> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getthread.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Triage Ticket Type

> Correct the ticket type on a new ticket that is still on the PSA default, telling broken from requested, without touching a type a person chose.

Runs asAgent Build it with Agent Builder: add the action to a Flow, choose Prompt the Agent, and paste this in. It runs unattended on a matching ticket event. You can also run it yourself in Super Magic while you prove it out.Works withThreadRole[Dispatcher](https://docs.getthread.com/start-here/roles/dispatcher)OutcomeFaster Resolution & ResponseCategory[Triage & Routing](https://docs.getthread.com/skill-library/triage-and-routing/overview) · [View source ↗](https://github.com/Thread-Magic/super-magic-skills/blob/main/skills/triage-and-routing/triage-ticket-type/SKILL.md)

**When to use:** Every ticket arrives as the PSA's default type (usually Incident), so service requests get reported as incidents. Run by the Self-Learning Triage Orchestrator (`automation-and-flows/self-learning-triage-orchestrator`), after Triage Learnings and Triage Similar Tickets.

**Run it:** on one ticket · or inside a triage Flow. Match the type names to the exact ones on your board.

## Prompt

```
Purpose: correct the ticket type on a new ticket. Only run when the type in the orchestrator's snapshot was still the PSA default (<e.g. Incident>). Never touch a type a person chose.

TYPES (use the exact names on this board's type list)
- Incident: something that worked is now broken, failing, slow or erroring. Includes failed backups, outages, login failures, error messages, "stopped working".
- Service Request: a request for something new or a change. New user, offboarding, new laptop or Mac setup, install software, add to a group or mailbox, permission or access change, license assignment, documentation or inventory updates, a quote.
- Problem: ONLY when the ticket says the issue recurs across several incidents, or asks for root-cause investigation. Never infer Problem from a single report.
- Change: ONLY for a planned infrastructure change the client asked to schedule (firewall rule change, migration window), and only if the board has this type.

HOW TO DECIDE
1. Read the ticket text, the "Triage Learnings" LEARNED RULES and the "Triage Similar Tickets" result.
2. If a learned rule matches, use it.
3. Else if the type agreement is Strong, follow it.
4. Otherwise ask: is something broken (Incident) or is someone asking for something (Service Request)?
5. If it really is an Incident, leave it unchanged and report "left default".
6. If you can't tell, leave the default. Changing it by mistake costs more than leaving it.
Never use a type that isn't on the board's list.

OUTPUT
Write the new type to the ticket only if it changed. Report back to the orchestrator (no note of your own):
Type: <value> | set or left default | Reason: <one line> | Confidence: High/Medium/Low
```


## Related topics

- [Chain skills into a self-learning triage agent](https://docs.getthread.com/super-magic/chain-skills-into-a-self-learning-triage-agent.md)
- [Configure Ticket Type Categorization in Autotask and Halo](https://docs.getthread.com/assistive-ai/configuring-ticket-type-categorization.md)
- [Configure HaloPSA Action Mapping for Thread](https://docs.getthread.com/integrations/action-mapping-configuration-with-thread.md)