Planhat includes a wide range of AI features, which you can read an overview of here. There are native AI features that use Planhat's AI connection and therefore Planhat AI credits, such as Writing Assistant and Conversation Summary; you can also set up your own AI connection ("bring your own LLM") and use it in Automations.

In addition, there is also built-in functionality within Planhat that makes use of Machine Learning (ML), rather than connecting to an external LLM. These are the "Deviations from Normal" Calculated Metric Templates, and the "Relevance" End User system field, which we'll go through in this article.

"Deviations from Normal" Calculated Metric Templates are a great way for deviations/anomalies in time-series data to be detected and flagged for you. They look at historic trending averages to identify when there is a spike in your data.

And what about the End User Relevance Score? Well, knowing which of your End Users (individuals who are your customers or other contacts) are the most active, the most relevant, and the ones you need to pay attention to is important to your business strategy. "Relevance" is a system (standard/default) field that helps you understand which of your End Users are particularly engaged or not engaged with your product and your company. This automatically calculated score is based on two aspects: User Activities (product usage) and Conversations (interactions).

Let's take a closer look at each of these features in turn.

Calculated Metrics enable you to build upon raw time-series data (such as the number of logins, or tickets, or reports downloaded, etc.), looking at averages and trends, and so on. Rather than needing your development team to carry out lots of different calculations for you, it's easy for you to perform these calculations yourself within Planhat. You can create fully custom Calculated Metrics, or use our Metrics Library to apply pre-built - yet still customizable - Calculated Metrics.

One category of Calculated Metrics Templates is "Deviations from Normal". The two (very similar) Templates you can select from are:

If you select either of these, it opens up a modal where you can configure the Template (e.g. select the Metric to monitor) - we show this below.

These Calculated Metrics help you to identify when time-series data is very different from its historic trending average, so they are great for detecting deviations and anomalies.

In other words, they keep track of your data and flag anything that's out of the ordinary.

As with other Calculated Metrics, you can then act in response, either manually or automatically - for example, a Workflow or Automation could be triggered when there are positive or negative signals, so you don't miss opportunities or risks.

As you can see, although these are Templates, there is a lot you can customize here - meaning you can actually create a range of different Calculated Metrics from a single Template.

Once you have created your Calculated Metrics, you can then use them in various ways across Planhat.

"Relevance Score" is a system (default) field on the End User model that shows you, at a glance, how "relevant" each End User is.

To calculate this, Planhat uses a special algorithm to assess each of your End Users and compare them to the others within your Planhat tenant. The Relevance Score is calculated automatically via their activity level (usage) and interactions (with your team, as detected via emails, tickets and meeting notes etc.), and it considers both recent data and data over time.

Each End User is given a score from 0 to 100, with 100 being the highest and 0 being the lowest.

Click the image to view it enlarged

This is a really quick and easy way to help you target your actions to make the most impact. High relevancy End Users may be suitable for advocacy programs, whereas low relevancy End Users may need support to get them engaged.

As usual in Planhat, this data can be used in numerous ways for analysis and data-driven action. For example, you could trigger a Workflow or Automation for End Users with a Relevance Score higher than 80 - maybe you want to automatically email them to ask for a review, for instance.

This is super easy - no setup is required!

Simply select the "Relevance" field on the End User model where you need it - e.g. here's the column preference selector when viewing the End User model in Data Explorer.

You can easily sort End Users by Relevance, for example.

Click the image to view it enlarged

Both "Deviations from Normal" Calculated Metrics and the Relevance field use intelligence built into Planhat. They do not connect to any external LLM, so there are no additional security considerations or pricing implications.