Feroze1888 WhatsApp AI Customer Support System — client logo

24/7 AI-Powered Customer Support for a Global Textile Leader

Feroze1888 Mills Limited — Pakistan's premier towel manufacturer needed to modernize their fragmented, form-based inquiry system into a seamless, instant-answer experience. We designed and deployed a multi-agent AI orchestration system on WhatsApp that routes customer queries to the right specialist agent in milliseconds, powered by a comprehensive knowledge base spanning products, careers, investor relations, sustainability, and procurement.

Feroze1888 WhatsApp AI Customer Support System — project screenshot by Neura Agency

Sub-2s

Average AI response time — instant answers replacing hours/days of waiting

8

Specialist agent domains covering every business function from products to procurement

98%

Reduction in manual inquiry triage through automated intent classification and routing

THE CHALLENGE

Static forms were costing them global opportunities

Feroze1888 relied on separate static web forms for Marketing, HR, Procurement, and General inquiries — a fragmented system that created response delays ranging from hours to days. Global partners, job seekers, investors, and suppliers in different time zones had no way to get instant answers about products, open bids, financial data, or career opportunities. The support team was overwhelmed with repetitive queries, while complex domain-specific questions (e.g., investor governance details, sustainability metrics, or supplier registration steps) frequently got misrouted, requiring multiple back-and-forth emails to resolve.

THE SOLUTION

A WhatsApp-native multi-agent brain with enterprise guardrails

We built a FastAPI-based orchestration layer that connects WhatsApp (via Evolution API) to a network of 8 specialist AI agents, each trained on a curated knowledge base scraped directly from Feroze1888's official website. A Router Agent uses keyword fast-pathing augmented by LLM-based intent classification to dispatch messages to the correct specialist in under 500ms — Product, Company, Career, Investor, Sustainability, Procurement, General, or Escalation.

Core Capabilities

Multi-Agent Intent Routing Engine

A Router Agent classifies incoming WhatsApp messages into 8 intent categories using a hybrid fast-path keyword matcher and LLM-based fallback, achieving sub-second dispatch to the correct specialist domain.

8 Specialist Domain Agents

Dedicated AI agents for Products, Company Info, Careers, Investor Relations, Sustainability, Procurement, General Support, and Human Escalation — each trained on a structured, domain-specific knowledge base with confidence self-assessment.

Enterprise Content Guardrails

Multi-layer defense system including rate limiting, prompt injection detection, off-topic blocking, PII redaction, output sanitization, and escalation detection — ensuring safe, on-brand responses at all times.

Conversation Memory & Context

In-memory per-session context stores the last 3 exchanges per user, enabling natural follow-up conversations without repeating context — with automatic escalation when user frustration is detected.

WhatsApp Presence & Formatting Engine

Real-time typing indicators ('composing...', 'paused') for human-like interaction, auto-splitting of long messages with progress markers, and WhatsApp-native bold/emoji formatting across all agent responses.

One-Command Docker Deployment

Full microservices stack (FastAPI backend, Evolution API gateway, PostgreSQL, Redis) deployable via `docker-compose up -d` with Nginx reverse proxy support, health checks, and isolated networking.

Architecture & Technology

Backend

  • Python 3.11
  • FastAPI
  • OpenRouter API (Google Gemini 2.0 Flash)
  • httpx
  • Pydantic
  • Uvicorn

Infrastructure

  • Docker
  • Docker Compose
  • PostgreSQL 15
  • Redis 7
  • Evolution API (WhatsApp Gateway)

External APIs

  • OpenRouter AI API
  • Evolution API
  • WhatsApp Cloud API (via Evolution)