LLMs in production — one problem

You've shipped an LLM feature and can't tell whether it's working. Or you're trying to convince your team that evals aren't optional.

Bring one specific problem. Not a general chat.

I do this daily — evaluation frameworks, tracing, observability for enterprise GenAI. Not theory.

Good fit: engineers and ML or platform leads with something live.

Less useful: "how do I break into ML" — I'll send you links instead, faster for both of us.