gpd-list-phase-assumptions

AI assumption analysis in research planning identifies the model's implicit physics, methodology, computational approach, scope, anchors, risks, and dependencies. It surfaces hidden biases before planning, enabling early course correction when the AI's assumptions do not match project reality.

Phase assumption analysis evaluates AI's understanding across physical, mathematical, computational, methodological, and scope categories. You need it before planning to catch incorrect assumptions about your research phase, enabling early course correction and informed decision-making through conversational feedback.

Identify computational and methodological assumptions by running an assumption analysis on the research phase. The process assesses the AI's baseline understanding across five categories—physical, mathematical, computational, methodological, and scope—then prompts for user feedback.

Yes, you can generate AI feedback for research planning without specific technical dependencies. This assumption analysis operates independently to evaluate phase physics, methodology, scope, and risks, requiring no external frameworks to function.

AI planning fails when phase assumptions go unverified because the model's implicit physics, methodology, and scope constraints remain hidden. Surfacing these assumptions across physical, mathematical, and computational categories prevents mismatched expectations and enables early course correction.