Back home

Work

Projects

Research, products, and experiments. Things I've built or shipped.

Featured

Founderactive

Regulus AI

Solo-built regulatory intelligence platform monitoring legislation, agency rulemaking, and enforcement across jurisdictions, scoring each signal by risk. A RAG reasoning pipeline (Claude) turns a 72-hour research lag into executive briefs in seconds.

RAGClaudeNext.jsReg-Tech
IEEE ICHI 2026published

DEDICATE, Multi-Agent Clinical AI

NIST-funded, 8-agent LLM diagnostic system for sleep disorders, built with UPMC. A five-layer LangChain + ChromaDB RAG pipeline and a 224-persona generator reach 87.8% faithfulness, 94% retrieval, and a 100% safety pass rate across 1,000+ cases.

LangChainChromaDBMulti-AgentTEVV
Link coming soon

Other Projects

Agent Alignment Evaluation Workbench

active

Fully local tool (Streamlit + Ollama/Qwen3) evaluating AI-agent alignment inside simulated org hierarchies, scoring responses on the RICE framework (Robustness, Interpretability, Controllability, Ethicality). Behavioral flagging auto-detects deception, power-seeking, and self-preservation.

AlignmentRICEFAISS + BM25Evals

LLM Red-Team Harness

active

Open-source, provider-agnostic framework (OpenAI, Anthropic, HuggingFace) for adversarial LLM evaluation across jailbreak, prompt injection, privacy leakage, harmful instructions, misinformation, and bias, with a modular, severity-tiered scoring architecture.

PythonRed-TeamingLLM SafetyOpen Source

Red-Team Policy Analyzer

active

Python/SQL pipeline generating adversarial prompt variations across 5 jailbreak framing patterns and 15+ attack vectors spanning a 5-domain harm taxonomy, surfacing policy coverage gaps where over 30% of variations return unsafe.

PythonPolicy AIRed-TeamingGovernance

ML Fairness Auditor

active

Python/SQLite pipeline training and auditing three classifiers on the UCI Adult Income dataset (48,842 samples) for bias across sex, race, and age, operationalizing demographic parity, disparate impact, equalized odds, and calibration error with significance testing.

PythonFairnessBias DetectionML Auditing