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: - How Stripe built an internal AI prototyping tool using Cursor rules, MCPs, and their design system - Why “blurple slop” happens when designers use generic AI tools—and how to fix it - The architecture behind Protodash: React router, design system components, and MCP integrations - How Stripe prototypes in dev boxes so designers never have to worry about local setup - Why “demos, not memos” transformed Stripe’s design review culture - How Stripe built design review modes, variant testing, and AI annotation directly into your prototyping tool - Why internal tools don’t need to be production-grade to be transformative — Brought to you by: Celigo—Intelligent automation built for AI Cursor—The best way to code with AI — 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/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [redacted email].