💡 Predictive winter colony readiness score with actionable preparation checklist

[github-actions[bot]]

Summary

Generate a per-colony Winter Ready score (0-100) starting in late summer, based on mite load trajectory, food stores, queen performance, brood population trend, and regional climate forecast. Surface a prioritized preparation checklist with deadlines. Directly addresses the record 55.6% annual colony loss rate by turning vague winter preparation awareness into an executable, quantified plan.

Market Signal

2024-2025 saw the highest colony losses ever recorded (55.6% annual, 40.2% winter — Bee Informed Partnership / Apiary Inspectors of America). Varroa mite Amitraz resistance is now documented in peer-reviewed research (2025), compounding winter mortality risk. No competitor offers a predictive winter readiness score — HiveTracks, HiveSense, BroodMinder, and ApiaryBook all track data but none synthesize it into an actionable preparation assessment. BroodMinder's 2026 strategic pivot toward 'turning information into tools that help beekeepers act' validates market demand for decision-oriented features over passive dashboards.

User Signal

The PRD's core value proposition is 'turning ambiguity into clear, context-aware next actions.' Winter preparation is the highest-stakes decision window of the year — a single missed treatment or feeding deadline can mean colony death. The recommendation contract (action + rationale + confidence + fallback) maps directly to preparation gap analysis. Seasonal planning calendar (implementation artifact 10-4) and weekly action queue (10-2) provide the delivery infrastructure. No existing issues or feature requests address this gap, but the 55.6% loss rate represents the #1 pain point in the hobbyist beekeeping community.

Technical Opportunity

Uses existing data types — mite counts, hive weight, queen observations, brood assessments — already defined in the inspection/observation schema (Story 3.2). Regional climate data comes through the environmental intelligence layer (Discussion #476). The recommendation engine's confidence scoring framework naturally supports a readiness score with transparent evidence attribution. No new sensor hardware required — works with manual observations alone, enhanced by optional sensor data.

Assessment

Dimension	Score	Rationale
Feasibility	high	Uses existing data types, schema, and recommendation engine. Score calculation is a weighted aggregation of known colony health predictors.
Impact	high	Directly addresses the #1 beekeeper problem (colony loss) with a quantified, actionable output. No competitor offers this.
Urgency	high	Record colony losses (55.6%) and emerging Amitraz resistance make proactive preparation tools critically needed. Seasonal timing: score should be available by late summer for fall preparation.

Adversarial Review

Strongest objection: If the score provides false reassurance (90/100) and the colony still dies, it catastrophically destroys user trust — the exact opposite of Broodly's 'confidence-first' mission.

Rebuttal: The recommendation contract already mandates confidence + fallback for every output. The Winter Ready score would explicitly surface data quality indicators ('Based on 3 of 5 required signals — weight data missing') and never claim to predict survival. It quantifies PREPARATION COMPLETENESS, not colony fate. The score frames as 'here's what you can control' rather than 'here's what will happen.' This distinction — preparation audit vs. survival prediction — is critical to maintaining trust.

Suggested Next Step

Create a domain model spike defining the 5-7 input signals (mite load trajectory, food store weight, queen age/performance, brood population estimate, feeding history, regional climate severity), their weights, and the score calculation algorithm. Validate the signal weights against published colony loss predictor research (Bee Informed Partnership, USDA data). Design the score card UI component following the HiveHealthCard pattern with status-driven tva() variants.