Quality-check loop for AI agents

Build a quality check living INSIDE the agent, and it works the same for everything the agent makes... here's how it works: step 1: the agent makes something... a post, an image, a video, a piece of software step 2: a second model reviews it and scores it against a checklist built from your best work step 3: if the score is too low -> the output never reaches you, the agent takes the notes and redoes it step 4: repeat until the score clears the bar step 5: you only ever see work that already passed the whole trick is turning quality into a number, because a feeling ("this feels like AI") can't be fixed, a score can