Skip to content
How I AIHow I AI

The internal AI tool that's transforming how Stripe designs products | Owen Williams

Owen Williams is a design manager at Stripe who built Protodash, an internal AI-powered prototyping platform that lets designers and PMs create high-quality Stripe dashboard prototypes without writing code. What started as a bundle of Cursor rules and React components evolved into a full web-based prototyping studio that runs in dev boxes, complete with design review modes, variant testing, and AI-powered iteration. Surprisingly, PMs now use Protodash just as much as designers, fundamentally changing how Stripe approaches prototyping, design reviews, and engineering handoffs. *What you’ll learn:* 1. How Stripe built an internal AI prototyping tool using Cursor rules, MCPs, and their design system 2. Why “blurple slop” happens when designers use generic AI tools—and how to fix it 3. The architecture behind Protodash: React router, design system components, and MCP integrations 4. How Stripe prototypes in dev boxes so designers never have to worry about local setup 5. Why “demos, not memos” transformed Stripe’s design review culture 6. How Stripe built design review modes, variant testing, and AI annotation directly into your prototyping tool 7. Why internal tools don’t need to be production-grade to be transformative *Brought to you by:* Celigo—Intelligent automation built for AI: https://celigo.com/howIAI Cursor—The best way to code with AI: https://www.chatprd.ai/howiai *In this episode, we cover:* (00:00) Welcome and intro to Owen Williams (02:19) The “blurple slop” problem with AI design tools (03:50) Protodash: an internal vibe-coding tool for Stripe prototypes (05:26) Why an engineering background helped Owen lower the bar for designers (07:55) The Cursor rules that taught the Stripe design system (09:04) Running prototypes on dev boxes vs. locally (10:30) “Demos, not memos” and rewiring design reviews at Stripe (14:50) Building Protodash Studio: a browser-based wrapper for prototyping (19:04) Live demo: variants, line charts, and remixing prototypes in browser (21:02) Self-testing prototypes that take screenshots and check their work (23:20) Multiple variant features (26:08) The annotate-for-AI button for in-canvas feedback (27:21) Design review mode: comments, summaries, and AI follow-up (29:39) Why building internal tools beats buying off-the-shelf (32:50) PMs as the surprise power users of Protodash (35:20) Live demo: a Black Friday/Cyber Monday pet store dashboard (42:03) Lo-fi modes, monospace fonts, and “Comic Sans for WIP” at Shopify (44:45) Quick recap (45:35) The Radar prototype that changed engineering handoff (49:08) Lightning round and final thoughts *Blog & detailed workflow walkthroughs from this episode:* Stripe’s Owen Williams on Killing ‘Blurple Slop’ with an Internal Prototyping Studio: http://chatprd.ai/how-i-ai/stripe-owen-williams-on-buildling-internal-prototyping-studio ↳ How To Connect a Design System to an AI Code Editor for High Fidelity Prototypes: https://www.chatprd.ai/how-i-ai/workflows/how-to-connect-a-design-system-to-an-ai-code-editor-for-high-fidelity-prototypes ↳ Streamline Design Reviews with an AI-Powered Prototyping Studio: https://www.chatprd.ai/how-i-ai/workflows/streamline-design-reviews-with-an-ai-powered-prototyping-studio ↳ Build a Personal AI App to Track Purchases and User Manuals: https://www.chatprd.ai/how-i-ai/workflows/build-a-personal-ai-app-to-track-purchases-and-user-manuals *Tools referenced:* • v0: https://v0.app/ • Cursor: https://cursor.com/ • Claude Code: https://www.claude.com/product/claude-code • Claude Design: https://www.anthropic.com/news/claude-design-anthropic-labs • Figma: https://www.figma.com/ • Stripe Radar: https://stripe.com/radar • Balsamiq: https://balsamiq.com/ *Where to find Owen Williams:* X: https://x.com/ow Website: https://owenwillia.ms/ LinkedIn: https://www.linkedin.com/in/owenpwilliams *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Owen WilliamsguestClaire Vohost
May 4, 202654mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Stripe’s Protodash makes AI prototypes realistic, shareable, review-ready fast

  1. Stripe designers found off-the-shelf AI design tools produced uncanny, off-brand “blurple slop” because they lacked awareness of Stripe’s Sail design system.
  2. Williams built Protodash as an opinionated prototyping starter kit (React scaffold + Sail components + MCP integration + Cursor/LLM rules) that reliably generates Stripe-native dashboards and flows about 90% of the way.
  3. Stripe’s devbox infrastructure made prototypes easy to run and share via URLs, enabling “demos, not memos” design reviews where stakeholders click through real interactions instead of viewing slides.
  4. Protodash Studio extends the system into a browser-based experience with embedded LLM chat, variant generation, self-testing via screenshots, and in-canvas annotation that queues targeted AI fixes.
  5. Internal-tool customization (review mode, summaries, culture-specific workflows) drove adoption—surprisingly with PMs becoming major power users for early exploration, communication, and faster user testing.

IDEAS WORTH REMEMBERING

5 ideas

Design-system grounding is the difference between usable AI prototypes and “slop.”

Protodash improves realism by forcing the model to consult Stripe’s Sail components (via MCP) and follow strict rules (e.g., don’t invent components, avoid Tailwind unless enabled), so prototypes look and feel like the real product.

Lowering the “NPM/terminal cliff” unlocks prototyping for non-engineers.

Williams designed the workflow so designers/PMs need minimal local setup—often just opening a preconfigured devbox and prompting—turning coding literacy into an accessible, AI-mediated skill.

Shareable URLs rewire reviews from presentations to interactive critique.

Running prototypes on dev boxes lets teams review by clicking through real states and flows, reducing reliance on Figma screenshots/slide decks and making feedback more concrete and actionable.

Browser-native prototyping makes iteration faster than editor-centric workflows.

Protodash Studio embeds the LLM into the prototyping environment so users can request changes, generate variants, deploy/share, and “remix” others’ prototypes without switching tools or dealing with repo setup.

Automated self-testing increases trust in AI-generated UI changes.

Having the agent take screenshots, check console/errors, and iterate until the UI matches intent helps maintain Stripe’s high quality bar and reduces time spent debugging AI’s partial or broken edits.

WORDS WORTH SAVING

5 quotes

So like blurple slop is what I would call them and like they do a really, really good job, but they don't know about your design system, right?

Owen Williams

It's sort of been this very transformative thing because all of a sudden I'm sitting in these design reviews and like it, it's so convincing that I'm like, "Is this the real product or am I looking at like something fake?"

Owen Williams

Like, I never want to see a slideshow again. It's like Demos, not memos.

Owen Williams

Like yelling at Claude Code for 18 months.

Owen Williams

As soon as I've sent the first shouty prompt, it's time to, like, reset the, like, slash clear and start again.

Owen Williams

“Blurple slop” and design-system mismatch in AI outputsProtodash architecture: React scaffold, routing, Chrome/nav, Sail componentsMCP server integration for design-system-aware generationCursor rules / prompting guardrails and failure modesDev boxes and shareable prototype URLsProtodash Studio: in-browser LLM, remixing, variantsDesign review mode: comments, summaries, AI follow-ups, handoff improvements

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome