Answer masked customer support tickets with Claude and Google Gemini RAG
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 32 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects Anthropic and Embeddings Google Gemini.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).
- Normalize and mask input (Code): runs custom JavaScript code
- Get the case (Data table): get
- Get learned Q&A (Data table): get
- Search similar Q&A (Simple Vector Store): searches the Simple vector store, with embeddings: Embeddings Google Gemini
- Validate and mask with regex (Code): runs custom JavaScript code
- Drop empty rows (Code): runs custom JavaScript code
- Check similarity (Code): runs custom JavaScript code
- Accepted? (If): checks a condition and branches into true / false
- Rebuild: add to vector store (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embeddings Google Gemini; document loader: Default Data Loader
- Similar answer found? (If): checks a condition and branches into true / false
…plus 17 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 (8)
- Webhook
n8n-nodes-base.webhook - Code
n8n-nodes-base.code - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - If
n8n-nodes-base.if - Anthropic
@n8n/n8n-nodes-langchain.anthropic - Data table
n8n-nodes-base.dataTable - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader
From the author
Quick overview This workflow receives support inquiries via webhook, masks personal data, searches similar past Q&A in an in-memory vector store using Google Gemini embeddings, and uses Anthropic Claude to draft safe auto-replies when confidence is high while…