Glossary term
Evaluation set
A curated collection of realistic inputs with definitions of correct output, used to measure AI system quality.
Evaluation sets turn quality from opinion into measurement and make model or prompt changes safe to ship.
They should include common cases, hard cases and cases where the right behaviour is to refuse or escalate.
Related terms
- LLM-as-a-judgeUsing a language model to score or compare outputs of an AI system against criteria.
- LLM observabilityCollecting traces, metrics and quality signals from language model applications to understand behaviour in production.
- GroundingConstraining a model’s output to information in supplied sources, so that claims can be traced and verified.
Turning concepts into a working system?
We help teams choose the right pattern and build it with evaluation from day one.