AS 360 · OPERATOR INTELLIGENCE · FIELD DATA LAYER

FOUR INDEPENDENT SIGNALS.
ONE DEFENSIBLE SCORE.

The critical property of AS 360's data layer is that its sources cannot be gamed simultaneously. OpsScan ingests what your park already produces. VoxIntel listens to every radio call. LensIQ counts every guest through the turnstile. And the Anomaly Detection engine watches for patterns that humans miss. When all four agree, confidence is high. When they diverge — that gap is the finding.

📱 OpsScan 📡 VoxIntel 👁️ LensIQ 🔍 Anomaly Detection ← Back to Platform

The Four Components

Each layer operates independently.

No single data source can dominate or be fabricated to control the composite score. An operator who games one system faces three others that will expose the discrepancy.

📱

OPSSCAN

Field Intelligence

Three deployment tiers — passive data ingest, CV position tracking, active QR + voice. Parks choose their entry point. Every tier feeds the same score.

Passive RF monitoring of all venue radio channels. Ride-down detection, response timing, step-on collisions — an operational timeline no one can alter.

CV throughput from existing cameras — Nola, Safari AI, SenSource. Guest counts per cycle, TPH, operator presence. Zero operator involvement in data capture.

AI pattern recognition across all data streams. Speed flags, zero-variance patterns, clustering detection. Measures whether inspections were done, not just documented.

See Patterns ↓

Signal Triangulation

When sources diverge, that is the finding.

The value of multiple independent sources isn't redundancy — it's triangulation. Agreement strengthens confidence. Disagreement exposes risk that no single source would catch.

✓ ALL SOURCES AGREE — HIGH CONFIDENCE

VoxIntel: operational all day, no ride-down calls
OpsScan CV: all positions staffed, rotations on schedule
Kronos: shift records match operator assignments
LensIQ: TPH 820/hr sustained, no anomalies

→ Score holds. Integrity pillar: 91.

⚠ DIVERGENCE DETECTED — INTEGRITY FLAG

VoxIntel: ride-down radio call at 10:45
OpsScan CV: zero bodies at station 10:45–13:20
Kronos: operators still clocked in during downtime
LensIQ: TPH drops to 0 — confirms stoppage

→ Unreported 2.5hr stoppage. No CAR opened. Integrity: −14 pts.

WHY DIVERGENCE MATTERS TO UNDERWRITERS

A park that reports "all inspections complete, no incidents, full staffing" while radio traffic, camera data, and time-clock records tell a different story — that divergence is the most valuable data point in the system. It's the difference between a well-run facility and a facility that's good at paperwork. Traditional loss control cannot make this distinction. AS 360 makes it automatically, continuously, and without operator consent.

OpsScan · 3-Tier Deployment

Start passive. Scale with confidence.

Every tier feeds the same RIDE Score. Signal quality increases with each tier. Adoption friction decreases. Parks choose their entry point — most start at Tier 1 with zero new workflows, then layer up as trust builds.

PASSIVE INGEST

Ingest shift logs the park already produces. Kronos, ADP, Mobaro, CommandCentr. No new hardware. No new software. No operator training. Zero adoption friction.

Kronos/ADP shift data → staffing compliance

Mobaro inspections → completion rates

CommandCentr → ride checks, incidents

Zero new workflows for operators

CV TRACKING

Computer vision on the park's existing CCTV infrastructure. No new cameras. Passive position tracking, rotation timing, operator presence verification — independent of self-reporting.

Existing CCTV — Verkada, Hikvision, RTSP

Operator position tracking at stations

Rotation timing vs. schedule compliance

Validates T1 data independently

ACTIVE CAPTURE

QR scan-in at ride positions, voice-to-incident reporting, camera-validated behavioral timestamps. Maximum signal quality — every action is independently verified.

QR scan-in → exact position + time

Voice-to-incident → hands-free reporting

Camera validates QR timestamps

Works on any smartphone over 4G

Each tier adds signal depth. Source divergence across tiers = the finding. AI anomaly detection runs at every tier.

Behavioral Anomaly Detection

Measuring whether inspections actually happened.

Traditional compliance systems ask "was the box checked?" AS 360 asks "was the inspection physically performed?" The anomaly engine runs across all data streams and flags three behavioral patterns that distinguish real compliance from fabricated compliance.

SPEED FLAG

34s

vs. 4.1 min peer average

A 22-item daily ride inspection completed in 34 seconds. Consistently. Across 14 operating days. Nobody can physically inspect hydraulic lines, restraint mechanisms, and emergency systems in half a minute. The checklist was checked — the inspection was not performed.

ZERO-VARIANCE FLAG

14 days

consecutive 100% PASS on all items

Two straight weeks with every item passing on every inspection. On a 22-item checklist covering mechanical, electrical, and environmental conditions across real-world operating days. Statistically improbable. When everything is always fine, nothing is being checked.

CLUSTERING FLAG

90s

3 checklists submitted before supervisor arrival

Three separate ride inspections submitted within a 90-second window — timed exactly to coincide with the shift supervisor's arrival. Batch-completion before the boss shows up. The timestamp clustering pattern itself is evidence of fabricated compliance.

WHAT HAPPENS WHEN A FLAG IS RAISED

Operator
XP penalty (−100). Streak broken. Flag visible on personal record.

Supervisor
Alert in amendment queue. Direct observation required next 5 shifts.

Ops Manager
Anomaly surfaces on dashboard. Integrity pillar impact calculated. CAR may be generated.

Insurer
Flag count visible in portal. Pattern trend in quarterly review. No operator names — facility-level only.

Score Integration

Every signal feeds one composite.

Readiness

Staffing compliance, training currency, pre-opening checklists, schedule adherence, OpsScan position data

Integrity

Audit completion quality, anomaly flag rate, amendment patterns, AuditScore, source divergence signals

Delivery

LensIQ throughput, rotation compliance, guest service audit scores, queue stress, OLI capacity utilization

Environment

Maintenance velocity, CAR closure rate, facility condition, VoxIntel response timing, weather-adjusted decisions

Each pillar weights data from multiple layers. No single source can dominate. Convergence increases confidence. Divergence flags risk.

RIDE Score Architecture → Methodology → ← Back to Platform

FOUR INDEPENDENT SIGNALS.ONE DEFENSIBLE SCORE.

FOUR INDEPENDENT SIGNALS.
ONE DEFENSIBLE SCORE.