AGENTS.md outperforms skills in our agent evals

Published: (January 27, 2026 at 08:00 AM EST)
1 min read

Source: Vercel Blog

We expected to be the solution for teaching coding agents framework-specific knowledge. After building evals focused on Next.js 16 APIs, we found something unexpected. A compressed 8KB docs index embedded directly in achieved a 100% pass rate, while skills maxed out at 79% even with explicit…

Back to Blog

Related posts

Read more »

Introducing OpenAI Frontier

OpenAI Frontier is an enterprise platform for building, deploying, and managing AI agents with shared context, onboarding, permissions, and governance....