Qualify inbound WhatsApp leads with Wafly and OpenAI GPT-4o-mini
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 12 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI Chat Model and Wafly (community).
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Config (Edit Fields (Set)): sets 1 field: salesPhone
- A customer wrote in? (If): checks a condition and branches into true / false
- Qualify the lead (AI Agent): runs an AI agent, with model: OpenAI Chat Model; memory: Memory per phone number
- Parse the qualification (Code): runs custom JavaScript code
- Reply to the lead (Wafly): send text (message)
- Hot lead? (If): checks a condition and branches into true / false
- Page the sales number (Wafly): send text (message)
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Qualify the lead (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Qualify the lead (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Code
n8n-nodes-base.code - Wafly
n8n-nodes-wafly.wafly - No Operation, do nothing
n8n-nodes-base.noOp
From the author
Quick overview This workflow receives inbound WhatsApp messages via Wafly, uses OpenAI (GPT-4o-mini) with per-phone memory to classify each lead as hot/warm/cold, replies to the sender, and sends hot leads as a handoff message to a configured sales phone…