Skip to main content

Create a principle

POST 
/targets/:tid/principles

Adds one principle to this target — a rule the AI service under test is expected to uphold, which every evaluated transcript is then judged against. Phrase it as a checkable expectation about the service's behaviour rather than a topic. importance weights how heavily a violation counts, from 1 (lowest) to 5 (highest).

Request​

Responses​

Successful Response

Response Headers
    Idempotent-Replayed

    Present and true when this response is a replay.