eval-driven development

[ ih-VAL-driv-uhn dih-VEL-uhp-muhnt ]noun

Writing the check before the feature, so you can tell whether a change actually made anything better.

Explanation

The same habit as writing the test first, adapted for a machine that never gives the same answer twice. Without it, “the new prompt seems better” is all you have, and that is not evidence.

Related words

• evals — Repeatable checks that score what an AI gave you against what it was supposed to give you.
• characterization test — A test that writes down what code does today, right or wrong, so you can tell later whether you broke it.

Prompts that deal with it

• Red Before Green — The test exists before the feature does