Automated customer support system with Gemini AI, RAG & security guardrails
Ready for 3.0What this workflow does
This AI workflow has 32 nodes and runs on Gmail events (plus 2 other triggers). Along the way it connects Guardrails, Gmail, Slack and Google Gemini Chat Model and 3 more.
How it runs
Trigger: On Gmail events (plus 2 other triggers).
- Guardrails: uses Guardrails, with model: Guard LLM
- Knowledge Base Storage (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
- Orchestrator Agent (AI Agent): runs an AI agent, with model: Reasoning Model for Orchestrator; 5 tools (Slack Tool, Email Reply Tool, Call Resolution Agent, Call Ticket Analyser Agent…); memory: Simple Memory
- Log Threats in Airtable (Airtable): create or update
- Placeholder 1(Read Note and Setup) (Edit Fields (Set)): sets 3 fields: senderEmail, threadId, query
- Email / Ticket Analyser Agent (AI Agent): runs an AI agent, with model: Ticket Analyser LLM; memory: Simple Memory
- Clean JSON (Code): runs custom JavaScript code
- Placeholder 2(Read Note and Setup) (Edit Fields (Set)): sets 5 fields: senderEmail, threadId, query…
- Knowledge worker and Investigator (AI Agent): runs an AI agent, with model: RAG LLM; 1 tool (Knowledge Base Retrieval); memory: Simple Memory
- Clean Json (Code): runs custom JavaScript code
…plus 2 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.
- Still check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll) (Gmail Trigger).
Nodes used (16)
- Guardrails
@n8n/n8n-nodes-langchain.guardrails - AI Agent
@n8n/n8n-nodes-langchain.agent - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Gmail Trigger
n8n-nodes-base.gmailTrigger - Gmail Tool
n8n-nodes-base.gmailTool - Slack Tool
n8n-nodes-base.slackTool - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Airtable
n8n-nodes-base.airtable - Email Trigger (IMAP)
n8n-nodes-base.emailReadImap - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Code
n8n-nodes-base.code - n8n Form Trigger
n8n-nodes-base.formTrigger - Edit Fields (Set)
n8n-nodes-base.set
From the author
Description This workflow acts as an autonomous Tier 2 Customer Support Agent. It doesn't just answer questions; it manages the entire lifecycle of a support ticket—from triage to resolution with Guardrails to deal with prompt injections, PII information…