Skip to main content

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

Enabling the training data recording for an email bot

Updated on July 22, 2021

To train Pega Email Bot™ to make better email content predictions, enable the recording of training data in the system. You can then edit and classify the training data in the system by reviewing records and applying changes to the text analytics model. With these tasks, you ensure that the email bot detects the correct topics and entities.

Before you begin: Build an email bot by creating an Email channel and configuring its behavior. For more information, see Creating an Email channel and Defining Email channel behavior.
  1. In the navigation pane of App Studio, click Channels.
  2. In the Current channel interfaces section, click the icon that represents your existing Email channel.
  3. On the Email channel configuration page, click the Behavior tab.
  4. In the Text Analyzer section, activate the recording of training data:
    For the default text analyzer
    1. Select the Record training data check box.
    For an advanced configuration
    1. In the text analyzer list, click the Switch to edit mode icon for a text analyzer.
    2. In the Text analyzer configuration window, select the Enable model training check box.
    3. Click Submit.
  5. Click Save.
For example: The following figure shows the Text analyzer configuration window, with the model training setting enabled for an email bot:
The advanced text analyzer configuration for an Email channel
Advanced text analyzer configuration for an email bot with the training model setting enabled.
What to do next: Improve the text analytics model by manually creating data records for the email bot. For more information, see Creating training data manually for an email bot.

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