Auxx.ai
AI AgentsSimulations

Assertions

Define the checks that decide whether a simulation passes — from how the conversation ends to which tools the agent must and must not call.

An assertion is a check that runs after a simulation completes and decides whether it passed. Every simulation needs at least one.

The assertion types

TypeChecksExample
Terminal outcomeHow the conversation should endShould finish, not hand off to a human
Response criteriaNatural-language checks on the reply"Mentioned the order number," "stayed empathetic"
Tool calledThe agent must call a specific toolMust call find order with the order number
Tool not calledThe agent must not call a toolMust not issue a refund for an ineligible item

Terminal outcome can expect the conversation to finish, hand off, or switch to another procedure.

Response criteria is a list of independent statements — each one is checked separately, and the assertion fails if any of them isn't met.

Tool called / not called can optionally match the tool's inputs, using exact or subset matching just like mocks.

How grading works

Assertions are graded two ways:

  • Deterministic checks — terminal outcome and tool called/not called are checked instantly and exactly.
  • AI-judged checks — response criteria are judged by a model, one statement at a time, because they involve understanding language.

Verdicts

Each run ends with one of three verdicts:

VerdictMeaning
PassedEvery assertion passed
FailedThe run completed, but at least one assertion failed
ErrorThe run couldn't complete cleanly

Errors override a pass

If the run hits an error — such as the agent calling an unmocked tool or exceeding the turn limit — the verdict is error, even if the assertions would have passed. The run is incomplete, so the result can't be trusted.

Next steps