“I haven’t written a single line of front-end code in 3 months”: How Notion’s design team uses Claude Code to prototype
Episode
51 min
Read time
2 min
Topics
Design & UX
AI-Generated Summary
Key Takeaways
- ✓Shared Prototype Repository: Build a single Next.js repo where each designer gets a namespaced directory for their prototypes. This eliminates redundant setup, surfaces teammates' work in one list, and lets anyone copy useful code across prototypes by simply instructing Claude to pull from another designer's directory.
- ✓Claude.md Layering Strategy: Maintain two Claude context files: a committed global claude.md defining shared tooling, project structure, and rules like "don't modify other users' files," plus a personal claude.local.md per machine that sets the current user's directory and individual preferences. This combination keeps team consistency while allowing personal customization.
- ✓Teach Claude to Self-Verify: Every time Claude asks the user to check something — browser output, CI status, TypeScript errors — convert that request into a permanent instruction. Connect Playwright or Chrome DevTools MCP so Claude opens the browser, clicks elements, and confirms functionality itself, reducing interruptions and enabling longer unattended runs.
- ✓Figma-to-Code Verification Loop: A custom slash command called `/figma` force-invokes the Figma MCP, extracts the design, implements it, then enters a verification loop comparing the browser output against the original Figma frame using Chrome DevTools MCP. The loop repeats up to three iterations with no changes before stopping, reaching roughly 80% accuracy on the first pass.
- ✓Icon Hallucination Fix via Scripted Skills: Claude consistently guesses wrong icon names, defaulting to generic labels like "search icon" instead of the actual codebase name like "magnifying glass icon." A Claude skill called `find-icon` runs a TypeScript script that searches all 5,000 icons programmatically, including synonyms, before any implementation — eliminating repeated broken imports without manual intervention.
What It Covers
Brian Levin, designer at Notion AI, demonstrates how he built a shared Next.js prototype playground for Notion's design team, enabling code-first prototyping via Claude Code. The system uses shared components, Claude slash commands, skills, and MCP integrations to help 5–10 designers prototype directly in the browser without writing code manually.
Key Questions Answered
- •Shared Prototype Repository: Build a single Next.js repo where each designer gets a namespaced directory for their prototypes. This eliminates redundant setup, surfaces teammates' work in one list, and lets anyone copy useful code across prototypes by simply instructing Claude to pull from another designer's directory.
- •Claude.md Layering Strategy: Maintain two Claude context files: a committed global claude.md defining shared tooling, project structure, and rules like "don't modify other users' files," plus a personal claude.local.md per machine that sets the current user's directory and individual preferences. This combination keeps team consistency while allowing personal customization.
- •Teach Claude to Self-Verify: Every time Claude asks the user to check something — browser output, CI status, TypeScript errors — convert that request into a permanent instruction. Connect Playwright or Chrome DevTools MCP so Claude opens the browser, clicks elements, and confirms functionality itself, reducing interruptions and enabling longer unattended runs.
- •Figma-to-Code Verification Loop: A custom slash command called `/figma` force-invokes the Figma MCP, extracts the design, implements it, then enters a verification loop comparing the browser output against the original Figma frame using Chrome DevTools MCP. The loop repeats up to three iterations with no changes before stopping, reaching roughly 80% accuracy on the first pass.
- •Icon Hallucination Fix via Scripted Skills: Claude consistently guesses wrong icon names, defaulting to generic labels like "search icon" instead of the actual codebase name like "magnifying glass icon." A Claude skill called `find-icon` runs a TypeScript script that searches all 5,000 icons programmatically, including synonyms, before any implementation — eliminating repeated broken imports without manual intervention.
Notable Moment
Levin reveals that prototype playground originated because he was designing Notion AI chat flows entirely in Figma, mapping out perfect golden-path conversations. Once engineers built them, models behaved unpredictably — getting stuck, asking follow-ups, producing errors — exposing how static design tools cannot capture real AI model behavior.
You just read a 3-minute summary of a 48-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
GPT 5.5 just did what no other model could
Apr 23 · 23 min
The Model Health Show
The Menopause Gut: Why Metabolism Changes & How to Reclaim Your Body - With Cynthia Thurlow
Apr 27
More from How I AI
What Claude Design is actually good for (and why Figma isn’t dead, yet)
Apr 22 · 27 min
The Rest is History
664. Britain in the 70s: Scandal in Downing Street (Part 3)
Apr 26
More from How I AI
We summarize every new episode. Want them in your inbox?
GPT 5.5 just did what no other model could
What Claude Design is actually good for (and why Figma isn’t dead, yet)
How Intercom 2x’d their engineering velocity in 9 months with Claude Code | Brian Scanlan
Claude Cowork 101: How to automate your workday without touching code | JJ Englert (Tenex)
I built a custom Slack inbox. It was easier than you’d think. | Yash Tekriwal (Clay)
Similar Episodes
Related episodes from other podcasts
The Model Health Show
Apr 27
The Menopause Gut: Why Metabolism Changes & How to Reclaim Your Body - With Cynthia Thurlow
The Rest is History
Apr 26
664. Britain in the 70s: Scandal in Downing Street (Part 3)
The Learning Leader Show
Apr 26
685: David Epstein - The Freedom Trap, Narrative Values, General Magic, The Nobel Prize Winner Who Simplified Everything, Wearing the Same Thing Everyday, and Why Constraints Are the Secret to Your Best Work
The AI Breakdown
Apr 26
Where the Economy Thrives After AI
Cognitive Revolution
Apr 26
AI in the AM: 99% off search, GPT-5.5 is "clean", model welfare analysis, & efficient analog compute
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for up to 3 shows.
Start My Monday DigestNo credit card · Unsubscribe anytime