I built Flex to repair an AI data center's training scheduler when operating conditions change. In the simulation, restart energy rose 30x and the frozen scheduler passed 10 of 12 validation cases. Claude proposed new rules, and a fixed evaluator accepted a repair that passed all 12. It also rejected a later proposal that made a job late. On three separate test workloads using real California electricity prices, the frozen champion completed all 38 jobs on time and cut training electricity cost by 12.18%. Removing its simulated keep-warm rule reduced the saving to 4.28%. MongoDB Atlas stores the versions, evaluation evidence, and champion record. The jobs and restart behavior are simulated.
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…
