Alexey Shurov.
Manufacturing

An AI quoting agent for a manufacturer, from days to hours

The quoting inbox took one to three days per quote. An agent now reads the enquiry and the bill of quantities and prices it against the live catalogue, behind a rules engine that keeps every price explainable.

1 to 3 days → under 3 hours
About 90 percent faster, per quote
Priced against the live ERP catalogue, client-confirmed.

The problem

Enquiries arrived with multi-sheet bills of quantities covering several brands. An estimator had to read each line, find the matching item in the catalogue, apply the right price and discount rules, and build the quote by hand.

At one to three days per quote, the delay was not the estimator's speed. It was the volume of lookups and the queue of enquiries waiting their turn, and slow quotes lose work to faster competitors.

How the agent works

The design splits judgement from arithmetic, because a model is good at reading messy input and a rules engine is good at getting the same price every time.

  1. The agent reads the enquiry and every sheet of the bill of quantities, whatever the layout.
  2. It matches each line to an item in the live ERP catalogue across the brands in the schedule.
  3. A deterministic rules engine applies prices and pricing rules, so every figure on the quote can be traced to a catalogue entry and a rule.
  4. The draft quote goes to a person to review and send.

The pricing logic sits behind a suite of 87 tests, so a change to a rule or a model cannot quietly change a price.

What changed

Quote turnaround went from one to three days to under three hours, about 90 percent faster, priced against the live catalogue rather than a copy that drifts out of date.

What a project like this needs from you

Access to the systems the work already lives in, usually a mailbox and the system of record, with a login the agent can use safely. The rules written down, or a person who knows them and has an afternoon to explain them.

A set of real past cases to test against. Replaying last month through a new version before it goes live is what lets a team trust the change. A named owner for the decisions the agent will not make, and a period where it runs alongside the team in shadow mode before it acts on anything.

Common questions

Can AI generate quotes for a manufacturer?

It can draft them, and drafting is where the hours go. The reliable pattern is an agent that reads the enquiry and matches lines to your catalogue, a rules engine that applies prices the same way every time, and a person who reviews the quote before it is sent.

How do you stop an AI quote from getting the price wrong?

Keep the model away from the arithmetic. The model reads and matches, a deterministic rules engine prices, and a test suite over real past quotes runs before any change ships. A price you cannot trace to a catalogue entry and a rule should never reach a customer.

What does an AI quoting system need to connect to?

The mailbox or portal where enquiries arrive and the ERP or catalogue that holds your items and prices. It works best against the live catalogue, because a copied price list drifts out of date and the quotes drift with it.

Is quoting a good first AI project for a manufacturer?

Often yes, because it is high volume, the inputs repeat, and the outcome is easy to measure in hours per quote. The catalogue mapping is the real work, so it pays to check how clean your item data is before you start.

Have the same problem

Each system above was built around one client's process. Yours will differ in the details, which is where the work is. Tell me what your team spends too long on.

shurco.aiGuidesFree toolsSolutionsInsightsRSSllms.txt