It was testing that the code worked, of course :) That was the only place that had human intervention, other than a) providing the initial prompt, and b) providing icons and stuff for the GUI, instead of using generated ones. That was the “get out of jail free” card:

In cases where an interpreter struggles with identifying fine-grained logical issues, the involvement of a human client in software testing becomes optional. CHATDEV enables the human client to provide feedback and suggestions in natural language, similar to a reviewer or tester, using black-box testing or other strategies.