An AI receptionist on a real WhatsApp number: architecture, routing logic, and failure modes

Описание и применение

Автоматизированный «рецепционист» на обычном номере WhatsApp использует Evolution API, n8n и LLM для обработки сообщений, с фильтрацией, передачей на человека и учётом рабочего времени.

Задача

WhatsApp is the primary front desk in Gulf and Levant regions; human operators must constantly monitor messages, leading to high labor costs and missed opportunities.

Результат

The architecture delivers a reliable, low‑cost AI receptionist that handles routing, human handoff, and office‑hours logic, while persisting sessions to avoid QR rescans and mitigating version drift and unofficial‑client risks.

Рабочий процесс

• 1. WhatsApp messages received via Evolution API webhooks
• 2. n8n workflow filters out non‑text, outgoing, and group messages
• 3. Detects human handoff keyword and stops bot replies, notifying team
• 4. Checks office hours; if closed, sends automated out‑of‑office reply
• 5. For remaining messages, calls LLM with system prompt containing business facts and language preference
• 6. Sends LLM reply back to WhatsApp
• 7. Persist session and message data in Postgres; cache in Redis

Доказательства

Four services: WhatsApp ⇄ Evolution API → webhook → n8n workflow → LLM (Claude/GPT) ↑ │ └── send reply ──────────┘ Postgres (sessions, messages) · Redis (instance cache)

Источник

The naive version — "forward every message to an LLM" — fails in production within a day.

Источник