Steel Quoting Engine
Quoting engine for made-to-order steel fabrication

- Steel fabrication
- AI
- Pricing
- ERP
The project
A made-to-order steel fabricator relied on one senior estimator to price every job. Quotes took up to two days, and the business could not grow past what one person could estimate.
We built a quoting engine that captures the estimator's pricing rules, tested it against three years of past quotes, and now returns a priced quote in about four minutes. The project took nine weeks.
The challenge
Pricing a fabrication job means steel weight and grade, cutting, drilling, welding, finishing, labour and delivery. Twenty years of judgement on all of that lived in one estimator's head.
Customers wanted faster answers, the estimator was the bottleneck, and the business needed confidence that an automated price would be as good as his before it went near a customer.
The solution
We sat with the estimator and modelled his rules for material, cutting, fabrication, finishing and margins. Then we replayed three years of real quotes through the model and tuned it until it matched his judgement.
The quoting engine now builds a price from the job spec, shows the breakdown line by line, and flags anything unusual for the estimator to check. Quote turnaround went from two days to four minutes.
What it does
- Pricing rules modelled from the estimator
- Tested against three years of quotes
- Quote from a job spec in minutes
- Line by line price breakdown
- Material grade and weight pricing
- Labour and finishing rates
- Unusual jobs flagged for review
- Quotes exported to send to customers
How we built it
- Shadow the estimator: Recorded how each type of job is priced, and why.
- Model the rules: Turned material, labour and finishing rules into a pricing model.
- Prove it on history: Replayed three years of quotes and tuned until it matched.
- Automate: Put the engine in front of the sales team with review flags.
The results
- 2 days → 4 min Quote turnaround
Backendz & Steel Quoting Engine: Highlights



They modelled twenty years of an estimator's judgement and then proved it against our own history before we let it near a customer.
More case studies
- Factory Floor AppOffline-first field app for nine production linesView case study

- Fleet Driver AppDriver app and telematics platform for a 300-vehicle fleetView case study

- Ops CopilotPlain-English answers across job, purchasing and finance systems, with evidence and approval before action.View case study

Still running on workarounds?
AIHow much does an AI agent cost to build and run in the UK?Read article
AIPredictive maintenance with machine learning for UK manufacturersRead article
AIWhere to start with AI workflow automation in operationsRead article
EngineeringCustom CRM or off-the-shelf? When building your own makes senseRead article