Using Pega GenAI in Insights

Transcript

In this demonstration, we will show how a Customer Service Representative (CSR) manager can efficiently create insights using AI-generated data on the interaction portal.

The process consists of three main steps:

Writing a query to obtain the necessary data, modifying the automatically generated visualization, and saving the visualization according to your requirements.

Let's create an insight that displays the interaction workload for the past three months.

First, navigate to the Explore Data landing page. Click Explore Data and select the interaction object.

Next, write your query.

The initial query can be generic, like "How many interactions created," which will provide the total count of interactions. Click on Generate with AI, and the data is produced.

Because the data includes all interactions, and we only want the last three months, modify the query and click Generate with AI again. This gives us an okay picture, but to see what we are really after, let's add "week by week" to the query. This will show us which weeks have high utilization.

To add more details to the visualization, such as the channels through which these interactions occurred, drag the "channel" property as a dimension and update the chart type to a multi-line chart.

Now we can make display edits to improve the visualization's readability. Change "case counts" to "interactions" and add markers to the chart to see the data points to make it easier to visualize data points for specific weeks.

CSR managers are aware that their teams can only handle a certain amount of interaction workload. Add a reference region to the chart to indicate the maximum workload that the team can manage. This helps the CSR manager identify weeks when the workload exceeds or approaches the team's capacity.

Additionally, add a top line to the chart to indicate when the workload is too high and may require additional resources if the pattern continues. Change the legend to checkboxes, which enables you to show or hide specific lines for comparison during runtime.

After making these adjustments, save the insight with a unique name and description. Set visibility options and share it with others. The saved insight will be available in your list of insights, and you can edit it or change its sharing settings at any time.

You can now add your new insight to the dashboard.

This guide concludes the demonstration on creating insights using AI-generated data on the interaction portal.