AI fee anomaly detection cuts client costs 32%
The signal-to-meeting workflow
Match arrival/departure timestamps to billed detention.
Adjust for timezone + dock dwell outliers.
Indicates billing leakage or inefficiency.
Assign responsibility (shipper, carrier, consignee).
Score by overcharge potential (60%), shipper scale (30%), compliance exposure (10%).
Send quantified savings projection and invite to automate auditing.
A freight payments automation and audit SaaS platform serving shippers, third-party logistics providers (3PLs), and freight brokers managing thousands of monthly carrier invoices across truckload, less-than-truckload (LTL), and intermodal transportation modes.
The company has built competitive differentiation by transforming from reactive freight bill payment processing—where systems merely match invoices to purchase orders and release payments—into proactive anomaly detection that identifies billing leakage, contract compliance failures, and operational inefficiencies before they become chronic cost drains.
Their core insight is that recurring detention and demurrage charges (fees assessed when trucks wait too long at shipper/receiver docks or chassis are held beyond free time periods) represent both immediate financial waste and deeper operational breakdowns in dock scheduling, inventory management, or carrier communication.
While most shippers view occasional detention fees as inevitable cost of doing business, this platform recognized that systematic patterns—the same facilities generating detention charges month after month, the same carriers repeatedly affected, the same days-of-week showing loading delays—signal fixable process problems worth tens of thousands in monthly savings.
By fusing EDI shipment tracking data with carrier invoice line items, the AI surfaces detention patterns invisible in traditional freight audit processes that focus on rate validation and accessorial charge accuracy but miss operational insights embedded in those charges.
EDI 214 shipment status messages from carriers and transportation management systems provide real-time shipment lifecycle data: truck arrival timestamps at pickup and delivery facilities, departure times, detention start/stop windows when drivers wait for loading or unloading, and free time allowances specified in carrier contracts (typically 2 hours for truckload, 1 hour for LTL).
Carrier freight invoices in EDI 210 format contain line-item charges including base freight rates, fuel surcharges, and accessorial fees (detention, driver assist, reweigh, reclassification), each tagged with charge codes and timestamp references.
The platform reconciles arrival/departure timing from EDI 214 against billed detention charges in EDI 210 to detect discrepancies: carriers charging detention when trucks arrived late due to their own delays, double-billing detention and driver assist for the same wait time, or claiming detention beyond contracted free time periods.
Facility operating calendars and dock scheduling systems reveal whether detention events correlate with specific operational patterns: Monday morning receiving bottlenecks, end-of-month shipping surges overwhelming dock capacity, or inventory system outages causing put-away delays that hold inbound trucks.
The platform builds benchmark databases showing industry-standard detention rates by facility type and shipment characteristics, enabling comparison of each customer's performance against peers operating similar warehouses, distinguishing between acceptable occasional delays and problematic chronic inefficiencies.
The primary trigger fires when a facility or business unit generates five or more detention fee events within a single month, indicating systematic operational issues rather than isolated incidents.
The model looks for pattern clustering: detention concentrated on specific weekdays (Monday bottlenecks from weekend inventory buildups), specific time windows (morning receiving peaks, end-of-shift changeover delays), or specific carrier relationships (suggesting communication breakdowns or incompatible equipment/processes).
High-priority escalation occurs when detention fees exceed cost thresholds—cumulative monthly charges over $5K (signaling material financial impact) or individual events exceeding $500 (suggesting multi-hour delays indicating serious process failures).
The system particularly prioritizes patterns where invoice timestamps suggest billing errors rather than operational delays: detention charged when EDI 214 shows truck arrived within appointment window, or detention overlapping with carrier-caused delays (truck breakdown, driver schedule conflicts).
The model distinguishes between shipper-caused detention (warehouse not ready to load, inventory not picked, dock congestion) versus consignee-caused (receiver closed despite appointment, unloading equipment failures) versus carrier-caused (late arrival outside appointment window, equipment issues), enabling targeted responsibility assignment and intervention strategies.
The platform suppresses triggers for legitimately complex shipments where some detention is expected and contractually accepted (trade show deliveries, retail store small package, temperature-controlled requiring long product conditioning) to focus alerts on genuinely anomalous and avoidable charge patterns.
AI-powered qualification uses root cause classification algorithms analyzing detention event narratives, timestamps, and facility contexts to diagnose whether problems stem from dock capacity constraints (requiring capex in additional bays or staffing increases), inventory management failures (WMS integration issues, cycle count inaccuracies causing shipment holds), carrier communication breakdowns (missed appointment updates, equipment compatibility), or seasonal surge capacity mismatches (predictable peak periods lacking temporary labor or extended hours).
For each identified root cause, the platform estimates savings potential by calculating fully loaded cost: direct detention fees paid, freight budget variance from charges not in original quotes, carrier relationship damage from chronic delays potentially leading to capacity refusals or rate increases, and inventory carrying cost from delayed inbound shipments or held outbound customer orders.
Freight volume and rate class scoring assesses total addressable savings—a shipper with 10,000 monthly shipments where 3% incur detention has vastly larger opportunity than one with 500 monthly shipments and the same rate.
The qualification model weights overcharge potential and savings opportunity at 60% (larger financial impact creates stronger business cases for process improvements and automation investments), shipper scale and complexity at 30% (multi-facility operations with sophisticated supply chains have larger problems worth solving and budgets to address them), and compliance exposure at 10% (detention patterns suggesting Hours of Service violations or safety issues carry regulatory risk beyond pure cost).
The platform specifically targets shippers and 3PLs in the $100M-$2B annual freight spend range—large enough that detention leakage represents material absolute dollars ($500K-$5M annually) justifying automation investment but small enough that they lack enterprise-scale transportation management systems with built-in advanced analytics that larger Fortune 500 logistics operations deploy.
Reply rate increased from 20 to 57 percent as personalized outreach emails quantifying exact detention costs by facility and month ("your Memphis DC paid $47K in detention fees last quarter") with pattern analysis ("68% occur Monday mornings between 6-9am") demonstrated specific operational intelligence that generic freight audit vendors never provide.
Demo conversion jumped from 45 to 85 percent because product demonstrations used prospect's actual EDI data to showcase real detention events with facility-specific root cause diagnoses and projected savings from recommended interventions—showing concrete ROI calculations rather than theoretical benefits.
Win rate improved from 30 to 66 percent driven by the shift in value proposition from commoditized freight payment processing (where purchasing decisions focus on per-transaction pricing and incumbent switching costs are high) to strategic operational consulting identifying and fixing process failures (where customers willingly pay premium pricing for actionable intelligence that drives cost reductions).
Revenue grew $17M from $25M to $42M as the detention analytics module became the leading wedge product driving new customer acquisition and expanding within existing accounts as initial facility deployments proved ROI and expanded enterprise-wide.
The platform successfully transformed freight payments—traditionally viewed as back-office accounts payable drudgery—into strategic supply chain intelligence, elevating buyer personas from AP managers focused on cost-per-transaction to VP-level supply chain leaders evaluating network efficiency tools, fundamentally changing both deal sizes and customer lifetime value as operational intelligence creates far stickier relationships than transactional payment processing ever could.
You will speak with a market engineer, review the signals and workflows that fit your market, and leave with concrete next steps.
Book a Strategy Call