The projects page is where users start their workflow on Superwise. from here the can navigate to different projects, get a quick overview, or create new projects.  
A new user to Superwise can start with a demo project or go through the onboarding process to connect his own data.

Metrics are measurements used to evaluate how well a machine learning model is performing. Superwise automatically computes various metrics for each part of your data, and you can also create custom metrics. These metrics help you understand and improve your model's performance.

Adding a model to Superwise is the fundamental step users must take to begin benefiting from the system. To simplify this technical process, we've created a four-step wizard designed to make it as easy and straightforward as possible. However, this action typically requires the expertise of ML engineers.

Users can create segments to better understand how their model performs across different groups or categories within their data. By creating segments, users can gain deeper insights into their model's performance and make more informed decisions about how to optimize it for better results.

Setting up policies helps users monitor their models automatically. a policy is a set of rules, that will trigger alert. If anything looks off, Superwise alerts you so you can investigate

Incidents are created when a monitoring policy detects anomalies in model behavior. Users can drill down into each incident to investigate anomalies, view metrics, and compare distributions, helping them understand the cause of the issue and take corrective actions.

Superwise's analytics screen allows a free explorations on data and models. We designed the screen in a way that presents the data in a more visual way that will allow users to better understand the data,  monitor performance, identify issues and optimize their models