AI glossary
Golden set
A golden set is a fixed collection of inputs with agreed good answers, used as the trusted reference an AI feature is scored against.
Each case pairs an input with what a correct output must contain or look like, agreed by people who know the domain. It is the "expected" half of every eval run.
Good golden sets include the easy cases, the awkward edge cases and real examples from production that once went wrong.
Keep it separate from anything you tune on. If you adjust the prompt until the golden set passes, the score stops telling you how it does on new inputs.
Learn it hands-on
These free lessons teach it with commands to run in a lab and checked tasks. Read them whole with no account.