Creating an agent for an Agentic Messaging interface
An agent is a conversational AI-powered assistant that interacts with users to facilitate automated actions and provide context-aware responses. Agents are integrated within applications to enhance user experience by streamlining processes and providing immediate assistance. With the support of Pega GenAI™, Infinity Studio enables rapid agent development by offering preconfigured elements to simplify setup.
Business scenario
U+, a retail bank, wants to create an agent named Self-Service Agent to assist customers with updating their residential or mailing addresses. The agent guides them through the process of updating their address information without needing to connect them to the customer service representatives.To implement the business scenario, in the Infinity Studio header, click Create, select Generative AI, and then click Agent to begin creating the Self-Service Agent.
In the Label field, enter a descriptive name for the agent (for example, Self-Service Agent), and then in the Scope section, determine whether the agent applies to your current application, a Case Type or Other. Because the company wants to help customers update their address, select Case Type.
In the Applies To list, select the Address change Case Type to associate it with the Intelligent Virtual Agent, and then click Submit.
The agent definition opens; On the Definition landing page, complete the following fields:
- In the Agent instructions field, enter a definition that summarizes the role you want the Self-Service Agent to assume.
For example, You are a smart, conversational AI assistant for the U+ Bank Customer Service self-service portal. Your purpose is to assist customers with updating their address information, verify the required details, ensure account records are updated accurately, and guide customers through the address change process while addressing any related questions or concerns. - In the Guardrails fields, define validation Rules to ensure that user inputs are in the correct format.
For example: When a user asks for information outside of your domain, politely remind them of your domain of expertise. - In the Response Style & Tone field, enter the response style and tone guidelines from the Prompt document.
For example, Use a soft, empathetic, and reassuring tone always. Communicate in simple, natural language -- avoid technical jargon, backend field names, and system terminology. Responses must be concise and non-repetitive. Confirm details in a single sentence before moving to the next step.
To provide more context for the agent, in the Additional context section, provide Data Pages that the agent always accesses while generating a response by clicking Add Data page. In this case, add D_pxDMSContextData to pass contextual information from the U+ website to Pega Platform. The purpose of this Data Page is to make website-provided context available to the agent while generating responses. Customer data remains in Pega, where the logic for retrieving and exposing that data is defined.
In the Add Data Page dialog box, in the Name field, provide a descriptive name for the data source. For example, Customer context data. In the Data page field, enter the name of the Data Page, D_pxDMSContextData, and then click Submit.
Optional: To retrieve only specific values from the Data Page, in the Apply Data Transform field, enter the Data Transform that maps the required fields from the Data Page.
To enable the agent to start and process Cases at run time, on the CASE TYPES tab, select the Case Type that you want to associate with the agent from the list.
In the Tool section, click Add.
In the list, select the first AddressChange to enable the Agent to initiate and process this Case Type at run time.
Click +Add, and then select Interaction from the list to initiate an interaction with the Agent.
Click Save to save the changes.
Optional: To enable the agent to source information from a Pega GenAI Knowledge Buddy™, on the Knowledge tab, in the Buddy section, select one of the Buddies provided by default or your own Buddy. For more information, see Creating Knowledge Buddies.
On the SETTINGS tab, in the Model section, select the AI model that you want the agent to use. In this example, ensure that the Pega-Default-Fast AI model for the Agent is the default selection.
Click Save to save the Self-Service Agent.
Go back to the Agent's landing page by navigating to App > Generative AI > Agent and then observe that the Self-Service Agent is on the list of agents.
Save the configurations.
You have reached the end of this topic. You learned:
- How to create an agent for an Agentic Messaging interface.
This Topic is available in the following Module:
Want to help us improve this content?