Skip to content
Product data & engineeringPumps & ValvesElectronics & SensorsWater & EnvironmentMachinery & Plant Engineering+2

Classify products to ECLASS and ETIM

Attributes filled in, data sheets and catalogue exports ready for distributors, release after release.

Today

Distributors and marketplaces want classified product data in the current release of the standard. Classifying a whole catalogue by hand keeps product management busy for a long time. With every new release the work starts over.

An example

At Wallner+Hardt Sensortechnik, 4,800 pressure sensors and M12 connectors need classifying. The agent proposes the classes, fills 18 attributes per article, such as IP67 protection and a 0–10 bar range, flags 210 articles with no thread data and produces the distributor export.
Fictional company, typical workflow.

Your data, wherever it lives

Today items and attributes are scattered across the PLM and ERP, technical values sit in PDF data sheets and drawings, old mappings in spreadsheets, and distributors post their requirements on their portals. demi reads, understands and links them per item and attribute, with your rights. The AI proposes the class and attribute values with their source in seconds instead of ten minutes per item, again with every new release, and product management reviews and releases the export.

Where the data lives today

  • PLM
  • ERP
  • PDFs
  • CAD & drawings
  • Office files
  • Web & portals
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 PLM, ERP, portal and spreadsheets. demi replaces nothing and links product master data, data sheets and drawings with the classification standards and the mapping tables between their releases.

  2. 2 · PermitPermission Layer

    Product management confirms classes and approves exports, and distributors receive only released data through a portal or an export file. Every approval is recorded.

  3. 3 · ActIntelligence Layer

    The agent proposes a class for each article, maps attributes and converts units by fixed rules. Values come from the master data, not from the model, missing values are reported, and every value names its source.

How it runs

  1. 1

    The agent processes the articles that live in PLM and ERP.

  2. 2

    It proposes the right class for each article.

  3. 3

    It fills in the attributes and converts units.

  4. 4

    Product management reviews proposals and gaps.

  5. 5

    Data sheet and distributor export are built from the released data.

What changes

  • Faster listings with distributors

  • Consistent data sheets from one source

  • New releases without manual rework

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

+240 hfreed per year

Assumptions and calculation

demi assigns the class and fills the attributes from your data; you check and release the export.

10 min → 6 min per case

How does it run today?

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

How we calculate

300 products × 10 min × 40% × 1.0 (manual) × 12 months = 14,400 min = 240 h

Value per year, before demi costs

Freed per year+240 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

+€15,600

gained per year

240 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

Which releases of the standards are supported?

The releases your distributors ask for. Between releases, demi uses the official mapping tables and shows where a class or an attribute has changed. That way you can serve different buyers with different releases.

Can data sheets be created in several languages?

Yes. Attributes and values are stored language-neutral in the master data, and data sheets are built from them in the languages you need. Free text is translated and checked before release.

How are missing values reported?

As a list per article and attribute, with a hint where the value might be found, for example in the data sheet or the drawing. The agent never invents values. Anything missing stays empty until someone confirms it.

Is the data written back?

Yes, after release. demi writes confirmed classes and attributes back, and every change is recorded. Your PLM stays the leading system.

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