bmad-advanced-elicitation

To refine LLM-generated content, apply structured elicitation methods like Identify Assumptions or Explore Counterarguments. This facilitates iterative improvement by analyzing context and applying targeted techniques to enhance proposal robustness and clarity.

Iterative elicitation for LLM output improvement is a process of pushing the model to reconsider its recent drafts. It applies targeted techniques from a method registry to enhance content, assess risks, and generate creative ideas based on context.

You need elicitation methods for AI content generation when initial drafts require deeper analysis or risk assessment. Use these techniques to strengthen complex proposals, explore counterarguments, and adapt outputs to specific stakeholder needs.

Yes, you can adapt elicitation complexity for different content types and stakeholders. The process dynamically adjusts methods and output formats based on contextual needs, ensuring the refinement approach matches the specific scenario.

The best way to assess risks in AI-generated drafts is applying targeted elicitation methods from a risk category. This pushes the LLM to explore counterarguments and identify underlying assumptions, strengthening the final output.

Yes, this elicitation workflow requires a method registry to function properly. The registry provides categorized techniques—such as core, structural, and risk methods—which are dynamically applied to refine content based on context.