Case Study · Distribution / Central America · 2025–2026

WHATSAPP AI
AT ENTERPRISE
SCALE.

Architecting a full-stack conversational AI system for a 40-year-old HVAC and refrigeration distributor — replacing a one-person manual operation handling 100+ daily conversations with an intelligent, SAP-integrated agent across 7 countries.

HVAC & Refrigeration
7 Countries
36,000+ conversations
n8n · SAP B1 · WhatsApp API
36K+
Regional conversations
75%
Inbound via WhatsApp
5
Automated routes
7
Countries in scope
The Client

40 years of distribution. 100 manual conversations a day.

Our client is a leading HVAC and refrigeration distributor with 40+ years of regional presence across 7 countries in Latin America and the United States. They are the primary importer for major brands in their markets, serving a diverse customer base of end consumers, independent technicians, contractors, corporate clients, and multi-country distributors.



Their WhatsApp number had become the backbone of their sales operation — receiving over 100 conversations per day in their pilot market alone, representing 75% of total inbound volume. A single person was managing all of it, manually. The cost of that fragmentation was becoming impossible to ignore.

The Problem

One person. 36,000 conversations.

MetricCurrent State
Daily conversations (pilot market)~100 chats on WhatsApp
Total regional volume+36,000 conversations
Primary inbound channel75% via WhatsApp
Lead type breakdown80% new / 20% returning
Existing bot capabilityStalls without human handoff
Current sales process1 person "putting out fires"

~3,000 unqualified leads per month — arriving without context, product interest, or customer type identified, requiring manual triage before any sale could begin.

30–40% estimated revenue loss from poor lead management — conversations that went cold, unanswered inquiries, and delayed quotes that competitors closed first.

900–1,200 lost opportunities per month — potential transactions that fell through the cracks due to volume the team couldn't absorb.

Zero metrics on which channel actually converts, which customer type closes fastest, or where the pipeline breaks down.

No structured follow-up — once a conversation went silent, it was gone. No recovery sequences, no re-engagement, no second chance.

The Solution

Five intelligent routes. One unified system.

CCG designed and is building a full-stack conversational AI system integrating WhatsApp Business API, SAP Business One, and a custom n8n automation layer — deployed in a Central American pilot market before regional rollout across all 7 countries.

Route 01

Quotation Engine

Handles quote requests via text, PDF, image, or screenshot. Queries the SAP data warehouse for real-time pricing by customer type (End Consumer, Technician, Corporate, Distributor). Generates quotes directly in SAP B1 and delivers them via WhatsApp. Complex items — chillers, cooling towers, applied projects — are detected and escalated to Engineering.

SAP B1Data WarehouseMulti-item cartITBMS included
Route 02

Availability Check

Queries the data warehouse for real-time stock across multiple warehouses. Returns availability status per customer type, with delivery timelines: 2–4 business days in the pilot market, coordinated delivery to all major cities in-country. Express dispatch coordinated with client's own carrier.

Multi-warehouseReal-time stockDelivery logic
Route 03

Claims & Warranties

Collects claim details from the customer, verifies purchase against SAP records, and routes the case via the confirmed handoff method — email notification, human-in-the-loop WhatsApp escalation, or SAP case creation. Warranty terms served per brand: ADINA (2yr compressor / 1yr factory), TCL (10yr compressor), McQuay/Daikin (5yr compressor).

SAP case creationBrand-specific termsHITL escalation
Route 04

Technician Training

Serves the training catalog from a vector knowledge base. Handles enrollment booking — either via link or automated n8n booking flow. ADINA-certified technician network is surfaced for installation inquiries. Training content is maintained and updated without re-deployment.

Vector KBAuto-enrollmentADINA certified
Route 05

FAQ & General Inquiries

RAG-powered knowledge base covering the full product catalog across 20+ brands: Adina, TCL, Daikin, Trane, Panasonic, Elgin and more. Handles BTU sizing guidance, refrigerant type queries (R410a, R32, R404, R507), inverter technology questions, spare parts requests, store hours, payment methods, and more — with full multi-turn context handling.

RAG / Vector DB20+ brandsMulti-turn context
Cross-Route

Smart Handoff & Follow-up

When a conversation is ready for a human, the system generates a complete summary and routes it intelligently: simple requests to local sales, remote clients to televentas, complex engineering projects to the technical team. Automated re-engagement sequences activate when a customer goes silent. Every outcome is tracked across 4 states for dashboard reporting.

