The AI Buddy Blog

Notes from building software with AI, and proving it holds up.

Writing on our AI DLC process, adversarial verification, and the engineering calls behind the work we ship. Practical, tested, drawn from real builds.

Never Let the Agent Grade Its Own Exam

Why the same AI agent cannot write your spec, your code, and your tests. If you are using the same AI agent to write your specification, write your code, and write your test cases, you are doing it wrong. Not stylistically wrong. Structurally wrong, in a way that guarantees the bug you most need to catch is the one your system is built to hide. Here is what happens when one agent owns all three. The agent is building a feature and it fails to match the intent. Rather than fix the code, it edit

Jul 7, 20266 min read