway work, not original designs.
  • Computer use unlocks specialized software without learning it: Codex paired with computer use can operate industry-specific tools like CLO (fashion pattern software) and 3D modeling programs without the founder learning those applications. This approach generates usable output files — CAD files, pattern files — that Codex alone cannot produce through code generation.
  • AI as parallel vendor and research engine: Use deep research mode to identify and rank manufacturing partners, then chain directly into drafting outreach emails and queuing them in email tools like Superhuman for human approval before sending. This compresses vendor sourcing from days of tedious research into a background task completed while doing other work.
  • Pattern-making remains the unsolved bottleneck: Getting AI to generate accurate garment patterns from original designs is still unreliable. Welinder runs human pattern makers and Codex simultaneously, treating it as a race to see which produces the most accurate result fastest — a practical hedge strategy for any workflow where AI output quality remains inconsistent.

Notable Moment

Welinder described a garment directly inspired by Ruth Asawa's wire sculptures — a dress she conceived without a sketch, purely from repeated exposure to the artist's work in a single day. The piece requires 3D printing and was considered previously unmanufacturable, now executable by one person with no engineering background.

Know someone who'd find this useful?

Episode Transcript

Normally, 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. Literally, my technical cofounder. 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. 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 the silhouettes, the proportion or the volume of 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. The 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 humans and AI in parallel. So I I am working with human pattern makers codex and just saying who's gonna get to making my thing fastest. Welcome to How I, AI. I'm Claire Vow, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I have Jana Wallander, and she is building an AI native fashion startup. And she's gonna 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. Most teams end up piecing that together themselves. So instead of building the products 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/howiai to start building for free. Yana, thanks for joining How I AI. I'm an art and fashion girl. 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 …

Get the full transcript (6,013 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all How I AI transcripts →

You just read a 3-minute summary of a 29-minute episode.

Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

More from How I AI

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Startups & Product Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into How I AI.

Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime