The delivery note that reaches the ERP with a photo and a tap

The problem

Traceability for a warranty return starts at the receiving dock.

The receiving supervisor types dozens of ERP lines while the truck racks up demurrage. If they rush, batches get mis-entered and surface weeks later in a warranty return with no clear traceability.

• The truck arrives with resin bags, pre-painted sheet metal coils, compressors or control boards. Each delivery note has dozens of lines and each pallet its own batch label.
• The receiving supervisor types it all into the ERP while the truck racks up demurrage at the dock and the next one waits outside. On a busy morning, the receiving office becomes the plant's bottleneck.
• If they rush, a compressor batch gets entered against the wrong line, or two batches get merged into one, and nobody notices. The ERP accepts it, because the number is valid; it is just the wrong one.
• It surfaces weeks or months later in a warranty return with no clear traceability: the field failure exists, the batch it came from does not.

How it fits the IRIS system

Connect in photo mode — delivery note and pallet labels, no supplier changes.

Vision AI recognizes the delivery-note format without asking the supplier to change it, plus the GS1-128/QR/barcode labels on each pallet. One-tap validation on an industrial tablet.

The supplier keeps its delivery note and the plant keeps its labels. What changes is that the batch of every compressor and every resin bag enters the ERP correctly the first time, which is the first link of any warranty investigation. The truck leaves in minutes.

See the full IRIS architecture →

Before and after

Receiving today versus receiving with a photo

Aspect	Today	With iLEAN Connect
Truck time at the dock	Long, with demurrage	Minutes
Batch entry errors	Hidden until a warranty return	Zero, caught at the tablet
Pallet labels	Read and retyped	GS1-128, QR or barcode read from the photo
Supplier's delivery note format	Has to be learned by each typist	Recognized as it is
Compressor batch to appliance	Broken link	Complete via photo and GS1
Receiving-module licenses in white goods	Several	Only the one who validates

Long carrier demurrage → minutes. Hidden batch errors → zero. Broken traceability → complete via photo and GS1.

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.

• Estimated payback 3-8 months, depending on the number of trucks per day.
• CFO angle: a typical 50-70% reduction in receiving and warehouse-module licenses, recurring every year. The license logic is the same as in the lab: whoever only typed stops needing access.
• Carrier demurrage cut from long waits to minutes per truck.
• Hidden batch errors at zero, and traceability complete from the dock to the finished appliance. A warranty claim on a compressor can be traced back to the truck it arrived on.

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

"We have thirty suppliers, each with its own delivery note — will it read them all?" — yes, without templates per supplier: reading lines, quantities and batches from a delivery note is an anchored task where the best models drop below 1.5% error [1]. Pallet labels are read by their GS1-128, QR or barcode symbology where present, and the supervisor validates with one tap before anything enters the ERP. Low-confidence fields are highlighted so the supervisor looks exactly where it matters.

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