# Auto-close thank-you replies and prioritize support tickets with ChatGPT

Allen Lai's customer experience team at Otter.ai used Zapier and ChatGPT to spot reopened Zendesk tickets that only said thanks and close them, and to tag new tickets by urgency and category. Over 1,000 tickets were auto-solved in three months and more than 10,000 were enriched and routed.

- Blaze Score: 64/100
- Proof: One public report
- Difficulty: Beginner
- Tools: ChatGPT, Zapier
- Setup time: 45 min
- Monthly cost: $20/mo
- Saves: several hours per agent per week
- Source: https://www.zapier.com/blog/otter-ai-customer-support-automation
- URL: https://www.blazefish.com/use-case/auto-close-thank-you-replies-and-prioritize-support-tickets-with-chatgpt/

### Steps

1. Create a Zap triggered when a help-desk ticket is reopened or gets a new customer comment.
2. Send the latest comment to ChatGPT and ask whether it needs any reply.
3. Add a filter: if the answer is no, mark the ticket solved and leave an internal note.
4. Build a second Zap for new tickets that asks ChatGPT for urgency, sentiment and category and writes them as tags.
5. Spot-check auto-closed tickets for the first two weeks before trusting it fully.

### Prompt

```
Read this customer message from a support ticket. Answer with JSON only: {"needs_reply": true/false, "sentiment": "positive|neutral|negative", "urgency": "low|medium|high", "category": one of [billing, bug, how-to, account, other]}. A message that only says thanks or confirms the issue is fixed does not need a reply. Message: [comment]
```