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

说明与用途

在普通 WhatsApp 号码上使用 Evolution API、n8n 和 LLM 的自托管 AI 接待员，处理消息并实现过滤、人工交接和工作时间逻辑。

问题

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.

结果

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.

工作流

• 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

证据

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

来源

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

来源