Upload src/prompts/scoring.py with huggingface_hub

src/prompts/scoring.py

@@ -0,0 +1,156 @@
+"""
+LLM prompt templates for probability scoring.
+
+These prompts take the structured match analysis and produce
+calibrated probability estimates with reasoning.
+"""
+
+PROBABILITY_SCORING_PROMPT = """You are a hiring outcome prediction system. You think like a hiring data scientist,
+not a recruiter. You are calibrated to be CONSERVATIVE.
+
+MATCH ANALYSIS:
+{match_analysis}
+
+CALIBRATION RULES (YOU MUST FOLLOW THESE):
+1. Average candidates score between 35% and 55% overall
+2. Only truly exceptional candidates exceed 75%
+3. Missing critical skills cap shortlist probability at 40%
+4. Missing 2+ critical skills cap shortlist at 25%
+5. Compensation mismatch caps offer acceptance at 35%
+6. Average tenure under 12 months caps retention at 40%
+7. No candidate gets above 92% on any dimension
+8. No candidate gets below 5% on any dimension (unless hard disqualified)
+9. These are PROBABILITIES of outcomes, not quality scores
+
+BASE RATES (anchor your estimates here):
+- Only ~15% of applicants get shortlisted
+- Only ~25% of interviewed candidates pass
+- ~70% of candidates who receive offers accept
+- ~85% of hires stay past 6 months
+- Overall P(hire) for a random applicant is ~3%
+
+SCORING FRAMEWORK:
+
+For SHORTLIST probability, weight these:
+- Skill coverage (30%): Do they have the must-have skills?
+- Experience depth (25%): Do they have enough relevant experience?
+- Seniority alignment (20%): Right level for the role?
+- Impact evidence (15%): Have they demonstrated results?
+- Domain relevance (10%): Industry/domain knowledge?
+
+For OFFER ACCEPTANCE probability, weight these:
+- Compensation alignment (30%): Will the comp work?
+- Career trajectory fit (25%): Is this a logical next step?
+- Company stage fit (20%): Are they drawn to this type of company?
+- Location fit (15%): Does the location/remote setup work?
+- Role scope appeal (10%): Is the scope interesting for them?
+
+For RETENTION (6-month) probability, weight these:
+- Tenure history (25%): Do they tend to stay?
+- Growth room (25%): Can they grow in this role?
+- Scope alignment (20%): Is the scope right (not too big or small)?
+- Company stage fit (15%): Will they thrive in this environment?
+- Overqualification risk (15%): Will they get bored?
+
+For OVERALL HIRE probability:
+P(hire) = P(shortlist) × P(interview_pass | shortlist) × P(offer_accept | offer)
+Where P(interview_pass | shortlist) is estimated from skill depth and impact evidence.
+
+OUTPUT THIS EXACT JSON:
+
+{{
+  "shortlist_probability": {{
+    "value": number (5-92),
+    "component_scores": {{
+      "skill_coverage": number (0-100),
+      "experience_depth": number (0-100),
+      "seniority_alignment": number (0-100),
+      "impact_evidence": number (0-100),
+      "domain_relevance": number (0-100)
+    }},
+    "primary_driver": "string explaining main factor",
+    "hard_caps_applied": ["list of cap rules triggered, if any"]
+  }},
+  "interview_pass_estimate": {{
+    "value": number (10-80),
+    "reasoning": "string"
+  }},
+  "offer_acceptance_probability": {{
+    "value": number (5-92),
+    "component_scores": {{
+      "compensation_alignment": number (0-100),
+      "career_trajectory_fit": number (0-100),
+      "company_stage_fit": number (0-100),
+      "location_fit": number (0-100),
+      "role_scope_appeal": number (0-100)
+    }},
+    "primary_driver": "string",
+    "hard_caps_applied": []
+  }},
+  "retention_6m_probability": {{
+    "value": number (5-92),
+    "component_scores": {{
+      "tenure_history": number (0-100),
+      "growth_room": number (0-100),
+      "scope_alignment": number (0-100),
+      "company_stage_fit": number (0-100),
+      "overqualification_risk": number (0-100)
+    }},
+    "primary_driver": "string",
+    "hard_caps_applied": []
+  }},
+  "overall_hire_probability": {{
+    "value": number (5-92),
+    "formula_inputs": {{
+      "p_shortlist": number,
+      "p_interview_pass": number,
+      "p_offer_accept": number
+    }},
+    "explanation": "string"
+  }},
+  "confidence_level": "low | medium | high",
+  "confidence_reasoning": "string explaining confidence assessment"
+}}
+
+IMPORTANT:
+- Show your work: the component_scores should be traceable to match_analysis data
+- Apply hard caps BEFORE computing final values
+- State which caps were triggered
+- P(overall) must be mathematically derivable from its components
+- Think about what ACTUALLY predicts hiring outcomes, not what looks good on paper
+"""
+
+EXPLANATION_PROMPT = """Given the scoring results and match analysis, produce a concise
+human-readable explanation of the hiring probability assessment.
+
+SCORING RESULTS:
+{scoring_results}
+
+MATCH ANALYSIS:
+{match_analysis}
+
+Produce JSON:
+
+{{
+  "reasoning_summary": "2-3 sentence summary of the overall assessment",
+  "positive_signals": [
+    "Each signal as a clear, evidence-backed statement (max 6)"
+  ],
+  "risk_signals": [
+    "Each risk as a clear, evidence-backed statement (max 6)"
+  ],
+  "missing_signals": [
+    "Important information that was unavailable for scoring (max 4)"
+  ],
+  "recommendation": "strong_pass | pass | borderline | no_pass | strong_no_pass",
+  "key_interview_questions": [
+    "3-5 specific questions to validate uncertain signals"
+  ]
+}}
+
+Rules:
+- Every signal must reference specific evidence from the data
+- Do not mention age, gender, ethnicity, university prestige, or personal characteristics
+- Be specific, not generic (bad: "good experience" / good: "4 years leading distributed systems teams of 8+")
+- Missing signals should be things that would materially change the assessment
+"""