Describe the product, its industry, and your current assumptions about
the buyer, and this prompt researches and builds two or three detailed
customer personas around them.
Covers demographics and psychographics, pain points, goals and
motivations, buying behavior, information sources, decision criteria, and
objections to overcome — treat the result as hypotheses to validate with
real customer interviews, not a finished answer.
Describe the research question, the two groups being compared with their
sample sizes, the outcome variable, and the significance level, and this
prompt runs a complete hypothesis test end to end.
- States the null and alternative hypotheses in plain language
- Checks the chosen test's assumptions (normality, variance, independence)
- Selects and justifies the right test, reporting the statistic, p-value
- Reports a confidence interval alongside the p-value
- Computes an effect size and comments on practical significance
- Delivers the full Python/R workflow as code
Paste in a raw interview transcript and this prompt produces a fast
first-pass summary before any formal coding work begins. It pulls out 3-5
main themes discussed, 3-5 verbatim key quotes from the participant, a
read on the participant's overall stance toward the research topic, and
any unusual or unexpected perspectives that don't fit neatly into the
theme bullets — useful for quickly deciding whether a transcript warrants
a deeper coding pass.
Name the research topic, the sources to draw on, the focus areas you
need covered, and the intended audience, and this prompt turns a stack
of research into one readable summary.
- A 3-5 sentence executive summary
- Key findings as bullets, plus the methodologies behind them
- Conflicting viewpoints and gaps in the research, flagged explicitly
- Practical implications, citations, and further-reading suggestions
Lists ten current research topics within a given {field}, explaining each topic's relevance to 2026 developments, one open challenge tied to it, and a key question it raises. Designed for the start of a research project — a thesis, dissertation, or grant proposal — when the researcher needs several defensible, current topic options to compare rather than a single idea to commit to immediately. Works best as an input to a follow-up prompt that narrows the shortlist down to one topic.
Builds a chronological timeline of key milestones in a given {topic} from 2011 through 2026, including major breakthroughs, the researchers or figures behind them, and their implications for the field.
Useful for the historical background or literature context section of a thesis, dissertation, or grant proposal, where reviewers expect the work positioned within the wider academic conversation.
Dates, names, and attributions should be cross-checked against primary sources before being cited in any formal document.
Condenses a pasted {abstract} into five clear bullet points covering its innovations, limitations, and 2026 applications.
- Input: the full abstract text to condense
- Output: 5 bullets spanning innovation, limitation, and application angles
- Useful for conference submissions and thesis abstracts with tight space limits
- Keeps the summary readable without losing the paper's key claims
Links two separate subjects, {topic1} and {topic2}, in four distinct ways and proposes hybrid, interdisciplinary project ideas built on each connection. Helpful for researchers exploring cross-field work — combining, say, a technical discipline with a social science — who need to articulate why merging the two adds genuine value rather than being a forced pairing. Frequently used to justify interdisciplinary grant applications that require a clear rationale for combining fields.
Generates ten question-and-answer pairs on a given {topic}, each with a short explanation attached, functioning as self-test study material.
Suited to comprehensive exam prep, viva or defense practice, or simply checking how solid your grasp of a subject is before presenting it.
Best used by attempting to answer each question yourself first, then comparing your answer to the model's explanation — that comparison is a better test of recall than reading passively.