Skip to content
Warehouse, shipping & traceabilityPlastics & PackagingChemicals & Process IndustryFood & Beverage

Tankers: check cleaning certificates and previous cargoes

Before filling, demi checks each tanker's cleaning certificate and previous cargoes against your rules and proposes release or block.

Today

Before a road tanker is filled, it has to be clean, and its previous cargoes have to suit the product. The driver brings the cleaning certificate and the list of recent loads as a slip, a photo or a PDF, often in a foreign language, and at the loading bay there is hardly time to check them against your banned list and the customer's requirements. If a wrong previous cargo slips through, the whole batch can be contaminated, and at the customer perhaps the storage tank as well.

An example

At Orvelon in Bad Dürrenberg, a tanker is due to load 24 tonnes of AR 240 plant cleaner for a dairy. The agent reads the cleaning certificate and previous cargo list from the photo the driver takes at the gate: cleaned two days ago, number plate, tank number and seals match. But the third-last cargo is a mineral oil product, and the dairy's specification excludes mineral oil in the last three cargoes. demi proposes a block, the shift supervisor confirms, and the haulier sends another tanker. In October the agent checks 186 fillings this way and blocks 9, each with the passage in the document.
Fictional company, typical workflow.

Your data, wherever it lives

Cleaning certificates and previous cargo lists arrive today as slips, photos or PDFs from the driver or by e-mail from the haulier, loading orders sit in the ERP, banned lists and customer specifications in the QM system and in contracts. demi reads, understands and links them for every filling, with your permissions. The AI checks in seconds what there is otherwise no time for at the loading bay, and your shift supervisor decides whether the tanker is loaded.

Where the data lives today

  • Photos, video & audio
  • Scans & paper
  • PDFs
  • E-mails
  • ERP
  • QM system
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: photos and scans from the gate, PDFs and e-mails from hauliers, the ERP with loading order and product, and the QM system with banned lists, compatibility rules and customer specifications. demi replaces nothing and attaches each filling to its order, vehicle, tank, cleaning certificate and previous cargoes. The loading bay sees in one record what is to be loaded and what was in the tank before.

  2. 2 · PermitPermission Layer

    Quality assurance maintains banned lists and customer specifications; the loading bay sees only the result with its reason. The shift supervisor decides on release or block, and only the head of quality can approve an exception to the rule. Every decision is logged with photo, reason and name.

  3. 3 · ActIntelligence Layer

    The agent reads cleaning certificates from photos and PDFs in any language and recognizes cleaning station, date, procedure, seal numbers and the last cargoes. demi checks by fixed rules, not by gut feeling, whether a previous cargo is allowed under your list and the customer's requirement. The agent maps unclear substance names via UN or CAS number and flags them when that is not certain.

How it runs

  1. 1

    The driver checks in at the gate; cleaning certificate and previous cargo list arrive as a photo, a scan or in advance by e-mail from the haulier.

  2. 2

    demi assigns them to the loading order and checks number plate, tank number, cleaning date and seals.

  3. 3

    The agent checks every previous cargo against your banned list and the customer's requirements for this product.

  4. 4

    The loading bay gets a proposal, release or block, with the passage in the document and the rule that applies.

  5. 5

    The shift supervisor decides, and if the tanker is blocked, demi drafts the message to the haulier.

What changes

  • Filling released only after cleaning and previous cargoes are checked

  • Wrong previous cargoes caught at the gate, not at the customer

  • Every filling fully documented, audits included

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

+144 hfreed per year

Assumptions and calculation

demi checks cleaning certificate and previous cargoes against your rules; the shift supervisor decides.

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

180 tanker fillings × 10 min × 40% × 1.0 (manual) × 12 months = 8,640 min = 144 h

Value per year, before demi costs

Freed per year+144 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

+$9,360

gained per year

144 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

Can demi read cleaning certificates from photos?

Yes, from photos, scans and PDFs, including the European Cleaning Document (ECD) and certificates in other languages. Fields the agent cannot read with certainty are flagged rather than guessed, and the filling stays on hold until someone confirms them.

Where do the rules for permitted previous cargoes come from?

From your QM system: your banned lists, compatibility rules per product and your customers' specifications, even if they exist only as a PDF in the contract. The agent shows which document each rule comes from; only quality assurance can change it.

Can demi block a tanker on its own?

demi proposes, and the decision is made at the loading bay, by the shift supervisor or quality assurance. No filling starts without release, and every decision is logged with photo, reason and name.

Does it also help in choosing hauliers?

Yes. demi counts blocks and missing documents per haulier and cleaning station and shows who often arrives with unsuitable previous cargoes. Dispatch sees this before awarding the next transport.

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