I build AI-native systems people trust enough to use in high-stakes decisions, where correctness, trust, and explainability actually matter. I lead the highest-risk, highest-leverage initiatives from ambiguity to working product, and the teams that ship them.
My work spans AI-native developer platforms and high-consequence operational software in financial services and insurance, the unforgiving kind where a small mistake carries real financial and compliance weight.
I prototype directly in Cursor and Claude Code rather than working from slides. I review around working product. I move fast, default to writing, and own the tradeoffs across speed, correctness, and trust.
I lead cross-functional teams across engineering, design, ML, GTM, and executive stakeholders in regulated enterprise environments, doing the player-coach work of driving the highest-leverage initiative while raising the craft bar for the team around me.
Engineers don't trust AI answers about their own systems. One confident wrong answer kills adoption. The product problem is making the output safe to act on.
An AI-native intelligence platform with an editorial soul. The first use case: giving teams who chase high-stakes opportunities a single, trustworthy brief instead of scattered sources, so they can decide what to pursue and act on it fast. The architecture layers an intelligence engine (Arauán Signals) beneath a dashboard experience (The Brief) and a workflow product on top. I originate the strategy, design the architecture, and prototype directly in Claude Code and Cursor, the same hands-on, working-product way I build everywhere.