Study finds well-written AGENTS.md files significantly boost AI code generation, while poor ones hurt performance
By
Slava Zhenylenko
Lightly toasted, lightly seasoned, mostly correct.
Summary
A systematic study of AGENTS.md files across a monorepo reveals that well-crafted files can dramatically improve AI code generation quality (equivalent to upgrading from Haiku to Opus models), while poorly written ones degrade performance below having no documentation at all. The research identifies specific patterns that work and warns that most existing AGENTS.md content is either unhelpful or actively harmful.
Key quotes
· 4 pulledThe best ones gave our coding agent a quality jump equivalent to upgrading from Haiku to Opus.
The worst ones made the output worse than having no AGENTS.md at all.
Most of what people put in AGENTS.md either doesn't help or actively hurts, and the patterns that work are specific and learnable.
The same file boosted best_practices by 25% on a routine bug
You might also wanna read
AGENTS.md: Standardized Documentation Format for AI Agents Adopted by Major Platforms
The article introduces AGENTS.md, a standardized format for AI agents that serves as a structured alternative to human-readable README files
Product Hunt·9mo ago
AGENTS.md: An Open Format for Guiding AI Coding Agents in Open-Source Projects
AGENTS.md is a simple, open format for guiding AI coding agents, functioning as a README specifically designed for agents rather than humans
agents.md·1d ago
AI-First Content Management: Rethinking CMS vs Markdown for Agentic Applications
The article explores whether traditional Content Management Systems (CMS) like WordPress are still necessary in an AI-first world where agen
Prototypr·4mo ago