Procurement manager reviewing supplier quotes in an industrial equipment warehouse
All case studies

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.

Client
Industrial equipment maker
Region
United Kingdom
Scale
120 to 200 employees
Timeline
5 weeks

Representative engagement. Client details are anonymised and figures reflect typical outcomes from comparable deployments.

What the client got

0%

Less buyer admin per RFQ

Sending, parsing, chasing and comparing are handled by the workflow.

0 days

Faster quote cycle

Deadlines and automatic reminders shortened supplier response time.

0

Retyped quotes

Structured data flows from supplier reply to ERP without manual entry.

The bottlenecks

  1. Bottleneck 1

    Every RFQ was a manual email thread

    A single component could mean five supplier emails, five follow-ups and a spreadsheet to compare answers. Buyers spent most of the week on admin rather than negotiation.

  2. Bottleneck 2

    Supplier replies arrived as PDFs, scans and prose

    Prices, lead times and MOQs came back in whatever format the supplier preferred, so someone had to read and retype every one.

  3. Bottleneck 3

    Purchase orders waited on approvals

    Approval requests sat in inboxes. Production sometimes learned a part was late because the PO was never raised.

What we built

  1. Step 1

    RFQ generation from demand

    A low-stock or planned-order signal from the ERP creates an RFQ pack and sends it to the approved supplier list with a reply deadline, automatically.

  2. Step 2

    AI reply extraction

    Supplier emails and attachments are parsed by an LLM into structured quotes: unit price, MOQ, lead time, validity. Ambiguous replies are flagged for the buyer with the original attached.

  3. Step 3

    Comparison and approval

    Quotes land in a comparison view ranked by landed cost and lead time. Approvers get a one-click request in Slack or email; the PO is raised in the ERP on approval.

  4. Step 4

    Chasing handled by the workflow

    Suppliers who miss the deadline get automatic reminders. Buyers see who has and has not responded without opening a single thread.

The automation workflow

RFQ to purchase order flow

Demand signal to raised PO

01

Demand Signal

Low stock or planned order

02

RFQ Sent

Approved supplier list

03

AI Extract

Price, MOQ, lead time

04

Compare

Ranked by landed cost

05

Approve

One click in Slack

06

PO Raised

Written to ERP

Step 1 of 6
6 steps · Fully automated
StackMake.comOpenAIERP APISlackGoogle Sheets

Questions clients ask about this engagement

What if a supplier reply cannot be parsed?

The workflow routes it to the buyer with the original attachment and a note on what was unclear. Nothing is guessed.

Which ERPs can this connect to?

Any system with an API or scheduled export. We have built against SAP Business One, NetSuite, Odoo and custom SQL databases.

More in Manufacturing & Supply Chain

Industry overview
Engineers reviewing an AI operations dashboard on a precision manufacturing floor
Manufacturing

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

Engineer reviewing a CAD drawing and quote on a tablet beside a CNC machining centre
Manufacturing

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.

20 min

Median time to quote

Field service technician checking a packaging machine with a maintenance alert on a handheld device
Manufacturing

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

Electronics assembly line with surface-mount machines at a contract manufacturer
Manufacturing

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.