Our client is a construction-technology company in the United States whose estimators priced projects from building information models (BIM) produced by design teams.
Before every estimate, an estimator measured walls, slabs, doors and windows from the model or drawings and typed the quantities into the estimating system. On a large project this took days, and it had to be repeated whenever the design changed.
Building models describe what a designer drew, not what an estimator prices. The integration had to translate one into the other.
Models from different design teams classify and name components differently.
IFC element types had to be mapped to the estimating system's items and cost codes.
Areas, volumes, lengths and counts had to be taken from the right properties, in the right units.
A revised model had to be re-run without the estimator rebuilding the estimate from scratch.
We worked from real models and real estimates, so the mapping matched how the client's estimators actually price work.
We compared sample IFC models with the estimates priced from them, line by line.
With the estimators we defined how each IFC element type maps to an item and cost code.
Services that read the IFC file and calculate quantities from its geometry and properties.
Quantities are loaded into the estimating system, and on to the ERP, through their APIs.
Elements that do not map cleanly are listed for the estimator instead of being guessed.
Run alongside manual take-off on live projects, then adopted as the standard starting point.
The estimator exports the IFC model and starts the run; the quantities arrive in the estimating system in the structure they already use.
The integration does the counting; estimators still own the estimate.
Estimators start from quantities taken from the model instead of measuring by hand.
Estimators spend their time on pricing, risk and exceptions rather than counting.
Every modelled element is either mapped or listed as an exception, so nothing disappears quietly.
From the first model review to use on live projects.
Client name withheld. Details that could identify the company have been left out.
Metwaves built a LangGraph agent that reads around 1,000 supplier documents a month with Azure Document Intelligence and posts them to SAP Business One, cutting manual data entry by about 80%.
Learn More >
Metwaves built a Copilot Studio agent in Microsoft Teams that answers staff IT, HR and policy questions from SharePoint and resolves 30–50% of requests without a human.
Learn More >
Metwaves built and deployed an AI recommendation engine inside BioBuild's BIM workflow that scores materials on cost, carbon and structural fit. Live since January 2025: selection time down 40%, material cost down 20%.
Learn More >Discover IT Industry Insights and Technology Trends
Nikit Nandan
November 12, 2026
Nine AI agent development firms a small or mid-sized business can shortlist, with Clutch figures, minimum budgets and the weaknesses their own clients name. Published by Metwaves, which is not ranked.
Learn More >
Nikit Nandan
November 12, 2026
An architecture review of the four big enterprise agent platforms: where each one reasons, acts, finds its data and connects to outside agents, what it costs, and when a custom build is the better choice.
Learn More >
Nikit Nandan
November 01, 2026
Ten custom software firms a small or mid-sized business can shortlist, with Clutch figures, minimum budgets and the weaknesses their own clients name. Published by Metwaves, which is not ranked.
Learn More >
Let us help you with free analysis & estimate.
Our product expert will contact you within 12 hours.