evals

[ ee-VALZ ]noun

Repeatable checks that score what an AI gave you against what it was supposed to give you.

Explanation

Your safety net for something that will not answer the same way twice. Growing up means trading “that looked right” for a number you can watch over time.

Related words

• eval-driven development — Writing the check before the feature, so you can tell whether a change actually made anything better.
• success criteria — The things you can actually watch happen that tell you the job is finished.