1. The Agents on Rails Files: designing black-box evals for coding agents (evilmartians.com)
Authors: Vladimir Dementyev, Principal Backend Engineer, and Travis Turner, Tech EditorTopics: AI, Rails, DX, LLM benchmarking, Agentic development, LLMsTips and tricks on writing robust evals for coding agents that test apps whose code we've never seen: different UI/UX contract strategies, UI mutat...