1. They may have to seek approval from seniors to proceed.
   
2. Share the ticket with other team members to get details.
   
3. Get a confirmation on the solution from peers.
   

1. who should be assigned the ticket
   
2. what action and solution is needed
3. how long would it take to resolve?
   

Note: Currently, Zia supports only English, and we are working on adding more language support soon.

Zia's role in reducing resolution time and improving customer satisfaction

Ticket segmentation and auto assigning them to the right agent

1. their severity
   
2. problem or product type
   
3. support tier
   
4. subcategory
   

Identifying customer requirement from the ticket description

Understanding field predictions

Points to remember

1. Zia can predict only picklist values. It can predict both system and custom picklist field values.
   
2. You must ensure that the picklist fields are added to the default layout because prediction can be executed only in the default layout.
   
3. A department must have at least 500 tickets for Zia to train. It is recommended to have at least 500 tickets for each picklist value for Zia to predict effectively.
   
4. Zia will predict based on the tickets that are available at the time of configuration. Tickets received after this period must be manually added to the prediction in order to retrain Zia.
   

Training Zia to analyze tickets and predict values

Zia can predict picklist values and also determine the ticket owner. Once field prediction is enabled in the Desk account, Zia begins its training using the existing tickets. During configuration, as you set the field(s) and the picklist values that you want to predict. Also, you can decide whether Zia should train only using specific tickets.

1. Training using specific tickets - Consider you want Zia to classify the issue and predict if it's a bug fix, feature request, incident, or data loss, then it's recommended to use specific tickets for training. This will allow Zia to analyze relevant tickets and interpret the values based on the pattern.
   
2. Training using all tickets - Likewise, if you want to assign tickets to a particular person and want Zia to predict the owner, then it's best to train Zia using all the tickets so that the training data is vast, versatile, and provides a wider scope to learn, analyze, interpret, and predict.
   

Determining prediction accuracy

Best practices to achieve a better accuracy score

1. Set a criteria to train Zia only on specific tickets if you want explicit predictions. Eg., predict problem type for tickets from the IT sector.
   
2. Give a wide range of training data to enhance Zia's learning ability. Eg., predict the product type.
   
3. Retrain Zia using the latest tickets to append the prediction.
   
4. Set the criteria as created time to train on specific data. Eg., predict issue type based on tickets that were received from January to June.
   

Flow of events during field prediction

Configuring field predictions

You can create a maximum of 20 field predictions/department. 

1. When the ticket is created - For example, to automate ticket profiling, the prediction must take place during ticket creation. In a new ticket, agents have to evaluate the "issue type" and the "service that is needed"; based on that information, the ticket should be assigned to an agent. Zia can automate this by predicting "Issue Type", "Service Type", and "Ticket owner".
   
2. When the customer response is received on a ticket - For example, if the customer replies to an old ticket and you want to predict the "problem" to assign it to the right agent, then you can choose this option.
   

Note that Zia will auto-update the predicted value only if it meets the accuracy score that you set during configuration. For eg., if you set the accuracy score as 70% and the predicted value is only 65% accurate, then Zia will not auto-update the value.

1. "Issue" contains "Replacement", "Technical issue", "Faulty product"
   
2. "Service charges" is "Yes"
   
3. "Ticket category" contains "Service needed"
   
4. "Service cost" is "Greater than or equal to 10$ 

1. Go to Setup > Zia > Field Predictions.
   
2. Click Create New Field Prediction.
   
3. In What do you want to predict?, select a field from the drop-down.
   
4. In Execute on, select Ticket creation, Customer reply or both.
   
5. In Field Update mode, choose Auto-update predicted value or Manually confirm the predicted value.
   
6. Select the Accuracy Score from the drop-down list.
   
7. Select the fields that Zia can use for training.
   
8. Click Save.
   
   

Enabling field prediction

Once the status is completed and the accuracy score meets your requirement, you can toggle the corresponding fields to enable field prediction.

