Talent Systems — Science Team
Scorer System

Output Format

The JSON schema the scorer produces — engineering-owned, not editable via UI.

The scorer outputs a structured JSON scorecard. This format is engineering-managed (not exposed in the admin UI) because it defines the data contract between the scorer and the rest of the system.

Scorecard Structure

{
  "scores": [
    {
      "competency": "Problem Solving",
      "score": 4,
      "evidence": "Candidate described redesigning the checkout flow...",
      "strengths": ["Methodical approach to root cause analysis..."],
      "concerns": ["Did not mention measuring outcomes..."]
    }
  ],
  "weighted_score": 3.7,
  "recommendation": "Advance",
  "red_flags": [],
  "overall_strengths": ["Strong analytical thinking..."],
  "overall_concerns": ["Limited examples of cross-functional work..."]
}

Key Fields

FieldTypeDescription
scoresArrayPer-competency: name, score (1-5), evidence quote, strengths list, concerns list
weighted_scoreNumberCalculated from scores × competency weights. Recalculated server-side for integrity.
recommendationString"Advance" (≥ advance_threshold), "Hold" (≥ hold_threshold), or "Decline"
red_flagsArrayCoached response flags, adverse impact flags, etc.
overall_strengthsArrayCross-cutting strengths across all competencies
overall_concernsArrayCross-cutting concerns across all competencies

Weighted Score Calculation

The weighted_score is recalculated server-side (not trusted from the AI output):

weighted_score = Σ (competency_score × competency_weight) / Σ (competency_weights)

Recommendation Thresholds

ConditionRecommendation
weighted_score >= advance_threshold (default 3.5)Advance
weighted_score >= hold_threshold (default 2.5)Hold
weighted_score < hold_thresholdDecline

Both thresholds are configurable via the scorer rubric admin page.

On this page