Skip to Main Content

AIZOYA’s Engineering That Remembers helps coding assistants resume engineering work from verified evidence instead of starting over. MongoDB Atlas preserves the mission contract, sessions, failed checks, decisions, candidate hashes, and independent verification results. Our demonstration begins with a transaction importer passing 9 of 10 checks. In a second session, the operator retrieves the recorded Unicode parsing failure from Atlas and supplies it to Kiro. Kiro repairs the parser, and independent verification passes all 10 checks. The dashboard shows the failure, retrieved evidence, repair decision, and verified outcome. The project combines a Python engineering harness with a TypeScript/React presenter deployed through Modelence. This is a demonstrated human-assisted recovery workflow using fictional data, with MongoDB Atlas providing persistent memory and traceable evidence across sessions.

Team

aizoya

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…

MongoMation project preview

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…

LabRat project preview

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…

Recursive Harness Scientist project preview

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…

SuperBid project preview

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…

WorldSTATE project preview