This article walks you through the process of training an AI model based on your historic Zendesk tickets and ticket fields. It then describes how you activate that model to update the ticket fields automatically on incoming new tickets.

1. Set up Zendesk Integration

First, you have to follow the steps 1-3 in Integrating with Zendesk to have your Zendesk integration set up.

2. Sync Zendesk Data

Go to the add a dataset page of and select the Zendesk option.

3. Choose the Right Column for where the Ticket Text is Situated.

4. Choose which Field to Train on

Enable the "Do you bring your own labels button and hit continue.

On this page. Pick which field that holds the column you want automatically set in Zendesk later. You can leave the Size of dataset for validation set at 10%. Hit continue.

Note: you don't have to enable the "Do you bring your own labels?" option, but then you have to set up your own labels and train it manually before step 6

5. Name your dataset

Enter a Suitable Name and (optionally) Description, hit continue.

6. Wait for the Dataset Model to Train.

Go to the overview for your newly added dataset

The status in the top left corner will first show "Uploading", then "Training" and then finally "Complete". You have to refresh the page to update the status.

Once the status is "complete" you can go on to the next step.

7. Deploy your Model

While still in the dataset overview. Hit the "Deploy" option in the navigation bar.

Hit the "Deploy to API" button:

8. Activate your new model in Zendesk

Go back to Zendesk and refresh the page to update the model list. Go to the AI Ticket Tagger App by Labelf using the left navigation bar.

Pick the model you just deployed and the field that you trained your model on (or create a new field).

Hit activate and your model should from now on automatically update your incoming support tickets with the correct field! It will also set a tag with the automatic label.

Did this answer your question?