Skip to main content

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

Configuring a Unified Messaging chatbot

Updated on March 25, 2020

A Unified Messaging chatbot interacts with your customers through various social messaging platforms to answer common questions, execute a service case, and escalate to a customer service representative (CSR).

Note: Due to changes by Twitter in the API and the licensing model, direct integration with Twitter is no longer supported in the Unified Messaging channel interface.
You must purchase a separate license before using Pega Intelligent Virtual Assistant in your application. For more information, contact Pega Support.

Supported channels

By defining your CS-Self Service application implementation settings in the integration manager, you can create a Unified Messaging channel for the following messaging platforms:

Apple Business ChatApple Business Chat
Send text messages in the Apple Messages app to connect with organizations and ask questions, schedule appointments, and make purchases.
Facebook Messenger
Send text messages in the Facebook Messenger app.
MMS (Twilio)
MMS (Twilio)
Send Multimedia Messaging Service (MMS) messages by using the Twilio communications platform.
SMS (Twilio)
SMS (Twilio)
Send text messages with the short message service (SMS) text messaging service by using Twilio communications platform.
Send text messages in the WhatsApp Messenger app.

Pega Customer Service provides a sample Unified Messaging chatbot channel so that you can quickly get started with the configuration for the supported messaging channels. The sample chatbot channel consists of the most frequently used case types and response commands, such as greeting, help, escalation, and thank you, to enable your Unified Messaging chatbot to handle real-time problems. Natural language processing (NLP) is used to detect the sentiments and trigger the corresponding actions. Some sentiments, such as greetings, escalation, thank you, and help, are detected by using artificial intelligence (AI) models and not by using keywords. The AI models are more flexible and can learn based on the past usage.

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

Close Deprecation Notice
Contact us