# Summarize and answer Re:amaze support emails with Gemini: n8n workflow > Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Gemini. Source: https://millionrounds.com/workflow/summarize-and-answer-re-amaze-support-emails-with-gemini (Millionrounds; every figure on the page links to its filing or article) [Automation library](https://millionrounds.com/workflows) 路 [Customer support](https://millionrounds.com/workflows?category=Customer+support#library) # Summarize and answer Re:amaze support emails with Gemini Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Gemini. 13 steps, 1 branch: a working afternoon to understand properly. Medium Calls a model: Gemini [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsummarize-and-answer-re-amaze-support-emails-with-gemini) **13 steps** Medium: a working afternoon **1** Branch: places the flow splits **0** Loops or waits **0** Services by connector: it calls them over plain HTTP ## The flow Starts it 1 Model 5 Logic 5 Service 2 The steps in the order they run, from what starts it. - 1 **LLM Response Generator** Lm Chat Google Gemini *Model* - 2 **Structured Response** Output Parser Structured *Model* - 3 **Manual Trigger (Test Workflow)** Manual trigger *Starts it* - 4 **馃摎 Knowledge Base** Tool Code *Model* - 5 **AI Support Agent** Agent *Model* - 6 **Fetch Conversations from Re:amaze API** Http Request *Service* - 7 **Prepare Final Response** Set *Logic* - 8 **Split Conversations into Individual Messages** Split Out *Logic* - 9 **Send Reply to Customer (Re:amaze API)** Http Request *Service* - 10 **Sort Messages by Latest First** Sort *Logic* - 11 **Remove Duplicate Conversations (Prevent Double Reply)** Remove Duplicates *Logic* - 12 **Filter Only Customer Emails** If *Logic* - 13 **Email Category Classifier** Google Gemini *Model* ## How it's built - **Starts on:** An event in a connected app - **Steps:** 13, with 1 branch - **Size:** Medium: a working afternoon - **Connects to:** Nothing by connector; it calls services over plain HTTP - **Model:** Gemini ## Questions What does it need to run? An n8n account, and a key for Gemini. You connect your own accounts after importing it; none are included. What starts it? It starts on an event in a connected app. Does it use AI? Yes. It calls Gemini. Model calls are billed by the provider, not by n8n. How long does it take to set up? Plan an afternoon. 13 steps is enough that you should read each one before running it. How do I import it? Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts. **Before you run it** Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 13 steps before you point it at anything that matters. ## Run it in n8n - **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account 鈫梋(https://millionrounds.com/n8n) - **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsummarize-and-answer-re-amaze-support-emails-with-gemini) - **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts. Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind. ## Workflows like it Also customer support, with the same services where possible, closest in size first. - [**AI Customer Support Bot: Auto-Classify, Route** 13 steps 路 calls a model 路 Slack](https://millionrounds.com/workflow/ai-customer-support-bot-auto-classify-route) - [**AI Customer Support Chat for Web Hosting with Gemini and WHMCS** 13 steps 路 calls a model 路 Google Sheets](https://millionrounds.com/workflow/ai-customer-support-chat-for-web-hosting-with-gemini-and-whm) - [**AI-powered support automation with Outlook and OpenAI** 13 steps 路 calls a model 路 Gmail, Jira](https://millionrounds.com/workflow/ai-powered-support-automation-with-outlook-and-openai) - [**Answer support chat questions from uploaded documents** 13 steps 路 calls a model 路 in-memory vectors](https://millionrounds.com/workflow/answer-support-chat-questions-from-uploaded-documents) - [**Assess churn risk from HubSpot tickets with DeepSeek and Slack** 13 steps 路 calls a model 路 HubSpot, Slack](https://millionrounds.com/workflow/assess-churn-risk-from-hubspot-tickets-with-deepseek-and-sla) - [**Automate customer support with WhatsApp AI** 13 steps 路 calls a model 路 Google Docs, Google Sheets](https://millionrounds.com/workflow/automate-customer-support-with-whatsapp-ai)