Configuring Intelligent Virtual Assistant for Pega Sales Automation
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:
For more information, see:
Enable NLP suggestions for email
To configure the NLP analysis for email in your application, enable NLP suggestions.
- In the navigation panel of App Studio, click Settings > Application Settings, and then click the Microsoft Exchange tab.
- In the section, select the check box.
- Switch from App Studio to Dev Studio.
- In the navigation panel of Dev Studio, click App, and then search for and open the Data-Channel-Email class.
- Open an existing email channel or create an email channel by performing the following steps:
- In Dev Studio, click the name of your application, and then click Channels and interfaces.
- In the section, click
- On the Configuration tab, add and configure your channel:
- Enter a name for the email channel that you want to create.
- Optional: Enter a description for the channel.
- Optional: Leave default values for the , and sections.
- Select the Record training data check box.
- Optional: Select the Enable subject analysis check box.
- Click
When you save the channel, the system creates the default text analyzer with your channel configuration.
.
- Click Actions > View XML, and then search for the pzInsKey value.
- Copy the pzInsKey value.
- In the header of Dev Studio, search for and select the EmailChannelHandle dynamic system setting (DSS).
- In the DSS, paste your pzInsKey contents into the Value field, and then click .
Edit the text analyzer rule
After configuring the channel, associate topics with reply templates.
- In Dev Studio, open your Email channel.
- On the tab, click the icon on the right of the PegaSalesAutomation1a443529ec5e46c991b0565447a7b812 text analyzer rule.
- Click .
- Configure your text analyzer:
- Add the topic model from your text analyzer.
- In the
- For new models, select the radio button.
- For models that you have already trained, select the radio button.
section, select one of the following options:
- Clear the Enable intent detection check box. Configuring a text analyzer
- Click .
What to do next
When the system runs NLP on an email or message, training data is submitted for a review. You can add the training data to the model based on your business context. For more information, see Train entity models with a single click.
Sample training data for the Outlook add-in
Configuring custom cases
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.
- In the header of Dev Studio, search for and select the section to view the suggested cases and a configuration example.
- To map entities, drag the parameters to the Create Work action.
Actions tab details
- Click the icon next to the cell that you want to modify.
- Click Create Work action. , and then drag the parameters to the
- 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 View properties, and then on the tab, add the RemovedFeedbackDataOnCancel data transform. Actions tab configuration for NLP support button, click
- To configure the View properties, and then on the tab, add the SetFeedbackForNLP data transform. button, click
- 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.
Configuring custom replies
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.
By default, the reply templates are configured for external users. If you leave a template with a blank value or select an incorrect value, both internal and external users can access it.
- To view the suggested reply configuration and extension points, open and use the PopulateSuggestedReplies data transform.
- Use the D_NLPEntities or SelectedWorkPage data pages to detect entities if you want to customize the content of reply templates based on competitors or products.
- 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. Configuring suggested reply templates as external or internal
Use the
field in App Studio settings to include internal replies:- In the navigation panel of App Studio, click Settings > Application Settings.
- On the tab, in the section, enter your internal domains.
Previous topic Configuring Sales Chatbot Next topic Configuring email signature parsing for contacts in Pega Sales Automation