Understanding & Using xNPS \[BETA\]
Required Feature Flags
The following feature flags and permissions are required to use this feature:
Feature Flag | Technical Name | Description |
xNPS Processing Only |
| Enables xNPS to be calculated for imported conversations |
xNPS Visibility |
| Enables xNPS results to be shown in the UI and as a filter |
Analytics Data Processing |
| Required for analysing imported conversations |
Required Permissions:
View conversation insights (
quality.view-insights) — to see xNPS results in the "evaluagent Insights" tab
BETA Notice
Please note, xNPS is currently within a closed BETA. To add xNPS to your account, please register your interest here.
What Is Expected Net Promoter Score (xNPS)
Once this feature has been enabled on your account, all future imported conversations will be assessed for the Expected Net Promoter Score (xNPS).
xNPS is a predictive measure of how likely we believe a customer would be to recommend your business on a scale of 0-10.
A score between 0-6 is marked as a Detractor. They are unlikely to recommend your business.
A score of 7 or 8 is marked as Passive. They are neither likely or unlikely to recommend your business
A score of 9 or 10 is marked as a Promoter. They are likely to recommend your business.
xNPS uses the same scale as Net Promoter Score above, however, we use GenerativeAI to make a "prediction" of the likely score by assuming the role of a customer and using the advanced reasoning capability of Large language models, rather than relying on customer surveys.
This means the "Actual" NPS score (ie: the feedback from your customers), may not always align with the xNPS which we have assigned to the conversation.
What is available within xNPS
Our xNPS feature currently enables you to:
Filter conversations based on the assigned xNPS Rating (Detractor, Passive, Promoter)
View the xNPS rating on each imported conversation
Report on your overall xNPS score and breakdown
Track your overall xNPS score over time
Requirements
xNPS is currently within a closed BETA programme. You can read more about what this means, and how to register your interest, via this product release blog.
To access the features listed above, xNPS must be enabled on your account with at least one full fetch integration enabled.
If you are using a Telephony channel, the quality of the voice recording is also very important to ensure accurate Transcription and xNPS results. Good quality stereo call recordings with speaker separation are perfect.
Viewing a Conversation's xNPS Rating
Each conversation that has been analysed will be tagged with the xNPS rating that the evaluagent platform has identified, along with some reasoning.
Using xNPS as Filters to Discover Conversations
Within the Imported Contacts view, you can access an xNPS filter. This enables you to use the xNPS Rating (Detractor, Passive, Promoters) to discover specific types of conversations that you might wish to explore further or carry out detailed evaluations on.
Like all filters, these can be combined. For example, find me conversations with a large amount of overtalk and where the xNPS rating is Detractor.
To find these filters:
Navigate to the Imported Contacts page,
Select 'Create new filter',
Choose evaluagent insights
Select the xNPS filter
Select how and which ratings you want to use within your filter
This filter will then find any conversations that match the criteria you have specified.
Reporting on xNPS
Your SmartView Dashboard can be used to create xNPS dashboard widgets to help you track this critical performance indicator. You can currently create widgets to show your xNPS and rating distribution, and track your xNPS score over time on a trend widget.
Please refer to our SmartView Dashboard user guides to learn how to add widgets to your custom dashboards.