← Back to projects

TodoPlagas · AI Assistant Suite

WhatsApp + phone calls, 24/7. Automated lead capture and customer support for a pest-control company, orchestrated on n8n.

Conversation with Sofía, TodoPlagas' WhatsApp assistant

I designed and built an AI assistant suite that automates the entire lead-capture cycle: it handles WhatsApp and phone calls 24/7, extracts lead data with AI, persists it in PostgreSQL and automatically pushes it into the industry CRM (iGEO), leaving the conversation ready for a technician to pick up. A second agent handles real-time voice calls reusing the same infrastructure.

Architecture

Channels

WhatsApp → Chatwoot
Llamada / Call → VAPI
Email → IMAP

n8n · Orchestration

Agente IA · LangChain
Motor FAQ / FAQ engine
Extracción de datos

Data & Outputs

PostgreSQL
RabbitMQ → iGEO (CRM)
Telegram · Google Drive

Components

Sofía — WhatsApp assistant

main workflow · ~93 nodes

  • Conversational agent (LangChain + OpenAI GPT-4.1-mini) with memory persisted in PostgreSQL.
  • Voice-note transcription with Whisper and a pest knowledge base fed from Google Drive (lightweight RAG).
  • Message debounce, response chunking and human handoff via Chatwoot (a label pauses the AI).

Dante — Voice call assistant

real-time voice

  • Answers inbound calls with VAPI wired to n8n via webhook.
  • Personalized greeting depending on whether the caller is already in the DB (reply in <20 s) and live tools (pest KB, customer data).
  • Post-processing with GPT-4o-mini: extracts the lead from the transcript as structured JSON.

iGEO integration (industry CRM)

async · RabbitMQ

  • Valid leads are transformed into iGEO's proprietary payload and sent over a RabbitMQ queue, decoupling the bot from the CRM.
  • A result listener and a timeout watcher close the async loop; anti-duplicate flag in the DB.

Support workflows

6+ in production

  • FAQ / state machine shared by both bots, lead insertion, email lead capture.
  • New-lead notifications and centralized error alerts via Telegram at every critical point of the pipeline.

Tech stack

Orquestación / Orchestration n8n (self-hosted · Docker · Easypanel)
LLMs OpenAI GPT-4.1-mini · GPT-4o-mini · Whisper
Agentes / Agents LangChain (n8n nodes)
Base de datos / Database PostgreSQL
Cola / Queue RabbitMQ
WhatsApp Chatwoot (omnicanal + handoff)
Voz / Voice VAPI
CRM / ERP iGEO
KB Google Drive → PDF → PostgreSQL
Alertas / Alerts Telegram

Technical challenges solved

Real project built for a client. The code lives in n8n and is not public (NDA); this page summarizes the architecture and behavior without exposing real data or configuration.