The fabric delivery note gets digitized with one photo

The problem

The truck waits while the dye lots are typed one roll at a time.

the truck waits, racking up demurrage, while the receiving lead types 10-20 lines into the ERP. Rushing it means dye-lot errors that surface weeks later in an untraceable color-matching problem.

• The receiving lead types 10-20 lines per delivery into the ERP: roll, yardage, supplier, dye lot. The truck waits and demurrage adds up. On a busy day, the next truck waits behind it.
• Rushing it is where the errors come from: a transposed lot number looks harmless at the dock. It is the least visible error in the plant and one of the most expensive later on.
• Weeks later it surfaces as a color-matching problem nobody can trace, because the roll's lot in the ERP is not the lot that was spread.
• And without the right lot on each roll, the chain from roll to bundle to garment breaks at its very first link. Every traceability promise made to a customer program depends on that first link.

How it fits the IRIS system

Connect in photo-to-analog mode — the supplier's paperwork, read as it comes.

Connect photo-to-analog mode recognizes the supplier's delivery-note layout and each roll's GS1-128/QR/barcode label, with no change required from the supplier. One-tap validation on the industrial tablet.

No supplier has to change its delivery note or its labels. The receiving lead photographs what arrived, validates with one tap, and the roll enters the ERP with the lot that will later follow it into every bundle. Traceability that starts wrong at the dock cannot be repaired further down the line.

See the full IRIS architecture →

Before and after

Typed receiving versus photographed receiving

Aspect	Today, typed	With iLEAN Connect
Truck unload time	About 1 hour	About 10 minutes
Dye lot per roll	Typed, sometimes transposed	Read from the roll label
Hidden lot errors	Surface weeks later at color matching	Zero
Roll-to-bundle-to-garment traceability	Broken at receiving	Complete via photo and GS1
Receiving-module licenses	One per typist	Only the validator
Supplier's paperwork	—	Unchanged

1-hour truck unload → 10 minutes. Hidden dye-lot errors → zero. Roll-to-bundle-to-garment traceability → complete via photo and GS1.

Impact estimate

Impact estimate — to be validated with your own receiving data.

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.

• Estimated payback 3-8 months.
• CFO angle: typical 50-70% reduction in receiving-module licenses. Only the person who validates needs one, not everyone who used to type.
• Truck unload from about an hour to 10 minutes, and the demurrage that came with it. The dock is freed for the next truck instead of being blocked by a keyboard.
• Hidden dye-lot errors to zero, with roll-to-bundle-to-garment traceability complete.

CFO angle — typical 50-70% reduction in receiving-module licenses, estimated 3-8 month payback. *Estimate to validate*.

And the fair question from the production manager

“What if it reads the wrong dye lot off a roll label?” — reading a GS1-128 or QR label and a delivery note with a known supplier layout is an anchored task, where the best models drop below 1.5% error [1]. On top of that, the code and the printed text are cross-checked against each other and against the delivery note, and the receiving lead confirms with one tap before the ERP is touched. A roll whose lot cannot be read with confidence is never entered by default.

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