Projects
A selection of personal and professional projects spanning AI agent systems, data pipelines, enterprise tooling, and game development.
Personal
Research & Game AI
FranData
Enterprise Data & AI
Stack
Python · AWS · Agents
Personal Projects
LLM benchmarks, game AI, agent architectures, reinforcement learning, and side projects.
ChronoBench
LLM benchmark measuring how far frontier models progress through Chrono Trigger using an autonomous, vision-based game agent. Live leaderboard with per-run telemetry, checkpoints, and cost tracking.
LM Battle Arena
LLM commanders draft tank squads, fight multi-round domination matches, and evolve between rounds — self-chosen identities, coach-driven edits, and opponent intel. ELO leaderboard and full match telemetry.
Ludic_Director
Python library for threaded "director" layers that enqueue LLM tool actions; host runs validation on the sim thread. No game engine dependency — tool calling, memory, persona markdown, multi-layer architecture.
GameAgentHarness
Framework for building and testing AI agents in game environments. Supports multi-agent orchestration and evaluation harnesses.
ClassicControl
Classic control and reinforcement learning experiments. Benchmarking agent architectures against standard control problems.
Loreofthelands
AI-driven game project exploring procedural narrative generation and world-building with LLM-powered systems.
scorched_earth
Game project built with AI agent integration — combining classic gameplay mechanics with modern AI techniques.
GameResearch
Research workspace for game AI experimentation — prototyping agent behaviors, decision systems, and simulation architectures.
Professional / FranData
Enterprise data pipelines, AI extraction systems, and lending platform tooling.
Built and maintained as Director of Lending & Risk Products.
Document Intelligence Pipeline
Multi-stage AI pipeline that converts dense franchise disclosure documents into structured, machine-readable data at scale.
AI Search & Validation System
Research tooling that surfaces findings across a large disclosure-document corpus, pairing retrieval with an AI validation layer and analyst-ready outputs.
Entity & Signal Extraction
Automated AI extraction and classification of company, franchisee, and technology signals from documents and public sources, feeding the franchise intelligence platform.
Data Ingestion & Scoring Automation
Automation that ingests analyst-completed research and proprietary scoring data into the central data platform, validating everything on the way in.
Core Data Platform Tooling
Internal query, upload, and operations utilities supporting the franchise intelligence data platform.