
01 / Independent lab
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.
Product leader. Systems builder. Curious by default.
I’m Paul. I lead lending and risk products at FranData, build AI-powered data systems, and give autonomous agents a world to figure out.
01 / Selected work

01 / Independent lab
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.
Round 1 map
02 / Independent lab
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.
03 / Professional work
Multi-stage AI pipeline that converts dense franchise disclosure documents into structured, machine-readable data at scale.
02 / Make something useful
I’m always up for a conversation about products, data, and what AI can do next.