The truck no longer waits on the ERP

The problem

At the dock, speed wins and the expiry date pays for it.

The truck arrives with a microbial strain, a plant extract or a chemical input. Every batch needs its lot and expiry recorded precisely, because an expired biological raw material loses potency and compromises the final batch. Today the receiving lead either types every line into the ERP — while the truck waits, racking up demurrage — or moves fast and risks a poorly traced batch.

• The truck arrives with a microbial strain, a plant extract or a chemical input. Each container needs its lot and expiry recorded precisely, and a single delivery can carry several lots of the same strain.
• An expired biological raw material loses potency: if it enters a fermenter or a formulation tank unnoticed, it compromises the whole final batch.
• Today the receiving lead either types every line into the ERP while the truck waits and demurrage runs, or moves fast and risks a poorly traced lot that nobody will be able to follow later.
• And for cold-chain materials, every minute the pallet sits at the dock waiting for the ERP is a minute out of refrigerated storage, and that loss of viability is not visible on the label.

How it fits the IRIS system

Connect in photo mode — delivery note and container labels, read in seconds.

With iLEAN Connect, they photograph the delivery note and the drum labels. Vision AI reads the note's layout and the barcode or QR on each label, extracting lot, quantity and expiry in seconds.

The receiving lead photographs the delivery note and the labels; vision reads the note's layout and each barcode or QR. What used to be the slowest step at the dock becomes one validation tap, and each strain lot enters the ERP with its expiry attached, ready to be checked again when it is called for dosing.

See the full IRIS architecture →

Before and after

Receiving typed by hand versus receiving by photo

Aspect	Today	With iLEAN Connect
Time per receiving	30-45 minutes	5 minutes
Lot and expiry per container	Typed line by line	Read from the label's code
Strain close to expiry	Found at dosing	Flagged at the dock
Cold-chain pallet at the dock	Waits for the typing	Moved to refrigerated storage sooner
Receiving-module licenses in biosolutions	Several	One
Demurrage while the truck waits	Accumulates	Cut short

With one validation tap, everything enters the ERP: receiving drops from 30-45 minutes to 5. The receiving module goes from several licenses to one. Typical 50 to 70% reduction, estimated payback 3 to 8 months.

Impact estimate

Impact estimate — to be validated against what the dock costs you.

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.
• Receiving drops from 30-45 minutes to 5, with lot, quantity and expiry for each container already in the ERP and checked against the purchase order.
• A typical 50-70% reduction in receiving/warehouse-module ERP licenses: the module goes from several users to one.
• And no expired or poorly traced biological raw material reaches a fermenter unnoticed, which protects every batch downstream and every grower who applies it.

Estimated payback 3-8 months · typical 50-70% reduction in receiving/warehouse-module ERP licenses.

And the fair question from the production manager

“What if it reads the wrong expiry on a damp label?” — reading a delivery note layout and a barcode or QR on a label is an anchored task, where the best models drop below 1.5% error [1]. The code is cross-checked against the printed text and the delivery note, and a mismatch is not loaded: it is shown to the receiving lead to resolve before the tap. The truck leaves sooner, and the lot that enters is the one actually on the pallet.

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