The coil delivery note that enters itself

The problem

The foundation of all structural traceability depends on typing under pressure.

The truck waits racking up demurrage while the receiving supervisor types. If they rush, wrong heat numbers get entered that surface weeks later as an untraceable nonconformity.

• The truck arrives with high-strength steel coils: a delivery note with several lines, a mill certificate per heat and a label on each coil with heat number, grade, thickness, width and weight.
• Both ways out are bad. Either the truck waits forty-five minutes racking up demurrage, or the receiving supervisor types in a hurry.
• A heat number typed wrong does not fail today. It fails weeks later, when a claim arrives and the heat the failed structural part came from cannot be proved.
• And the mill certificate ends up filed loose in a cabinet, when it is precisely the document that closes the genealogy an OEM asks for on a crash-relevant part. Nobody links it to anything at the dock, because linking it by hand would mean keeping the truck standing there even longer.

How it fits the IRIS system

Connect in photo-to-analog mode — delivery note, certificate and label, with no supplier changes.

Connect photo-to-analog mode: AI vision recognizes the supplier's delivery-note format and the heat-number labels (GS1-128, QR, barcode or OCR), with one-tap tablet validation.

The mill certificate stops being a filed sheet of paper and becomes linked to the coil from minute one, and from there to every structural part blanked out of it. That is what turns the heat-to-part genealogy into a query instead of a reconstruction with the clock running, which is the only version of that exercise the customer ever accepts.

See the full IRIS architecture →

Before and after

Today's receiving versus captured receiving

Aspect	Today	With iLEAN Connect
Truck at the dock	45 minutes	Minutes
Heat number in the ERP	Typed under pressure	Read from the label and confirmed
Mill certificate	Loose in a cabinet	Linked to the coil from minute one
Heat to structural part genealogy	Rebuilt during the claim	Complete and queryable
Carrier demurrage	Recurring	Eliminated
Receiving module licenses	Two or three	One, the supervisor who validates

From a 45-minute truck wait to minutes. From hidden heat-number errors to complete photo-based traceability.

Impact estimate

Impact estimate — to be validated with your 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: the receiving module typically needs two or three active licenses; with Connect only the supervisor validates: a typical 50-70% reduction, recurring.
• Estimated payback 3-8 months.
• From a 45-minute truck wait down to minutes, truck after truck, with the carrier demurrage that goes with it eliminated and the dock freed for the next delivery.
• And complete photo-based traceability, with the note and the label stored as they were, instead of hidden heat-number errors that surface weeks later as an untraceable nonconformity nobody can close.

CFO angle: typical 50-70% reduction in receiving-module ERP licenses. Estimated payback 3-8 months. Estimate to validate.

And the fair question from the production manager

“Does it recognize every steel supplier's delivery note?” — yes, and without asking any of them to change theirs: the model extracts the table structure with no per-supplier template. Labels are read by their symbology where there is one — GS1-128, QR or barcode — and by optical recognition where there is not. It is an anchored task, where the best models drop below 1.5% error [1], and the supervisor confirms before anything enters.

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