AI-powered ticket triage with multi-model classification & knowledge base
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 22 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenAI Chat Model, MCP Client, Postgres PGVector Store and Embeddings OpenAI and 2 more.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Workflow Configuration (Edit Fields (Set)): sets 4 fields: pgVectorTable, pgVectorHost, pgVectorDatabase…
- Ticket Classifier Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (MCP Server Tools, Knowledge Base Search); output parser: Classification Output Parser
- Check If Solution Found (If): checks a condition and branches into true / false
- Format Auto-Resolution (Edit Fields (Set)): sets 4 fields: status, resolution, resolvedBy…
- AI Solution Generator (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (MCP Server Tools); output parser: Solution Output Parser
- Update Ticket Status (Postgres): run a query
- Create Diagnostic Logs (Code): runs custom JavaScript code
- Prepare KB Entry (Edit Fields (Set)): sets 1 field: kbEntry
- Check If Engineer Needed (If): checks a condition and branches into true / false
- Add to Knowledge Base (Postgres PGVector Store): stores documents in the Postgres PGVector Store vector store, with embeddings: Embeddings OpenAI; document loader: Document Loader
…plus 1 more step. 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 (13)
- Webhook
n8n-nodes-base.webhook - Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - MCP Client Tool
@n8n/n8n-nodes-langchain.mcpClientTool - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - If
n8n-nodes-base.if - Code
n8n-nodes-base.code - Slack
n8n-nodes-base.slack - Postgres
n8n-nodes-base.postgres - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader
From the author
How It Works This workflow automates enterprise ticket management by combining AI-powered classification with knowledge base retrieval. It receives support tickets via webhook, routes them through multiple AI models (OpenAI ChatGPT, NVIDIA's text…