Skip to content
Sales & quotingPumps & ValvesElectronics & SensorsMachinery & Plant EngineeringMetal & Machining+3

A realistic delivery time right in the quote

At quoting, AI checks capacity, material and supplier lead times for this exact configuration and proposes a date production can meet.

Today

Sales quotes the lead time from the catalog or the last order. Production learns only after the order that a bought-in gearbox currently takes months, the welding shop is fully booked and the radio control is a special item. Then the date slips, with penalties, trouble and express freight.

An example

A steel stockholder asks Conveyra Fördertechnik for two double-girder bridge cranes BK 10 t with an 18 m span, mechanism group FEM 2m to EN 15011, with radio control and a requested date at the end of March. The catalog says 14 weeks. The agent sees that the gearbox for the hoist currently takes twelve instead of eight weeks from the supplier and is ordered only after design release, that the welding shop for the box girders is booked until mid-January, and that the radio control with a special button layout takes ten weeks. It proposes 20 weeks, or 16 weeks if the gearbox is ordered on the day the order comes in, and shows the lead time from the supplier's last order confirmation. Planning confirms, and the sales engineer quotes 16 weeks with the gearbox ordered early.
Fictional company, typical workflow.

Your data, wherever it lives

Lead times sit in the catalog and old quotes today, bills of materials in the PLM, replenishment times and open orders in the ERP, the production load in the MES and the suppliers' real dates in their e-mails. demi reads, understands and links them, with your rights. The AI proposes a date production can meet within minutes, and you decide what goes into the quote.

Where the data lives today

  • ERP
  • MES
  • PLM
  • 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: the ERP, the MES, the PLM and e-mail. demi replaces nothing and links the requested configuration with its bill of materials in the PLM, the replenishment times and open purchase orders in the ERP, the production load in the MES and the dates suppliers last confirmed by e-mail. So every configuration shows what it really needs and when that can be there.

  2. 2 · PermitPermission Layer

    Sales sees capacity, supplier conditions and internal bottlenecks as a result, not in detail; planning and purchasing see the full load. If the proposed date is shorter than the catalog time or needs a special release, planning confirms it before it goes into the quote. What was committed is logged.

  3. 3 · ActIntelligence Layer

    The agent breaks the configuration down into assemblies and critical parts, checks stock, replenishment time and open orders for each part and places the production steps on free capacity. The result is a delivery date with the bottleneck that sets it, plus variants that would be faster. Dates and times come from the ERP and MES; the language model only explains how the date was reached.

How it runs

  1. 1

    The inquiry names configuration, quantity and the customer's requested date.

  2. 2

    The agent breaks the configuration into assemblies and critical parts and checks stock, replenishment time and open orders.

  3. 3

    It places design, production and assembly on free capacity and finds the bottleneck.

  4. 4

    It proposes a delivery date with its reason, plus variants that would be faster, such as ordering the critical part earlier.

  5. 5

    Planning confirms, and you put the date into the quote.

What changes

  • Commitments production can keep

  • Bottlenecks visible before the order arrives

  • Fewer penalties, express shipments and crisis meetings

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 capacity, material and lead times for each quote and proposes a date; you commit to it.

30 min → 21 min per case

How does it run today?

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

How we calculate

80 quotes × 30 min × 30% × 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

How does demi know our suppliers' current lead times?

From the ERP: replenishment times in the master data, open purchase orders and their confirmations. Because master data is often out of date, the agent also reads the suppliers' latest order confirmations and date e-mails and shows which time it uses and why.

Does demi know how busy production is right now?

Yes, from the MES and ERP: production orders, operations, shift models and capacity per work center. The agent places the new configuration on free capacity as a trial, without scheduling anything. What really gets scheduled is planning's decision.

What if the customer needs an earlier date?

Then the agent shows what sets the date and what would shorten it: ordering a critical part earlier, a different version, assembly in two shifts or a partial delivery. Every variant is shown with its consequences, and you decide with planning.

Who releases the delivery date in the quote?

You do, after planning has confirmed it when the date is shorter than the catalog time or ties up capacity. The agent proposes and gives reasons; it commits nothing to the customer.

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