Rachet: a self-improving harness for MongoDB query tuning. Slow queries cost money and frustrate users, and fixing them takes expert time: reading explain plans, choosing indexes, and rewriting pipelines. AI agents can help, but they often overfit to the workload in front of them, or “win” by quietly changing what a query returns. RADA solves both problems. A tuning agent fixes slow MongoDB workloads, and the harness that steers it (its rules, context policy, guardrails, and tool access) improves itself from every workload it tunes. A proposer model studies past runs and suggests a new harness version. A strict gate then promotes that version only if it scores better on held-out workloads it has never seen, with every query result unchanged. If either check fails, the candidate is rejected with a reason code, and known cheats are tested and blocked. Every harness version, trace, and lesson is stored in MongoDB Atlas, so each improvement is measurable, auditable, and reversible.
More from The Harness Engineering & Model Wrangling #SFTechWeek Hackathon
MongoMation is an autonomous PLC engineer. You describe a machine in plain English, and Claude agents write IEC 61131-3 PLC code, compile and deploy it to a…

LabRat is a self-improving harness for a physical lab agent, running on a real bench: two SO-101 arms, a 3018 CNC carrying a servo pipette I designed during…

Recursive Harness Scientist: an AI scientist that improves its own scientific method, and must replicate every gain on data it has never seen. Why it…

Super Bid is a self-improving AI estimator that teaches itself to price bids the way a specific company would. It practices on the company’s real past bids…

A robot that gets better at handling objects it’s never seen, without retraining. After every round, an AI coach reviews what broke and rewrites the robot’s…
WORLDSTATE gives physical spaces a memory. Any phone becomes an observer: open a link, point the camera, and WORLDSTATE tracks what's inside fridges, shelves…
