Route customer support requests to AI specialists with OpenRouter
Needs changesWhat this workflow does
This AI workflow has 14 nodes and runs when an HTTP POST request hits its webhook URL. Along the way it connects OpenRouter Chat Model.
How it runs
Trigger: When an HTTP POST request hits its webhook URL.
- Normalize Request (Code): runs custom JavaScript code
- Orchestrator Agent (AI Agent): runs an AI agent, with model: OpenRouter Chat Model; 3 tools (Account_Specialist, Billing_Specialist, Technical_Specialist)
- Parse Final Response (Code): runs custom JavaScript code
- Orchestrator Succeeded? (If): checks a condition and branches into true / false
- Respond to Customer (Respond to Webhook): sends the response back to the webhook caller
- Escalate to Human (Code): runs custom JavaScript code
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Orchestrator Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Orchestrator Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (7)
- Webhook
n8n-nodes-base.webhook - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - AI Agent Tool
@n8n/n8n-nodes-langchain.agentTool - If
n8n-nodes-base.if - Respond to Webhook
n8n-nodes-base.respondToWebhook - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter
From the author
Quick overview This workflow receives customer support requests via a webhook, normalizes the payload, and uses an OpenRouter-powered orchestrator agent to route the request to a Billing, Technical, or Account specialist agent. It then returns a structured…