Conversation summarySmart routingOutcome trackingRe-engagement
Technical Architecture

Six phases. Ten weeks.

The system was architected across six sequential phases with intentional parallel execution — targeting a go-live deadline of 10 weeks from project kick-off, with a soft launch period built in before hard go-live.

Phase 1 — Foundation
Critical
n8n Environment

Cloud vs. on-prem deployment confirmed per client data privacy requirements. Dev/staging/prod environments with CI/CD pipeline.

Critical
WhatsApp Business API

Meta Business account configuration, webhook setup, inbound/outbound message testing across all conversation types.

Critical
SAP B1 Connectivity

Service Layer / OData endpoint validation for both read (pricing, inventory) and write operations (customer creation, quote, order).

High
Data Warehouse Access

Read-only credentials, schema documentation, and query validation for products, inventory, and pricing tables.

High
Vector Store Setup

Two instances: (1) FAQ / Knowledge Base, (2) product catalog fallback. Tooling: Pinecone / Qdrant / pgvector.

High
Data Model Design

Customer types, conversation state machine, outcome tracking schema, lead storage — designed before any routes are built.

Phase 2 — Conversation Routes
Critical
Customer Classification

4-way classification logic: End Consumer, Technician, Corporate, Distributor. Drives all downstream pricing and routing rules.

Critical
Quote Creation + SAP Write

DW price lookup, customer-type pricing rules, multi-item cart, SAP B1 quote object creation. Complex items escalated to Engineering.

Critical
Smart Handoff

Conversation summary generation, CRM/WhatsApp group push, intelligent routing: Simple → Local Sales, Remote → Televentas, Complex → Engineering.

High
Availability & Claims

Multi-warehouse stock queries. Claims collection, warranty verification, and SAP case creation or escalation.

High
FAQ RAG + Follow-up

RAG over knowledge base vector store with multi-turn context. Automated follow-up sequences triggered on conversation silence.

High
Outcome Tracking

4-state logging: bot-closed sale, bot-no sale, human-closed sale, human-no sale. Feeds all dashboard KPIs.

Phases 3–6 — Web, Leads, Dashboard & Launch
High
Web Quotation Widget

Embedded on client website. Reuses same AI/SAP backend as WhatsApp — customer builds their own quote without contacting anyone. PDF downloadable.

High
KPI Dashboard

Conversation volume, conversion by route, handoff rate, outcome breakdown, response times. Sales and engineering team views included.

High
Load Testing & UAT

5,000 conversations/month throughput simulation. 20 test flows (5 routes × 4 customer types). Structured UAT with client team before soft launch.

Technology Stack

Custom-built. No platform ceiling.

Every component was selected for its ability to handle the specific requirements of a multi-country distributor operating on SAP — not for ease of setup.

n8
n8n Automation

Orchestration layer connecting all systems. Custom conversation state machine, routing logic, and follow-up sequences.

WA
WhatsApp Business API

Primary communication channel via Meta Business. SIP trunk routing for voice agent extension (optional phase).

SAP
SAP Business One

Service Layer / OData for write operations: customer creation, quote generation, order creation. DW for read queries.

AI
LLM Layer

Conversational AI for natural language understanding, customer classification, quote parsing, and summary generation.

VEC
Vector Store

Two-instance setup: FAQ/KB and product catalog. Pinecone / Qdrant / pgvector evaluated per performance requirements.

DB
Custom Data Layer

Conversation state, outcome tracking, lead storage, and CRM views — designed to feed both dashboard and sales team workflows.

Implementation Timeline

10 weeks from kick-off to go-live.

Phase 1
Foundation
2 wks
n8n environment, WhatsApp API, SAP connectivity, vector stores, data model design.
Phase 2
Conversation Routes
4 wks
All 5 routes, classification logic, smart handoff, outcome tracking — 38 dev-days of effort.
Phases 3–5
Web, Leads & Dashboard
3 wks
Web quotation widget, chatbot, lead routing, CRM views, KPI dashboard.
Phase 6
Testing & Launch
2 wks
20 test flows, SAP write stress testing, 5,000 conversation load test, UAT, soft launch, hard go-live.
The Impact

One system. Seven countries.

Deployed first in a Central American pilot market before regional rollout — transforming a manual, single-person WhatsApp operation into an intelligent, always-on system that qualifies, quotes, and routes every conversation with precision.

5K
Conversations / month capacity
24/7
Availability across all routes
4
Customer types classified automatically
5
Automated conversation routes
7
Countries in regional scope
0
Manual triage required