> For the complete documentation index, see [llms.txt](https://docs.harmony.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.harmony.io/service-desk-and-tickets/automatic-re-evaluation-of-itsm-tickets.md).

# Automatic Re-Evaluation of ITSM Tickets

Harmony can automatically re-evaluate your ITSM tickets using the latest AI agent logic, so ticket assessments stay accurate as conversations evolve. When a re-evaluation is triggered, Harmony reruns the full agent evaluation workflow against the ticket, overrides the previous results in the Harmony ticket record, detects relevant workflows, and regenerates internal notes. Your team always has the most current context available without needing to intervene manually.

### How Automatic Re-Evaluation Works

When a re-evaluation is triggered for an ITSM ticket, Harmony performs the following steps:

1. **Reruns the full agent evaluation workflow** - Harmony processes the ticket through the same AI agent logic used during the initial evaluation, applying any updates or improvements made to the agent since the ticket was first assessed.
2. **Overrides previous results** - The existing assessment in the Harmony ticket record is replaced with the new evaluation output, ensuring the record always reflects the most current AI-driven analysis.
3. **Detects relevant workflows** - Harmony identifies workflows that apply to the ticket based on the updated evaluation.
4. **Regenerates internal notes** - Internal notes are rewritten to reflect the latest context, giving your team an accurate and up-to-date summary directly within the ticket.

### When Re-Evaluation Is Triggered

Re-evaluation can be triggered automatically as a ticket conversation evolves - for example, when new messages or updates are added to the ticket. This means assessments remain aligned with the full conversation history rather than only the state of the ticket at the time of initial evaluation.

### Benefits

* **Accuracy over time** - Ticket assessments are not frozen at the moment of creation. As more information becomes available in a conversation, the evaluation reflects that updated context.
* **Up-to-date internal notes** - Your team does not need to manually review and rewrite notes when a ticket changes. Harmony handles regeneration automatically.
* **Consistent application of the latest AI logic** - Any improvements made to your AI agent configuration are applied to re-evaluated tickets, keeping your assessments aligned with your current setup.
* **Reduced manual effort** - Because the process runs automatically, your team can focus on resolving tickets rather than maintaining assessment accuracy.

### Considerations

* Re-evaluation **overrides** the previous results in the Harmony ticket record. If you need to retain a history of prior evaluations, ensure your workflows or integrations account for this before enabling the feature.
* Internal notes are **regenerated** during re-evaluation, so any manually edited notes in the Harmony record may be overwritten. Review your team's note-taking practices to avoid losing manually added context.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.harmony.io/service-desk-and-tickets/automatic-re-evaluation-of-itsm-tickets.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.