Viewing tickets used for training

1. Go to Setup > Zia > Field Prediction.
   
2. Click on the Predictor, from the list view.
   
3. In the Ticket Annotation page, click the Trained Tickets tab.
   
4. Select a field value.
   The ticket will be added to the annotated list for retraining purpose.
   
   

Importing new tickets to retrain Zia

1. Auto-assignment of the tickets to the correct team
   
2. Notification to the relevant team preventing oversight
   
3. Workflow-based email to the customers ensuring the FRT adheres to the SLA 
   

1. Selecting a field prediction: The field predictions that are created will be listed under Zia > Field predictions. You can select a prediction you want to improve the accuracy for. Additionally, the predictions that have an accuracy score less than 70% will display an option to annotate. Note that, predictions that have less than 70% score need to be annotated to enable.
   
   
2. Selecting tickets to import: You can import both annotated and unannotated tickets. When a picklist field that needs to be predicted has the "None" value, its tickets are referred to as unannotated. For example, if you are predicting the ticket owner, all the tickets where Zia couldn't predict an owner and left the field empty will be listed under the Unannotated Tickets tab. Likewise, if an agent is unsure of the severity level and has not chosen a value for the field, will have the ticket listed under the Unannotated tab. 
   
   
3. Setting criteria for tickets: If you want to train Zia using specific tickets, you can set the criteria to filter the relevant tickets. This is not a mandatory step.
   
   
4. Changing the number of tickets to import: By default, Zia will consider all the tickets that are unannotated or annotated. Users can edit the number of tickets that should be imported. For example, if you are predicting the "Issue Severity" field and the number of tickets are as follows:
   
1. Level 1 - 120
   
2. Level 2 - 180
   
3. Level 3 - 50
   
4. None - 10
   If you want only 10 tickets from level 3 to be imported, you can change the value to 10. The first 10 tickets from the 50 tickets will be imported. 

A maximum of 500 tickets for each value can be imported at any point of time. That is, considering the above example, Level 1 (500 tickets), Level 2 (500 tickets) and so on. 

To import tickets to field prediction

1. Go to Setup > Zia > Field prediction.
   
2. Hover on a Field Prediction that you want to import more tickets to.
   
3. Click Annotate.
   You will be redirected to the Ticket Annotation page, under the Unannotated tab.
4. In the Unannotated Tickets tab, click Import.
   
5. In the Set Criteria popup, select the field and value as needed. This is an optional step.
   
6. Click + to add more criteria.
   
7. Click Fetch Tickets.
   
8. In the Import Tickets popup, edit the number of tickets for each picklist value, if needed.
   
9. Select the picklist values that should be imported.
   
10. Click Change criteria, if needed.
    
11. Click Import Tickets.
    Once the import is completed, it will be displayed under Zia Notification. The tickets that have a value will be displayed under the annotated tab, the tickets that have "none" value will be displayed under the Unannotated tab. From there, users can retrain Zia.
    
12. Click on Zia Notiifcation icon from the bottom panel to view the import status under the Alert tab.
    

1. Adding tickets to the prediction
   
2. Moving the ticket from unannotated to annotated
   
3. Moving trained tickets to annotated
   
4. Selecting annotated tickets for retraining
   

I. Adding tickets to the prediction

1. From the Tickets module, select a ticket.
   
2. In the Ticket detail page, hover on the ticket content and click the More icon.
   
3. Click Add to Prediction.
   
4. Select the values for the fields.
   
5. Click Add.
   The ticket will be added to the unannotated tickets list.
   

II. Moving tickets from unannotated list to annotated

1. Go to Field Predictions, and click on the desired Predictor from the list view.
   You will be redirected to the ticket annotation page.
2. Click the Unannotated tickets tab.
   
3. Select each ticket and choose a value for the predicted field.
   Alternately, select tickets in bulk and update the fields.
4. Click Add to Annotated View.
   

III. Moving training data to annotated view

IV. Selecting annotated tickets to retrain

1. Field values - The picklist values can be used to filter the tickets
   
2. Ticket type - Tickets are categorized into two:
   
1. Annotated - Unannotated tickets for which the user selected a field value is added to the annotated ticket list view.
   
2. Overidden - Tickets for which Zia predicted a value, however the user replaced it with another are listed under this list view.

1. Go to the Annotated tickets tab and select all or few tickets.
   
2. Click Retrain Zia.
   
3. In the popup, click Confirm.