Case studies · Manufacturing
GenAI quoting agent: from 4 to 6 hours to 15 minutes
An agent prepares the full quote from scattered requests; manufacturing and sales engineers approve it.
Client: Manufacturing company · Industry: Manufacturing
The challenge
Quote requests arrive by email, phone and web form, often with changed documentation. Each one has to be checked against the previous order, costs, subcontractors and the production schedule.
Preparing a single quote took four to six hours of collecting data from several systems.
01 / Data layer
The agent links separate channels (documents, emails, phone notes) into one case and compares the requirements with the previous order.
Costs come from company systems; prices and schedules are calculated by the company's own tools, not invented by the model.
02 / AI layer
The agent finds changes in scope, sends them for recalculation, collects production, inspection and transport costs, requests a subcontractor quote and checks delivery options against the deadline.
Manufacturing and sales engineers review scope, costs and dates and approve the quote. The system learns from their corrections and approved quotes; cases that need an individual decision go to a person.
The project, scene by scene
The frames come from our film about this deployment.
01 / 03
GenAI: documentation changes the cost
A manufacturer is asked to quote five hundred metal housings. The customer sends new documentation and asks by phone for the first hundred in three weeks. The agent combines these and compares requirements with the previous order. It finds a change: every unit now needs measurements and its own report. It sends this scope for recalculation.
02 / 03
GenAI: full cost and delivery plan
The agent collects production, inspection and transport costs. It also gets a subcontractor's quote. Company tools calculate the price and check the schedule. Thirty thousand euros for everything in six weeks misses the first deadline. Staged delivery costs thirty-two thousand five hundred, gets the first hundred there on time and keeps the planned margin. Manufacturing and sales engineers check scope, costs and dates. They approve the quote with every line item justified.
03 / 03
GenAI: 4-6 hours to 15 minutes
A quote that used to take four to six hours is ready in fifteen minutes. The agent does most of the work on its own. The system learns from expert corrections and approved quotes. It applies this knowledge to future requests. With complete data and known requirements, it can prepare the entire quote on its own. Cases that need an individual decision are routed to a person.
Results
- A quote that took four to six hours is ready in fifteen minutes.
- With complete data and known requirements, the agent can prepare the entire quote on its own; engineers approve it.
Start with
Fixed scope, fixed price
AI readiness assessment
Which AI use cases pay off for you, and is your data ready for them? A ranked shortlist, an architecture and a roadmap.
From
€6,000net
Duration: 3 weeks
Who leads it: A senior data architect together with an AI engineer who has deployed models in production. You talk to the people who would build the solution.
Order the assessmentServices:AI engineering into production
Related case studies
Weld quality AI: 86% fewer defective parts
Global automotive parts manufacturer · Automotive, metal components
Kit inspection with computer vision: 63% fewer complaints
Global manufacturer of industrial equipment · Industrial equipment manufacturing
Logistics control tower: 37.6k containers tracked in real time
Global logistics provider, 30,000+ active shipping containers · Logistics
Let's talk about your project
Tell us about your case
Pick one problem.
Show us the data you have.
Let's agree a measurable goal.
Name the process and the data you have. An engineer, not a call centre, gets back to you.
We reply within one business day.