Teaching agents product design at Vercel

Short summary

Vercel teaches AI agents product design decisions by encoding them as structured documentation and lint rules in the codebase. Rather than leaving design context in Slack threads and PRs, they treat accepted decisions as code—routing agents to canonical sources, validating changes with deterministic checks, and testing generalization with evals. Other teams can adapt this framework to their own standards.

• •Vercel encodes product design decisions as structured SKILL.md files and lint rules for agents to follow
• •Uses routing to canonical sources and deterministic checks to validate agent changes against product standards
• •Weekly workflow collects design feedback and tests agent behavior on unseen interfaces to improve guidance

Generated with AI, which can make mistakes.