The problem
Customer reviews arrive as free text and pile up in a queue. Someone has to read each one to decide what it is about, how upset the customer is, and who should handle it.
How it works
The review's text and star rating go into the where clause of three _predict calls that run in parallel: category, sentiment, and assignee. Each returns its top value with confidence, alternatives, and $why, so the reviewer sees which words carried the prediction.
Whether the customer is about to leave is not read from the review text. The demo's Retention view answers that from the order history, and counts a 1–2 star review among the tells that came before customers stopped ordering.
For the full architecture, see the technology overview. For the broader narrative across multiple use cases, read The Predictive Application.
See it live
This use case runs in the 🛒 E-commerce demo today. Click through to the live application and inspect the queries that produce the result.
