> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/support-workflows/user-qa.md).

# User QA

Apply rubrics to issues to make sure guidelines and process are being followed.

User QA uses AI to grade closed issues against rubrics you define, so you can check that guidelines and processes are being followed at both the issue and the teammate level. Find it under **Settings > Support > User QA**.

{% hint style="info" %}
User QA is available on select plans. Contact your account team to enable it.
{% endhint %}

## Rubrics

Create rubrics on the [User Rubric](https://app.usepylon.com/settings/ai-controls/qa?tab=userRubric) tab:

1. Click **Add Metric**.
2. Describe how the AI should evaluate this metric: what to look for, how to judge it, and how to score it.
3. Add the scoring **Options**.
4. Under **Applies to**, choose **Issue** to grade the issue as a whole, or **each Agent individually** to grade every teammate who worked the issue.

<figure><img src="https://982123570-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9hXBoCTTNw5flARlUVJf%2Fuploads%2FfbQdqjdUKZTAOkr97xIe%2FCleanShot%202025-09-10%20at%2011.28.59%402x.png?alt=media&amp;token=0652e0da-f92b-497e-bf8c-56880373872e" alt="" width="563"><figcaption></figcaption></figure>

## Review

When issues are closed, they are evaluated against your rubrics. If an issue is reopened before grading finishes, it is graded the next time it closes.

* The [Issues](https://app.usepylon.com/settings/ai-controls/qa?tab=issues) tab lists evaluated issues. Filter by date and rubric results, for example to find issues not meeting expectations.
* The [Users](https://app.usepylon.com/settings/ai-controls/qa?tab=users) tab shows results per teammate for a date range. Open a teammate to see their results in detail.

<figure><img src="https://982123570-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9hXBoCTTNw5flARlUVJf%2Fuploads%2FDrkuymT8rst79Zym568C%2FCleanShot%202025-09-09%20at%2015.10.51%402x.png?alt=media&amp;token=0ed7cb2f-5fdb-400a-8323-a97f30aceb53" alt=""><figcaption></figcaption></figure>


---

# 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.usepylon.com/pylon-docs/support-workflows/user-qa.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.
