✳flâneur — a map of the web's best reading
Teaching agents product design at Vercel - Vercel
vercel.com · 3,875 words · saved by 1 readers
Learn how Vercel teaches agents product design with agent skills, lint rules, Vercel Agent code reviews, evals, and a human-led update loop.
Coding agents can produce working UI fast, but what's harder is a different shape. They can copy your product's style, match its patterns, and try to follow its conventions. What they cannot do is understand why those patterns exist. Code shows agents what shipped, not why one component, phrase, or interaction became your standard. That reasoning lives in design reviews, PR comments, Slack threads, and with the people who were in the room. For an agent, context that isn't in the codebase doesn't exist. Vercel is an agent-native team. We treat accepted product decisions like code, keeping them
Explore this link on the map →related reading
- Impeccable: The missing upgrade to Anthropic's impeccable skillimpeccable.style
- rams - Expert Design Reviews on Every PRrams.ai
- Using AI as a Design Engineerjakub.kr
- Demystifying evals for AI agents \ Anthropicanthropic.com
- The Shape of AI | UX Patterns for Artificial Intelligence Designshapeof.ai
- AI Design Field Guideaidesignfieldguide.com
- Best practices for Claude Code - Claude Code Docsanthropic.com
- How to prompt v0 - Vercelvercel.com
- Best practices for coding with agents · Cursorcursor.com
- Cookbookcookbook.openai.com
- Now – Updates from the Linear teamlinear.app
- GitHub - connorwhite-online/iterate: Parallel design exploration with agents on React. · GitHubgithub.com