The internal AI tool that’s transforming how Stripe designs products | Owen Williams · How I AI summary

Key takeaways

Internal tools tailored to specific company workflows can dramatically improve product prototyping, reviews, and collaboration, often outperforming generic solutions.
A combination of engineering and design expertise allows the creation of lower-barrier, high-fidelity prototyping tools that are both powerful and user-friendly.
Prototyping with real data, multiple states, and AI-driven feedback leads to more realistic and useful product development and experimentation.
Fostering an open, contributive culture around internal tools encourages continuous evolution and adaptation to team needs.
AI-powered design tools, even in early stages, can shift conversations from debate to actual work, enabling faster, clearer communication and iteration.

Summary

Building a High-Impact Internal Prototyping Tool at Stripe

Owen Williams, a design manager at Stripe, shares how he developed Protodash, an internal AI-powered platform for rapid prototyping of dashboards and product features. Starting from simple Cursor rules and React components, Protodash evolved into a browser-based studio that integrates with Stripe’s design system, allows multi-state and variant testing, and provides AI-driven iteration and feedback. This tool transforms design reviews into more realistic, interactive demonstrations that resemble the final product, elevating the entire process and fostering better communication between designers, PMs, and engineers.

The Technical Foundations and Philosophy of Protodash

Williams emphasizes the importance of lowering barriers for designers, leveraging his engineering background to create a tool that doesn’t require complex local setups or deep coding knowledge. Protodash uses React router, MCPs for data connections, and Stripe’s design system to automate dashboard creation. It is built to be opinionated yet flexible, allowing quick updates, randomization, and variant testing. The open, contributive culture of the internal team encourages continuous evolution and customization, making the tool tailored to Stripe’s specific needs.

Transforming Design and Product Development With Internal Tools and AI

The podcast highlights how internal tools like Protodash can be more effective than off-the-shelf solutions, because they are precisely matched to a team’s culture, workflows, and quality standards. These tools enable faster, higher-fidelity prototyping, support complex data visualizations, and facilitate an iterative, discovery-driven approach. Owen discusses how PMs and non-designers are using the tool to unblock themselves, improve communication, and contribute directly to product design, resulting in a more collaborative and efficient development environment.

Innovations in Prototyping: Features and Future Directions

Williams showcases key features like in-browser prototype creation, real-time updates, AI annotations, design review modes, and variant generation. He also discusses upcoming ideas such as low-fidelity modes, component downloads, and end-to-end cloning of dashboards. The focus remains on enhancing flexibility, reducing friction, and pushing creative boundaries while maintaining Stripe’s high standards. The session underscores the potential of AI to transform traditional workflows and foster a culture of continuous improvement.

Show notes

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