Skip to content
Artifisys
Menu
Start a conversation Talk to us

Manufacturing

One heat network, two pipe ranges, and every bid costed by hand

How does a pipe maker cost a whole heating network fast, when its product ranges come from different plants and catalogues?

Book a 20-minute call Free. No demo, no slides.

Figures and rules on this page apply to

Europe

Working somewhere else? The shape of the problem usually travels. The deadlines do not.

What this looks like

A city tender arrives: a network plan as a PDF, a bill of quantities in a spreadsheet, and a page of site notes. An engineer sizes each run and picks rigid or flexible pipe. Then two teams cost their parts in two tools. The bid goes out late, or with gaps.

The numbers

Every figure here is someone else’s. Check them.

  • 30%of medium-sized EU firms used any AI technology in 2025
  • 55%of large EU firms used AI in 2025, almost twice the medium-sized rate
  • About halfof all the energy used in the EU goes on heating and cooling buildings
  • About two-thirdsof the energy used for heating and cooling in the EU still came from fossil fuels in 2025

Why it happens

It is not a people problem.

The network plan belongs to the client and its engineers. Every consultant draws, labels and lists quantities in its own way. Inside the maker, each product range has its own codes, prices and sizing rules. So every bid starts with a person reading and re-typing.

Why your current software has not fixed it

Because it was never built to.

Costing tools start once the bill of materials exists. None of them reads a consultant's network plan. Buying a second range makes the offer stronger, but it also adds a second catalogue. One shared ERP would take years, and the bids are due now.

Intelligence, plumbed in

A scanned network plan and a spreadsheet of quantities can be turned into a checked, costed parts list.

We build a layer that reads the client's plans and your own catalogues. Each bid starts as a draft costing, not a blank sheet. Underneath it: a connector, one agreed meaning per field, and a test set scored on your own records.

How we make AI survive real data
  • Connectors
  • A semantic layer
  • Evals you can check

However hard, whatever it is

Heat-network pipe systems are one example. Bring the bid that takes longest.

We wrote this about pipe makers because every tender arrives in someone else's format. The same gap exists wherever a firm sells engineered systems from more than one catalogue.

  1. 01

    We sit with you

    Days where the work happens, not a workshop in a meeting room. We watch the job get done and write down the shortcuts nobody wrote down.

  2. 02

    We read everything

    Your data, your rules, your vendors and their documentation, and the published research on your sector. We report what is actually in there.

  3. 03

    We break it to first principles

    Not which tool fixes this. What is actually causing it, taken apart until we reach the piece that cannot be divided further.

  4. 04

    Then we build

    Weeks, not quarters. By this point we are not guessing what to build, and guessing is the thing that makes projects long.

What we build

Specific enough to argue with.

Four mechanisms, not four features. Each one is a thing that happens on its own, every day, whether or not anyone remembers to run it.

  • Network plans, quantity lists and tender notes read on arrival, in whatever format the client used.

  • Each section of the network matched to the right pipe system, rigid or flexible, using your own sizing rules.

  • One draft costing that draws on every product range, for an engineer to check and send.

  • One view of open bids, margins and win rates across every country.

How you would know it worked

Numbers in your own reporting, not ours.

  • Days from a tender arriving to a costed bid being sent.
  • Share of bids that cost both product ranges together instead of separately.
  • Engineer hours spent re-typing quantities, per bid.

Straight answers

Where a model is involved, it is scored against your own records first. Accuracy per source, not one flattering average.

The questions this raises

  • Our engineers make judgement calls on every network.

    They still do. The layer does the reading and re-typing. The engineer checks the sizing and signs off every bid.

  • Our plants run different systems.

    That is the point. The layer reads each catalogue as it is. No plant has to change its ERP.

  • How soon would we see a difference?

    Usually within weeks, starting with the market that sends the most tenders. Each new range or country can be added the same way.

Every partner sends a different shape

The format belongs to them. The cost lands on you.

Documents arrive from outside in whatever shape the sender chose, and the sender changes it whenever their own system does. No vendor can ship this. The set of formats is specific to who you trade with, which is why it ends up as a script nobody owns.

Bordereaux, carrier files, supplier invoices, delivery notes. Whatever arrives in your inbox in nine shapes is the same job.Send us the messiest one you have.

The plan already says what the network needs. Nobody should have to type it twice.

We build a layer that reads the client's plans and your own catalogues. Each bid starts as a draft costing, not a blank sheet.

See everything we build
  • Software
  • Hardware
  • Ways of working
  • Whole ventures

Is this happening to you? Tell us the size of it.

Twenty minutes. We will tell you honestly whether the numbers justify doing anything about it.