Route support messages with GPT-4.1-mini, Slack, email and human review
Needs changesWhat this workflow does
This AI workflow has 16 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects OpenAI Chat Model. It also calls api.sendgrid.com, slack.com and sheets.googleapis.com over HTTP.
How it runs
Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).
- Normalize Message Context (Edit Fields (Set)): sets 7 fields: sender, channel, subject…
- Filter: keeps only the items that match a condition
- Python - Classify Sensitivity Tier (Code): runs custom Python code
- Send Reply to Customer (HTTP Request): calls api.sendgrid.com (POST)
- AI - Classify and Draft Reply (AI Agent): runs an AI agent, with model: OpenAI Chat Model
- Send Slack Reply (if Slack channel) (HTTP Request): calls slack.com (POST)
- JS - Parse AI Classification (Code): runs custom JavaScript code
- Wait: pauses before continuing
- Route - Sensitive or Routine? (Filter): keeps only the items that match a condition
- Log to Support Audit Sheet (HTTP Request): calls sheets.googleapis.com (POST)
…plus 2 more steps. See the full node list below.
Services it uses
HTTP calls to: api.sendgrid.com, slack.com, sheets.googleapis.com
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 and Draft Reply (v1.6): 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) AI - Classify and Draft Reply (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Webhook
n8n-nodes-base.webhook - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Edit Fields (Set)
n8n-nodes-base.set - Code
n8n-nodes-base.code - AI Agent
@n8n/n8n-nodes-langchain.agent - Filter
n8n-nodes-base.filter - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi
From the author
This workflow classifies incoming support messages from email or Slack, drafts AI-generated replies for routine queries, and automatically pauses to notify a human agent for sensitive topics such as complaints, emotional distress, billing disputes, legal…