AI engineering glossary · Evals guardrails AI security
What is eval set?
Eval set (also called evals, eval dataset): A fixed collection of test inputs, each paired with the expected answer or a scoring rule, used to measure how well an AI system performs on the task it is built for. Running the same set after every change to a prompt, model or pipeline shows whether quality went up or down, replacing gut feeling with numbers.
Eval set: an example
A team building a Hindi customer-support bot keeps 300 real past tickets with approved replies and re-scores the bot on them before each release.
Related terms
More Evals guardrails AI security terms
- Evaluation harness
- Evasion attack
- Excessive agency
- Extrinsic hallucination
- Fast Gradient Sign Method
- G-Eval
- Garak
- Greedy Coordinate Gradient
Where you learn it
Eval set is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.