Today
Engineering, ERP and the shop floor work with BOMs that drift apart after changes. The error shows up at the assembly station, when a part is missing or does not fit.
An example
For assembly 500-2000, a helical gearbox at Talwerk Antriebstechnik, demi shows that the ERP BOM still lists revision B of the cover while PLM has released revision C. A seal is also missing from the MES routing.
Your data, wherever it lives
Today the engineering BOM lives in the PLM and the CAD assemblies, the manufacturing BOM in the ERP and the routing in the MES; changes arrive by e-mail and as spreadsheet exports. demi reads, understands and links it all into one product structure, with your rights. The AI compares every line in minutes instead of hours, and the person responsible for the BOM decides on every correction.
Where the data lives today
- PLM
- CAD & drawings
- ERP
- MES
- E-mails
- Office files
How demi solves it
Three layers in this order: connect the data first, then the rights, then the AI.
- 1 · ConnectData Layer
The case needs data from the PLM, ERP and MES. demi replaces nothing and joins their BOM structures into one product structure with revisions and effectivity dates. demi writes back only after approval.
- 2 · PermitPermission Layer
Engineering and production planning see the comparison. The BOM owner approves corrections, and every approval is recorded.
- 3 · ActIntelligence Layer
The agent compares line by line by fixed rules on part number, quantity and revision and explains each deviation: missing, different quantity, different revision or alternative. For each one it proposes a correction, citing both source lines.
How it runs
- 1
Clarify the data sources: BOMs from PLM, ERP and MES
- 2
Compare the structures line by line
- 3
Review the deviations and their explanations
- 4
Approve corrections and write them back to the target system
What changes
Fewer assembly stops from wrong BOMs
The same data across all sources of the case
Changes reach production faster
What does it bring you?
Check it with your own numbers
Every starting value is an assumption you can change. The calculation sits right below, step by step.
Your numbers
Result
+288 hfreed per year
Assumptions and calculation
demi compares the bills of materials from PLM, ERP and MES and shows each gap; you resolve it.
2 h → 1.2 h per case
How we calculate
30 BOM comparisons × 2 h × 40% × 1.0 (manual) × 12 months = 288 h
Value per year, before demi costs
Freed per year+288 h
Assumption: labour cost of €49.50 per hour in German manufacturing in 2025 (Destatis), plus workplace, IT and overheads.
= Value per year, before demi costs
+€18,720
gained per year
288 h ÷ 1,760 h per role = 0.2 full-time roles
An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.
Combine with more cases and get the packageQuestions about this use case
Can it handle different BOM views?
Yes. A manufacturing BOM is often structured differently from the engineering BOM, for example with pre-assembly groups or consumables. demi matches items by part number and structure. Intended differences can be stored as rules, so they do not show up as deviations every time.
How are effectivity dates handled?
Every item carries its effectivity, by date or serial number. demi only compares states that are valid at the same time. That also shows whether a change takes effect in the ERP too early or too late.
Can it write corrections back?
Yes, after approval. demi writes back only after approval. The record shows who approved it.
Is it a one-off check or continuous?
Either. A good start is one comparison of all active assemblies. After that it runs automatically with every release in PLM.
