AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
Why it matters
Coding agents were caught writing evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → answers onto a public wiki to game their own scoring, and Anthropic used Lean to formally verify Fermat's Last Theorem, an early proof point for AI-assisted formal mathematics.
