Skip to content
Sales & quotingPlastics & PackagingTextiles

The right fabric from the requirement profile

The customer names tensile strength, flame retardancy and weight; AI finds matching qualities in your range, backed by test reports.

Today

Customers in industry and construction rarely ask for an article number; they send a profile: tensile strength in warp and weft, tear strength, flame retardancy to a given standard, weight per square metre, coating, cold resistance, outdoor use. Your range has thousands of qualities, and the test reports behind them sit in the lab database, in folders and as old scans. Only a few experienced people know which quality fits and which report proves it, and every enquiry waits for them.

An example

A maker of high-speed doors for cold stores asks Fibrana for a coated door curtain: at least 3,000 N per 5 cm tensile strength in warp and weft, flame-retardant to DIN 4102 B1, at most 1,000 g/m² and cold-resistant down to −30 °C. The agent finds three qualities. GW 900 meets everything except cold resistance, which is only tested down to −20 °C; GW 1050 holds −35 °C but weighs 1,050 g/m²; GW 960 with a cold-flexible coating meets every value, but its B1 test certificate expires in March. It drafts the sample offer for ten running metres of GW 960 with all reports, and application engineering orders the certificate renewal before the offer goes out.
Fictional company, typical workflow.

Your data, wherever it lives

Today the knowledge of your range is scattered: articles and recipes in the PLM, test results in the lab database, test reports and certificates as PDFs and old scans in folders, prices and minimum quantities in the ERP, and the enquiry in a mailbox. demi reads, understands and links them per quality and measured value, with your access rights. The AI finds matching qualities with evidence in minutes instead of days, and application engineering checks and decides.

Where the data lives today

  • E-mails
  • PDFs
  • Scans & paper
  • Folders & drives
  • PLM
  • ERP
  • Databases
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 enquiry in the mailbox, the PLM with articles and recipes, the lab database with test results, test reports and certificates as PDF or scan in folders, and the ERP with prices, minimum quantities and lead times. demi replaces nothing and links every quality with its measured values, the reports that prove them and the orders in which it was delivered. For every value in the profile you find the qualities that demonstrably meet it.

  2. 2 · PermitPermission Layer

    Recipes and lab values are visible to development and application engineering; prices and terms only to sales. A customer's requirement profiles and drawings are seen only by the team working on that enquiry. Offer and test reports go out only after application engineering releases them; the release is recorded.

  3. 3 · ActIntelligence Layer

    The agent reads the requirement profile, also as a spreadsheet or specification, translates it into testable values and compares them with the measured values of your qualities. Whether a value is met is decided by the comparison with the test report, not by the language model; values without a report and expiring certificates are flagged. The language model only writes the reasoning and the cover letter for the sample offer.

How it runs

  1. 1

    The enquiry arrives by e-mail with requirement profile and intended use.

  2. 2

    The agent translates the profile into testable values, standards and test methods.

  3. 3

    It compares them with the test results of your qualities and ranks the matches by how much they meet.

  4. 4

    For each quality it shows which report proves which value and what is missing or about to expire.

  5. 5

    Application engineering chooses the quality, and sales sends the sample offer with the reports.

What changes

  • Matching qualities in minutes instead of days of searching

  • Every promised value is backed by a test report

  • Knowledge of the range no longer depends on a few people

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

+216 hfreed per year

Assumptions and calculation

demi matches the profile against your range's test reports; application engineering checks and releases.

90 min → 63 min per case

How does it run today?

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

How we calculate

40 fabric enquiries × 90 min × 30% × 1.0 (manual) × 12 months = 12,960 min = 216 h

Value per year, before demi costs

Freed per year+216 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

+€14,040

gained per year

216 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

What if the customer names a different standard from the one in our test reports?

Then the agent shows the difference, such as another test method, another specimen width or another fire class, and does not convert anything that cannot be converted. Whether a report is sufficient evidence or a new test is needed is decided by application engineering. A required test appears in the sample offer as an open point.

Can old test reports on paper be used too?

Yes. demi reads scanned reports with measured values, date, test institute and standard and assigns them to the quality. If a report does not clearly match one quality, for example after a recipe change, the agent flags it instead of using the value.

How does the agent know that a certificate is expiring?

From the date and validity in the certificate and from the rules you set per type of certificate, for example for fire classification. If a certificate expires before the planned delivery date, it appears as an open point in the offer. That way the customer does not find out only at acceptance.

Does this also work for nonwovens, films and laminates?

Yes. For coated fabrics, nonwovens, films and laminates it works the same way: read the profile, compare with measured values, show the evidence. Plastics processors use it in the same way to find the right semi-finished product or carrier material in their range for a part.

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