Precision (AI metric)
The share of returned results that are actually correct: of everything the system flagged or retrieved, how much was right.
Precision is true positives divided by everything the system returned as positive. A spam filter with high precision rarely puts a good email in spam; a search with high precision returns few irrelevant passages. It says nothing about what was missed, which is what recall measures, and pushing one up usually pulls the other down. In search and RAG it is often reported as precision@k: the share of relevant items among the first k results.
Related terms
- Recall (AI metric): The share of all correct items that the system actually found: of everything it should have caught, how much it did.
- F1 score: One number that combines precision and recall as their harmonic mean, so it is high only when both are high.
- Confusion matrix: A table that counts a classifier’s right and wrong decisions by type: true and false positives, true and false negatives.
- Context precision: A RAG retrieval metric: whether the passages relevant to the question are ranked at the top of what was retrieved.
- Evals: A repeatable test set that scores an AI feature, so changes can be measured instead of guessed.
