The date string that invented $725 in a synthetic margin report

This is a submission for .

Project Overview

I built , now merged into main at commit still uses synthetic data and deterministic financial calculations. It does not connect to a POS or execute restaurant changes.

How AI helped, and where it stopped

The LeakLens application defaults to GPT-5.6 for its optional narrative provider. Separately, GPT-5.5 through Codex performed the read-only bug audit and found the malformed-date path by probing beyond the existing tests. I reproduced the finding independently and constrained the repair to test-driven date validation. Codex implemented the narrow patch after the tests failed. Claude Opus through Claude Code on a Max subscription then reviewed the uncommitted diff in read-only Plan mode and returned READY FOR COMMIT.

The models did not choose the operating policy, publish the code, or decide that malformed financial data should be rejected rather than guessed. I made those calls and verified every command and result before merging.

Keeping a model away from arithmetic is useful, but it is not enough. Every boundary feeding deterministic code needs a contract strong enough to fail loudly before a tidy report makes bad data look trustworthy.