What I have built, and what it returned

The written contract, packaged so that someone else can run it. Every criterion starts at fail and only moves on a citation that resolves; the grader is a read-only subagent that never saw the work being produced and cannot fix what it finds; and a pre-commit hook refuses the commit rather than trusting an agent to behave.

What makes it worth reading is not the machinery. It is what happened when I measured that machinery across seven projects: the installed checks refused one thing, work grading itself caught nothing, and the largest single share of the catches that changed a result came from a reader with no stake in it. The repository opens with that rather than with a feature list, and says first, and at length, that seven runs by one operator on one machine cannot settle it. agent-research-protocol on GitHub.

It supersedes default-fail, which stays public because the instrument write-ups are in it and nowhere else: a claim-checker whose number mask deleted every decimal it existed to check, a quality gate that passed four fabricated summaries and failed the clean one. How I work has that story; the default-fail repository has the detail.

ResolveIt was a five-person university course project; I built the web application on my own. It let someone in debt gather what they owed in one place and receive an automatically generated repayment plan. The plan generation worked end to end. It had zero users and zero revenue and never left prototype stage. What stopped it was not the software: making it real required every creditor to agree to release a person's debt data, plus data-protection clearance on top. That is a permissions problem, and no amount of engineering solves it.

Alphatrack was a solo side project, deployed on its own domain and working end to end for equities. Signups were limited to friends and family; there was no revenue and I never got as far as charging. It stopped because good market data is expensive, and the paid feeds it needed to cover more than equities cost more than a student budget allows.

The project turns diagrams describing a system's structure into working application code. My share is about three per cent of its history, so this is not my project and is not presented as one. What it demonstrates is fitting into an existing codebase with automated quality checks already in place and a review process to satisfy — which is what most professional work actually looks like.