Interface Evaluation

The result returned by AI Guard after evaluating a conversation.

interface Evaluation {
    action: "ALLOW" | "DENY" | "ABORT";
    reason: string;
    tags: string[];
}

Index

Properties

action reason tags

Properties

action

action: "ALLOW" | "DENY" | "ABORT"

The security action determined by AI Guard:

'ALLOW': The conversation is safe to proceed
'DENY': The current conversation exchange should be blocked
'ABORT': The full workflow should be terminated immediately

reason

reason: string

Human-readable explanation for why this action was chosen.

tags

tags: string[]

List of tags associated with the evaluation (e.g. indirect-prompt-injection)