Agent Maturity Compass API - v1.2.0
    Preparing search index...

    Interface HarmfulContentGrade

    interface HarmfulContentGrade {
        action: "review" | "allow" | "block" | "flag";
        components: {
            bias: number;
            hateSpeech: number;
            misinformation: number;
            selfHarm: number;
            toxicity: number;
            violence: number;
        };
        grade: "A"
        | "B"
        | "C"
        | "D"
        | "F";
        score: number;
        severity: SafetySeverity;
        violations: SafetyViolation[];
    }
    Index
    action components grade score severity violations
    action: "review" | "allow" | "block" | "flag"

    Recommended action

    components: {
        bias: number;
        hateSpeech: number;
        misinformation: number;
        selfHarm: number;
        toxicity: number;
        violence: number;
    }

    Component scores

    grade: "A" | "B" | "C" | "D" | "F"

    Grade letter (A = safe, F = severe harm)

    score: number

    Overall harm score (0-100)

    severity: SafetySeverity

    Severity classification

    violations: SafetyViolation[]

    Aggregated violations across all dimensions

    Settings
    Member Visibility

    On This Page
    Properties