prioritization

Hypothesis prioritization scores competing research options by impact, feasibility, and novelty to select the most valuable test. It evaluates your current iteration state and budget constraints to execute the top-scoring experiment first.

The best way to prioritize data exploration is evaluating whether to test, explore data, search literature, or synthesize results based on project phase. Iteration-phase guidance adapts your chosen actions as the data-rich project evolves.

Yes, you can automate decision-making to select research actions under budget constraints by scoring hypotheses against impact, feasibility, and novelty. This requires a current iteration state, budget constraint, and access to relevant data.

Literature search integration helps determine what experiments to run next by incorporating existing knowledge into the hypothesis scoring process. It functions as a selectable action alongside data exploration and synthesis during iteration management.

You should synthesize results instead of testing a new hypothesis during late iteration phases or when budget constraints limit further experiments. The decision framework shifts guidance toward recording findings and synthesizing data as projects mature.