Autonomous AI Customer Support Agent with Multi-KB RAG & Human Escalation
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 50 nodes and runs when an HTTP POST request hits its webhook URL (plus 1 other trigger). Along the way it connects Supabase, Ollama Chat Model, Embeddings Ollama and Postgres Chat Memory and 4 more.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 1 other trigger).
- Validate API Key (If): checks a condition and branches into true / false
- Build Error Summary (Code): runs custom JavaScript code
- Normalise Request (Edit Fields (Set)): sets or maps fields
- Return 401 Unauthorized (Respond to Webhook): sends the response back to the webhook caller
- Send Error Alert (Slack): uses Slack
- Log Request Timestamp (Supabase): uses Supabase
- Count Recent Requests (Supabase): get many
- Check Rate Limit (If): checks a condition and branches into true / false
- Return 429 Too Many Requests (Respond to Webhook): sends the response back to the webhook caller
- Check Message Body (If): checks a condition and branches into true / false
…plus 31 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 (17)
- Webhook
n8n-nodes-base.webhook - If
n8n-nodes-base.if - Respond to Webhook
n8n-nodes-base.respondToWebhook - Edit Fields (Set)
n8n-nodes-base.set - Supabase
n8n-nodes-base.supabase - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Switch
n8n-nodes-base.switch - Slack
n8n-nodes-base.slack - Gmail
n8n-nodes-base.gmail - HTTP Request
n8n-nodes-base.httpRequest - Error Trigger
n8n-nodes-base.errorTrigger - Wikipedia
@n8n/n8n-nodes-langchain.toolWikipedia
From the author
Quick Overview This workflow receives support requests via webhook, validates and rate-limits them in Supabase, then uses an Ollama-powered LangChain agent with three Supabase vector knowledge bases and Wikipedia search to answer via Slack, Gmail, or HTTP…