Skip to content
Procurement & supply chainFor every industry

Review reorder proposals and safety stock

MRP proposals checked against consumption, orders and lead times, with an explanation of where stock levels are set wrong.

Today

Reorder points and safety stocks were set years ago and no longer match demand. The result is shortages on one side and slow-moving stock on the other. Planners have no time to review every item.

An example

At Talwerk Antriebstechnik the agent finds 310 items whose safety stock covers more than a year of demand, among them 8 × 7 × 40 parallel keys. It also finds 42 items with frequent shortages, such as 40 × 62 × 7 shaft seals. It proposes new values for both groups, each with consumption and lead time.
Fictional company, typical workflow.

Your data, wherever it lives

Stock, consumption and open orders sit today in the ERP, reorder points and safety stocks as parameters set years ago in the item master, lead times and supplier reliability in planners' spreadsheets on the drive and in order confirmations by e-mail. demi reads, understands and links them per item, with your rights. The AI checks every item in minutes instead of just a sample and proposes new values with the calculation, and materials management decides what goes back into the ERP.

Where the data lives today

  • ERP
  • Office files
  • Folders & drives
  • 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 ERP and spreadsheets. demi replaces nothing and joins stock, consumption history, open orders, replenishment lead times and supplier reliability per item. demi writes back only after approval.

  2. 2 · PermitPermission Layer

    Buyers see the proposals for their items. The materials manager approves parameter changes, and every change is recorded.

  3. 3 · ActIntelligence Layer

    The agent calculates demand and variation from recorded consumption with fixed formulas, compares them with the current parameters and explains every outlier. It proposes new reorder points and safety stocks with the calculation behind them.

How it runs

  1. 1

    demi reads stock, consumption and lead times per item.

  2. 2

    The agent calculates demand and variability with fixed formulas.

  3. 3

    Items with too much or too little safety stock are flagged and explained.

  4. 4

    New parameters go to materials management for approval.

  5. 5

    demi writes back only after approval.

What changes

  • Fewer shortages

  • Less capital tied up in stock

  • Parameters that match demand

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

+160 hfreed per year

Assumptions and calculation

demi checks each proposal against usage, orders and lead times and explains it; you order.

5 min → 3 min per case

How does it run today?

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

How we calculate

400 order proposals × 5 min × 40% × 1.0 (manual) × 12 months = 9,600 min = 160 h

Value per year, before demi costs

Freed per year+160 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

+$10,400

gained per year

160 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

Does it replace our MRP?

No. MRP keeps running in the ERP. demi checks the parameters it calculates with and proposes better values. demi writes back only after approval.

How often are parameters reviewed?

As often as you like, for example monthly or whenever demand shifts noticeably. demi keeps calculating in the background and reports items whose parameters have drifted away from actual consumption. Maintenance becomes routine instead of a yearly project.

Can it consider supplier reliability?

Yes. If a supplier often delivers later than confirmed, that spread goes into the safety stock. The proposal shows how much comes from fluctuating demand and how much from unreliable delivery.

What if the consumption data is distorted?

One-off orders, stock-take corrections or transfers can distort consumption. The agent flags such outliers and shows the postings behind them. Planners decide whether they count in the calculation.

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