AI Architecture
The system I operate to make AI-written code trustworthy. Standards are encoded as enforceable rules; agents apply those rules on a schedule; I am the escalation path for the cases the rules don't cover. Click any tile to see the mechanism in detail.
Human in the loop
The rules and CI gates are robust enough that tight low-level PRs auto-merge once they pass. I review the high-level and architectural PRs by hand, resolve escalations from the decisions ledger and accept or reject each auto-call in the weekly review. Human QA testing catches whatever the rules don't. The rule set grows exactly where my judgment is exercised.