In the AI era, many business applications which consider themselves “intelligent” cannot simply execute a complex rules-based transaction and wait for the next one. To become really “intelligent” applications,  they should be able to learn from already executed transactions, accept new facts as they become available, and, when necessary, they should make changes in their own execution logic. These stateful applications should be able to support both decisioning and behavioral rules, validate and propagate changes in the states of involved business entities, and finally “connect the dots”.

In this presentation, we will describe an ingenious architecture that supports the creation and continuing development of such intelligent, perpetually running applications. This proposed architecture utilizes the modern pub/sub tools with continuous data streams and state machines,  allowing subject matter experts to define and maintain behavioral and decisioning rules. We will demonstrate the architecture by using several real-world scenarios.

Learning Objectives:

• How to develop “live” intelligent applications
• How to define both behavioral and decisioning rules
• How to validate and propagate real-time changes