Skip to Main Content

Problem statement: Two, Long Horizon Engineering. Also covers One: the agent evolves its own rules. Bookie is a long-horizon agent system that makes money on prediction markets. Today it forecasts NYC's daily high and trades the Kalshi market on it. Agents form the view and size the order, a fast decision model gates every step, code enforces the limits, and a human is only asked when a call isn't routine. The problem: agents that run for days can't tell if they're getting better. Bookie grades itself against the official outcome every night and rewrites its own rulebooks from its mistakes. All day it marks positions against the live book, takes profit, and cuts losses. Stack: deepagents, Hatchet, Langfuse, MongoDB Atlas, Jev + GPT-5.6 Luna via OpenRouter, Voyage AI.

Team

nideesh

Placement

Participant

More from The Harness Engineering & Model Wrangling Hackathon

Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

Ripple project preview

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…

Offload project preview

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

Morgadarsha project preview

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

Da Vinci: Recursive Improvement CAD Harness project preview

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

CyclopsDiary project preview

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…

Sightline project preview