🎙️ This week on How I AI: The internal AI tool that’s transforming how Stripe designs products

· Source: Lenny's Newsletter · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Project & Product Management · Depth: Intermediate, short

Summary

Stripe's design manager, Owen Williams, developed Protodash, an internal AI prototyping tool that enables designers and Product Managers (PMs) to generate production-quality, clickable prototypes using Stripe's proprietary design system, Sail. Initially a collection of Cursor rules and React components, Protodash evolved into a comprehensive web-based platform. It addresses the limitations of generic AI design tools, which often produce inconsistent "blurple slop" due to their lack of integration with specific design systems. Protodash facilitates early exploration of product ideas, improves designer-PM collaboration by allowing PMs to build and test concepts, and supports dynamic data-driven prototyping, which is challenging in traditional tools like Figma. The tool also incorporates a design review mode that summarizes feedback and suggests fixes via AI.

Key takeaway

For Product Managers and designers seeking to accelerate product development and improve collaboration, consider building or adopting internal AI prototyping tools that are deeply integrated with your company's specific design system. This approach allows for earlier exploration of ideas, reduces reliance on abstract discussions, and enables testing of diverse use cases with real data, ultimately leading to more robust and aligned product outcomes. You can shift conversations from staffing needs to concrete design improvements.

Key insights

Internal AI prototyping tools tailored to a company's design system enhance product development and collaboration.

Principles

Method

Protodash integrates Cursor rules, React components, and an MCP server for Stripe's Sail design system, enabling AI to construct prototypes from defined building blocks and support dynamic data states.

In practice

Topics

Best for: Product Manager, AI Product Manager, Product Designer, Director of AI/ML

Related on AIssential

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Lenny's Newsletter.