Today
Cutting lists for panels are put together by hand from many orders. A transposed digit in a dimension or edge shows up only at the saw or the edgebander. The result is scrap and delay.
An example
At Tannried Möbelwerk the agent builds cutting lists for 9 decors from 26 kitchen orders, including 19 mm MFC in RAL 9016. Before the list goes to the optimizer, it flags one part whose edge banding does not match the panel thickness.
Your data, wherever it lives
Orders and furniture BOMs sit today in the ERP, dimensions and edges in the drawings from CAD, decors, board thicknesses and edge rules in production planning's spreadsheets, and the cutting list is put together by hand. demi reads, understands and links them per part and order, with your rights. The AI breaks the BOMs down into single parts in minutes, groups them by material, decor and thickness and reports every conflict, and production planning releases the list for the optimizer.
Where the data lives today
- ERP
- CAD & drawings
- Office files
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 ERP, spreadsheets and CAD. demi replaces nothing and ties every part from furniture BOMs and orders to its order, material, decor, edge data and the dimensions from CAD. demi hands the approved list over in your optimizer's format.
- 2 · PermitPermission Layer
Production planning approves cutting lists, and the shop floor sees only the approved list. Every approval is recorded.
- 3 · ActIntelligence Layer
The agent explodes BOMs into parts, groups them by material, decor and thickness and checks dimensions and edges against fixed rules. It takes dimensions only from the BOM and reports every conflict with part and order instead of changing it silently.
How it runs
- 1
The orders for the next cutting run are selected.
- 2
The agent explodes the BOMs into individual parts.
- 3
It groups them by material, decor and thickness.
- 4
It checks dimensions and edges and flags conflicts.
- 5
Production planning releases, and the list goes to the optimizer.
What changes
Less manual list work
Fewer cutting errors
Clean input for optimization
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
+300 hfreed per year
Assumptions and calculation
demi builds the list per material and finish from bills of materials and orders; you run the optimizer.
15 min → 7.5 min per case
How we calculate
200 cutting lists × 15 min × 50% × 1.0 (manual) × 12 months = 18,000 min = 300 h
Value per year, before demi costs
Freed per year+300 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
+$19,500
gained per year
300 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
Does it replace our optimization software?
No. demi prepares the input; your optimization software still computes the cutting patterns. Results such as board usage can flow back into demi and stay linked to the order.
Can it check edge data?
Yes. The agent checks, for example, whether the edge matches the panel thickness, whether the edged sides are right and whether the edge allowance is included. You set the rules. It flags conflicts and never changes them silently.
Which formats can it export?
Whatever your optimization software reads, such as a CSV file or a spreadsheet with fixed columns. The format is set up once and then applies to every list.
What if the BOM in the ERP is wrong?
The rule check catches many errors, such as implausible dimensions or missing edges, and flags the part. The fix happens in the BOM in the ERP, not in the cutting list, so the error does not come back with the next order.
