Azure Streaming Analytics and Anomaly Detection

Let's talk about this feature of Azure called stream analytics and how to detect an anomaly before it becomes a failure. Data stream is a set of data that is coming through and is very transient, it's not sitting in a traditional SQL database. If we had so, we can just run a batch job and run SQL query over that data and extract whatever insights we want under that data. But what if we have data that is just passing through an event hub? How do we run queries, get reports, raise alerts if something becomes unusual?