Skip to content
Sales & quotingPumps & ValvesMachinery & Plant EngineeringMetal & MachiningPlastics & Packaging+4

Build quotes from similar past orders

You get a justified draft from earlier quotes and actual job costs, with every source linked.

Today

Every special machine, tool or custom part is costed from scratch, although similar jobs were quoted and built before. That knowledge sits in old folders and in the heads of two or three estimators. When they are away, quotes stall.

An example

Norvelta receives a request for an 8-cavity injection mould in 1.2343 for part 3150-220. The agent finds three earlier moulds and shows that mould M-1834 overran its planned hours by a third. It proposes higher hours for EDM and polishing accordingly.
Fictional company, typical workflow.

Your data, wherever it lives

Your old quotes sit today as PDFs and costing spreadsheets in folders on the drive, orders and actual job costs in the ERP, drawings and 3D models in CAD and PLM, and what was agreed with the customer in e-mails. demi reads, understands and links them per job, with your rights. The AI finds the closest past jobs with hours, prices and plan versus actual in seconds instead of hours of searching, and you decide what goes into the quote.

Where the data lives today

  • PDFs
  • Office files
  • Folders & drives
  • ERP
  • CAD & drawings
  • 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, PLM and file share. demi replaces nothing and joins past quotes, orders, drawings, routings and actual job costs into one record per job. You can then find similar jobs by geometry, material, quantity and customer requirement.

  2. 2 · PermitPermission Layer

    Costing data and margins are visible only to estimators and sales management. Only after an authorised estimator approves the quote does it go out; the approval is recorded.

  3. 3 · ActIntelligence Layer

    The agent ranks past jobs by similarity, shows planned against actual cost and drafts the cost structure, each line with the job it comes from. Prices and times come from recorded data; the language model only explains the differences.

How it runs

  1. 1

    A new request arrives with a drawing or a specification.

  2. 2

    The agent finds comparable jobs and shows where they match and where they differ.

  3. 3

    For each reference, planned and actual hours, material and outside work sit side by side.

  4. 4

    A cost draft follows, every line naming the job it comes from.

  5. 5

    Costing adjusts it, sets the price and releases the quote.

What changes

  • Faster, more consistent quotes

  • Job costing lessons flow into the next quote

  • Less dependence on a few estimators

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

+864 hfreed per year

Assumptions and calculation

demi reads the enquiry and pulls together similar orders, prices and data sheets; you check and send.

3 h → 2.1 h 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 × 3 h × 30% × 1.0 (manual) × 12 months = 864 h

Value per year, before demi costs

Freed per year+864 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

+€56,160

gained per year

864 h ÷ 1,760 h per role = 0.5 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 it find a job that is really comparable?

By features you define: geometry, material, quantity, number of cavities or special customer requirements. Each match shows where it agrees and where it differs. You decide which references go into the costing.

Does it need job costing data from our ERP?

Yes. The case needs actual hours, material and outside work from the ERP, linked to the original quote. How the data gets from the ERP to demi, we clarify in conversation. So you see planned and actual side by side for every reference. If actual job costs live in spreadsheets, those are connected too.

Who decides on the final price?

You do. The agent proposes the cost structure and hours with their origin; costing or sales management sets price and margin. The quote goes out only after release by an authorised person.

What if our old jobs were recorded incompletely?

Then the agent shows the gap instead of filling it. If a reference has no job costing, that is flagged on the match, and only recorded values are used. Every new job makes the base more complete.

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