Ga naar hoofdinhoud

Een bericht getagd met "Measurement"

Laat alle tags zien

Hermiq skills tutorial series — Part 3: Measuring skills with paired evals

· 9 minuten leestijd
Conduction
Open-source workspace stack

A skill that "feels right" can still add nothing, or make the agent worse. Paired evals answer the question with two runs of the same cases: one with the skill, one without. In this part you use the seeded woo-triage-paired-eval dataset to run a paired baseline against woo-request-triage, read the delta, and watch the L5 evidence appear where Part 2 left a named gap.