Now
What I'm doing now.
A snapshot of where my attention actually is — not where it was, and not where I'd like it to be. Inspired by Derek Sivers' /now idea.
Last updated
2026
New Brunswick, NJ
Currently building
- Agentic systems that keep a human expert at the center
- Auditable explanation tooling for clinical models
Currently reading
- Papers on calibration & expert trust
- Fiction, for the first sentences
Currently learning
- Agent orchestration patterns that stay legible
- Evaluation design for generative time-series
Thinking about
When an expert and a model disagree, who should win — and how do we design the moment that decides?
Current goals
- Turn two research threads into submitted papers
- Ship a legible agent prototype end to end
- Find the right PhD-track lab for this work
Current challenges
- Evaluating explanations without an expert in every loop
- Keeping agents both capable and fully auditable
If any of this overlaps with your work, I'd love to hear from you.
Email me ↗