Answer WhatsApp support chats with OpenRouter, Pinecone, Gemini and Gmail
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 10 nodes and runs on WhatsApp events (messages). Along the way it connects WhatsApp Business Cloud, OpenRouter Chat Model, Pinecone Vector Store and Embeddings Google Gemini and 1 more.
How it runs
Trigger: On WhatsApp events (messages).
- Configuration (Edit Fields (Set)): sets 11 fields: business_name, support_email, chat_model…
- Only incoming text messages (Filter): keeps only the items that match a condition
- AI Support Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 2 tools (Company knowledge base, Escalate to human support); memory: Conversation Memory
- Send WhatsApp reply (WhatsApp Business Cloud): send
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)
- WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Edit Fields (Set)
n8n-nodes-base.set - Filter
n8n-nodes-base.filter - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Gmail Tool
n8n-nodes-base.gmailTool - WhatsApp Business Cloud
n8n-nodes-base.whatsApp
From the author
Quick overview This workflow triggers on incoming WhatsApp messages, uses an OpenRouter chat model with Pinecone retrieval (Gemini embeddings) to answer from your support knowledge base, and escalates unanswered or sensitive requests to a human via Gmail…