The lab's Excel is not the problem — it is that nobody on the ERP sees it.

The problem

Two parallel worlds in the same factory — the real one (Excel) and the official one (ERP).

In factories making breadsticks, crispbreads and grissini there is a pattern repeating with surprising consistency: quality control operates on a lab Excel, and the ERP operates on a transcription someone makes at the end of the month.

• The lab's Excel is the REAL operating tool. The operator knows it, opens it fast, needs no training for it, customizes it with their columns (moisture, weight, color, hardness, each parameter's acceptance range), and saves the data in the shift's shared folder. It works.
• The ERP is the official system of record, but nobody opens it to enter quality data. It takes ten minutes per batch between starting the session, navigating to the module, entering the fields, validating and closing. And it demands an extra license for every person who enters. The lab does not use it.
• The result: two parallel worlds. The real one (Excel, where the shift's live data is) and the official one (ERP, where the data transcribed at month's end lives, by a person who spends half a day copying and pasting). They coexist, but they are never the same data at the same hour.

The hidden cost of this duality has four stacking layers: (1) the person who transcribes — half a day of administrative work every month; (2) the lag of up to 30 days between the lab's real data and what the ERP sees, right when management asks for the dashboard; (3) the transcription errors that slip in — one miscopied decimal in moisture can change a batch's verdict; (4) when the IFS or BRC auditor arrives, there is no way to cross the Excel with the ERP because the cells do not match — the data is in both places but with different naming and misaligned dates, so it gets rebuilt by hand.

How it fits the IRIS system

iLEAN Connect does not replace the Excel — it connects it to the ERP without anyone noticing.

The problem is not the Excel. The problem is that the Excel and the ERP never talk, and forcing the lab to operate inside the ERP costs dearly (in time and licenses) without solving anything. iLEAN Connect, in "inward listening" mode, seals that crack: the Excel stays where it is, and the data flows to the ERP on its own.

Connect watches the lab's shared folder. When the quality manager saves the Excel, Connect reads the new cells, identifies them, deposits them in central memory, and after one tap of human validation inserts them into the ERP automatically. The operator changes nothing. The ERP stops needing 5 lab licenses.

The concrete mechanics of Connect applied to the quality control Excel in a breadstick and crispbread factory:

• "Inward listening" mode — Connect watches the lab's shared folder where the shift's Excel lives. It does not watch the operator; it watches the file. When it detects a new save, it activates.
• Reading only the delta — Connect reads only the cells changed since the last save. It does not reprocess the whole Excel or the old data: only the running batch's new data. That is what lets the system work in seconds, without saturating the network or the ERP.
• Parsing with an anchored LLM (not free generation) — the model identifies the lab Excel's column and row structure (sourdough moisture, average breadstick weight, bake color, hardness, batch, shift), without asking the operator to change a single column of their template. If the factory changes its Excel's format, Connect re-maps. The operator does not notice.
• iLEAN central memory instantly — the data crosses into central memory as soon as it is saved, not at month's end. That is what makes live dashboards possible, trend alerts (moisture rising three shifts in a row), and real-time batch dossiers for the auditor.
• Human validation before the ERP — the data stays in pending state until the quality manager validates it with one tap (on the earpiece, the tablet, the mobile app). Once validated, Connect inserts it into the ERP via API or RPC, per what the vendor supports.
• CRITICAL — the ERP license saving. Today the ERP demands a license per active user. If 5 lab people access the ERP only to enter quality data, that is 5 full licenses. With Connect, those 5 people keep their Excel and the ERP receives the data automatically without anyone from the lab entering the system. Typical result: from 5 licenses down to 1 — the validating manager's, and even then that manager often validates from the phone without opening the ERP. The vendor's invoice changes.

See the full IRIS architecture →

Before and after

Excel + manual transcription to the ERP vs. Excel + automatic Connect

Aspect	Today — Excel + monthly transcription	With iLEAN Connect "inward listening"
Data worlds	Two parallel ones (real Excel / official ERP)	A single one — the operator's Excel, the ERP receives what is validated
Time spent transcribing	Half a day of work every month	Zero — Connect reads and pushes on its own
Lag between real data and the ERP	Up to 30 days	Seconds — after the human validation
The lab's ERP licenses	5 (one per person entering to type data)	1 (only the validating manager)
Transcription errors	Inevitable — the miscopied decimal	Zero — the data is the same as the original Excel's
The IFS/BRC auditor asks for the Excel ↔ ERP cross-check	Manual reconstruction, days of work	An automatic per-batch dossier, the same data on both sides
Changes to the lab's Excel template	Retraining, re-proceduring	Connect re-maps — the operator does not notice

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 breadstick, crispbread and grissini factory, 2 shifts, quality control with a per-batch Excel in a shared folder, 4-6 lab people with ERP access exclusively to enter quality data.
• Connect pilot on the lab's folder (no machine touched, no Excel touched, no ERP touched in the initial phase — only delta reading and deposit into central memory). First visible value within a few weeks.
• Estimated payback between 4 and 9 months, depending on the number of Excels iLEAN absorbs (one per shift, one per line, one per SKU) and the volume of manual transcription avoided today.
• Direct saving in ERP licenses: a typical reduction of 50-80% in the quality/lab module's licenses, depending on how many users enter the ERP today just to transcribe. This lever alone can pay for the pilot in the first year.
• Recovery of half a day a month for every person who today spends time copying from the Excel to the ERP — time returned to the lab, not removed from the org chart.
• IFS/BRC compliance reinforced: an automatic Excel ↔ ERP cross-check per batch, a dossier rebuildable without manual work when the auditor arrives.
• The combined hard lever (licenses + time + zero transcription errors + audits) usually convinces the CFO before the quality lead — and that speeds up the decision.

And the fair question from the quality manager

"What if the AI misinterprets an Excel cell and puts wrong data 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 an Excel cell and mapping it to the ERP's equivalent field), the best models brought the error below 1.5% ^[1]. And even then, nothing critical is decided alone: iLEAN deposits the data as pending and the person signs before it crosses into the ERP. The three safety rings are there precisely for this.

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