Ask a clinical or health question, find the relevant papers and check what they support before you make a recommendation.
Starter · About 15 min to try; setup approval may take longer.
Bring: A population-level research question and a public paper.
Make: A checked claim with a source and limits.
Suggested starting tools:OpenEvidence, Consensus, Elicit. Use fictional inputs for this exercise; check the exact account and data path before real records.
Guide sources and teaching inputs checked . Vendor directory claims retain their own review dates.
Start with a question you can answer
Specify the population, intervention, comparator and outcome. For example: in postmenopausal women, what human evidence links menopause symptoms with disrupted sleep? Ask for studies and guidelines, with links, limitations and a clear separation between association and causation.
Follow up conversationally: who was excluded, how was sleep measured, how large was the effect, and what remains uncertain? Ask what source material the assistant actually accessed. If it has only an abstract, it should say so; provide a paper you are allowed to share rather than accepting invented full-text details.
A real citation can accompany a wrong claim
The Her Longevity talk uses a deliberately incorrect draft claim about creatine increasing bone density. The cited 2023 trial is real: 237 postmenopausal women received creatine or placebo alongside exercise for two years. It found no added bone mineral density benefit, although some bone geometry measures improved. That does not establish fracture prevention.
This is an authored teaching example, not a captured model failure. Its lesson is to compare the exact sentence with the study’s population, comparison and measured outcome. A plausible citation alone does not validate the sentence.
Make the review visible
Keep a small claim log: proposed sentence, source link, supporting passage or table, limitations and reviewer decision. Mark claims supported, overstated or unverified. Revise the wording before using it in a handout, talk or care discussion.
Research support does not settle an individual treatment decision. The clinician still evaluates the patient, alternatives, feasibility and uncertainty.
Copy a prompt to try
Evidence conversation
Research
Research this question: {{population_and_question}}.
Use human studies and relevant guidelines from {{allowed_public_sources}}.
For each item, give a direct source link, design, population, comparator,
measured outcome, main finding and limitations. Separate association from causation.
State what you actually accessed: full text, abstract or other material.
If access is limited, say what cannot be checked. Do not invent citations.
Finish with one useful follow-up question and the claim I should verify first.
Use a population-level question and public sources. Open the source and check the claim before applying the answer to clinical care.
Check this sentence: {{draft_claim}}.
Against this source that I am allowed to share: {{source_link_or_text}}.
Identify the exact population, comparator and measured outcome.
Show the passage or table that supports or contradicts the sentence.
Label the claim supported, overstated or unverified, and explain why.
Suggest the narrowest accurate revision. Distinguish surrogate outcomes
from clinical outcomes. If you cannot access the relevant material, stop and say so.
The assistant’s check is another draft to verify. A real citation can still accompany an inaccurate statement.
This is an authored teaching example, not a captured AI output or a clinical plan.
Draft claim: “Creatine increases bone density in postmenopausal women.”
Review: Overstated. The cited two-year trial found no added bone mineral density benefit. Some bone geometry measures improved; fracture prevention was not established.
Next step: Check the measured outcome and revise the sentence before using it.
Check before you use the result
Open the cited source and confirm what the assistant could access.
Check the population, comparison and measured outcome.
Keep association, surrogate outcomes and clinical outcomes distinct.
Record your decision and revise unsupported wording.