Skip to content
Product data & engineeringPlastics & PackagingTool & Mould MakingAutomotive Suppliers

Track customer changes to the tool

With each new revision you see the affected areas and effort, so every change gets billed.

Today

While the tool is being built, the customer sends new part revisions, often by e-mail. Soon nobody is sure which revision the tool reflects or who pays for the change. The result: changes that never get billed, and arguments at tool acceptance.

An example

At Norvelta, revision F of a housing arrives: two ribs move and a wall thickness changes. The agent maps the change to positions 3 and 7 of the 4-cavity tool W-2219, core and cavity inserts in 1.2343, four of each, and drafts a change quote based on three comparable past changes.
Fictional company, typical workflow.

Your data, wherever it lives

New part revisions arrive today by e-mail or from the customer portal, as CAD models and PDF drawings; the revision the tool is built to sits in the PLM, booked hours and earlier change quotes in the ERP. demi reads, understands and links them per tool and customer revision, with your rights. The AI shows the affected inserts, slides and effort in minutes instead of two hours of comparing, and the project manager releases the change quote.

Where the data lives today

  • E-mails
  • Web & portals
  • CAD & drawings
  • PDFs
  • PLM
  • ERP
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 e-mail, ERP, PLM and CAD. demi replaces nothing and links customer revisions and change notices to the tool project, its components, the booked hours and the quotes. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Project managers see costs and hours. The project manager approves the change quote before it goes to the customer, and every approval is recorded.

  3. 3 · ActIntelligence Layer

    The agent compares revisions feature by feature and maps each change to the affected inserts and slides, with its source document. It derives the effort from booked hours on similar past changes and keeps the revision history for each tool.

How it runs

  1. 1

    The new customer revision arrives by e-mail or portal.

  2. 2

    The agent compares it with the revision the tool is built to.

  3. 3

    It maps the changes to the affected inserts and slides.

  4. 4

    It estimates the effort from similar past changes.

  5. 5

    The change quote goes to the project manager for release.

What changes

  • Every change gets billed

  • A clear revision status for every tool

  • Fewer disputes with customers

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

+144 hfreed per year

Assumptions and calculation

demi assesses the new customer revision and shows the affected areas and effort; you decide and quote.

2 h → 1.4 h per case

How does it run today?

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

How we calculate

20 customer changes × 2 h × 30% × 1.0 (manual) × 12 months = 144 h

Value per year, before demi costs

Freed per year+144 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

+€9,360

gained per year

144 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

Can it compare revisions from customer portals?

Yes, if the portal offers access or an export; how the revisions get to demi, we work out in a call. Anything sent by e-mail is picked up from the mailbox. Every revision ends up with the right tool project, however it arrived.

How is the change effort estimated?

From similar past changes and the hours actually booked on them. The agent shows which cases it relied on. The project manager adjusts the estimate before the quote goes out.

Is there a history for each tool?

Yes. Every customer revision, change, quote and release is linked to the tool. At acceptance you can see which revision has been built and which changes have been billed.

What if the customer only mentions a change on the phone?

The project manager adds a note to the tool, and the agent drafts a request for the written revision. The request only goes out after release. Until the revision arrives, the change stays marked as open.

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