Uploaded May 2026 | Updated September 2026, 2 weeks ago
Episode 3 is where the app starts to feel real.
Up to now, it could retrieve knowledge and remember context. In this episode, we add tool calling so the assistant can look up orders, initiate returns, and create support tickets against Oracle-backed business data.
This is also where the distinction between AI orchestration and backend logic becomes important. The model can ask for an action, but the application still enforces the rules. That is what makes the whole thing useful instead of reckless.
Source code: [github.com/markxnelson/shopassist](https://github.com/markxnelson/shopassist)
#springai #oracle #springboot #java #aiapplications #rag
Episode 3 is where the app starts to feel real.
Up to now, it could retrieve knowledge and remember context. In this episode, we add tool calling so the assistant can look up orders, initiate returns, and create support tickets against Oracle-backed business data.
This is also where the distinction between AI orchestration and backend logic becomes important. The model can ask for an action, but the application still enforces the rules. That is what makes the whole thing useful instead of reckless.
Source code: [github.com/markxnelson/shopassist](https://github.com/markxnelson/shopassist)
#springai #oracle #springboot #java #aiapplications #rag
