AI Agent Evaluation

AI Evals

Everyone agrees you should evaluate an AI system. Far fewer people agree on what an evaluation is supposed to prove, and that is where most of them go wrong.

What are AI evals?

An AI eval is a test of whether an AI system did what it was required to do. Not whether the output looked reasonable, and not whether a reviewer liked it. Whether it met a requirement someone wrote down in advance.

That last clause is the whole of it. An eval is made of four things: the criteria that say what acceptable behavior is, the cases the system is run against, the expected behavior that says what a correct result looks like, and the evidence left behind so someone who did not build the system can check the claim themselves.

Take any one of those away and you still have a number. You no longer have an evaluation.

What an Eval Is Not

Where an Eval Actually Starts

Most eval work starts at the output and reasons backwards. That is the wrong end. You cannot judge a result until you have said what a correct one would be, so the work runs in this order:

  1. Requirement

    What the system is actually supposed to do, written down.

  2. Evaluation criteria

    What counts as acceptable behavior, stated before you look.

  3. Test cases

    The situations it has to handle.

  4. Edge cases

    The situations where the requirement is most likely to break.

  5. Expected behavior

    What a correct result looks like, so a result can be judged.

  6. Evaluation

    How the system actually performed against all of it.

  7. Evidence

    What you can show someone who did not build it.

Skip the first step and everything below it inherits the gap. The criteria measure the wrong thing, the cases test the wrong behavior, and the score comes back green on a requirement nobody ever wrote down. That failure is the reason this practice exists.

Running Them More Than Once

An eval you run by hand once is a report. An eval you can re-run after a prompt change, a model upgrade or a new tool is infrastructure, and building that is a discipline of its own: harness engineering. That is the rung above this one.

Read Next

The same subject, taken one decision at a time.

We design evaluations and build the harnesses that run them. See how that works, or tell us what you need to prove.