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

# Read a compliance ticket

> Understand the note Primo AI leaves, what an employee reply changes, how to instruct it from an internal note, and what closes a compliance ticket.

A compliance ticket looks like any other ticket, with one difference: its assignee reports back in writing after every run. This article covers how to read those notes and how to steer Primo AI from the ticket itself.

For what Primo AI is allowed to do in the first place, see [What Primo AI does on a compliance ticket](/mdm/compliance/primo-ai-remediation).

## Read the note

Every run ends with a note in one of three shapes. The first line is the outcome, the last line is the one thing you have to do.

| Note            | What it means                                                                                  | What you do                                                                                                      |
| --------------- | ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- |
| **Fixed**       | Primo AI pushed a fix and re-read the device to confirm it landed.                             | Nothing. The ticket closes when the device next reports compliant.                                               |
| **Waiting**     | The fix is out and the device has not confirmed it yet, or the employee has been asked to act. | Nothing yet. Primo AI does not chase the employee a second time — after a reasonable delay, the ticket is yours. |
| **Handed back** | Only an admin can go further. The note names why.                                              | Act on the last line. Primo AI will not retry.                                                                   |

A note that ends a run with the issue still open is a valid outcome, not a failure to read past.

## Reply as an employee

An employee's public reply on the ticket is **information, never an instruction**. It can tell Primo AI that the device was restarted; it cannot make it run something, grant an exemption, or reopen a question that was already settled.

If an employee asks for a human, Primo AI stops writing to them.

## Instruct Primo AI from an internal note

An internal note from an admin **is** an instruction, and it is carried out — move the device to stock, unassign it, retry a push, close this ticket. There is no second question and no proposal first.

Only a ticket's admins and its assignee can post internal notes, which is what makes the note proof of authority.

An instruction Primo AI can only half satisfy is half carried out, with one line about the rest.

<Warning>
  Destructive actions need the policy open, not just the note. Wiping, locking, retiring, and unenrolling stay shut unless your [remediation policy](/mdm/compliance/remediation-policy) explicitly opens them. An instruction in a ticket does not open them on its own.
</Warning>

## Close a compliance ticket

* **Primo closes the ticket by itself** when the device reports compliant again and the issue disappears. This is the normal path.
* **You can ask Primo AI to close a ticket** in an internal note. It does, and it tells you what stays behind: the issue is still raised, the device still reads non-compliant everywhere in the dashboard, and no new ticket opens for it while it stays that way.
* **Primo AI never closes or reopens a compliance ticket on its own initiative.**

## Approve what Primo AI learned

When a run ends on a fact that will decide the next ten tickets — an office network that blocks the agent, a device group held in stock — Primo AI offers, in one line and quoting the exact sentence, to add it to the **Company knowledge** section of your policy.

<Steps>
  <Step title="Read the proposed sentence">
    It is quoted verbatim in the note, so you approve the exact wording that will be saved.
  </Step>

  <Step title="Reply yes in an internal note">
    That reply is the approval. Only a ticket's admins and its assignee can post internal notes.
  </Step>

  <Step title="Primo AI merges, saves, and publishes">
    It confirms in the ticket once done. If you have unfinished draft edits on the policy, it saves the addition, skips the publish, and says so.
  </Step>
</Steps>

A **yes** adds knowledge. It never widens what Primo AI is allowed to do — only the policy's other sections do that.

## What if the ticket is on a demo company?

Demo companies run the real path with fabricated agent comments, and the demo assistant is live. A comment on a demo compliance ticket starts a real run against fake device data.

## Related articles

* [What Primo AI does on a compliance ticket](/mdm/compliance/primo-ai-remediation)
* [Write your remediation policy](/mdm/compliance/remediation-policy)
* [Limits and platform constraints](/mdm/compliance/remediation-limits)