Human-readable explanation from AI Guard describing why the conversation was blocked.
Sensitive Data Scanner findings from the evaluation.
Dictionary of tag probabilities (e.g. { indirect-prompt-injection: 0.2, jailbreak-attempt: 0.8 })
List of tags associated with the evaluation (e.g. indirect-prompt-injection)
Error thrown when AI Guard evaluation determines that a conversation should be blocked and the client is configured to enforce blocking mode.