Operations & Supply Chain · Find

RFQ normalizer.

Turns quotes that arrive in twenty different formats into one comparable table, priced on landed cost rather than unit price.

Operational lens11% sourcing savings modeled targets · not client results
.crft/RFQ normalizer

sourcing savings

to the Scan's evidence — before any scope

4–10 wks

to a system in production, not a pilot

modeled targets · not client results · timings are CRFT's standard engagement

The work, today.

Quotes arrive as PDFs, spreadsheets and email bodies, each with its own units, terms and inclusions. Somebody rekeys them into a comparison sheet, and the comparison is on unit price because normalizing to landed cost by hand takes longer than anyone has.

Where the Scan startsWith your quote formats, supplier list and how landed cost is calculated today.

What the system is.

Four lines, the same four on every system we build. Where they fall is what makes this one different from the last one.

Inbound quotes in whatever format the supplier sends
Your specification and the tolerances that actually matter
Freight, duty, payment terms and MOQ
Historical pricing and what each supplier has actually delivered
01

What it reads

The signals it works from. Typically connects to ERP or procurement, Email, Supplier records and Spend data.

01What each quote means in one common unit
02What the landed cost is, not the sticker price
03Which quotes are non-compliant with the spec, and where
04Which supplier is genuinely cheapest once terms are counted
02

What it decides

The calls it makes on its own, unattended, every time it runs.

One comparison table with every quote normalized
A flagged list of spec deviations and missing information
The clarification emails back to suppliers, ready to send
03

What it writes back

Into the tools the work already lives in.

04

Where the human stays

The buyer awards. Supplier relationships are relationships, and the award decision carries context — a second source you are cultivating, a quality history — that does not fit in a table.

How we set it up.

The same four legs as every CRFT engagement — written for this system rather than in general.

  1. 01
    Scan48 hrs · evidence before scope

    We collect a real round of quotes and normalize them by hand once, with your team. That is where the true landed-cost formula surfaces, usually differing from the documented one.

  2. 02
    Scope1 week · the report is the scope

    Scope is set by format variety and category count. One category with ten regular suppliers is a contained first build.

  3. 03
    Build4–10 wks · production, not a pilot

    Extraction accuracy is the whole system. It ships with a confidence threshold, and anything under it goes to a human rather than into the table quietly.

  4. 04
    Compoundongoing · it reports, then improves

    Every corrected extraction is training data for the formats your suppliers actually use. Accuracy climbs on your mail, not on a generic corpus.

What we hold it to

Cycle time from quote deadline to award, and realized savings against the pre-normalized comparison.

Get CRFT

Build the intelligence your company compounds on.

Five inputs, a published price, a report in 48 hours. Decide with numbers — then own what gets built.

Or just send us a note
What kind of system? Pick any that apply