---

My path has taken me through backend engineering, machine learning, and now systems where language models are part of the stack.

That background shaped how I think.

I don't approach these systems from the demo outward. I approach them from the failure modes inward: what breaks, what scales, what can be trusted, what needs to be measured, and what happens when real users depend on them.

My default question is simple:

What is the simplest thing that actually works?

That usually means resisting complexity before adding it. Before reaching for a larger model, a multi-step workflow, or a network of agents, I want to understand the need underneath: the user problem, the edge cases, the cost of being wrong, and the point where automation should stop.

I'm most interested in the space between emerging AI capabilities and the real problems they can solve for end users.