The lab Excel sheet that's already in the ERP

The problem

The battery lab lives in a spreadsheet the ERP never sees.

Two parallel worlds — the real Excel (live test data) and the official ERP (data transcribed weeks late by someone who spends meaningful time each month copy-pasting and making mistakes in data a customer OEM may later audit).

• Every shift, the lab supervisor fills in a spreadsheet with electrolyte density, CCA, reserve capacity and internal resistance for the sampled batteries. Sometimes cold-cranking and capacity results come from different benches and are merged by hand.
• That sheet sits in a shared folder. The official ERP holds a transcribed version that runs weeks behind the real test data. Anyone looking for a lot's test results in the ERP sees an incomplete picture.
• Someone spends meaningful time each month copying and pasting cells, and copying errors land in data an OEM may later audit. Those errors tend to surface in front of a customer, which is the worst place to find them.
• Two parallel worlds, and the one the customer audits is the one that is out of date. And the person copying is usually the most qualified one in the lab. It also lets quality compare CCA and capacity trends across battery models without opening a single spreadsheet.

How it fits the IRIS system

Connect in listen-inward mode — it watches the lab's shared folder, not the technician.

Connect "listen inward" mode — it watches the shared folder (not the person), reads the delta when the file is saved, parses it with an anchored LLM, validates on screen, and pushes it to the ERP via API.

The lab keeps its spreadsheet exactly as it is. When the file is saved, the new rows are read, checked on screen and pushed to the ERP, so the CCA history the OEM asks for is already there on the day they ask. The lab supervisor recovers the hours spent copying, and the ERP stops being the place where test data goes to age.

See the full IRIS architecture →

Before and after

The battery lab spreadsheet today versus connected to the ERP

Aspect	Today	With iLEAN Connect
Gap between lab test and ERP record	Weeks	Zero-second, after validation
Electrolyte density and CCA per sample	In a sheet nobody else queries	In the ERP, by lot and date
Monthly copy-paste time	Hours of a lab supervisor	Zero
Transcription errors in audited data	Found when the OEM asks	Eliminated at the source
Spreadsheet format	Must be respected	Read as it is, even when it changes
Quality and lab module seats	One per person who types	Only those who validate

Weeks of lag → zero-second. Monthly transcription time → zero.

Impact estimate

Impact estimate — to be validated against your ERP invoice.

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.

• 💰 CFO angle: the ERP bills per named user. People who log in only to type lab results no longer need a seat: typically a 50-80% reduction in quality and lab module licenses.
• Estimated payback 4-9 months on top of that recurring saving.
• From weeks of lag to zero-second, and monthly transcription time down to zero. The lab supervisor gets those hours back for analysis and for supporting the formation line.
• And the CCA and capacity history requested in an OEM review stops being rebuilt by hand.

CFO angle — typical 50-80% reduction in quality/lab-module licenses, plus estimated 4-9 month payback. *Figure to validate*.

And the fair question from the production manager

“Our lab spreadsheet has been edited by several people for years — will it cope?” — that is the expected case: parsing does not rely on fixed cell positions, it interprets columns, units and margin notes as they are. It is an anchored task, where the best models drop below 1.5% error [1], and the lab supervisor validates on screen before anything is pushed to the ERP.

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