Improving sales rep productivity in Pega Sales Automation by analyzing email conversations

From PegaWiki
This is the approved revision of this page, as well as being the most recent.
Jump to navigation Jump to search

Improving sales rep productivity in Pega Sales Automation by analyzing email conversations

Description Use the natural language processing (NLP) capabilities of Pega Sales Automation to provide intelligent suggestions to sales reps
Version as of 8.5
Application Pega Sales Automation
Capability/Industry Area Sales Automation

This article examines the natural language processing (NLP) capabilities of Pega Sales Automation to provide intelligent suggestions to sales reps in the Email Client, and to increase overall sales rep productivity. NLP analyzes incoming and outgoing data in emails to analyze the sentiment of received emails, appointments, and corresponding attachments. Based on this analysis, the system can suggest appropriate actions. You can also use pre-configured templates to quickly create emails.

Intelligent analysis of email conversations[edit]

The intelligent processing capabilities (analyzing text through NLP) can be implemented by using the Intelligent Virtual Assistant (IVA).

Text analysis[edit]

An IVA allows the system to examine content by using NLP, adaptive analytics, and artificial intelligence to interact with a user in a natural, conversational manner. An IVA can detect the general subject matter of the email (topic), text that falls into a common category (entities), sentiment, and language in a message by using text analysis. To perform the text analysis, a channel developer first defines text analyzers for the IVA, for example, the Pega NLP module. Next, a channel developer trains the data for the IVA in the preview console, so that the system knows how to correctly analyze and interpret content.

For more information, see the Pega Community article Understanding text analysis.

For more information about configuring text analyzers, see Configuring text analyzer settings.

For more information about Pega IVA features, see Pega Intelligent Virtual Assistant features

Analyzing Pega Sales Automation Emails and Appointments[edit]

You can use an IVA to improve the productivity of a sales rep who is processing business emails. IVAs use a natural language processing algorithm to analyze email content and provide the following information to sales reps, sales managers, and sales ops personas:

  • Suggests cases
  • Suggests response email templates
  • Sentiment - determines whether the message from a prospect or a customer is positive, negative, or neutral.

SA IVA.png

Match scores prioritize the best actions for every email. The actions of sales reps become the baseline for the models to train, and increase the accuracy of their suggestions over time. You can also extend these provisions (for example, you can suggest other cases based on certain triggering text, suggest other email templates based on the triggering text, and so on). For more information, see Configuring Intelligent Virtual Assistant for Pega Sales Automation.

Analysis models[edit]

The following are the two types of models in Pega Platform for performing NLP analysis: 

  • Rule-based topic model - The default, rule-based topic model. The rule-based topic option always works with taxonomy. Pega Sales Automation's out-of-the-box taxonomy is shipped for default cases (for example, create task, and so on), as well as suggested replies (for example, for send product info, send competitor info, and so on).
  • Topic-based model - If you have already trained a model with the proper data, you can set the topic preference to the Use Model based topics if available option. Otherwise, it is recommended that you select Always use rule-based topics. When you use this feature, training data is submitted for a review. After you get the sufficient and relevant business data, you need to train the model for your business context. Then, you can choose the model-based topics, so that you can get proper suggestions relevant to your business context within the Outlook Add-in and Gmail extensions.

For more information, see Train entity models with a single click.

Email signature parsing[edit]

Pega Sales Automation uses natural language processing NLP on a contact's email signature to create default contact values. For example, NLP can extract the first and last name, title, and phone number from a contact in Outlook add-in based on the email signature and add these values to a Pega Sales Automation contact.

For more information on configuring email signature parsing capabilities, see Configuring email signature parsing for contacts in Pega Sales Automation.

Feature limitations[edit]

The following are the main limitations:

  • Suggested replies sections are limited on iOS and Android Mobile Outlook clients.
  • NLP suggestions are not supported by default. When you create emails or appointments or when you select meeting-related items, you must perform additional customization.


This article described NLP capabilities in Pega Sales Automation and how they can be used to increase a sales rep’s productivity by providing intelligent suggestions for emails. Sales reps can use the out-of-the-box templates and send product information and competitor details to a prospect with minimum effort. An NLP model's efficiency is based on the training data provided by your data scientist.

For more information on Pega Sales Automaton's IVA capabilities, see Pega Intelligent Virtual Assistant for Pega Sales Automation.