Shipium Rethinks Freight Audit as Forensics, Not Archaeology

Freight audit has long been a mundane aspect of supply chain operations, involving stacks of paper or teams poring over spreadsheets to reconcile invoices weeks after shipments have been delivered. Seattle-based shipping platform Shipium has launched Always On Audit, an AI-driven system designed to replace the old model of monthly invoice reconciliation with continuous, real-time monitoring of every shipment a customer sends.

Jason Murray, Shipium's CEO and co-founder, and Penny Allen, the company's SVP of AI Product and Engineering, joined FreightWaves Today to discuss the product and its significance as the next era of financial controllership for shippers. Murray, who built Shipium around a premise from nearly two decades in supply chain organizations, explained that the company views itself as the "rails for shipping," handling everything from promise to payment in the shipping process. The audit system completes the final piece, tying financial records to the shipment itself.

Allen emphasized the distinction between the old and new models of auditing. "Monthly audit and continuous audit are not the same job at different speeds. They audit different objects. Monthly audit is a batch job over one artifact: the invoice. It's archaeology. Continuous audit's object is the shipment itself from the moment it comes into existence to the moment it's delivered and an invoice occurs.

It's forensics." This shift required rethinking the architecture from scratch, focusing on a record that opens at the start and is continually updated as the shipment progresses. Allen explained that real-time data collection and AI training are crucial for this architecture.

The AI layer is trained to recognize subtle nuances, such as how different carriers' bills may use similar codes. The result is a relentless, always-on system that checks every decision Shipium makes against the "gold standard" and explains any discrepancies in real-time. While the system is not fully automated, humans still handle the most complex exceptions, which feed back into the model to improve accuracy.

Shipium's "digital twin" is a real-time model of a shipment's cost and physical specifications, built at the moment the package is rated and routed. This digital twin helps trace errors to their exact origin, allowing for forensic analysis of the issue. By retaining the full shipment record, Shipium can pinpoint the source of billing disputes, which often stem from shipper-side errors like declared weight or dimension problems.

The system's ability to identify issues before they generate bad charges sets it apart from competitors. Early beta results show immediate detection of issues such as carriers charging base rates instead of contracted rates, as well as misapplied surcharges. While Shipium's broader platform typically delivers a 12% cost reduction for parcel customers, Always On Audit is still in its early stages.

Murray's conviction in the importance of prevention over documentation stems from his experience overseeing vendor chargebacks in the early 2010s.