Skip to content
Product data & engineeringPlastics & PackagingChemicals & Process IndustryFood & Beverage

Reuse proven formulations

For a customer requirement you find similar formulations with test results as a starting point.

Today

Formulation knowledge sits in lab notebooks, spreadsheets and the heads of a few developers. New requests start from scratch, and failed trials get repeated. When an experienced developer leaves, the knowledge leaves too.

An example

At Polivo Kunststoffverpackungen, a cosmetics customer asks for a white PP cream jar with 30 % post-consumer recycled content that matches the shade of the current jar. The agent finds three earlier formulations with their masterbatch share and test values: one matched the shade at ΔE 0.8, another failed the drop test.
Fictional company, typical workflow.

Your data, wherever it lives

Today your formulation know-how sits in paper lab notebooks and trial spreadsheets, test results in the LIMS, formulations and raw materials in the ERP, safety data sheets and customer specifications as PDFs in the DMS and in e-mails. demi reads, understands and links them per formulation and raw material, with your rights. For a new request the AI finds the closest formulations with their measured results in minutes and flags restricted raw materials, and the lab manager approves the trial plan.

Where the data lives today

  • Scans & paper
  • Office files
  • Databases
  • ERP
  • PDFs
  • DMS & archive
  • E-mails
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 LIMS, ERP, spreadsheets and DMS. demi replaces nothing and links formulations, raw-material data, lab trials and test results with customer specifications and the regulatory status of raw materials. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Developers see the formulations of their business unit, and confidential ones only named people, in search results too. The lab manager approves the trial plan, and this is recorded.

  3. 3 · ActIntelligence Layer

    The agent ranks similar formulations by their measured results and flags restricted raw materials. Proposals are always existing formulations with measured values and sources; it never claims a property it cannot show.

How it runs

  1. 1

    The customer requirement is captured with its target properties.

  2. 2

    The agent looks for similar formulations and their test results.

  3. 3

    It flags restricted and excluded raw materials.

  4. 4

    It ranks the starting points by their results.

  5. 5

    The trial plan goes to the lab as a draft.

What changes

  • Development starts from proven work

  • Failed trials are not repeated

  • Knowledge stays when developers leave

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 finds similar formulations with test results as a starting point; you develop the new one.

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

30 formulation requests × 2 h × 30% × 1.0 (manual) × 12 months = 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

How are confidential formulations protected?

Rights follow your org chart: anyone who may not see a formulation won't get it as a search hit or in an answer either. You can limit especially sensitive formulations to named people. Every access is recorded.

Can I search by measured properties?

Yes. You search by target values such as impact strength, density or fire behaviour, and the agent compares them with the test results in the LIMS. For each hit it shows the measurement it is based on.

Does it check regulatory restrictions on raw materials?

It flags raw materials marked as restricted or banned in your data, and those the customer specification excludes. Whether a substance is permitted in a given market is for your experts to judge; that assessment stays with your company.

What if our trials are only in lab notebooks?

demi reads the notebooks, scans included, and links the trials to the formulations. Anything unclear is flagged for review. With every new project, the searchable base grows.

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