Back to guide/Business & Marketing

Support Ticket Classifier

Structured JSON output can feed directly into ticket routing systems. The 'reason' field lets you audit the AI's classification logic. Identifying auto-resolvable tickets reduces agent workload.

chatgpt-prompts-for-customer-serviceticket_text
Edit View
Prompt
Classify this support ticket and extract structured data:

**Ticket:** "{{ticket_text}}"

Return a JSON object with:
{
  "category": "billing | technical | shipping | returns | account | feature_request | other",
  "urgency": "low | medium | high | critical",
  "sentiment": "positive | neutral | frustrated | angry",
  "key_issue": "one sentence summary",
  "product_mentioned": "product name or null",
  "action_needed": "what the customer wants",
  "suggested_response_type": "template | custom | escalation",
  "auto_resolve_possible": true/false,
  "reason": "why you classified it this way"
}

If the ticket contains multiple issues, return the primary issue and note secondary issues in a "secondary_issues" array.

Variables to customize

{{ticket_text}}

Why this prompt works

Structured JSON output can feed directly into ticket routing systems. The 'reason' field lets you audit the AI's classification logic. Identifying auto-resolvable tickets reduces agent workload.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Complaint Response (Email)

Banning generic phrases like 'I understand your frustration' forces the AI to write specific, genuine responses. Including the resolution options prevents the AI from making promises you can't keep.

Live Chat Quick Response

The 3-sentence limit forces concise chat responses. Banning filler phrases produces responses that sound human, not bot-generated. Requiring a specific next step prevents dead-end conversations.

Escalation Script

Separating internal notes from customer-facing messages prevents agents from accidentally sharing internal context. The handoff checklist eliminates the 'can you explain your issue again' experience.

FAQ Generator from Tickets

Using real tickets ensures the FAQ covers actual customer problems, not hypothetical ones. The keyword field helps with internal search and SEO. The navigation format makes instructions scannable.