Architecture Over Model: How We Got 13/13 Bug Detection Without Upgrading to a Stronger AI

A story about attention dilution, three failed experiments, and the counterintuitive fix that finally worked. You've spent weeks refining your AI code-review skill. You've added explicit rules. You've rewritten the checklist. You've added mandatory language: "Execute ALL checklist categories regardless of how many High findings have already been identified." The next week, a Medium-severity performance issue slips through again. The model had found 4 High-severity concurrency bugs in the same function. It was warned. The rule was right there in its context. It did it anyway. Here's the hard truth we learned after many rounds of iterations: you're not dealing with a prompting problem. You're dealing with an architecture problem. And no amount of prompt engineering will fix an architecture problem. This is the story of how we diagnosed attention dilution as a structural LLM limitation, ran three experiments that failed in increasingly instructive ways, and arrived at an architecture — Or