Skip to content
Planning & productionMachinery & Plant EngineeringMetal & MachiningPlastics & PackagingTool & Mold Making

Routing and setup sheet from proven parts

Operations, tools and cutting data come as a proposal from similar parts you have already made.

Today

Routings and setup sheets are often written from scratch, although proven tools and cutting data exist for similar parts. The know-how sits in old jobs and in the heads of a few setters. When one of them is away, it is trial and error again.

An example

Rabenhammer Präzisionsteile gets a new flange FL-4418 in 1.4301 with a Ø 60 h6 fit. The agent finds two similar flanges, proposes the same tools with their recorded cutting data and takes the shorter of the two actual times, citing job 23-1187. The process planner adjusts one operation and releases the setup sheet.
Fictional company, typical workflow.

Your data, wherever it lives

Routings and actual times sit in the ERP today, confirmations in the MES, drawings in CAD and PLM, tool lists and cutting data in the setters' spreadsheets on the drive, and old setup sheets as scans. demi reads, understands and links them per part family, with your rights. The AI proposes operations, tools and cutting data from proven parts in minutes instead of long searches or trial runs at the machine, and the process planner decides.

Where the data lives today

  • ERP
  • MES
  • CAD & drawings
  • PLM
  • Office files
  • Folders & drives
  • Scans & paper
Data LayerOne view of everything, with your rights

How demi solves it

Three layers in this order: connect the data first, then the rights, then the AI.

  1. 1 · ConnectData Layer

    The case needs data from the ERP, MES, PLM and the setters' spreadsheets. demi replaces nothing and links drawings, routings, tool lists, cutting data and actual times of past jobs per part family. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Process planners release routings; setters see the released setup sheet. Changes at the machine flow back as feedback tied to the job and are recorded.

  3. 3 · ActIntelligence Layer

    The agent finds similar parts already made by material, dimensions and tolerances and proposes operations, tools and cutting data. It takes times and cutting data from recorded jobs, never by estimate, and every proposal names its source job.

How it runs

  1. 1

    Read in the new drawing, detect material and tolerances

  2. 2

    Find similar parts already made, with actual times

  3. 3

    Propose operations, tools and cutting data

  4. 4

    Draft the setup sheet; the process planner reviews and releases

  5. 5

    Feed machine feedback back into the part family

What changes

  • Faster process planning

  • Proven parameters reused

  • Setter know-how stays in the company

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.

Assumption, editable

Your numbers

Result

+288 hfreed per year

Assumptions and calculation

demi proposes operations, tools and cutting data from similar parts; you check and approve.

60 min → 42 min per case

How does it run today?

What is already digital saves less: the factor lowers the share demi brings.

How we calculate

80 routings × 60 min × 30% × 1.0 (manual) × 12 months = 17,280 min = 288 h

Value per year, before demi costs

Freed per year+288 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

+$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 package

Questions about this use case

How does demi find similar parts?

By material, dimensions, tolerances, features from the drawing and the part family in the ERP. For each match you see how it differs from the new part. That makes it quick to judge whether a proposal fits.

Does it use our tool database?

Yes. demi reads tool master data, holders and storage locations as an export and only proposes tools you actually have. If a tool is missing, the proposal says so.

Where do the cutting data come from?

From your own recorded jobs: setup sheets, programs and machine feedback. Every value in a proposal names the job it comes from. Manufacturer recommendations are used only if you add them as a source.

Does this work for injection molding or stamping too?

Yes, the principle is the same: find similar parts and reuse proven parameters. In injection molding that means mold, machine, temperatures and cycle time from earlier setting sheets.

See this case with your data

In the demo we show you the workflow on your own systems.

Your configurator

No use cases yet

Your configurator is still empty

Add a use case from any card or case page and see what it brings per year, with the calculation. Free, no sign-up, no commitment: try it out and change any number.

Browse use cases