Every company pays thousands of supplier invoices, and someone has to check each one against the purchase order before money goes out. Most of that work is tribal knowledge: this supplier always adds a fuel surcharge, that one bills in euros, this one just changed their bank account so be careful. AP Harness is an AI agent that does the checking, and more importantly, learns that tribal knowledge on its own. Every time a human corrects one of its decisions, it rewrites its own rules and safety checks, tests the new version against past cases, and keeps the change only if it actually got better. It started knowing nothing about any supplier and ended up handling nearly every quirk we threw at it, without ever approving a bad invoice.
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…
