AI feels like the obvious answer when we need to scale automation. It is broad and flexible, yet these general-purpose AI models can add cost, latency, and drift where simple, deterministic tools would do. This talk walks a real product case: scoring assignments against a rubric. We show where GenAI/NLP/ML underdelivered, and how Regex, static checks, and tiny heuristics anchored results. You’ll get a practical chooser: a quick pattern test, basic economics for latency and cost, and controls that keep failures visible. We also cover hybrid routes, where rules handle the easy wins and AI takes ambiguity. No AI fluency required, just a desire to pick the right tool.

Learning outcomes
* Choose AI vs simple tools with a clear, five-question rubric
* Design hybrid routes: rules first, AI on ambiguity
* Instrument latency, cost, and drift as acceptance criteria
* Reduce incidents by keeping failures observable and testable