Skip to main content

Adding an Agent Trainer connection

Pega GenAI Agent Trainer™ enables you to utilize advanced AI-powered chatbots that simulate authentic customer interactions within your configured Digital Messaging channel, enabling CSRs to practice and refine their skills in a risk-free environment. This facilitates effective training and provides valuable feedback for your customer service representatives (CSRs), helping them to boost their performance and provide outstanding customer service.

Agent Trainer

Video

Transcript

This demonstration shows you how to add an Agent Trainer connection to your Digital Messaging channel interface. 

U+, a retail bank, aims to establish a Pega GenAI Agent Trainer™ connection with their Digital Messaging channel interface to train its customer service representatives and provide valuable feedback.

To establish an Agent Trainer connection, navigate to the Messaging Channel section, and then select your existing Digital Messaging Channel.

Click the Connection tab of the Digital Messaging channel interface, and then click Manage connections

The system displays the Digital Messaging Manager window. Here, you can add several connections for the Digital Messaging channel interface. To add the Agent Trainer connection to your Digital Messaging channel interface, you need to first activate the Agent Trainer and then obtain a ChatGPT OpenAI or Microsoft Azure API key to connect to a generative AI solution host or use the Pega GenAI™ solution.

Note: The Pega GenAI Agent Trainer connection has already been enabled.
Digital Messaging Manager with Agent Trainer connection

In this scenario, let's add an Agent Trainer for the Azure GenAI service.

Enter a Name for the Agent Trainer connection. In the Pega application template list, select Financial services. Agent Trainer uses the selected Pega application template to improve the simulation for CSRs in the context of a specific Pega Customer Service application.

You now choose whether to add a Pega GenAI™ host by clicking Yes or No. If you defer configuring a Pega GenAI host by clicking No, you can configure the host later on the Connection and GenAI tab for your Agent Trainer connection.

In this case, select Yes to add an Agent Trainer for the Azure GenAI service.

In the Host list, select Azure, and then in the Resource field, enter the resource name for your Azure connection.

Note: You can obtain the resource name directly from the Azure GenAI endpoint URL:
https://{{resource_name}}.openai.azure.com/openai/deployments/{{deployment_id}}/chat/completions?api-version={{api-version}}

In the Azure OAuth endpoint field, enter the GenAI endpoint for your Azure connection, and then in the GenAI model list, select a Pega GenAI model.

In the API version field, enter the API version for your Azure connection.

Note: You can obtain the API version directly from Azure GenAI endpoint URL:
https://{{resource_name}}.openai.azure.com/openai/deployments/{{deployment_id}}/chat/completions?api-version={{api-version}}

In the Client Id field, enter your unique OAuth Client ID for the Azure connection. In the Client secret field, enter your unique OAuth Client secret for the Azure connection.

Add Agent Trainer

After you enter all the required details, save the changes to successfully register the Pega GenAI Agent Trainer account. You can return to the Digital Messaging Channel interface and observe that the Pega GenAI Agent Trainer connection is now displayed.


You have reached the end of this demo. You have learned:

  • How to add an Agent Trainer connection to your Digital Messaging channel interface.

This Topic is available in the following Module:

If you are having problems with your training, please review the Pega Academy Support FAQs.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega Academy has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice