Paul Barnhurst shows how AI can generate deterministic rules that run the same way every time. He built a Python script and skills file with Claude for a German company's training, proving AI outputs can be auditable and reproducible instead of opaque.
Over time, you're going to see AI generating that deterministic rule on the fly, and it'll make the decision that you've asked me like 5 questions, 4 of them are the same, I'm just going to create a rule, I'm going to run that rule for reproducible and transparent execution of that same question. In the 5th case, you know, it's softer, I don't have all the data that I need, I'm going to run it through the inference engine, I'm going to tell you that I used AI to generate this one, so it might not be exactly correct.
Yeah, I think on this reproducibility, 100% agree with you that AI is going to write deterministic. We're seeing it today. I'll share an example. We did some training this morning with a company in Germany and shared an example of I asked Claude to help me build something and it went through and said, hey, for this I'm going to build Python script. That's basically a deterministic rule. It's running the exact same thing every time. It said that's how I should do it. It created a skills file, but both reference files it asked to use were scripts and they were Python scripts. And so I think we're already starting to see that the reproducibility, the audit trail, all those arguments that it can't be transparent, it's quickly going away.
Trust and Leadership Lessons for FP&A From 100+ Top Leaders with CFO Jon Laudie
