Between a hypothesis and a running study sits a wall of decisions: design type, conditions, measures, sample size, exclusion rules. Each one is defensible only in the context of the others — which is why design documents written piecemeal fall apart under review. Neutropic drafts the whole structure at once.
Grounded in how the field designs
Before proposing anything, the agent surveys how related studies designed theirs: typical manipulations, standard instruments, common sample sizes and their observed effects. Your design starts from the field's actual practice, not a blank page — with the option to deviate deliberately, on the record.
A design document, not a chat transcript
The output is a structured document your collaborators, IRB, and future self can read:
- Protocol flow — conditions, randomization, counterbalancing, and timing, as a diagram.
- Measures — each instrument tied to the construct it operationalizes, with scoring rules.
- Sampling plan — target population, recruitment, inclusion and exclusion criteria stated up front.
- Analysis plan — the statistical models you intend to run, written before the data exists.
Power you can defend
Sample size comes from an explicit power analysis, not a lab convention. The agent derives plausible effect sizes from the literature you reviewed, shows the power curve across sample sizes, and states the assumptions — so when a reviewer asks "why n = 128?", the answer is a figure, not a shrug.
Ready for your tools
The finished design exports to where studies actually run: survey structures for Qualtrics, task specifications for PsychoPy, and a pre-registration draft formatted for OSF. The design document stays linked to the eventual data and analysis, closing the loop from plan to paper.
