Skip to content
Sales & quotingConstruction & Building Services

Price bills of quantities faster

Unit prices come from past projects, with gaps and change-order risks flagged.

Today

Construction and building-services firms price long bills of quantities under deadline. Unit prices and lessons from past projects are scattered across old estimates, spreadsheets and people's heads. Unclear items surface only once the job is running.

An example

Nortavo Gebäudetechnik prices a bill of quantities with 420 items for a school's heating renewal, including two 24 kW heat pumps (R290) and DN 50 manifolds. The agent prices 380 items from four past projects and flags 11 with unclear quantities that carry a claim risk.
Fictional company, typical workflow.

Your data, wherever it lives

The bill of quantities arrives today as an exchange file, PDF or Excel; earlier estimates sit in the DMS and in folders, actual costs in the ERP, supplier prices in e-mailed quotes and articles in manufacturers' online catalogs. demi reads, understands and links them per item, with your rights. The AI prices most items in minutes instead of a working day spent digging through old estimates, and estimating decides on every price.

Where the data lives today

  • PDFs
  • Office files
  • DMS & archive
  • Folders & drives
  • ERP
  • E-mails
  • Web & portals
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, DMS and spreadsheets. demi replaces nothing and links each item to comparable items from earlier projects, their actual costs, supplier prices and articles from building-services catalogs. demi returns the result as an exchange file to your estimating software.

  2. 2 · PermitPermission Layer

    Estimating and management see the calculation data. The responsible manager approves the finished bid, and the approval is recorded.

  3. 3 · ActIntelligence Layer

    The agent proposes a unit price per item from recorded actual costs, naming the source project, and takes quantities unchanged from the bill of quantities. Unclear or missing items are listed as claim risks with their location in the document.

How it runs

  1. 1

    Load the bill of quantities as an exchange file, PDF or spreadsheet.

  2. 2

    The agent matches each item to comparable items from past projects.

  3. 3

    It proposes unit prices from actual costs and names the source.

  4. 4

    Unclear quantities, missing items and claim risks are flagged.

  5. 5

    Estimating reviews, adjusts and releases the bid.

What changes

  • Faster bid pricing

  • Risks found before the bid goes in

  • Prices based on real project costs

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

+230 hfreed per year

Assumptions and calculation

demi maps each item to past projects and proposes unit prices; you finish the costing.

8 h → 5.6 h per case

How does it run today?

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

How we calculate

8 bills of quantities × 8 h × 30% × 1.0 (manual) × 12 months = 230 h

Value per year, before demi costs

Freed per year+230 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

+$14,950

gained per year

230 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 it read the usual exchange formats for bills of quantities?

Yes. Besides the common exchange files for bills of quantities, the agent also reads PDF and spreadsheets. It can hand the result back as an exchange file for your estimating software.

How does it handle price increases since the old project?

Every proposal shows the year of its source project. Where current supplier prices exist, the agent uses them. Otherwise it can apply an index you choose. Estimating decides which correction applies.

Does it point out items that could become claims later?

It flags items where quantity, execution or scope is unclear and explains why that could lead to a claim. Whether you clarify it in the bid or claim it later is your call.

What if our old actual job costs are incomplete?

Then the agent says so. Items without reliable actual costs get a note instead of a price, so nobody adopts a guessed number.

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