Batch and expiry travel from ERP to coder with no typing

The problem

The number one recall cause in this sub-sector is a keystroke.

A wrong expiry date is the number one cause of product recall in this sub-sector, and the hardest to explain to a retail account. The error is not caught on the line: it is caught at the point of sale or in the customer's warehouse, when product is already out there. In a plant with many products and many format changes a day, the exposure is permanent.

• The coder is one of the most modern machines on the floor and has a network interface. But it sits outside the flow.
• At every batch or format change somebody types the new code into its panel, by hand, with the line waiting.
• A wrong expiry is the number one cause of product recall in this sub-sector, and the hardest to explain to a retail customer.
• The error is not caught on the line: it is caught at the point of sale or in the customer's warehouse, when product is already out there.
• With many products and many format changes a day, the exposure is permanent.

How it fits the IRIS system

Connect stitches the two systems through APIs, replacing neither.

Connect stitches the two systems together via API. Neither system is replaced. When the ERP marks the order as started, iLEAN automatically publishes batch, packing date and calculated expiry to the coder based on that product's shelf life. Changing batch becomes a tap in the ERP instead of typing on the panel. And the coder confirms what it is really printing. The integration runs both ways: the machine returns what it is actually printing, so the system does not assume, it verifies. That signal is also the first ring of the zero-variance flagship case, because it identifies every bottle from the moment it is marked.

The machine returns confirmation of what it actually printed, not of what it was asked to print. That difference is what turns the coding record into evidence instead of an assumption.

See the full IRIS architecture →

Before and after

The isolated coder versus the stitched coder

Aspect	Today	With iLEAN Connect
Keystrokes per batch change	One, with the line waiting	Zero
Risk of wrong expiry	Permanent	Eliminated at human origin
Where the error is caught	Point of sale or customer warehouse	It does not occur
What was actually printed	Assumed	Confirmed by the machine and filed
Format change	One more manual step	A tap in the ERP
Either system	—	Neither is replaced

Impact estimate

Estimated impact — to validate 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.

• Estimated payback 3-6 months — among the fastest, because the machine already ships an interface and integration effort is low.
• Recall risk from wrong coding disappears: a long-tail cost that is hard to estimate and very high when it lands.
• One manual step removed from the changeover sequence, several times a day.
• And a per-batch record of what the machine confirmed it printed.

The return is fast and comes in two forms: the recall risk from miscoding disappears, a long-tail cost that is hard to estimate but very high when it lands, and one manual step drops out of the changeover sequence, shortening every format change of the day. Estimate to be validated.

And the fair question from the production manager

«Isn't a classic integration cleaner?» — it is the day the project reaches the top of the list, and that is the problem: it competes with producing and never gets there. This stitching replaces neither system and asks for no shutdown window, so it does not join that queue.

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