AI-powered ServiceNow chat triage with GPT-4 — Incident & request router

Short description

Automatically triage incoming chat messages into Incidents, Service Requests, or Other using an LLM-powered classifier; create Incidents in ServiceNow, submit Service Catalog requests (HTTP), and route everything else to an AI Agent with web search + memory. Includes an optional summarization step for ticket context.

Full description

This n8n template wires a chat trigger to an LLM-based Text Classifier and then routes messages to the appropriate downstream action:

1. Trigger: When chat message received — incoming messages from your chat channel. 2. Text Classifier: small LLM prompt/classifier that returns one of three labels: Incident, Request, or Everything Else. 3. Create Incident (ServiceNow connector): when labeled Incident, the workflow creates a Servicenow Incident record (short fields: short\description, description, priority, caller). 4. Submit General Request (HTTP Request): when labeled Request, the workflow calls your Service Catalog API (POST) to place a catalog item / submit a request. 5. AI Agent: when labeled Everything Else, route to an AI Agent node that:

uses an OpenAI chat model for contextual replies, can consult SerpAPI (web search) as a tool, saves relevant context to Simple Memory for future conversations. 6. Summarization Chain: optional chain to summarize long chat threads into concise ticket descriptions before creating incidents/requests.

This template is ideal for support desks that want automated triage with human-quality context and searchable memory.

Key highlights (what to call out)