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

# Read a test on past tickets

> Each ticket beside what your team replied and what the Support employee would have proposed.

Requires `agent.read`. Every text field of a ticket came from the ticket and is text, never markup. `confidence.score` is the retrieval score of the strongest source the reply cites, and 0 when the answer engine declined; it is not the model grading itself.

> [!WARNING]
>
> AI employees are in **beta**. Every route answers `404` unless your deployment has switched the
> beta on. See [Test on past tickets](https://docs.mithunai.com/team/test-on-past-tickets.md). This has not yet run on a real
> Zendesk account.

## Path

**run\_id** `string` *required*

The test.

## Response

**tickets** `object[]`

Each with `human_reply`, `proposed_reply`, `outcome`, `sources`, `confidence` and `verdict`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.