Topic
Vercel
4 episodes
-
How our agents build on Brand pages with design
Vercel's design.md post describes a three-part system for keeping AI-generated pages on-brand outside a codebase: a public guidance file, a public stylesheet that takes layout decisions away from the model entirely, and an eval loop that converts human corrections into rules and deterministic checks. Pippa and Tyler dig into what actually makes it work, why the naive port-the-prompt approach failed, and what it means that Vercel had to build an eval harness just to ship a markdown file.
-
eve – The Agent Framework Vercel
Jessica and Cathy dig into Vercel's eve, a filesystem-first framework for durable AI agents, and why its boring production defaults may matter more than the agent hype around it.
-
Why AI sandboxes suck Freestyle Blog
Freestyle argues that AI sandboxes—lightweight isolates, fake filesystems, and constrained APIs—break the moment agents become genuinely capable. The core claim: sandboxes are built on the premise that you can predict what an agent will need, but you can't. Real work requires a real OS (Linux), real processes, real permissions, real networking. VMs are the correct primitive because they provide genuine isolation without removing the feedback loops that make agents functional. Sandboxes optimize for provider control, not agent capability.
-
Introducing: React Best Practices Vercel
Vercel releases react-best-practices, a structured framework that captures 10+ years of React optimization knowledge. It focuses on ordering performance work by impact—starting with eliminating waterfalls and reducing bundle size before micro-optimizations. The repository includes 40+ rules across 8 categories and compiles into a single document that AI coding agents can use for code reviews and refactoring suggestions.