Summarize and answer Re:amaze support emails with Gemini and SOP knowledge base

Go to Workflow
2 views
Built by Divyanshu Gupta Divyanshu Gupta
Created on June 06, 2026

Description

This template demonstrates an AI-powered email automation system for Re:amaze, summarizing and responding to customer inquiries using a structured knowledge base to ensure accurate and consistent replies.

🔹 Ideal for:
Customer support teams handling high volumes of email queries (e.g., e-commerce, SaaS)
Businesses looking to automate SOP-based responses with AI while integrating actions like order lookup or issue logging

What this workflow does
Fetches incoming customer emails from Re:amaze
Filters only customer messages (ignores agent replies)
Classifies email intent (e.g. security, pricing, setup etc.)
Matches the request against a structured SOP knowledge base
Generates a response using AI based strictly on SOP
Sends reply back to the customer automatically

Key Features:
Prevents duplicate replies using deduplication logic
Ensures responses follow SOP (reduces hallucination)
Scalable for high-volume email handling

Requirements
Re:amaze API access (for fetching & replying to conversations)
AI model (e.g., OpenAI / Gemini configured in n8n)
SOP knowledge base (Google Sheets or Code tool)

How to set up
Add your Re:amaze API credentials in HTTP nodes

To get the API Key, you have to login to the Re:amaze plateform(https://www.reamaze.com/)

Here is the API documentation -https://www.reamaze.com/api/get_messages

Configure your AI model credentials
Connect your SOP knowledge base (Google Sheets or internal tool)
Test the workflow using sample customer emails

🚀 This template can be extended to support multi-channel support (chat, tickets, etc.)

Need Help?
ask in the Forum!

Happy Hacking!

Nodes Used (6)

AI Agent
@n8n/n8n-nodes-langchain.agent
Code Tool
@n8n/n8n-nodes-langchain.toolCode
Google Gemini
@n8n/n8n-nodes-langchain.googleGemini
Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini
HTTP Request
n8n-nodes-base.httpRequest
Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured