Automated gate systems built by EAIGLE are catching attempted cargo theft two to three times a month per site at the company's higher-volume facilities, according to chief executive Amir Hoss — and the fraud they detect is precisely the kind that slips past a human checker working under time pressure.

The pattern the system flags most often is disarmingly simple. A fraudster uses an expired bill of lading to pick up a different load from the same carrier, pairing it with a trailer number where four of five or six digits match the legitimate one and a single digit does not. A person scanning paperwork in a queue waves that through. A gate that validates the bill of lading, handles multiple bills per shipment and maps them against each other does not.

Hoss did not hedge on the core question of whether automation makes a facility harder or easier to steal from. Harder, he said — provided the gate is well integrated. The qualifier carries weight.

Theft detections drove expansion

EAIGLE offered a concrete proof point. At a deployment with what the company described as a top-five consumer packaged goods customer, the system detected three theft events in the first month. All three involved either fake documentation or attempts to take empty trailers. That result, Hoss said, drove the expansion to additional sites.

The framing the company leans on is velocity. A gate is a high-throughput environment, and the errors that matter are single-digit ones. Humans miss those. Machines do not.

From validating transactions to scoring carriers

The more consequential shift sits in how the gate treats the carrier itself. EAIGLE reads the DOT number from camera in real time — it is always visible and always present, making it what Hoss called the low-hanging fruit — then pulls the carrier's history tied to that number, including theft history and claims, and evaluates it against a risk profile the customer defines in advance. Cross a threshold the customer set, and the transaction becomes an exception regardless of whether the paperwork is clean.

The gate no longer validates a transaction. It scores a counterparty.

Pressed on the obvious hole — US carrier identity fraud frequently involves a compromised DOT number, sometimes as crudely as a placard on a truck door — Hoss argued a digital identity is not one identifier but the collection of everything visible at once: license plate, DOT number, truck number, color, existing damage, cross-referenced against prior sightings across the network. The practical version, he said, is matching two identifiers, the plate and the DOT, and confirming they belong together.

Risk scoring also does not have to be binary. A clean grade proceeds normally. A middling grade triggers a license verification. No information at all triggers a deeper check where the driver photographs their license, takes a selfie, and the system confirms the two match — identity verification at the gate itself.

Who owns the failure

Contractually, liability turns on the standard operating procedure, which the customer defines and EAIGLE maps. If the system followed the SOP and everything matched, the company's position is that it did the job it was contracted to do. If the system checked, nothing matched, and the gate opened anyway, that lands on EAIGLE. Hoss said he could not recall a case where the SOP was followed correctly and the system failed.

A $800 camera against tens of thousands

Loblaw, EAIGLE's flagship reference, previously built a heavy portal intermodal arc for a different vendor before changing direction. Hoss drew three lessons from watching that effort fail: the capital expenditure does not scale — no finance organization approves generational infrastructure projects across a hypothetical 400-site network; the underlying models were built for intermodal rather than carrier-heavy inland freight; and twenty-year-old technology carries real integration limits.

The hardware comparison was blunt. EAIGLE uses off-the-shelf cameras in the range of $800 to $1,200 each. The legacy installation at that site used cameras with OCR built into the hardware at tens of thousands of dollars apiece, plus the arc.

Fragmented data is the product

Asked whether EAIGLE has walked away from deals because a customer's underlying stack was not in shape, Hoss said the question does not apply. Filling that gap is the product. The company brings more value where systems are fragmented and no data lake exists, because that is the condition creating the problem. Where systems integrate, they integrate. Where they do not, EAIGLE reads the data and acts as middleware, using flat files if necessary — cement plants running programmable logic controllers from the 1960s being the extreme case.

That inverts the usual enterprise software pitch: the worse your data environment, the more this is worth.

On data ownership, Hoss was clear. The customer owns the data and the per-site model improvements, which are not shared with other customers by default. A subset permits sharing, and what moves is the model itself — the coefficients and weights — rather than the underlying data. Most customers allow it, with a handful of exceptions.

Volume, ports and autonomy

Pricing is an annual software fee plus a one-time hardware cost for kiosks and servers, with security integrators handling installation, scaling by site and volume. The smallest facility EAIGLE serves runs about 50 transactions a day, the largest over 1,500, with an average near 500. The economics work from 50.

At ports, where automation collides with organized labor in ways retail distribution does not, the approach is augmentation. At a California port customer handling roughly 1,500 to 2,000 trucks a day, guards remain in place; the system pre-populates their tablet, and the guard checks the trailer, photographs the seal and uploads it. At that volume, shaving fifteen or twenty seconds per truck is the whole business case.

On autonomy, roughly half a dozen of EAIGLE's thirty-plus clients are testing autonomous operations. Loblaw's work with Gatik is public. One customer is beginning to test twenty autonomous Class 8 trucks on distribution-centre-to-store runs. Autonomous shunting inside the yard is further along — enabled by the detail that roughly half of EAIGLE's customers do not have paved, marked spots, so the system geomaps trailer positions on dirt and gravel rather than reading painted numbers.

The company processes more than half a million trailers a month. Whether its claimed moat — computer vision models reading non-conforming carrier equipment in multi-lane environments, where intermodal-era systems dating to 2004-2008 never aimed — proves durable or merely a head start is a question the market will answer. For shippers and 3PLs running facilities, the question has already shifted: not whether to automate the gate, but whether the data feeding it is good enough for the decision it is now being asked to make.