Training the email bot with Pega Gen AI

1 Tâche

10 mins

Pega Customer Service '25

Pega Customer Service '24.1

Visible par : All users Applies to: Pega Customer Service '25

Débutant

Anglais

Scénario

U+ Bank wants to use Pega Email Bot™ to respond to customer problems and speed up business processes seamlessly. As a system architect, you are tasked to help train the already built email bot by adding training records to interpret emails and detect the correct information, such as topics and entities.

Use the following table provides the credentials you need to complete the challenge:

Role	User name	Password
System Architect	CSAppadmin	password123!

Your assignment consists of the following task:

Task: Train the email bot to understand topics

In the Training data tab of the email bot, click Add records using GenAI to help train the email bot by adding training records to interpret emails.

 

Vous devez initier votre votre propre instance Pega pour compléter ce Défi.

L'initialisation peut prendre jusqu'à 5 minutes, donc soyez patient.

• Se connecter

Présentation du défi

Détail des tâches

1 Train the email bot to understand topics

1. Log in to App Studio as Customer Service Application Administrator:
   1. In the User name field, enter CSAppadmin.
   2. In the Password field, enter password123!.
2. In the navigation pane of App Studio, click Channels.
3. On the Channels landing page, click MySupport to update the Channel configuration.
   
4. Click the Training data tab.
5. To add training records, click Add records using GenAI.
6. From Topic list, select the Address Change case and then set the number of records to 5.
7. Enter the following sample email content:

   Hi,

   I have a new address. It is 55 Elm Drive, Allston, MA 02134. Can you update my account to reflects this change?

   Thanks,

   Frederic

   The following figure shows the completed dialog:

   
8. Click Create record.

   Pega GenAI uses the sample data to generate five similar training records and displays the records for your review. You can see the classification details in the right pane.

   
    

   In the NLP analysis section, the Language model, Topic, and any entities present are displayed on the bottom tile. The training data text is displayed in the upper tile, where any entities detected are highlighted.

9. Under the Language list, click Select all to select all the records, and then click Mark reviewed to add the records to the queue.
   
    
10. To the right of Add records, click the More icon, and then select Build Model to rebuild the natural language processing (NLP) model.
    
    
    If the model build is successful, a message that shows the new F-Score is displayed at the top.
    
11. Click Save.

---

---

Disponible dans la mission suivante :

• Email Bots for Pega Customer Service v9