Deterministic Core, Agentic Shell (blog.davemo.com)

So, similar to how functional core was Gary’s answer to testability in a world full of side effects, my assertion is that state machines are the answer to determinism in the era of AI agents. I have seen time and again that if we draw a larger box around that core and try as hard as possible to shove all the things that are important into it, and into a state machine, that the layers above (both imperative and agentic) become minimized, reducing risk, and making it much easier to verify correctness in the core of the system.

Functional Core, Imperative Shell was truly transformational and changed the way I approached programming. This analogous paradigm applied to LLMs is intriguing. Time to brush up my thinking on state machines.