- π currrently @ UVA Darden '27
- π οΈ Building for fun + use cases in ai x bio/longevity, ai x blockchain, VC and PE, AI-native services, e-learning, etc.
Tranche AI β condition-gated capital release for VC deals: an AI agent reviews milestone evidence and posts a signed, on-chain attestation (EAS). Solidity, live on Base Sepolia network.
TraceHound β agentic crypto hack tracer: live hop-by-hop tracing from compromised wallet via the Etherscan API, cross-references an OFAC watchlist populated with current sanctioned addresses from Treasury's SDN list, LLM narration, and drafts demand letter. Built from experience with FBI & U.S. Secret Service on a hack + tracking/referring $6M of crypto crime.
LiveForever (live, private health control tower) β personal longevity engine that unifies Oura Ring, Apple Health, Nori, 10+ years of clinical bloodwork and daily self-logged inputs into one owned data layer.
Computes a PhenoAge biological-age clock, benchmarks vs. Bryan Johnson's public Blueprint targets and age/sex population cohorts, runs N-of-1 correlation engine quantifying what each input (nootropics, biohacking, fitness, sleep, medication, etc.) does to HRV, recovery, resilience scores + 28-day before/after analysis on interventions. Genetically personalized by cross-referencing against my DNA via 23andMe (caffeine/dopamine pharmacogenomics, APOE and metabolic-risk variants). Daily auto-refresh via MCP + REST APIs.
PhaseSignal β pulls real, live trial data from the ClinicalTrials.gov API, scores against a cited published base rate, adjusted by four computed factors with a live-reweighting breakdown.
Deal Docket β deal-screening dashboard built around an AI-enabled service-roll-up thesis; five-box scoring framework with adjustable weights.
The AI Stack β interactive map of the AI industry from silicon to application layer, ~30 company profiles, three money-flow traces, and a personal AI-cost calculator (subscription vs. pay-as-you-go, at your own usage).
IB Technicals Fluency Trainer β merger-model cockpit, purchase-price allocator, DCF sensitivity heatmap - live playgrounds, generative math drills, spaced repetition.
Consulting Case Prep Trainer β profit-diagnosis game scores hypothesis-driven reasoning under a limited information budget, market-sizing builder, exhibit reader.
The Operator's P&L Room β eight-quarter run-the-business simulator under leverage and covenants, 13-week cash-crisis room for distress-operator decision-making.
Most are self-contained apps β vanilla HTML/CSS/JS, no framework, no build step, no dependencies β designed, built, and shipped solo end-to-end. Some split data from rendering (data.json + app.js) for content updates. Some use a real Python data pipeline (data/build_dataset.py) that pulls and scores live data. TraceHound is a Next.js app with server-side API keys.