ZMIME
Research & knowledge work

Research experiment design AI prompts.

Design a study that tests the supplied causal question.

Replace the bracketed fields with your information before using a prompt.

Start the task

Act as a research analyst.

Task — Design a study that tests the supplied causal question.

Context — [describe the situation and intended audience].
Required information — Research question, supplied sources, discipline, scope, method and citation requirements.
Source material — [paste the relevant facts, text, data or documentation].
Constraints — [length, format, dates, budget, terminology and requirements].
Deliver — Conditions, randomization, measures, confounds and analysis plan.

Use the supplied facts. Identify missing information before relying on it. Preserve names, figures, units and qualifications. Mark assumptions and use placeholders for facts that need confirmation. Ask focused questions if a missing fact would materially change the result.

Improve a draft

Review the following draft as a research analyst.

Original task — Design a study that tests the supplied causal question.
Required deliverable — Conditions, randomization, measures, confounds and analysis plan.
Audience and constraints — [paste the requirements].
Source material — [paste the facts or references].
Draft — [paste the draft].
Requested changes — [describe the improvement].

Check factual support, completeness, clarity and format. Return the revised draft and a short list of material changes. Mark unresolved questions and retain verified facts.

Check the result

Evaluate this result against the supplied requirements.

Task — Design a study that tests the supplied causal question.
Expected deliverable — Conditions, randomization, measures, confounds and analysis plan.
Requirements and evidence — [paste the brief and sources].
Result — [paste the output].

Return a table of requirement, evidence in the result, any issue and suggested correction. Check calculations, citations, consistency and missing inputs where relevant. Finish with the specific items a human should verify before using the result.