bmad-advanced-elicitation

To refine an AI draft using structured critique, apply targeted elicitation methods to systematically challenge assumptions, uncover gaps, and iteratively strengthen the content. You select the analytical method, and the system proposes user-controlled changes for acceptance.

Red teaming for AI outputs is a structured critique method that re-examines existing responses to expose reasoning gaps and challenge underlying assumptions. You need it when a draft feels incomplete, too shallow, or requires rigorous refinement for high-stakes content.

To apply first-principles analysis to a shallow AI response, request a deeper critique of the recent output using targeted analytical methods. The system breaks down the content, challenges foundational assumptions, and proposes stepwise revisions for your acceptance.

Yes, you can iteratively improve specific sections of a complex draft while preserving original content. The process requires content preservation and user-controlled acceptance, meaning proposed changes only apply when you explicitly approve them during stepwise refinement.

The best way to red-team ambiguous or high-stakes AI content is applying structured elicitation methods that systematically challenge assumptions and uncover gaps. This iterative approach selects relevant analytical techniques and proposes targeted revisions for rigorous refinement.

Your AI draft needs structured critique when it requires deeper analysis, sharper reasoning, or rigorous refinement across complex content. Limitations include reliance on iterative method selection and the necessity of user-controlled acceptance for all proposed changes.