| name | sentiment-priority-scorer |
| description | Score normalized real-estate leads using sentiment, urgency, intent, recency, and record type to produce deterministic priority rankings and P1-P3 buckets. Use when users ask to prioritize hot leads, rank callback queue, or triage follow-ups without performing writes or outbound sends. Recommended chain: india-location-normalizer then sentiment-priority-scorer then summary-generator and action-suggester. |
Sentiment Priority Scorer
Produce deterministic priority scores for leads without mutating any state.
Quick Triggers
- Rank leads by urgency and tone for callback priority.
- Classify leads into P1/P2/P3 queue.
- Score follow-up priority from normalized lead records.
Recommended Chain
india-location-normalizer -> sentiment-priority-scorer -> summary-generator
Execute Workflow
- Accept input from Supervisor containing normalized leads.
- Validate input with
references/sentiment-priority-input.schema.json.
- Score each lead with:
sentiment_score in range [-1, 1]intent_score in range [0, 1]recency_score in range [0, 1]- mapped
urgency_score from lead urgency (high=1.0, medium=0.6, low=0.3)
- Use
record_type to avoid over-prioritizing generic bulk inventory:
buyer_requirement: apply +0.10 intent lift (hard demand signal)inventory_listing: no lift unless high-action cues are present
- Boost
intent_score when high-action cues exist in listing text:
