Usage Endpoint for Zammad AI On-Premise

Feature requests
1

Title: Implement / Provide Usage information for On-Premise Zammad AI

  1. What is your original issue/pain point you want to solve?
    Zammad On Premise users have the option to retrieve a Zammad AI API-Key in order to be able to use the AI Provider “Zammad AI”. This API-Token has usage limits - you pay sum X to retrieve Y AI-Calls.

    As each invocation of the Zammad AI costs 1 AI-Call and thus reduces your allowance / quota. Right now, there’s no officially documented way on how to monitor the remaining AI Calls you have.

  2. Which are one or two concrete situations where this problem hurts the most?
    Missing transparency for the usage state of your AI calls. This affects On Premise users only.

  3. Why is it not solvable with the Zammad standard?
    Technically this must already be available, because Zammads SaaS does provide an information on how many Calls you have used and how many you have in total. This is most likely just a “documentation issue”.

  4. What is your expectation/what do you want to achieve?
    A short detail page within the AI-Provider documentation that tells me on how to monitor the number of AI calls I have left. No need to add explicit information for certain monitoring software.

If there is any more useful information, feel free to share it all (e.g.: mockup screenshots, if something is UI related, or the API URL/documentation URL for a service you need a connection to).

Your Zammad environment:

  • Average concurrent agent count: 1
  • Average tickets a day: 1
  • What roles/people are involved: Administrators

Anything else which you think is useful to understand your use case:

Thank you and have fun.

2

Hi @MrGeneration ,

we’ve discussed your suggestion and liked it. We’ll be adding this as an enhancement :+1:

Here’s a rough outline of how we envision it:
There will be a dashboard where you can log in, manage API tokens, view your usage history, and access a log showing which features you’ve used and how much.

So far so good. We’ll discuss this further internally and fine-tune it, but thanks already for the idea :slight_smile:

1 Like