Skip to main content

Scoring Engine

PILLAR’s scoring engine evaluates every account against a comprehensive set of rules across 8 categories, producing a composite 0-100 health score. All weights are configurable per organization.
Correctness of every output on this page is enforced by The Guarantee — specifically the Decomposition (D) and Calibration (C) invariant categories. Every weighted contribution sums to the final score within ±1, every formula’s weights sum to 1.0 ±0.001, and the golden-fixture snapshot tracked by G-D-02 locks scoring behavior against regressions.

How It Works

  1. Context Building: The engine assembles a complete picture of each account — contacts, opportunities, renewals, activities, signals, products, and derived metrics
  2. Rule Evaluation: Each rule evaluates the account context and produces a 0-100 sub-score
  3. Category Aggregation: Rules are grouped into 8 categories. Each category score is a weighted average of its rule sub-scores
  4. Composite Score: The final score is a weighted sum of category scores
  5. Audit Trail: Every computation is logged for traceability

8 Categories

Early Detection

PILLAR’s signal-triggering thresholds are designed to surface risk earlier than traditional health scoring approaches, giving revenue teams more time to intervene before accounts reach a critical state. Eight thresholds are configurable per organization in Settings → Configuration → Segments & Thresholds, including health score warning and critical levels, renewal risk level, ICP fit minimum, and engagement velocity floor.

Configurable Weights

Organizations can customize the scoring engine through Settings:
Detailed scoring methodology, including exact rule definitions, weight distributions, and default threshold values, is available in the PILLAR Implementation Guide provided to active customers.