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

August 17, 2026

AI Summary

5 min read

Yana Welinder is a solo founder building an AI-native fashion brand called Yana Bana. She uses AI as her technical co-founder, design assistant, research department, and manufacturing liaison — all without hiring a single engineer. The conversation walks through her end-to-end process, from hand-drawn sketches to 3D-printed garments to a live e-commerce site built and maintained entirely through voice prompts to Codex.

The design spec as a prompt

Welinder’s design process starts with a hand-drawn sketch, but the critical piece is what she calls the “fashion prompt” — a detailed specification that describes silhouette, proportion, volume, fabric behavior, construction details, how the garment moves, and even how it sounds. She plugs this prompt into ChatGPT’s image generation (Image 2.0) to get a visual output. She chose Image 2.0 over other models because it follows visual directions — especially sketches — more faithfully than competitors, which tend to produce beautiful but generic results that look like “the most similar thing that’s walked the runway some other time.”

Continue reading the full summary in the app — free to try.

Read Full Summary →

Free • No credit card required

Listen to Audio Summary Open in App

Never miss an episode of How I AI

Get every new episode summarized in your inbox — free, ~5 minutes to read.

No spam. Unsubscribe anytime.

What you'll learn

1 (00:00) **Opening: AI as the Technical Co-Founder** - Yana Welinder introduces her AI-native fashion brand and the core thesis: using AI everywhere it makes sense, including as her literal technical co-founder.
2 (03:00) **The Brand & Design Philosophy: Yana Bana** - Yana presents the brand and explains how AI transforms hand-drawn sketches into fashion collateral.
3 (06:31) **The Fashion Prompt: A Technical Spec for AI** - Yana reveals her detailed "fashion prompt" that acts as a spec for the AI, describing everything from silhouette to how the fabric sounds.
4 (09:00) **Iterating on the Design: From Product Shot to Vogue Runway** - Yana shows how she iterates a single image through different visual contexts (product, runway, influencer) to explore the design.
5 (14:20) **From Concept to Production: The Previously Unmanufacturable Dress** - Yana walks through the process of creating a dress inspired by Ruth Asawa’s sculptures, a garment that was previously unmanufacturable.
6 (19:09) **Computer Use + Codex: The Secret to Using Unlearned Software** - Yana explains how she combines Codex with computer use to operate specialized software, bypassing the need to learn it herself.
7 (20:50) **Sourcing & Vendor Outreach: AI as a Research Assistant** - Yana describes using AI to find and contact manufacturers for garments like the keyboard shirt.

+ Full timestamped outline available in the app

Show Notes

Yana Welinder is the solo founder of Yana Bana, an AI-native fashion brand built with AI as her technical co-founder, starting from hand-drawn sketches and ending with runway photos, CAD files for 3D printing, and a live Stripe-connected pre-order site—no engineers required. A former product leader, she brings an operator’s rigor to her creative process: her “fashion prompt” is a detailed spec covering silhouette, volume, fabric behavior, movement, and sound, and watching her use Codex plus computer use to navigate 3D design software that’s entirely new to her is a clarifying demo of what today’s toolset actually makes possible.

What you’ll learn:

How Yana uses a custom fashion prompt as a technical spec to get consistent, realistic, on-design outputs
Why ChatGPT Images 2.0 outperforms other models for fashion design
How she uses Codex plus computer use to operate CAD and fashion software she’s never personally learned
The workflow for taking a garment from hand-drawn sketch to product photo, runway photo, and influencer shot in a single session
How she ran vendor outreach end to end using deep research and browser use
How she built a full e-commerce site with voting, databases, and Stripe integration
Why she’s testing human patternmakers and Codex in parallel

—

Brought to you by:

Merge—Connective infrastructure for production AI

Jira AI SDLC—Get your tokens’ worth with Jira

—

In this episode, we cover:

(00:00) Introducing Yana Welinder and Yana Bana

(02:38) Tour of the Yana Bana site

(05:20) The fashion prompt stack

(07:39) Live demo: generating a jacket from a prompt in ChatGPT

(10:01) Why Image Gen 2.0 beats other models

(11:51) The “prompt as spec” principle

(14:02) Iterating the design

(17:12) Using Codex and computer use to build CAD files in 3D software

(20:50) Vendor research, outreach emails, and Superhuman browser use

(23:34) Building the full e-commerce site

(27:40) Quick recap and what’s still hard

(30:05) How Yana prompts when AI pushes back

(31:15) Where to find Yana and how to vote on her garmen