Metrology connected to the ERP

The problem

Two parallel worlds, and a technician copying cells between them.

Two parallel worlds: the real spreadsheet with live data, and the official ERP with data transcribed weeks late by someone spending hours a month copy-pasting.

• The spreadsheet holds the live data: the dimensions measured on the coordinate measuring machine, the control plan characteristics, the deviations per batch and the capability history the OEM asks for at every review.
• The official ERP holds a transcribed, incomplete and out-of-date version. The practical gap runs to weeks, and everybody on the floor knows which of the two to trust.
• Transcription errors surface at the worst possible moment: preparing a PPAP submission or answering a claim on a structural dimension.
• And hours a month of an expensive metrology technician go into copy and paste instead of into measuring, which is the one thing only they can do. It is also the least defensible line in the department's budget, because everybody already knows the transcription adds nothing except a second chance to make a mistake.

How it fits the IRIS system

Connect listens inward — to the file, not to the person.

Connect listens inward: it watches the shared folder, reads the delta when the file is saved, parses it with a grounded LLM, validates on screen and pushes to the ERP via API.

The capability indices the customer asks for at each review stop being rebuilt: they are in the system, up to date, on the day they are asked for. That turns an afternoon's work into a query, and it removes the quiet risk of presenting an OEM with figures that were transcribed by hand from a sheet somebody had already corrected.

See the full IRIS architecture →

Before and after

Today's metrology lab versus the connected lab

Aspect	Today	With iLEAN Connect
Gap between real data and ERP	Weeks	Second zero
Manual transcription	Hours a month, minimum	Zero
Capability for an OEM review	Rebuilt by hand	Ready in the system
Copy-paste errors	Surface during a PPAP	Eliminated
Spreadsheet format	Has to be respected	Tolerated as it is, even as it changes
Quality and lab ERP licenses	Several named users	One, the supervisor who validates

From weeks of lag to zero. From hours a month transcribing to zero.

Impact estimate

Impact estimate — to be validated against your actual 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. If several metrology and quality people log in purely to enter results, those are licenses you stop paying: a typical 50-80% reduction, recurring every year.
• Estimated payback 4-9 months.
• Hours a month of an expensive technician recovered, and given back to measuring.
• And from a gap of weeks between the dimension measured on the machine and the figure the ERP shows, down to second zero, with both worlds finally saying the same thing.

CFO angle: typical 50-80% reduction in quality/lab-module ERP licenses. Estimated payback 4-9 months. Estimate to validate.

And the fair question from the production manager

“Several people have been editing that sheet for years — does it really hold up?” — that is the anticipated case. Parsing does not depend on fixed cell positions: it interprets columns, units, merged cells and margin notes without asking the lab to standardize anything. It is an anchored task, where the best models drop below 1.5% error [1], and the quality supervisor validates before the push.

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