Adding a routing condition based on NLP text analysis

Define routing conditions for Pega Email Bot to carry out automatic actions when email content meets these conditions. For example, you can configure the system to create a top-level case or route to a work queue based on detected information using natural language processing (NLP). For the routing condition, you can use a detected entity, topic, sentiment, or language based on text analysis, so that your email bot trigger an appropriate action for intelligent routing.

Before you begin: Select a routing processing mode so that the system either triggers only the first action from the top of the list that matches conditions, or every create case and automatic reply action in the list that matches conditions. For more information, see Selecting the routing processing mode.
If a routing condition holds true, the system triggers an action or several actions, depending on the routing processing mode that you select. If the email content does not meet any of the routing conditions, you can also specify how the email bot responds.
  1. In the header of Dev Studio, click the name of the application, and then click Channels and interfaces.
  2. In the Current channel interfaces section, click the icon that represents your existing Email channel.
  3. In the Email channel, click the Behavior tab.
  4. In the Intelligent routing section, click Add condition.
  5. In the Action list, select an action that you want to run automatically in email routing.
    For example: Route to work queue
  6. In the Value field, enter an email template, case name, operator, or work queue.
    For example: For the Route to work queue action, enter a name of a work queue: Sales requests.
  7. Define the validation conditions for a field on the form:
    1. In the list of fields, select NLP and the name of the text analysis field that you want to validate.
      For example: 
      • To detect email text, select NLP > Entity, and an entity name.
      • To detect the email topic, the intent, select NLP > Topic.
      • To detect the positive, negative, or neutral sentiment of the email, select NLP > Sentiment.
      • To detect the language of the email, select NLP > Language.
    2. In the comparator list, select the test that you want to perform on the field.
      For example: Is equal
    3. In the value field, enter or select a value to compare against the user input.
    For example: To route an email to a work queue when the email bot detects the language of the email, select NLP > Language from the list, set the Is equal comparator, and then select French from the value field. When the email bot receives an email that is in the French language, the email is automatically routed to the Sales requests work queue.
  8. Optional: To add more automatic responses based on NLP text analysis, repeat step 4 through 7 for other routing conditions.
    You can also add an automatic response based on an email header content or a when rule.
  9. Optional: To specify how your email bot responds when you do not define any criteria or when the email content does not meet any of the criteria, define the default action:
    1. In the Otherwise area, in the Action list, click an action to perform.
    2. In the Value field, enter an email template, case name, operator name, or work queue.
  10. Click Save.
What to do next: Verify that the email routing conditions work as expected. For more information, see Testing email routing conditions.