Build an AI agent for WhatsApp with WOZTELL and Google Gemini
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 7 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects Google Gemini Chat Model and Woztell Sanuker (community).
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Filter: keeps only the items that match a condition
- Get conversation history by id (Woztell): get conversation history (member api)
- Edit Fields (Edit Fields (Set)): sets 2 fields: messages, member
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model
- Send responses (Woztell): uses Woztell
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that @woztell-sanuker/n8n-nodes-woztell-sanuker is verified or supports 3.0 (used in Send responses, Get conversation history by id1).
Nodes used (6)
- Webhook
n8n-nodes-base.webhook - Filter
n8n-nodes-base.filter - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Woztell
@woztell-sanuker/n8n-nodes-woztell-sanuker.woztell
From the author
✨ What this template does This workflow automatically replies to incoming WhatsApp messages using AI. When a customer sends a text message, the workflow retrieves the recent conversation history, generates a professional AI reply based on context, and sends…