Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Implementing an Intelligent Virtual Assistant for a conversational channel

Updated on May 15, 2023

Provide users with the ability to interact with your application by getting answers to simple questions and completing complex work, without having to engage with or wait for a human agent. Pega Intelligent Virtual Assistant™ (IVA), which you design in the system, interacts with users in a simple question and answer form by sending text messages, and by using artificial intelligence, natural language processing (NLP), and your existing Pega Platform case processing.

The convenience of this chat functionality is available across multiple messaging platforms and ensures that you instantly provide essential business services to users in a consistent way. For example, users can quickly request information about their account or even update the account directly by interacting with your chatbot in Apple Messages for Business, Facebook Messenger, WhatsApp, and other messaging platforms.

IVA for Digital Messaging includes a built-in preview console. You use the preview console to test the chatbot during the design phase, before moving the bot to a production environment. You test and configure your chatbot on the same page. You can also train machine learning models to recognize the way in which your customers communicate with you, without any data science expertise or a single line of code.

Note:
  • The process of creating a Pega Platform application, including the design and development of an IVA channel for a conversational channel, requires open rulesets. However, after moving your IVA to a production environment, you can lock the rulesets. Only when you need to build models further or change the IVA channel configuration in a production environment, must you then unlock the rulesets.
  • This release introduces new built-in data types, Conversation Event and Conversation Summary that you can use in your custom reports to gain insights about the chatbot processing characteristics. For example, you can get statistics about the number of interactions, the average time, number of messages, efficiency, interaction classification, and social channel utilization.
  1. Build and configure a conversational channel:
    1. Create an IVA for Digital Messaging so that users can interact with your application by using the Apple Messages for Business, Facebook, SMS/MMS, Web Messaging, and WhatsApp messaging platforms.
      For more information, see Creating a Digital Messaging channel.
    2. Define conversational channel behavior.
      You define conversational channel behavior by creating stand-alone conversation processes or conversation processes for a case type, adding suggested cases, defining suggested responses, configuring text analyzer settings, and configuring system responses. For more information, see Defining conversational channel behavior.
    3. Simulate a conversation and build a chatbot.
      You can verify chatbot responses, modify questions and response text, extract data from a conversation, and apply simulation changes. For more information, see Simulating a conversation and building a chatbot.
  2. Record and train the data for the text analytics model in the IVA channel.
    For more information, see Training the model for the IVA channel.
  3. Troubleshoot the IVA channel.
For example: The following video describes new chatbot and email bot features that are available in Pega Platform version 8.7:

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

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.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us