Showing 1–2 of 2 · #evals
AGENTSTool-use evals are broken. Here's how to fix them.
Exact-match grading, single runs and perfect mock APIs make tool-use scores look better than reality. A better harness design, step by step.
JLJonas LindOct 11 · 6 min
AGENTSEvaluating AI agents end to end
Outcome checks, trajectory review, sandboxes, simulated users and pass^k. A complete method for knowing whether your agent really works.
MOMira OkaforJul 14 · 6 min