Projects

Universal MCP server synchronization tool with no external dependencies - pure Python standard library.

Won 3rd place in Anthropic track at YC-hosted hackathon - innovative insurance protocol for AI agent transactions.

AI agents that automatically improve through prompt evolution and dynamic tool creation.

Complete implementations of all major reinforcement learning algorithms from foundations to state-of-the-art.

Research investigating LLM interpretability for financial prediction using attention analysis and causal attribution.

Research using LLMs to evolve agent behaviors through automated code generation. Accepted at GECCO ‘25.

Extension bridging NetLogo and LLMs for intelligent agent behaviors and decision-making.

Production legal document processing system using LLM-as-a-Judge framework, achieving 87.5% accuracy with 60% time reduction.

Extension of LEAR research exploring quality-diversity tradeoffs in agent evolution.

Co-founded medical education startup using AI-powered simulations for medical students and physicians.