The truck no longer waits on your receiving dock

The problem

Heat-to-tube traceability starts with someone typing next to a waiting truck.

the truck waits racking up demurrage while the receiving lead types into the ERP. If they rush, they enter a mislabeled heat number that surfaces weeks later as an untraceable material nonconformance.

• The truck brings steel coil or raw tube for forming. The receiving lead keys the delivery note line by line, with heat number, gauge and quantity for each coil, plus the labels on every coil or bundle.
• Receiving takes around 45 minutes, and the truck racks up demurrage while it waits. On a busy morning, the next truck is already queuing behind it.
• Rushing it is worse: a mistyped heat number surfaces weeks later as an untraceable material nonconformance, usually in the middle of a customer investigation.
• And that heat number is exactly what an OEM asks for when a weld fails: which coil, which heat, which tubes. If that link is broken at the dock, the containment has to widen to every tube the plant cannot rule out.

How it fits the IRIS system

Connect in photo mode — the delivery note and the coil labels, as they arrive.

Connect photo mode. Vision AI recognizes the delivery note and the GS1-128, QR, or barcode labels, extracting heat number, gauge, and quantity. Validation with one tap on an industrial tablet.

The heat number is read off the coil's own label, not retyped from memory. That single change is what turns the chain from heat to coil to tube into a query instead of a reconstruction. And it is visible from the very first truck, without waiting for any other piece. The receiving lead validates, and the truck leaves while the next one backs in.

See the full IRIS architecture →

Before and after

Receiving by keyboard versus receiving by photo

Aspect	Today	With iLEAN Connect
Receiving time per truck	About 45 minutes	About 5 minutes
Heat number on record	Keyed by hand under pressure	Read from the label
GS1-128, QR or barcode labels	Scanned one by one, or ignored	Read in the same photo
Heat → coil → tube chain	Broken by one wrong digit	Complete
Truck demurrage	Paid every week	Eliminated
Seats in the receiving/warehouse module	Two or three	Reduced by 50-70%

45-minute receiving → 5 minutes. Hidden heat-number errors → zero. Broken heat-to-part traceability → complete via photo and GS1.

Impact estimate

Estimated impact — to validate with your own numbers.

The block below is an estimate to be validated against your plant's actual data. We put it forward so the committee has an order of magnitude; we refine it during the assessment.

• 💰 CFO angle: receiving and warehouse modules usually need two or three active seats; with Connect only the validator needs one: a typical 50-70% reduction, recurring.
• Estimated payback 3-8 months, counting dock time and the avoided cost of a mis-traced heat.
• From about 45 minutes per truck to about 5, and hidden heat-number errors down to zero, truck after truck.
• A complete heat-to-part chain, which is what closes a material nonconformance fast and keeps a containment to the coil actually involved.

typical 50-70% reduction in receiving/warehouse-module licenses, estimated payback 3-8 months. *Estimate to validate*.

And the fair question from the production manager

“Steel labels come in every format, some half torn — can it read them?” — labels are read by symbology where there is a GS1-128, QR or barcode, and by optical recognition where there is only printed text. Both are anchored tasks, where the best models drop below 1.5% error [1]. And a label that does not match the delivery note is flagged on the tablet before the one validation tap. No supplier is asked to change its paperwork.

^[1] OpenAI paper "Why Language Models Hallucinate", 2025 — on the reliability of AI in anchored tasks.