The paper delivery note should not block the truck's unloading.

The problem

Receiving's bottleneck is not the truck: it is the keyboard.

Any given morning in a factory producing breadsticks, crispbreads and grissini:

• At 9:30 the truck enters with a big order: strong flour, seasoning, sesame, packaging film. Twelve pallets in total.
• The supplier hands over an A3 delivery note with twelve detail lines, each with its product, quantity, batch and expiry. Each pallet also carries its own batch labels stuck on the side.
• The receiving lead has to sign the note and enter the ERP to record line by line, batch by batch, before that flour can be registered as available for production.
• If they do it slowly to avoid mistakes, the driver waits 45 minutes billing demurrage. The factory pays the demurrage invoice.
• If they do it fast, batch errors appear three weeks later in a health alert that can no longer be traced — because the batch the ERP says is not the batch that actually came in.
• Today's alternative: either an intern transcribing, or an ERP receiving module that costs a license per user plus implementation. And even then, someone keeps typing.

The bottleneck is not the truck, nor the warehouse, nor the ERP. It is the person who has to recontextualize by hand what is already written on a paper.

How it fits the IRIS system

Connect in "photo of the analog" mode — digitization starts at the dock.

iLEAN does not add another screen to the receiving lead; it takes away the two they had. The piece is iLEAN Connect in its most characteristic mode: photo of the analog, the one that digitizes paper reports, delivery notes, labels and signatures without asking the supplier to change anything in their system.

The receiving lead takes out the phone or the industrial tablet and takes two photos. Connect reads, extracts, proposes. The person validates with one tap. The ERP receives the clean entry. The truck leaves in 5 minutes, not 45.

The Connect pieces applied to raw material receiving:

• A photo of the whole delivery note. The camera recognizes the supplier's note format without asking the supplier to change theirs. The inference understands the tabular structure and extracts what matters: note number, lines (product, quantity, batch, expiry), supplier, date. It works for the lifelong flour miller's handwritten A3 and for the film supplier's printed A4 with a barcode.
• A photo of the incoming pallet. For the pallet's batch labels, the camera recognizes GS1-128, QR, barcodes or, if the label only has plain batch and date text, reads it by OCR. If three batches are mixed on one pallet, it separates them as three independent entries instead of inventing an average one.
• Everything goes to the AI central memory at second zero. It does not wait for the end of the shift, does not wait for "someone to write it up". The raw information is stored with its original photo as evidence.
• One-tap validation. The receiving lead sees on their tablet a summary ("12 lines extracted, 3 unique batches, one doubtful field flagged in yellow, confirm?") and signs with one tap. If something does not add up, they correct it before signing — never after.
• Automatic insertion into the ERP via API/RPC. Without anyone from receiving having opened the ERP's receiving module, the lines enter clean, with their batch, quantity and expiry. The ERP's bulk-capture module is no longer needed.
• The result at the dock: the driver leaves in five minutes. Zero demurrage invoice. The flour is registered as available for production without waiting for the last keystroke.
• A direct saving in ERP licenses. The ERP's receiving module typically demands 2-3 active licenses (receiving lead + peak-hour support + supervisor). With Connect, only the receiving lead validates with a tap, without properly entering the ERP. Typical result: a single receiving ERP license instead of three, and the bulk-capture module's cost removed. What used to be paid per user to "enter data" is now paid by the phone's camera.

See the full IRIS architecture →

Before and after

A keyboard at the dock vs. a photo to central memory

Aspect	Manual receiving + ERP module	With iLEAN Connect (photo to the ERP)
The truck's unloading time	45 min while someone types	5 min — the photo is processed afterwards
The receiving lead's work	Typing 12 lines into the ERP	One photo + one validation tap
Hidden batch errors	Surface 3 weeks later in an alert	Zero — validated with the photo in front
Batch-to-plant traceability	Rebuilt by hand when there is a scare	Photo + GS1 linked to the batch, automatic
Receiving module ERP licenses	2-3 active users	1 — the rest validate from the tablet
Carrier demurrage	A recurring invoice	Zero
The batch's IFS/BRC audit	An Excel rebuilt the night before	A per-batch dossier, automatic, with the photo

Impact estimate

Impact estimate for your plant — to be validated 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.

• Mid-sized plant making breadsticks, crispbreads and grissini, with 8-12 daily raw material receipts (strong flour, seasoning, seeds, packaging film, oil) and batch-to-plant traceability demanded by the retail customer and by IFS/BRC audits.
• Estimated payback 3-8 months, depending on the daily receipt volume and the carrier demurrage documented in recent years.
• A direct saving in ERP licenses: typically a 50-70% reduction in receiving/warehouse module licenses depending on how many people enter today just to record entries, plus removal of the ERP bulk-capture module's cost when it was contracted separately.
• Recovery of the receiving lead's time ≥ 1 hour/day returned to their real job (raw material quality control, supplier non-conformity management, coordination with production).
• Carrier demurrage cut to minutes: a direct saving on recurring demurrage invoices and a better relationship with carriers who stop losing the morning at your dock.
• Batch-to-plant traceability complete by photo (audits without archaeological reconstruction). The batch's file for the IFS/BRC auditor comes out on its own.
• Estimate to be validated with your numbers.

And the fair question from the logistics manager

"What if the AI misreads the batch and puts a wrong expiry into the ERP?" — hallucination is a problem of free generation, not of anchored tasks. In tasks where the AI limits itself to recontextualizing a data point from one system to another (reading a GS1-128 label or a delivery note line and translating it into an ERP entry), the best models brought the error below 1.5% ^[1]. And even then, nothing critical is decided alone: Connect proposes, the receiving lead validates with one tap, and only then does the data enter the ERP. The original note's photo is stored as evidence — if someone ever disputes a batch, the original paper is there, with its signature.

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