Cash-heavy businesses (I'm involved with one: Thillens) reconcile deposits, invoices, and billing lines by hand every day, and the same fixes repeat for years while the knowledge dies in spreadsheets - teams want AI to automate it, but no CFO will let an agent rewrite financial controls unchecked. Ledger turns repeated human corrections into governed automation: variance cases and operator corrections live in MongoDB Atlas, an AI agent reads that history and proposes a deterministic rule in a strict closed JSON DSL, a demo operator evaluates it against ground truth for precision and recall, and only a separate human approver presenting the hashed evaluation report can activate it. The agent proposes, the operator evaluates, the human approves - capability gates enforce the separation and every transition is an auditable event, so operations teams get agent leverage without handing over the keys.
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…
