Skip to content
Knowledge & documentationElectronics & SensorsMachinery & Plant EngineeringMetal & MachiningPlastics & Packaging+2

Facts on demand in the meeting

Mid-negotiation, you ask for last year's price or the last complaint and have the answer with its source before the talk moves on.

Today

In a price negotiation, the buyer points to a discount from last year; in a meeting, someone wants to know how the last complaint ended. The figure is in the ERP, the QMS or a contract, but nobody in the room can get to it. So people guess, or the decision moves to the next meeting.

An example

At Arnstein, the key account manager is negotiating the AH-2210 housing in AlSi10Mg with a vehicle manufacturer's purchasing team. The buyer points to a 4 percent discount last year. The key account manager types 'AH-2210 discount 2025 and complaints?' and reads within seconds: the discount applied to the predecessor part AH-2190, the price of AH-2210 has stayed at 18.40 euros since start of production, and the last complaint was closed with the 8D report in May. He corrects the point in the meeting, with the framework contract and the price list as evidence.
Fictional company, typical workflow.

Your data, wherever it lives

Prices and delivery schedules sit in the ERP, agreements and visit reports in the CRM, framework contracts in the DMS, complaints and 8D reports in the QMS, and some commitments only in an e-mail or a chat. demi reads, understands and links them, with your rights. In the middle of the conversation, the AI finds the figure with its source in seconds, where someone would otherwise have to leave the room, and you make the decision.

Where the data lives today

  • Chats
  • ERP
  • CRM
  • DMS & archive
  • QM system
  • 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

    This case needs data from chat, ERP, CRM, DMS, QMS and e-mail. demi replaces nothing and links prices, orders, delivery schedules, complaints, contracts and agreements into one body of data per customer and part. So even a terse question finds its answer when it needs three systems.

  2. 2 · PermitPermission Layer

    You only get answers from data you may see in the source systems; margins and costing stay with costing and sales management. The answer appears only on your device, never on the screen in the room. Every question is logged with its answer and sources.

  3. 3 · ActIntelligence Layer

    The agent understands terse questions such as 'AH-2210 price 2025?' and answers in one sentence. Prices, quantities and dates are quoted word for word from the source, with a link; any calculation follows fixed rules. If it finds nothing or two sources contradict each other, it says so.

How it runs

  1. 1

    During the meeting, you type a short question in Teams or on your phone, or say it quietly.

  2. 2

    demi works out from the question which customer, part or contract it is about.

  3. 3

    The agent searches ERP, CRM, DMS and QMS, only in what you may see.

  4. 4

    Within seconds, the answer appears in one sentence, with a link to the source.

  5. 5

    After the meeting, questions and answers are attached to the customer as a note, and you decide what follows.

What changes

  • Decisions are made in the meeting, not in the next one

  • Figures from the source, not from memory

  • Fewer follow-up requests to sales support and quality after the meeting

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 answers questions in meetings within seconds from your systems, with the source; you decide.

12 min → 8.4 min per case

How does it run today?

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

How we calculate

200 questions in meetings × 12 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

Can the others in the room see what I ask?

No. Question and answer appear only on your device, in the chat or as a short message. Nothing appears on a shared screen unless you share it yourself.

How fast does the answer come?

Usually within a few seconds, even when it needs data from several systems. demi keeps the connected systems current all the time instead of starting to search when you ask.

What if demi cannot find the answer?

Then demi says so and names where it looked. With one tap the question goes to the responsible colleague, and her answer arrives as a message, often while the meeting is still running.

Does demi listen in on the meeting?

No. For facts on demand, your question is enough, typed or spoken quietly. Listening in, for minutes or for the live fact sheet during a customer call, is a separate step and only runs with the consent of all participants.

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