Zendesk · Connector
How do we connect Zendesk to AI agents on our own infrastructure?
Katonic connects to Zendesk, reads tickets and help centre articles and indexes them in the Knowledge Engine on infrastructure you control. Agents answer from them with a model you serve, so customer conversations and the questions are not sent to a public AI service.
What it reads.
From Zendesk.
- 01Tickets
- 02Help centre articles
Through: Zendesk REST API v2
Where the content goes
Into a knowledge store you run.Content is pulled into the Knowledge Engine on infrastructure you own or control, and indexed there. Agents answer from it with a model you serve. The documents, the index and the questions are not sent to a public AI service.
How it signs in
An email address and an API token.
The set-up dialog asks for
- Subdomain
- API token
Permissions
Access is set on the source in Katonic: everyone given access to the source can retrieve its documents. The permissions Zendesk holds for each item are not read.
Sync
Incremental for tickets, by updated time. Full for help centre articles.
You set how often the source is read again, in minutes, hours, days or weeks.
Does it read tickets as well as articles?
Yes. It reads tickets and help centre articles.
Who can retrieve the tickets it indexes?
Everyone given access to the source in Katonic. Zendesk's own permissions are not read, so set that access with the tickets in mind.
Where are the tickets indexed?
In the Knowledge Engine, on infrastructure you own or control. They are not sent to a public AI service.