whoami
Founder · Technologist · Applied AI · Agentic Solutions Architecture
cat intro.txt
I design and build LLM applications, conversational agents, and multi-agent workflows. I'm CTO & Head of Applied AI at Snap eHealth, turning complex healthcare needs into working AI solutions.
It helps reduce the guesswork of choosing a place, while clearly showing when crowd information is recent, historical, or unavailable.
Predictive modeling, conversational AI, agent workflows, and the evaluation behind them.
An end-to-end, production-inspired NFL predictive ML application. Real current-season data, explainable frozen-model forecasts, historical evaluation, and an auditable forecast-to-outcome record.
Applied AI engineering · Frozen-model inference · Controlled improvement
A healthcare voice agent designed around three workloads: a responsive conversation loop, background analysis, and an evidence-checked visit brief.
Read the Sally essay 7 minEngineering workflows that connect a bounded task to an agent-produced change, reproducible checks, and human review.
Read the Symphony essay 7 minAn evaluation system for healthcare chat and summaries that makes changes in model behavior visible, reproducible, and actionable.
Read the AI Evaluation essay 7 minExplainable specialist ranking, alongside a separate predictive ML project building synthetic data and temporal validation for 30-day referral completion.
Read the Referral Intelligence essay 6 minNotes on applied AI, agentic architecture, and evaluation.
A banquet for 180 guests and a sub shop’s weekly turkey order reveal when to calculate, when to forecast, and how to combine the two.
How to evolve your models, evaluations, data, and engineering team while preserving the speed and customer focus of an early startup.
The orchestration, isolated execution, policy, and evidence that let autonomous agents deliver software safely.