Today
When a part is unavailable, engineers compare data sheets by hand under time pressure. Alternatives already approved elsewhere in the company get overlooked.
An example
A capacitor for the inverter board at Talwerk Antriebstechnik has a 26-week lead time. demi finds an alternative already approved for another product, with 4,000 pieces in stock, plus a pin-compatible second source.
Your data, wherever it lives
Today the item master and stock sit in the ERP, approved alternatives in the PLM, data sheets as PDFs on the drive, lead times and catalogs in supplier portals, and end-of-life notices in e-mails. demi reads, understands and links them per component and characteristic, with your rights. The AI compares the data sheets in minutes rather than by hand and ranks the candidates by approval and stock, and engineering makes the choice.
Where the data lives today
- ERP
- PLM
- PDFs
- Folders & drives
- Web & portals
- E-mails
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 ERP, PLM, supplier portals and file share. demi replaces nothing and links the item master, data sheets, approved alternatives, supplier catalogs and stock in consistent units. demi writes back only after approval.
- 2 · PermitPermission Layer
Purchasing proposes, and engineering approves an alternative per product. Every approval is recorded with its reason.
- 3 · ActIntelligence Layer
The agent compares attributes by fixed rules, lists every difference with its data sheet and ranks the candidates: already approved, in stock, drop-in. It then tracks the approval to the end.
How it runs
- 1
Flag the short part, in the ERP or by e-mail
- 2
demi searches approved alternatives, stock and catalogs
- 3
Compare candidates with every data-sheet difference
- 4
Engineering approves, purchasing orders
What changes
Faster reaction to shortages
Fewer production stops
Approved alternatives reused
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
+216 hfreed per year
Assumptions and calculation
demi compares data sheets and shows fitting alternatives with every difference; you choose.
60 min → 42 min per case
How we calculate
60 alternative-part searches × 60 min × 30% × 1.0 (manual) × 12 months = 12,960 min = 216 h
Value per year, before demi costs
Freed per year+216 h
Assumption: labor cost of $48.62 per hour in US manufacturing in June 2026 (BLS), plus workplace, IT and overhead.
= Value per year, before demi costs
+$14,040
gained per year
216 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
How does it decide that a part is a drop-in replacement?
demi compares the data-sheet attributes value by value, such as electrical ratings, package, pin-out and temperature range. A part only counts as drop-in when every relevant value fits. Every difference is listed, small ones included.
Who approves an alternative?
Engineering, per product. Purchasing can propose candidates but cannot approve them. The approval is stored with its reason and is ready the next time the part runs short.
Can it search supplier catalogs?
Yes, catalogs and data sheets that exist as files or are connected through a portal. Catalog parts are not approved yet and are marked that way.
Is this only for electronics?
No. It works the same for standard parts, seals, bearings or hydraulic components. All it needs is attributes in data sheets or the master record.
