Use the Pega Intelligent Virtual Assistant for Pega Sales Automation Outlook add-in to improve email productivity. The Outlook add-in uses natural language processing (NLP) to analyze email content and suggest tasks and email responses to sales representatives. Each email that a sales rep opens has real-time match scores attributed to it, and suggested next actions and tasks appear directly in Outlook, within a built-in dashboard. The sales rep's actions become the baseline for training of the NLP models, increasing the accuracy of suggestions over time. Pega sentiment analysis also determines whether content of an incoming email is positive, negative, or neutral.

Configure the NLP for Outlook add-in by performing the following steps:

To configure the NLP analysis for email in your application, enable NLP suggestions.

1. In the navigation pane of App Studio, click SettingsApplication Settings, and then click the Microsoft Exchange tab.
2. In the Outlook add-in settings section, select the Enable Suggestions Using NLP check box.
3. In the header of App Studio, click Switch Studio, and then click Dev Studio.
4. In the navigation pane of Dev Studio, click App, and then search for and open the Data-Channel-Email class.
5. Create an email channel by performing the following steps:
   1. In the header of Dev Studio, click your application name, and then click Channels and interfaces.
   2. In the Create new channel interface section, click Email.
   3. Add and configure your channel:
      1. On the Configuration tab, in the Email channel name field, enter a name for the email channel that you want to create.
      2. Optional: In the Description field, enter a description for the channel.
      3. On the Behavior tab, in the Text Analyzer field, select the Record training data and Enable subject analysis check boxes.
   4. Click Save.
      When you save the channel, the system creates the default text analyzer with your channel configuration.
6. In the top-right corner, click ActionsView XML, and then search for the pzInsKey value.
7. Copy the pzInsKey value.
8. In the header of Dev Studio, click RecordsSysAdminDynamic System Settings, and then search for and select the EmailChannelHandle dynamic system setting.
9. In Value field, paste the pzInsKey contents, and then click Save.

After configuring the channel, associate topics with reply templates.

1. In the header of Dev Studio, click the name of your application, and then click Channels and interfaces and open your email channel.
   Note: For the steps below, use the PegaSalesAutomation1a443529ec5e46c991b0565447a7b812 text analyzer rule as an example.
2. On the Behavior tab, in the Text Analyzer section, click Open the text analyzer rule.
3. Configure your text analyzer:
   1. On the Select Analysis tab, in the Text categorization section, in the Topic model field, add the topic model of your text analyzer.
   2. In the Topic preference section, choose one of the following options:
   • For new models, select the Always user rule based topics radio button.
   • For models that you have already trained, select the Use Model based topics if available radio button.
   1. Ensure that the Enable intent detection check box is cleared.
4. Click Save.

Pega Sales Automation features a Create task case that you can edit and use. To implement NLP suggestions for your business cases, review the suggested custom configuration steps for cases.

1. In the header of Dev Studio, search for and select the OutlookSuggestCase section to view the suggested cases and a configuration example.
2. To map entities, drag the parameters to the Create Work action.
   1. Click View properties next to the cell that you want to modify.
   2. On the Actions tab, drag the parameters to the Create Work action.
3. To further configure the Create Work action, choose any of the following actions:
   • To support the NLP feedback mechanism, select AssociatedID as one of the parameters.
   • To Support NLP suggestions for cases other than the Create task case, in the header of Dev Studio, search for and select the 8.2 compatible with Outlook crmNewHarnessButtons_Mobile section.
   • To configure the Discard button, click View properties, and then on the Actions tab, add the RemovedFeedbackDataOnCancel data transform.
   • To configure the Create task button, click View properties, and then on the Actions tab, add the SetFeedbackForNLP data transform.
   • To review all of the detected entities, open the D_NLPEntities.pyExtractedEntities page group.
   • To customize your implementation, use the D_GetSpecificEntities.pyExtractedEntities page group and GetSpecificEntitiesAsExt activity as an example extension.
4. Click Submit.

Pega Sales Automation also has Defuse, Competitor, and Product reply templates that you can edit and use. To implement NLP suggestions for your custom replies, review the suggested custom configuration.

1. In the header of Dev Studio, open the PopulateSuggestedReplies data transform to view the suggested reply configuration and extension points.
2. Optional: To customize the content of reply templates based on competitors or products, use the D_NLPEntities or SelectedWorkPage data pages to find entities.
3. In the header of Dev Studio, search for and select the SuggestedRepliesWithUserType map value rule, and then edit it by configuring your suggested replies templates as either internal or external.
4. In the Default field, for each reply template enter Internal or External.
5. Switch to App Studio.
6. In the navigation pane of App Studio, click SettingsApplication Settings.
7. On the Microsoft Exchange tab, in the Outlook add-in settings section, enter your internal domains.
8. Click Save.

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.

After you configure the integration between Microsoft Outlook and Pega Sales Automation, configure signature parsing to use NLP to fill out contact information.

• Configuring signature parsing for Pega Sales Automation 8.5
• Configuring signature parsing after upgrading to Pega Sales Automation 8.5
• Further customizing the shipped models

1. In the header of Dev Studio, click Your application nameChannels and interfaces.
2. Optional: If you have not created an Email channel as part of the Intelligent Virtual Assistant configuration, create an Email channel.

   For more information, see Configuring Intelligent Virtual Assistant for Pega Sales Automation.

3. Open the Email channel and perform the following steps:
   1. On the Behavior tab, in the Text Analyzer section, select the Record training data check box.
   2. Click Save.
   3. In the Text Analyzer section, click Open text analyzer rule.
   4. In the Text extraction section, verify that the pySystemEntities and SASystemEntities models are on the list.
   5. Optional: If these models are not listed, add them by clicking Add extraction model.
   6. Click Save.

1. In the header of Dev Studio, click Your application nameChannels and interfaces.
2. Open an existing email channel that you want to associate with signature parsing.
3. On the Behavior tab, in the Text Analyzer section, select the Record training data and Use advanced configuration check boxes.
4. In the Text Analyzer section, click the Switch to edit more icon on the right side of the iNLP text analyzer.
   1. In the Text Analyzer type field, select iNLP.
   2. Select the Enable model training check box.
   3. Click Submit.
5. In the Text Analyzer section, delete the existing pyNER model by clicking the trash icon on the right side of this extraction model.
6. Add the pySystemEntities and SASystemEntities models by clicking Add text analyzer.
7. Click Save.

1. In the navigation pane of Dev Studio, click RecordsDecisionDecision Table.
2. Search for and open the pyAllowedNLPShippableRulesets decision table.
3. Save the pyAllowedNLPShippableRulesets decision table into your implementation layer.
4. In the table, perform the following steps:
   1. Add your rulesets under the Ruleset column.
   2. Set the return value under the Actions column to true.
   3. Click Save.
5. In the navigation pane of Dev Studio, click RecordsDecisionDecision Data.
   1. Search for and open the SASystemEntities data model.
   2. On the Data tab, in the Entity analysis section, download the training data in every language by clicking Download.
6. Create a binary file for each model for each language that you want to use, by clicking CreateTechnicalBinary File.
   1. In the Label field, enter NLPDefault.
   2. In the App Name (Directory) field, enter information in the following format: Rule purpose>_<language>, for example, pyNER_English.
   3. In the File Type (extension) field, enter zip.
   4. Save the file in the implementation ruleset.
7. Open the binary file and upload the training data .zip file for each language by clicking Upload file.
   Tip: The extraction of entities depends on the training data that you feed to the model. The pySystemEntities model is a Pega Platform model, whereas the SASystemEntities model is a Pega Sales Automation model.

• Increase sales with artificial intelligence capabilities