In this example, a Workflow is set up for Ticket Parser Autofill to do the following:
Use AI to extract the date that an Order was made from the either the Ticket Subject or the First Customer Message in a new ticket, and add this to a Custom Field Order Date.
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 Order Date from the Ticket and Updates the Custom Field
Creating the Custom Field
If needed, create the Custom Field for the Ticket.
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 Order Date 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 Order Date. |
| 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. Using a Placeholder, you can use AI to extract information that is not in the exact format required. For example, if you want to extract the Order Date from the message, the customer may have added this as the word “today” , “yesterday”, “last week” etc. To use the Placeholder, you can copy this from the list of Supported Placeholders.
Return the date the order was created in the format YYYY-MM-DD.
Tip: The Format of the value to extract includes the text “given that the time now is” before the Placeholder. The reason for this is that, when using the API, ChatGPT does not know what time it is, so this needs to be provided in the prompt. In this example, the prompt instructs ChatGPT to think that the current time is the time when a ticket is created so that it can calculate the relative date.
|
The following is how this example looks when setting up the Rules in the Workflow.
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. Then select the Custom Field as Order Date. |
The following is how this example looks when the Order Date Custom Field has been selected in the Workflow.
Enabling the Workflow and Save
Enable the Workflow by clicking the Enable/Disable toggle and save it by clicking Save.
The Configuration displays and includes the saved Workflow.
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 Order Date from the Ticket and Updates the Custom Field
The following is an example of how this Workflow uses AI to extract the Order Date from the ticket and updates the Custom Field.
This is an example of the email that is sent by the customer. They have said that the order was placed "last Thursday". This email was sent on Friday 15th November, so the order would have been placed on Thursday 7th November.
The email arrives and creates a ticket.
When the ticket is opened, the Workflow triggers and extracts the Order Date from the message and updates the Order Date Custom Field with the date 2024-11-07.
In this example, the Order Number has also been added by another Workflow in the Ticket Parser Autofill.
Comments
0 comments
Article is closed for comments.