Skip to content
Quality, standards & complianceFood & Beverage

Calculate nutrition and ingredients for labels

After every recipe change, nutrition values, allergens and ingredient order are recalculated.

Today

Every recipe change needs new label data. Quality assurance recalculates it by hand from supplier specifications, often in spreadsheets. One error on the label can trigger a recall.

An example

At Tarvina, a supplier switches the oil in a sauce base. The agent recalculates nutrition values for 14 products and flags 3 labels whose fat value changes, among them a dressing at 250 kcal per 100 ml.
Fictional company, typical workflow.

Your data, wherever it lives

Today recipes sit in the ERP or PLM, raw-material specifications and allergen data arrive from suppliers as PDFs by e-mail, quality assurance recalculates nutrition values in spreadsheets, and label templates sit in the DMS. demi reads, understands and links them per recipe and label, with your rights. After every change the AI recalculates nutrition values, allergens and ingredient order in minutes instead of hours of manual work, each value with its source, and quality assurance approves the label.

Where the data lives today

  • ERP
  • PLM
  • PDFs
  • E-mails
  • Office files
  • DMS & archive
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, PLM, spreadsheets and DMS. demi replaces nothing and links recipes to raw-material specifications, allergen data and label templates; each recipe is tied to its product and labels. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Recipes are confidential and visible only to R&D and quality assurance. Quality assurance approves the labels, and every approval is recorded with its version.

  3. 3 · ActIntelligence Layer

    The agent calculates nutrition values and ingredient order deterministically from recipe quantities and specifications, never by estimate, and derives the allergen declaration. It backs every value with its specification and recipe line and reports which existing labels change.

How it runs

  1. 1

    A new recipe or a changed specification comes in.

  2. 2

    The agent calculates nutrition values and ingredient order.

  3. 3

    It derives the allergens from the raw-material data.

  4. 4

    It shows every difference from the current label.

  5. 5

    The new label data goes to quality assurance for release.

What changes

  • Label data recalculated after every change

  • Faster product launches

  • Lower recall risk

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 works out nutrition values, allergens and the ingredient list from the recipe; you approve the label.

90 min → 54 min per case

How does it run today?

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

How we calculate

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

Value per year, before demi costs

Freed per year+216 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

+$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

Which labeling regulations does it cover?

demi calculates by the rules your quality assurance sets up: reference quantities, rounding, order, allergen list. Which regulations apply in which market is assessed by your experts; that legal assessment stays with your company. demi makes sure the rules are applied the same way in every calculation.

How do changed supplier specifications get into the system?

New specifications arrive by e-mail, portal or upload and are linked to the raw material. When a value changes, the agent shows right away which recipes and labels are affected.

Who releases the label?

Quality assurance. The agent prepares the data and marks every change against the previous version. Only after release does the data go to label printing or prepress.

What if a specification is missing or incomplete?

The agent stops and reports the missing value and the raw material. It drafts a request to the supplier, which quality assurance releases. Values are never guessed from similar raw materials.

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