Source: https://www.zendesk.com/service/

Zendesk Service in cooperation with Cognigy.AI provides easy ticket maintenance through voice or chat channels. This tutorial will explain how to integrate an organization's Zendesk instance to a Cognigy.AI virtual agent and create or read Support Tickets.

Table of Contents

1. Install the Zendesk Extension
2. Create a Zendesk Connection
3. Create a new Support Ticket in Zendesk
4. Retrieve a Support Ticket from Zendesk
5. Search for Help Center Articles

Install the Zendesk Extension

The first step is to install the required integration. In this case, a so-called Extension is installed to Cognigy.AI. Thus, navigate to the Extensions Marketplace inside of the Virtual Agent and add the Zendesk Extension by clicking on the Install button. Now follow this installation guide and upload the Extension to Cognigy, where it will be displayed as the following:

Congrats! The installation of the Extension is finished!

Create a Zendesk Connection

In this step, a so-called Connection will be created. If one, in Cognigy.AI, clicks on the previously uploaded Extension, the following details can be observed:

The red-marked part in the above figure shows, that there is a Connection required. Therefore, it needs to be created and filled with Zendesk user information. In order to do so, one initial Zendesk Flow Node needs to be added to a Flow:

1. Create a new Flow in Cognigy.AI
2. Inside of the Flow Chart, click on + and navigate to the Zendesk Extension:
   
   
   
   
3. For example, add the Create Ticket Flow Node by clicking on it:
   
   
   
   
4. In order to edit the Flow Node and create the Connection, please click on it. An Edit Node menu will be opened on the right side of the screen:
   
   
5. Right next to the Connection field (the first one at the top), one needs to click on the + button. The Connection menu will be opened at the center of the screen:
   
   
6. Insert the related Zendesk credentials/information of the organization to the fields.
   
   1. username
      1. The username of the Zendesk user that should be used for Cognigy actions within Zendesk
   2. password
      1. The password of the Zendesk user that should be used for Cognigy actions within Zendesk
   3. subdomain
      1. The subdomain of the Zendesk instance, such as cognigy in https://cognigy.zendesk.com
7. Click on the Create button

Create a new Support Ticket in Zendesk

A common use-case for conversational AI in support is to create new tickets/incidents in order to notify the support team about the user's issue. In order to do so, the Create Ticket Flow Node can be used in Cognigy.AI:

More information about the JSON body can be found in this Zendesk documentation: https://developer.zendesk.com/rest_api/docs/support/tickets#create-ticket

The information about the user's issue could be collected during the conversation by asking different questions, such as:

Last but not least, these answers can be used in the JSON body with the help of Cognigy Script (Example):

{
    "ticket": {
        "subject":  "{{context.subject}}",
        "description": "{{context.description}}",
        "comment":  { 
            "body": "{{context.coment}}"
        },
        "priority": "{{context.priority}}"
    }
}

If one now logs in to the Zendesk Support agent dashboard, the newly created ticket will be visible.

Retrieve a Support Ticket from Zendesk

Next to the Create Ticket Node, one could retrieve the latest information about a support request by using the Get Ticket Flow Node:

The Ticket ID can be provided manually or by using Cognigy Script. Therefore, the virtual agent could ask the user for the actual ticket number before searching for it in Zendesk:

Such as displayed in the above figure, the virtual agent can use the result from Zendesk and insert it dynamically into a message. This is possible with Cognigy Script, since the result is stored into the Input object -- from default:

input.zendesk.ticket.status

would return the status of the returned ticket, such as "solved", "closed" or "open".

Search for Help Center Articles

Next to the maintain support tickets, a chat user should be able to search for knowledge articles. This functionality can be provided by using the Search Articles Flow Node:

In this case, the user input message can be used as a search query: