Skip to content
Quality, standards & complianceChemicals & Process IndustryFood & BeverageMedical TechnologyPharma & Biotech

Line clearance at product changeover

demi guides line clearance at every changeover, checks photos of the stations and the first label and documents the release.

Today

At a product changeover the line must be clear: no labels, packaging or leftovers of the previous product, the right cleaning after an allergen change, date coding and label matching the new item. In practice this is a paper checklist, ticked off in a hurry at night and filed in a binder. A forgotten label roll or a wrong best-before date shows up only at the customer, and a recall follows.

An example

At Tarvina, line 3 switches at night from the mustard and dill sauce SC 250 g to a vegan herb dip. Mustard and egg appear in the allergen matrix only for the previous product, so the agent asks for a wet clean of hopper and dosing unit with a rapid test for egg. On the photo of the labeller it spots an opened roll of sauce labels in the storage tray, and the first dip label shows a best-before date 60 days ahead instead of the 21 days in the item master, because the date coder is still set for the previous product. The shift leader has the roll removed and the coder reset, then releases the line.
Fictional company, typical workflow.

Your data, wherever it lives

Your line clearance lives today as a paper checklist at the line and later in a binder, changeovers in the MES, recipes, shelf lives and label templates in the ERP, the allergen matrix in the QM system or a spreadsheet. demi reads, understands and links them for every changeover, together with the photos from the line, with your rights. The AI checks stations and label in minutes instead of by eye, and the shift leader decides on the release.

Where the data lives today

  • Photos, video & audio
  • MES
  • ERP
  • QM system
  • Scans & paper
  • Office files
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: production plan and changeovers from the MES and ERP, item master with recipe, shelf life and label template from the ERP, allergen matrix and cleaning rules from the QM system, plus photos of the stations from the tablet at the line. demi replaces nothing and builds the right checklist for every changeover, from the previous product to the next.

  2. 2 · PermitPermission Layer

    The line crew sees the checklist of its line; shift leaders and quality see all releases. The photos show stations, not people, and serve only as evidence. Only the shift leader may release, and every release is recorded with photos and a time stamp.

  3. 3 · ActIntelligence Layer

    The agent derives from the allergen matrix which cleaning the changeover requires, for example a wet clean with a rapid test. It compares the photos of filler, labeller and conveyors with the clean standard and marks leftover labels, packaging or residue. On the first label it checks item, allergen labelling, batch and best-before date against the item master; the rules come from your specifications, and the language model only explains the finding.

How it runs

  1. 1

    When a changeover is due, demi creates the checklist for exactly this changeover.

  2. 2

    The line photographs the stations, and the agent compares each photo with the clean standard.

  3. 3

    If the allergen change requires a wet clean, it asks for the rapid test result.

  4. 4

    It checks the first label against item master, allergens, batch and best-before date.

  5. 5

    The shift leader sees the open points and releases the line, and the release goes into the record.

What changes

  • Line release only with proof that labels and leftovers are gone

  • Allergen changes with the cleaning your plan requires

  • Every release documented with photos and time stamp

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

+180 hfreed per year

Assumptions and calculation

demi guides the checklist and checks photos and label; you release the line.

15 min → 12 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 product changeovers × 15 min × 20% × 1.0 (manual) × 12 months = 10,800 min = 180 h

Value per year, before demi costs

Freed per year+180 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

+€11,700

gained per year

180 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 does demi know the clean state of each station?

From reference photos that your quality team takes and approves once per line and station. The agent compares every new photo with them and marks what does not belong. If a photo is blurred or a station is missing, it asks for a new one.

How does demi recognise an allergen changeover?

From the allergen matrix and the recipes of the previous and the next product. If the previous product contains an allergen that the next one does not declare, the checklist requires the cleaning and verification your rules prescribe for it.

What does the agent check on the label?

Item name, allergen labelling, batch, best-before date and barcode, each against the item master and the label template. If something differs, it shows photo and target side by side. The line resets the printer, not demi.

Does this also apply to medical devices and chemicals?

Yes. Wherever labels, packaging or leftovers of the previous product must not reach the next lot, line clearance is part of every changeover, for example for medical devices or hazard labelling in filling. demi builds the checklist from your rules per industry and line.

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