Summarise a health article critically with a prompt built for Claude and Perplexity. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.7(20 ratings)334 copies
Updated By Site Admin
45 words · v1.0
Fill in the blanks · 1 variable
Claude promptReplace every highlighted token before sending
<task>
Summarise this health article and evaluate its evidence. Identify the study design, sample, outcome, conflicts of interest and the gap between the headline and the data. Give the takeaway a clinician would want me to know. Do not turn it into personal advice.
Article:
{article}
</task>
Think carefully before answering. Keep any reasoning separate and put the final deliverable inside <answer> tags.
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Claude and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({article}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Every health decision with a qualified clinician. In an emergency, contact local emergency services.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Article: Paste the health article here.
Example output
**In plain language:** the test measures how well your kidneys filter waste. A single result outside the reference range does not confirm a diagnosis; hydration, recent exercise, medication and lab method can all affect it.
**What to ask your clinician:** What is my trend over time? Does this change my current treatment? Should we repeat the test? Are any of my medications affecting the result?
**Seek urgent care** for severe symptoms such as difficulty breathing, chest pain or confusion. This is general information, not medical advice.
Tips for a better result
Use these prompts to prepare questions and organise information, never to self-diagnose.
Ask the model to mark uncertainty and to state what it cannot know without your history.
Verify every term and number against a clinician or a national health service.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Asking for a diagnosis, medication dose or interpretation of a scan.
Delaying urgent care because a model suggested a benign explanation.
Assuming a general answer applies to your age, pregnancy, medication or conditions.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the summarise a health article critically prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
A healthcare prompt for prepare questions for a doctor's appointment. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
Explain a diagnosis to a family member with a prompt built for ChatGPT and Claude. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
A healthcare prompt for explain a lab result in context. It gives ChatGPT and Claude a clear role, explicit constraints and a defined output, so the first answer is closer to usable. Fill in the variables, run it once, then use the verification notes on this page to review the result.
ChatGPTClaudeGemini
4.7(17)267 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 15 June 2026 · version 1.0 · tested on Claude, Perplexity, NotebookLM
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.