Debounce and buffer WhatsApp AI replies with Redis and Google Gemini
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 29 nodes and runs on WhatsApp events. Along the way it connects WhatsApp Business Cloud, Redis and Google Gemini Chat Model.
How it runs
Trigger: On WhatsApp events.
- Set Message Details (Edit Fields (Set)): sets or maps fields
- Check for Message Content (If): checks a condition and branches into true / false
- Check If Text Message (If): checks a condition and branches into true / false
- Fetch Deduplication Key (Redis): uses Redis
- Notify Non-Text Message (WhatsApp Business Cloud): uses WhatsApp Business Cloud
- Check Processing Status (If): checks a condition and branches into true / false
- Record Deduplication Key (Redis): uses Redis
- Retrieve Message Buffer (Redis): uses Redis
- Integrate Message into Buffer (Edit Fields (Set)): sets or maps fields
- Store Merged Buffer (Redis): uses Redis
…plus 13 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - Redis
n8n-nodes-base.redis - No Operation, do nothing
n8n-nodes-base.noOp - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Wait
n8n-nodes-base.wait
From the author
Quick overview This workflow debounces incoming WhatsApp messages, buffers multiple quick-succession texts per sender in Redis, and replies once using a Google Gemini model via an n8n AI Agent, while deduplicating message IDs and preventing parallel replies…