Success criteria
Success criteria are the checkable conditions an output must satisfy, stated inside the prompt so the model can verify its own work before finishing.
Criteria differ from constraints: a constraint bounds how the work is done, a criterion defines when it is finished. Stating three or four checkable criteria measurably reduces incomplete answers, because the model has something concrete to test against.
Related terms
- Rubric
- A rubric is an explicit set of scored criteria used to judge output consistently, rather than relying on an overall impression.
- Vague qualifier
- A vague qualifier is a word such as "good", "engaging", or "comprehensive" that reads as a requirement but gives a model no way to check whether it has been satisfied.
- Specificity
- Specificity is the degree to which a prompt names concrete details — numbers, proper nouns, named formats — instead of leaving them to the model’s discretion.
More on evaluation
See the full glossary, read the guides, or put it into practice in the prompt builder.