Research
Review the literature
What the evidence actually says, including where it disagrees.
Fill it in
Stated narrowly enough to answer.
Sample size, design and who funded it.
Where findings conflict, rather than averaging them away.
Your prompt
Review the evidence on this. [the question] Weigh the studies rather than counting them. Twelve small unblinded studies and one large pre-registered trial is not thirteen pieces of evidence, and a review that treats them equally reaches the wrong conclusion confidently. Show where findings CONFLICT and say what might explain it: different populations, different measures, different lengths. Averaging a disagreement away is how a review becomes more certain than the literature it summarises. Name the publication bias risk if the field has one, and whether the funding pattern is worth mentioning. End with what would actually settle it. That is the most useful paragraph and it is usually missing. Every claim cited. No invented references.
Use Review the literatureOpens with everything above already filled in.
Why this works
Twelve small unblinded studies and one large pre-registered trial is not thirteen pieces of evidence. This weighs rather than counts, shows where findings conflict instead of averaging the disagreement away, and ends with what would actually settle the question.
Questions
- Are the citations real?
- Yes. It cites what it read and marks what it could not verify.