Skip to content
Service & spare partsMetal & MachiningPlastics & PackagingMining & Raw MaterialsEnergy & Utilities+4

Which missing part would stop you for weeks?

demi links spare-part lists, stock, lead times and breakdowns and shows every critical part you hold no spare for.

Today

Whether a plant stops for a week or for five months often comes down to one part: a gearbox, a bearing, a control board with a 20-week lead time. Nobody knows exactly which parts these are. Spare-part lists sit in the makers' PDFs, stock in the ERP, lead times in old orders, and the critical-parts list, if there is one, is kept by a supervisor on the side.

An example

At Montanis Hartsteinwerke, the agent links the spare-part lists of 58 machines, from the primary crusher to the washing screen, with stock, purchase history and four years of breakdowns. 31 parts have no spare and a lead time of more than twelve weeks. At the top is the gearbox of the inclined conveyor behind the primary crusher: without this belt the whole plant stops, and the last delivery took 22 weeks. In the store the agent finds the same gearbox under a different material number, booked as a spare for a conveyor idle since 2019. The plant manager has it rebooked and approves orders for three more parts, about 64,000 euros in total.
Fictional company, typical workflow.

Your data, wherever it lives

What is inside your machines sits today in the makers' spare-part lists as PDFs, stock and orders in the ERP, lead times in order confirmations in the mailbox, breakdowns in maintenance tickets, and the critical-parts list, if there is one, in a workshop spreadsheet. demi reads, understands and links them per machine and part, with your rights. The AI shows in hours instead of weeks which missing part would stop you longest, and your plant management decides what goes into stock.

Where the data lives today

  • PDFs
  • ERP
  • E-mails
  • Tickets
  • Office files
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

    Data sources in this case: the makers' spare-part lists and manuals as PDFs, the ERP with material master, stock and purchase history, the maintenance system, order confirmations in the mailbox and workshop spreadsheets. demi replaces nothing and links every part, by the maker's part number, to its machine, bin, consumption, lead time and breakdowns. You also see when the same part sits in several machines or under two material numbers in the store.

  2. 2 · PermitPermission Layer

    The workshop and maintenance see parts, stock and breakdowns of their machines; only purchasing and plant management see purchase prices and supplier terms. demi proposes orders and transfers; an authorised person triggers them in the ERP, and that is recorded.

  3. 3 · ActIntelligence Layer

    The agent reads the spare-part lists, maps every item to a material number and rates each part by criteria you set: does the plant stop without the machine, how long is the lead time, is there a spare, how often did the part fail. demi computes lead times from order and goods-receipt data, not by estimate. For every critical part without a spare it proposes quantity and storage place and sets the value of the spare against the cost of a stop.

How it runs

  1. 1

    demi reads the spare-part lists of your machines and maps every item to a material number.

  2. 2

    The agent links each part with stock, consumption, lead time and the breakdowns of recent years.

  3. 3

    Each part is rated by your criteria: bottleneck in the material flow, lead time, spare, failure frequency.

  4. 4

    For critical parts without a spare the agent proposes quantity and storage place and weighs the value of the spare against the cost of a stop.

  5. 5

    Plant management decides what to stock, and purchasing orders in the ERP.

What changes

  • You know which parts could stop your plant for weeks

  • Spares where a stop would cost most

  • Duplicate and forgotten stock comes to light

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

+192 hfreed per year

Assumptions and calculation

demi links spare-part lists with stock and lead times; you decide what to keep in stock.

4 h → 2.4 h per case

How does it run today?

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

How we calculate

10 machines × 4 h × 40% × 1.0 (manual) × 12 months = 192 h

Value per year, before demi costs

Freed per year+192 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

+€12,480

gained per year

192 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 package

Questions about this use case

Our spare-part lists exist only as PDFs from the maker. Is that enough?

Yes. The agent reads spare-part lists and exploded views, scanned ones included, and maps every item to your material master by the maker's part number. If it finds no matching material number, it shows the item for clarification instead of creating one.

How does demi know the real lead times?

From your orders and goods receipts in the ERP and from order confirmations in the mailbox. For every lead time the agent shows where it comes from and how old it is. If there is none, it flags the part and proposes a request to the supplier.

What counts as critical?

You define it. Typical criteria: does the whole plant stop without the machine, is the lead time long, is there no spare, does the part fail often. Every rating shows its reasons, so you can check and change it.

Doesn't a bigger spare stock tie up too much capital?

That is why demi weighs the value of every proposed spare against the downtime cost you set. Often stock turns up that is already there: the same part under two material numbers, or spares for machines shut down long ago. You decide what is ordered.

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