“Agent UX is mostly constraints.”
I design AI systems around measurable business outcomes, from the initial commercial case through to production. Co-founder at ContextJet. MS Data Science, UC San Diego.
Products that move business metrics, not just impress in demos. Every project I touch has a number attached.
Multi-agent pipelines, tool-calling, and prompt work that still holds up once the volume goes up.
Knowledge-aware systems over internal data. Auditable, fast, and accurate enough to trust.
“Agent UX is mostly constraints.”
“Eval before you scale.”
“Ship small, wire data after.”
“RAG should survive noisy queries.”
Tell us the problem and what needs to change. We will say honestly whether AI is the right instrument for it, or something else and how we would approach the solution.