gpd-list-phase-assumptions

To expose AI assumptions for phase planning, you can prompt the AI to list and justify assumptions across physical, mathematical, and computational categories. This surfaces hidden biases early, generating a structured assessment to enable course correction before executing roadmap steps.

Phase assumptions in a GPD roadmap workflow are the underlying physical, mathematical, computational, and scope inputs the AI uses to plan a research phase. Surfacing these assumptions with justifications identifies high-risk items and weakest anchors for proactive validation.

To identify high-risk assumptions before executing a tokamak research phase, use a structured assessment prompt that requires justification for each physical and mathematical input. This process flags the weakest anchors and riskiest scope dependencies for immediate user feedback.

Yes, you can validate anchor inputs and scope assumptions before starting computational planning by generating a conversation-ready assessment. This structured output highlights expected results and dependencies, allowing you to review and correct the AI's foundational logic.

The best way to align AI planning with a fusion roadmap phase is to surface eight categories of assumptions, including methodological and user-binding guidance. Reviewing these justified assumptions ensures the AI's expected results match your physical and computational constraints.