testing

A rigorous look at how to measure agent performance — trajectory-level vs final-answer evals, canonical multi-step benchmarks (SWE-bench, WebArena, OSWorld, GAIA), LLM-as-judge pitfalls, and why your eval is your spec.

Why traditional software testing falls apart on LLMs, the four evaluation regimes that work in practice (golden sets, LLM-as-judge, human review, online metrics), and how to wire them together without drowning in ungrounded scores.