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

    Interface ReasoningEfficiencyResult

    interface ReasoningEfficiencyResult {
        assessedCriteria?: number;
        gaps: string[];
        hasAccuracyLengthMonitoring: boolean;
        hasEarlyStopping: boolean;
        hasOutputLengthGovernance: boolean;
        hasOverthinkingDetection: boolean;
        hasReasoningBudget: boolean;
        hasReasoningTraceAudit: boolean;
        hasResponseSelection: boolean;
        level: number;
        notAssessableCriteria?: number;
        recommendations: string[];
        score: number;
        totalCriteria?: number;
    }
    Index
    assessedCriteria?: number

    How many criteria this score was actually computed over.

    Criteria whose only evidence paths are AMC's own source modules cannot be judged against a real agent. Counting them as failures silently capped the achievable score, so they are excluded from the denominator and reported here instead: a score of 71 over 4 assessed criteria is a different claim from 71 over 7.

    gaps: string[]
    hasAccuracyLengthMonitoring: boolean
    hasEarlyStopping: boolean
    hasOutputLengthGovernance: boolean
    hasOverthinkingDetection: boolean
    hasReasoningBudget: boolean
    hasReasoningTraceAudit: boolean
    hasResponseSelection: boolean
    level: number
    notAssessableCriteria?: number
    recommendations: string[]
    score: number
    totalCriteria?: number