Skip to content
Quality, standards & compliancePumps & ValvesElectronics & SensorsMachinery & Plant EngineeringPlastics & Packaging+5

Recall: narrow the scope, notify, prove effectiveness

Affected units narrowed by batch and serial number, notifications per country drafted, effectiveness proven with the return rate.

Today

When a safety issue arises, every day counts. Yet days go into working out from ERP exports, MES data and delivery notes which units are affected and where they are. When in doubt, the whole product line is recalled. Authorities expect a notification without delay and, later, proof that the recall works.

An example

Wallner+Hardt Sensortechnik finds that on its IO-Link pressure sensor WS the output can freeze at the last value in the cold; the cause is a capacitor from one component batch. Via batch, production order and serial number the agent narrows the scope to 3,240 affected sensors instead of all 18,000 in the series, pulls 212 customers and 4 distributors from delivery notes and the CRM, and drafts the customer information and notifications for 5 countries. After three weeks the return rate stands at 71 %, and the agent shows the two distributors whose confirmation is missing. The head of quality releases every notification.
Fictional company, typical workflow.

Your data, wherever it lives

The trail of a faulty batch runs through many systems today: component batches and delivery notes in the ERP, serial numbers in the MES, test results in the QM system, customers and distributors in the CRM, replies in e-mails. demi reads, understands and links them, with your rights. The AI narrows the scope in hours instead of days and drafts the notifications, and your head of quality decides.

Where the data lives today

  • ERP
  • MES
  • QM system
  • CRM
  • 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

    Data sources in this case: ERP, MES, QM system, CRM and e-mail. demi replaces nothing and links component batches, production orders, serial numbers, delivery notes, customers and distributors into one chain per unit, with replies and returns attached. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    The full scope is visible to quality, sales and management. Each customer receives only the information on its own deliveries, authorities only the released notification, and every release is recorded.

  3. 3 · ActIntelligence Layer

    The agent builds the chain from recorded bookings, not assumptions, and flags gaps such as missing serial numbers. It drafts customer information and notifications to the templates your experts store per country, and calculates the return rate from returns and confirmations.

How it runs

  1. 1

    Quality reports the defect with its cause and the affected components or batches.

  2. 2

    The agent follows batch, production order and serial number to every delivery and narrows down the affected units.

  3. 3

    It lists customers, distributors and stock; holds in the ERP are set only after approval.

  4. 4

    Customer information and notifications to the authorities per country are drafted, every figure with its source.

  5. 5

    The head of quality releases them, and the agent tracks replies and the return rate until closure.

What changes

  • A narrow, documented recall scope instead of whole product lines

  • Fast and complete notifications

  • Effectiveness proven to the authorities

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

+72 hfreed per year

Assumptions and calculation

demi narrows the affected units by batch and serial number and drafts the notices; you decide.

20 h → 14 h per case

How does it run today?

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

How we calculate

1 recalls and field actions × 20 h × 30% × 1.0 (manual) × 12 months = 72 h

Value per year, before demi costs

Freed per year+72 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

+€4,680

gained per year

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 precisely can the recall scope be narrowed?

As precisely as your bookings allow: by component batch, production order and serial number. Where a link is missing, the agent shows the gap and works with the more cautious, larger scope. How far the recall goes is decided by the head of quality.

Does demi know the notification routes in each country?

demi works with the routes and templates your experts store per country and product group, for example for consumer products, machinery or medical devices. The agent fills them with documented figures. Whether and when to notify is your decision.

How does demi reach customers who bought through distributors?

The agent prepares, per distributor, the list of affected deliveries and a template to pass on to their customers. It tracks who has confirmed and flags who is still missing after the deadline you set.

How does demi prove that the recall works?

With the return rate from returns, replaced devices and confirmed actions, per customer and country. The report for the authority is drafted with every figure linked to its booking.

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