Quote-to-order automation
Quotes for custom machined parts in 20 minutes instead of 3 days
A job shop quoting 60 to 80 custom parts a week was losing orders to faster competitors. Every RFQ needed an estimator to open the drawing, check material, count operations and price it. We built an AI quoting assistant that reads drawings and specs, drafts the quote, and lets the estimator approve in minutes.
- Client
- CNC machining job shop
- Region
- Germany
- Scale
- 80 to 120 employees
- Timeline
- 7 weeks to production
Representative engagement. Client details are anonymised and figures reflect typical outcomes from comparable deployments.
What the client got
0 min
Median time to quote
Down from roughly three working days during busy weeks.
0%
Higher quote win rate
Faster, more consistent pricing won jobs that used to go to quicker competitors.
0x
Quotes per estimator per week
The same three estimators handle double the RFQ volume without overtime.
The bottlenecks
Bottleneck 1
Three estimators, three-day backlog
RFQs arrived as emails with STEP files, PDFs and sometimes photographs of hand sketches. Each took 30 to 90 minutes to price. By the time the quote went out, the buyer had often ordered elsewhere.
Bottleneck 2
Pricing lived in one person’s head
Material rates, machine hourly costs and tolerance surcharges were applied from memory. Two estimators could price the same part 20 percent apart.
Bottleneck 3
Won quotes were retyped into the ERP
A purchase order meant re-entering the part, quantity, price and routing into the ERP by hand, with the original quote open in another window.
What we built
Step 1
RFQ intake and extraction
Inbound RFQ emails are parsed automatically. Attachments are classified, and an LLM extracts part names, quantities, materials, tolerances, finishes and delivery dates from drawings, spec sheets and the email body into a structured request.
Step 2
Costing engine with explicit rules
We codified the shop’s pricing logic: material cost by stock size, machine time by feature count and tolerance class, setup and finishing surcharges, volume breaks. Estimators tuned the rules in a spreadsheet the workflow reads at runtime.
Step 3
Draft quote for approval
The estimator sees the extracted spec, the drawing, the cost breakdown and a suggested price side by side. One click approves and sends the branded quote; edits are logged to improve the rules.
Step 4
Order creation on acceptance
When the customer accepts, the sales order, routing and material requisition are created in the ERP from the quote record. Nothing is retyped.
The automation workflow
RFQ to sales order flow
From inbound drawing to ERP order
Questions clients ask about this engagement
Can the AI read hand-drawn sketches?
Partially. Clear sketches with dimensions are extracted with a confidence score; anything below the threshold is routed to an estimator with the fields pre-filled where possible.
Who owns the pricing rules?
The shop does. They live in a spreadsheet the estimators edit; the workflow reads the current version each time it prices a part.
More in Manufacturing & Supply Chain
Industry overview
Custom AI operations platform
One AI dashboard for service, support and production
A mid-size manufacturer ran production, field service and customer support on three disconnected systems. We built a single AI dashboard that reads from all three, flags issues before customers call, and drafts the responses the team used to write by hand.
70%
Less time per support ticket
Procurement workflow automation
Supplier RFQs and purchase orders without the inbox
Buyers were sending requests for quotation one email at a time, chasing suppliers by phone, and retyping prices into the ERP. We automated the full loop from RFQ to approved purchase order, with AI reading supplier replies in any format.
80%
Less buyer admin per RFQ
Predictive maintenance and field service automation
Machine alerts that book the service visit before the line stops
An OEM with 2,000 machines in the field had telemetry it never acted on. Alerts went to a shared inbox, technicians were dispatched reactively, and customers called first. We built a workflow that reads machine data, predicts failures, and schedules the right technician with the right parts before the customer notices.
38%
Fewer unplanned stoppages
B2B outbound engine
Opening 14 new OEM accounts for a contract manufacturer in nine months
A contract manufacturer with two anchor customers wanted to diversify into European and North American OEMs. Trade shows produced business cards, not conversations. We built an account-based outbound engine that reached engineering and sourcing leaders with specific, relevant messages and handed sales a calendar of qualified meetings.
14
New OEM accounts opened
Have a similar bottleneck?
Tell us how the work happens today. We will show you the workflow we would build and prototype it on your own process.