Production AI Playbook: Deterministic Steps & AI Steps (3 of 5)
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What 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 Ticket (Code): runs custom JavaScript code
- AI - Classify (AI Agent): runs an AI agent, with model: OpenRouter Chat Model
- Parse + Validate (Code): runs custom JavaScript code
- Confidence Threshold (Switch): routes items into 3 branches
- Route by Category (Switch): routes items into 3 branches
- Flag for Review (Code): runs custom JavaScript code
- Send to Human Queue (Code): runs custom JavaScript code
- Billing Team (Code): runs custom JavaScript code
- Technical Team (Code): runs custom JavaScript code
- Sales Team (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
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI - Classify (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI - Classify (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (6)
- Webhook
n8n-nodes-base.webhook - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Switch
n8n-nodes-base.switch - Respond to Webhook
n8n-nodes-base.respondToWebhook - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter
From the author
Combine AI classification with confidence-based routing and category-based fan-out. This template classifies incoming support tickets, routes them by confidence level, and shows an example of how to fan high-confidence items out to the right team. What you'll…