Deep dive — methodology

How the A / B / C determination is derived

Every $499 Snapshot lands on exactly one overall determination. Not a color code, not a health score — an A/B/C determination tied to the operator's NERC + FERC attestation stance. Here is exactly how it is derived.

The three categories

CategoryMeaningAttestation stance
A No high-severity drift events. No zone-differential signal. Baseline vs recent distributions match within threshold. Sufficient for attestation. Signed evidence available on file.
B Medium-severity drift or single-event high-severity without zone-differential signal. Aggregate metrics stable. Conditional. Named remediation + re-audit within defined window supports attestation.
C Multiple high-severity drift events + zone-differential signal fired. Insufficient. Operator should not represent the AI as NERC EOP-011 compliant or FERC market-transparency-defensible until remediation completes.

The evidence chain

  1. Sensor thresholds active during the audit:
    • Mean-shift threshold: 1.5 standard deviations from baseline
    • Variance-ratio threshold: 1.5x baseline
    • KL-divergence threshold: 0.2
    • Zone differential-shift threshold: 12% shift across market zones
  2. Event classification:
    • Any single-threshold cross → medium-severity event
    • KL-divergence > 0.5 OR zone-differential signal → high-severity event
  3. Category assignment:
    • 0 high-severity + 0 zone-differential → A
    • 1-2 high-severity, no zone-differential signal → B
    • ≥ 3 high-severity or any zone-differential signal fired → C

Why this sample lands on C

13 high-severity drift events + zone E3 emergency-reserve-activation lane rate 29% → 6% (22-point differential vs baseline). Either condition alone is sufficient for C. Both are present. The determination is not marginal — zone E5 also fires with KL-divergence up to 2.39, which reinforces the finding on an independent zone.

Why the A/B/C structure matters

Continuous-scale scores (0-100 dashboard, red/yellow/green tri-lights, "health-score" percentages) push operators toward "just above the threshold" gaming behavior. A/B/C determinations force a single stance question:

Would you sign the NERC EOP-011 or FERC market-transparency attestation as-is today? A/B/C answers the question that NERC auditors, FERC staff, ISO/RTO market monitors, and state PUC customer-hearing panels actually ask — instead of the question the vendor's dashboard prefers.

How does this help me?

Knowing your category BEFORE the NERC audit letter, FERC 206 investigation, ISO/RTO market-monitor referral, or state PUC customer-hearing lands is the whole value of the $499 discipline.

Read: The value of knowing your category first →

$499 Snapshot. 3 business days.

Get your operator's A / B / C determination on your actual AI surface — before someone else's question forces the answer.

Buy $499