top of page

How generates Suggestions / Insights

Automated customer health scores are valuable, of course, but once you know a customer’s status, what do you do with it? “Great you’ve told me my client is going to churn! Now how do I prevent it??”’s patent-pending Named Entity Recognition (NER) model takes your data a step further through its prescriptive insights, or Suggestions:’s model reviews your customers’ metrics and weighs them based on your their business model, unique dataset, account sentiment analysis, and word usage patterns to generate dynamic relevance models across all industries. For example, an interaction like “Our leadership is very impressed with these outputs, let’s discuss adding seats for our sales teams as well” would translate to ROI/value achieved and Potential Upsell. Or a conversation like “With recent org changes, we no longer have the budget to continue support for this product.” would, unfortunately, translate into Loss of budget and Not wanting to renew.

Based on this information, our model can then suggest intervention tactics that will work best for each nuanced customer and situation.

You and your teams can then review suggestions in the dashboard, and convert and delegate them as appropriate in Workspaces.

Through Suggestions, not only takes the guesswork out of your customers health, it takes the guesswork out of how to improve it by telling your teams exactly where to focus.


Recent Posts

See All

How we test accuracy and performance

Our AI predicts customer behavior with greater than 90% accuracy. How do we know? We test and measure the performance of our models regularly, in a variety of ways. Model training test accuracy - 94


bottom of page