Today
Which elastomer or material suits a medium is buried in PDF tables and in the heads of a few experts. A wrong choice means leaks, failures at the customer and liability questions.
An example
A customer asks Hartwig & Brunn Pumpenwerk for a KP centrifugal pump (DN 80, PN 16, 1.4408 casing) for dilute sulphuric acid at 60 °C. demi rules out the standard NBR seal, proposes EPDM and FKM and cites table B-12, rows 47 and 48.
Your data, wherever it lives
Which material withstands which medium sits today in PDF tables from seal manufacturers and in your own compatibility tables in the DMS, which only a few experts read with confidence; variants and seals live in the PLM and ERP, and the request with medium and temperature arrives by e-mail. demi reads, understands and links all of it, with your rights. The AI gives sales the suitable materials with the table row in seconds, and engineering decides on every new rating.
Where the data lives today
- PDFs
- DMS & archive
- PLM
- ERP
- E-mails
How demi solves it
Three layers in this order: connect the data first, then the rights, then the AI.
- 1 · ConnectData Layer
Data sources in this case: the PLM, DMS and ERP. demi replaces nothing and links materials, media, your compatibility tables and the product variants; medium, concentration and temperature are captured the same way every time. demi carries the result into the quote or order in the ERP.
- 2 · PermitPermission Layer
Only engineering maintains the compatibility tables; sales can query them but not change them. Engineering approves new ratings before they enter the table, and every query is recorded.
- 3 · ActIntelligence Layer
The agent looks up compatibility in your tables by fixed rules, rules out unsuitable materials and proposes alternatives. Every answer cites the table row, with no free-text guess.
How it runs
- 1
Enter medium, concentration, temperature and pressure, or take them from the inquiry
- 2
demi checks every material of the variant against your tables
- 3
Unsuitable materials drop out, alternatives come with their source
- 4
Carry the result into the quote or order
What changes
Fewer field failures from wrong materials
Faster technical clarification
Expert knowledge available to sales
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
+128 hfreed per year
Assumptions and calculation
demi checks medium, concentration and temperature against your tables, with the source line; you answer.
20 min → 12 min per case
How we calculate
80 compatibility queries × 20 min × 40% × 1.0 (manual) × 12 months = 7,680 min = 128 h
Value per year, before demi costs
Freed per year+128 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
+€8,320
gained per year
128 h ÷ 1,760 h per role = 0.1 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 use our own compatibility tables?
Yes, that is what it is built for. demi makes your tables from PDFs and spreadsheets searchable. What counts is what you have approved, not a generic list from the internet.
What if the medium is not in the table?
demi says so plainly and gives no recommendation. The request goes to engineering, who assess the case. Once that assessment is approved, it is in the table next time.
Does every answer show its source?
Yes. Each answer names the table, the row and the revision. One click opens the source in the original document.
Does this work for materials other than seals?
Yes, as far as your tables cover them. The same check runs for casings, impellers, mechanical seal faces and O-rings.
