Route AI tasks between OpenAI agents with confidence-based email fallback
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 14 nodes and runs when an HTTP GET request hits its webhook URL. Along the way it connects OpenAI Chat Model.
How it runs
Trigger: When an HTTP GET request hits its webhook URL.
- Workflow Configuration (Edit Fields (Set)): sets 2 fields: userRequest, confidenceThreshold
- Supervisor Agent (AI Agent): runs an AI agent, with model: OpenAI Model - Supervisor; output parser: Routing Decision Parser
- Check Confidence Score (If): checks a condition and branches into true / false
- Execute Selected Agent (AI Agent): runs an AI agent, with model: OpenAI Model - Executor; 2 tools (Complex Task Agent Tool (5.4), Simple Task Agent Tool(5 MINI))
- Send Fallback Alert (Send Email): sends an email over SMTP
- Respond to Webhook: sends the response back to the webhook caller
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 (9)
- Edit Fields (Set)
n8n-nodes-base.set - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - If
n8n-nodes-base.if - Send Email
n8n-nodes-base.emailSend - Webhook
n8n-nodes-base.webhook - Respond to Webhook
n8n-nodes-base.respondToWebhook - AI Agent Tool
@n8n/n8n-nodes-langchain.agentTool
From the author
Overview This workflow demonstrates an AI task routing system using multiple agents in n8n. It analyzes incoming user requests, determines their complexity, and routes them to the most appropriate AI agent for processing. A Supervisor Agent evaluates each…