Is Observability Helping in Machine Learning?

The problem with observability, especially in machine learning, is that it gets overwhelming if you're not careful. Humans are not designed to look at 7,000 features in a front detection model and try to figure out the way to really decipher the way it's been informed. So what you really want to observe is the KPIs with respect to these important segments or automate that process. That's how we can surface these problematic segments in the data stream in a scalable manner.