WhatsApp Lead Replies with OpenAI, Supabase & Slack (n8n)

Turn every WhatsApp message into a qualified sales conversation—automatically

This n8n workflow receives WhatsApp Cloud API inbound messages, uses OpenAI to generate short, grounded sales replies, logs and scores leads in Supabase, and alerts your team in Slack when a lead is Hot or a human is needed.

What this workflow does

• Receives WhatsApp Cloud API webhooks for inbound messages and handles Meta’s one-time webhook verification challenge.
• Normalizes incoming payloads into clean customer message records, while ignoring non-message status callbacks.
• Deduplicates and manages CRM context by checking Supabase for the WhatsApp message ID, then creating or retrieving the customer by phone number and pulling recent conversation history.
• Generates an AI reply with OpenAI using the customer message, recent history, and business info to classify intent and draft a short response.
• Scores lead temperature (Cold/Warm/Hot) with rule-based lead scoring and prepares the final WhatsApp response payload.
• Sends the reply on WhatsApp, saves the conversation in Supabase, updates customer CRM fields, and posts a Slack alert when the lead is Hot or the agent flags that a human should take over.

Use cases

• Responding to inbound WhatsApp inquiries for SaaS demos with consistent, intent-aware follow-ups.
• Automatically qualifying leads and notifying sales when someone is ready for outreach (“Hot” lead).
• Reducing manual support load by escalating only when the conversation requires a human.

Technical details

• WhatsApp Cloud API: webhook handling and response delivery.
• OpenAI: agent classification and drafting short sales replies.
• Supabase: customers, conversation storage, deduplication by WhatsApp message ID, and CRM updates.
• Slack: team alerts for Hot leads and human-needed flags.
• n8n nodes: webhook, if, set, code, slack, supabase.