Example Workflow - Using AI to extract the Customer Name – Swifteq Ltd

In this example, a Workflow is set up for Ticket Parser Autofill to do the following:

Use AI to extract the customer name that is mentioned in a new ticket and add this as a Custom Field to the ticket.

For general information on setting up Workflows, refer to Setting up the Ticket Parser Autofill Workflows.

In this Article
Creating the Custom Field
Creating the Workflow
Name and Trigger
Creating the Rules for Parse and Extract
Choosing how to Update the Ticket with the Extracted Value
Enabling the Workflow and Save
Opening the Trigger that is Created
How the Workflow uses AI to Extract the Customer Name from the Ticket and Add a Customer Field

Creating the Custom Field

If needed, create the Custom Field for the Ticket. In this example, the extracted value will be added to the Custom Field Customer Name.

Tip: Ensure that the format of the Custom Field is set up to accept the value that is extracted. In this example, Customer Name needs to be set up in the Admin Center with the Field Type of "Text".

Creating the Workflow

The following is a summary of how to set up the Workflow for this example.

Name and Trigger

Name

Enter the Name, for example, Extract Customer Name with AI.

Trigger

This selects the Zendesk Trigger to use, and whether this is when the ticket is Created or Updated.

You can select When a ticket is created (new Trigger) to create a new Trigger.

You can also select an existing Trigger that has already been created for a Ticket Parser Autofill Workflow. For details on this, refer to Trigger in Setting up the Ticket Parser Autofill Workflows.

Creating the Rules for Parse and Extract

Create the parsing rules which determine how you want to extract the value from the tickets.

Click Add parsed value to open the Rule to extract a value from text section on the right-hand side.

Extract a value from the text in these ticket fields	You can select one or more of these ticket fields. In this example, select both Ticket Subject and First Customer Message.
How to extract the value	Select Use AI to extract value.
What to extract	This value helps ChatGPT recognize the information to extract. This is entered as text and is used in conjunction with the Format of the value to extract that you enter below. For this example, enter Customer Name.
Format of the value to extract	These are the ChatGPT prompts and they tell ChatGPT what to look for. You enter this using plain English to describe the text and the format of the value you want ChatGPT to extract. Be as specific as you can. You can have as many rules as you need. You can also give an example of the value. The following is an example of the prompts to enter for this scenario. Return the customer name from the message when the customer specifically refers to a text as being the customer name or the name to receive the order. If no customer name is mentioned, return an empty string. Example: John Smith

The following is how this example looks when setting up the Rules in the Workflow.

053 Example Workflow with AI for Customer Name.gif

Click Submit to close the Rule panel.

Choosing how to Update the Ticket with the Extracted Value

Next, select what to update in the ticket.

Set Custom Field Value

For this example, checkmark Set Custom Field Value and select Customer Name.

The following is how this example looks when the Set Custom Field Value has been selected in the Workflow.

054 Example Workflow with AI Completed for Customer Name.gif

Enabling the Workflow and Save

Enable the Workflow by clicking the Enable/Disable toggle and save it by clicking Save.

055 Example Workflow with AI for Customer Name Enable.gif

The Configuration displays and includes the saved Workflow.

056 Example Workflow with AI for Customer Name on Configuration.gif

You can open and edit the Workflow at any time from the Ticket Parser Autofill Configuration.

Refer to Editing a Workflow in Enabling and Saving the Workflow, Opening the Zendesk Trigger, Editing, Disabling or Deleting a Workflow.

Opening the Trigger that is Created

This example Workflow was configured by selecting When a ticket is created (new Trigger). When the Workflow is saved, this automatically creates a Zendesk Trigger in your Zendesk Admin Center.

There are no changes needed to the Trigger for this example. If you want to check it, you can open the trigger in your Zendesk Admin Center directly from the Workflow by clicking View Trigger.

Refer to Opening and Editing the Swifteq Trigger Created in your Zendesk Admin Center.

How the Workflow uses AI to Extract the Customer Name from the Ticket and Add a Custom Field

The following is an example of how this Workflow uses AI to extract the Customer Name from the ticket and add a Custom Field.

This is an example of the email that is sent by the customer.

057 Example Workflow with AI for Customer Name Email Sent.gif

The email arrives and creates a ticket.

When the ticket is opened, the Workflow triggers and extracts the Customer Name from the message and adds this to the Custom Field Customer Name.

058 Example Workflow with AI for Customer Name Ticket Updated.gif

Note: When you have set up this Workflow, you can set up another Workflow that will trigger when the ticket is updated so that the Customer Name Custom Field can be updated if the customer includes the Customer Name in a later message. This would be set up to extract from the Last Customer Message or Any Customer Message.