Case Study: End-to-End Deployment for an International Window Engineering Client

A real engineering procurement client's dual-system workflow: sales rep submits once → drawings auto-reviewed → engineer signs off → quotation decision card + V1.xlsx sent directly to client. 10–11 weeks to deliver; zero perceptible difference for end clients.

Back

This post walks through the actual dual-system implementation of Nox-Lumen Mfg for a real engineering procurement client. Every factory has different processes — what follows is for reference only, not directly replicable. The actual solution follows: P0 pain-point diagnosis → P1 PoC → P2 customization → P3 managed operation.

Business Background

DimensionScale
Business typeInternational window engineering procurement
CycleAverage 2–4 weeks from client inquiry to production order
Historical projects~2,000 scattered Excel / PDF files
Client typesMix of international developers + engineering contractors
Team6 sales reps + 4 drawing review engineers + 2 project managers

Pain Point List

Pain PointCurrent StateLoss
Slow drawing review responseEngineers review when they're free; multiple back-and-forthsLost orders
Drawing engineer is a bottleneckVacation / resignation stalls projectsPoor business continuity
Client preferences get lostClient A's preferred profile, Client B's preferred glass — all in senior employees' headsSenior staff leave = client attrition
Wrong orders reach the factoryWrong drawing sent to production; materials cut before the error is foundSingle-incident loss from tens to hundreds of thousands
Inconsistent quotesDifferent sales reps quote different prices for the same project typeClient complaints + margin leakage
Historical quotes can't be reused2,000 scattered files; retrieval relies on memoryNew employees can't handle orders at all

End-to-End Workflow

Sales Rep
  ↓ Upload drawings + window/door schedule + specification
Drawing Review (AI)
  ↓ Pull client preferences / error patterns
  ↓ Parse + multi-view reconciliation + rules check
Sales Rep ← Red/yellow/blue issue list + clarification questions
  ↓ Forward to client for answers
Drawing Review (AI)
  ↓ Re-reconcile (possibly multiple rounds)
Engineer ← Red issues pending sign-off
  ↓ Sign-off approval
Quotation System (AI)
  ↓ Pull historical neighbors / add-on coefficients / verify breakeven floor
Sales Rep ← Decision card + V1.xlsx
  ↓ Negotiate → Proforma Invoice
Shared Memory Store ← Store deal result (shared by both systems)

Key Delivery Milestones

Day 1: Sales Rep Submits Once

Uploaded FileSystem Recognition
Drawing PDFParsed per view per page; vector / scanned auto-distinguished
Window/door schedule xlsxRow-level field extraction for each unit; tagged with source + confidence
Specification docxClient default value recognition (e.g., "LowE glass for entire building")
Client attachment PDFContent classification (contract / node detail / hardware brand)

Within 5 minutes the system produces a first review card:

Project P-2026-0123: 21 window/door units. 18 units have complete fields; 3 units pending clarification. 🔴 Red 3 items (W-103 height mismatch between drawing and schedule / D-201 hardware not on NCC certified list / L2 quantity missing) 🟡 Yellow 5 items (4 units glass configuration not labeled / 1 unit opening direction unclear)

Day 1: Sales Rep Contacts Client

System automatically translates into plain-language questions, pushed to Lark:

📩 Project P-2026-0123 has 7 questions requiring client confirmation:

  1. W-103 height: Schedule says 1500; elevation drawing measures 1480 — which takes precedence?
  2. L2 master bedroom 4 windows' glass configuration not labeled — please confirm whether LowE+Argon.
  3. D-201 fire door hardware brand is not on the NCC certified list — please provide certification documents or change brand. ...

Sales rep forwards to client without technical jargon, with original drawing screenshot attached.

Day 2–3: Client Replies + Engineer Sign-Off

  • Client returns 7 clarification answers → sales rep fills them in
  • System automatically re-reconciles → 3 reds become yellows (waived with reasons) + 4 resolved
  • Remaining 0 red issues → pushed to engineer for review
  • Engineer completes review within 1 hour → signs off

Day 3: Quotation Decision Card

The approved structured list is automatically fed to the quotation system:

Project P-2026-0123 (M tier: 450 m²)
  ├ Recommended price: $380 / m² (all add-ons included)
  ├ Breakeven floor: $320 / m²
  ├ Negotiation floor: $340 / m²
  ├ Historical neighbors: 3 same-tier projects, $/m² range $365–395
  │   • P-2025-0892 Bay Area USA $380/m² — closed
  │   • P-2025-1104 BC Canada $372/m² — closed
  │   • P-2026-0045 Sydney Australia $391/m² — closed
  └ Add-on breakdown:
      • Fly screens: 12 units × $35/unit
      • LowE+Argon upgrade: 23 units × $18/m²
      • Hardware upgrade (NCC certified): 21 units × $25/unit
      • Finish (dark gray wood grain): all units × $8/m²

V1.xlsx rendered in parallel (identical to the existing template), ready for the sales rep to download and send to the client.

Day 4–7: Negotiation → Proforma Invoice

  • Sales rep negotiates with client based on the decision card
  • System validates in real time with every trial price the sales rep tries:
    • Proposed price ≥ breakeven floor? ✓
    • Above negotiation floor? ✓
    • Deviation from historical neighbors? ±5%
  • After deal closes, automatically accumulates in historical memory store: client, tier, final price, add-on combination, number of negotiation rounds

What the Agent Did / Didn't Do in This Case

What the Agent did:

  • Drawing parsing + multi-view reconciliation, review health card in 5 minutes
  • Client preference library auto-pulled — Client A's 30 series / Low-E glass default preferences not missed
  • All mechanical work for quotation's "find historical neighbors + add-ons + floor validation" handled
  • V1.xlsx identical Excel output — exactly the same as the original manual version; zero perceptible difference for clients
  • Real-time "breakeven floor" validation during negotiation
  • Auto-accumulation into historical memory store after deal closes

What the Agent didn't do:

  • Final sign-off for red hard-blocks → engineer does this
  • Negotiation strategy → sales rep does this
  • Setting the cost floor → general manager sets this
  • How to update client preferences → engineers manually accumulate this
  • Factory BOM / internal costs → factory black box, not replicated

"Critical decisions are explainable, signable, and traceable; red hard-stops intercept wrong orders before they reach production" — this principle wasn't retrofitted; it was there from day one of design.

Actual Changes This System Brought

DimensionBeforeAfterChange
Drawing review responseEngineers review when freeSales submits once → AI produces health card immediatelyDays → 5 minutes
Client preferencesIn senior staff's headsClient-isolated memory store; new staff can use it tooNo attrition when senior staff leave
Quotation outputSales manually compares historical projectsDecision card + V1.xlsx sent directlyHours → minutes
Wrong orders to factoryOccasionalIntercepted at source under hard contractSingle-incident loss avoided
Negotiation ceilingBased on sales experienceHistorical neighbors + floor validated in real timeMargin controllable
New staff independence1–2 years1–2 monthsTeam scales faster

Implementation Schedule

WeekPhaseContent
W1-2P0 (shared)Sample governance + client preference mapping
W3-5P1 PoC (dual system parallel)Each system re-runs 50 historical orders for validation
W6-8P2 Customization (dual system parallel)Client rule entry + V1.xlsx template alignment
W9Integration testingDrawing review → quotation data pipeline
W10-11Experience accumulation + company-wide go-liveShared memory store connected + full team training

Total duration: 10–11 weeks.

Pricing Packages

PackageIncludesBest For
Drawing Review onlyM1–M10 all capabilitiesCustomers who already have a quotation tool
Quotation System onlyM1–M10 all capabilitiesCustomers not yet ready for drawing review
Dual SystemBoth full systems + hard contract + shared memoryRecommended
Managed OperationFull suite + we continue maintainingCustomers who don't want to build an AI team

For pricing details, contact info@nox-lumen.com.

FAQ

Q: Our project drawings are in German / French — can the system parse them? A: Yes. OCR + multilingual model handles them. Accuracy depends on drawing quality. We recommend running 20 orders as a baseline during P1.

Q: Will client preference libraries leak across clients? A: No. Each client's preferences are physically isolated at the tenant level — even logs don't cross.

Q: Can we run without LLM and use only the rules engine? A: Yes. Multi-view reconciliation, rules validation, and breakeven floor are entirely rules-engine driven. LLM is mainly used for "unstructured text understanding" (specification docx, client emails, etc.). If client inputs are 100% structured, the LLM portion can be reduced to zero.

Q: Who sets negotiation floors / breakeven floors? A: Business owners / general managers set them; the system enforces them hard. Sales rep quotes below floor outside the system → Lark alert.

Case details, contract design, and memory store architecture at docs/solutions/manufacturing/double-system.

Written by

Nox-Lumen Tech-team

Published

May 14, 2026