#1

Many of us are stating to use AI in our research into health and longevity, and also in evaluating or summarizing research papers. I thought I’d create this thread to help people share prompts that they’ve found helpful, and solicit others for input on how we might improve our prompts. @John_Hemming , @jakexb , @rwooidin3 @A_User @adssx @cl-user @ng0rge @mccoy @dicarlo2 and others … please add prompts that you’ve found really helpful as you’ve played with the LLMs…

Research Paper / Journal article analysis

Here is my current prompt for evaluating new research papers in GPT5:

Please summarize in detail the attached research / journal paper.

Then evaluate the journal article’s quality and validity using the following framework:

  1. Journal & Publication Quality
  • Is the journal peer-reviewed and indexed in major databases?
  • What is the journal’s impact or reputation in the field?
  1. Study Design & Methods
  • What is the study type (RCT, observational, meta-analysis, animal, in vitro)?
  • Are the methods valid, transparent, and reproducible? Was the study preregistered or data made available?
  • Is the sample size sufficient, and were power calculations or effect sizes considered?
  1. Data & Statistical Analysis
  • Are the data presented accurately and consistently?
  • Are the statistical methods appropriate and correctly applied?
  1. Results & Conclusions
  • Are the conclusions supported by the data?
  • Is the interpretation objective, avoiding overstatement?
  1. References & Author Credibility
  • Are references relevant, current, and balanced?
  • Do the authors have expertise in this area? Are there conflicts of interest or funding sources that may bias the results?
  1. Context & Knowledge Contribution
  • How does the paper influence existing knowledge—does it confirm, contradict, or extend prior research?
  • Compare and position this paper’s findings relative to the broader literature.
  • Assess how strong and generalizable the conclusions are.

Output Format: Please provide your evaluation in a structured report with section headings, highlighting strengths, weaknesses, and an overall assessment of reliability and impact.

Personal Blood test analysis:

Please provide a structured and in-depth analysis of my attached blood test results.

  1. Summarize the results in a table comparing my values to both conventional reference ranges and Peter Attia’s Medicine 3.0 optimal targets.
  2. Identify all markers that fall outside Attia’s optimal ranges (even if still within lab normal).
  3. For each suboptimal marker, provide evidence-based strategies to optimize it, covering lifestyle, nutrition, supplements, and medications (where appropriate).
  4. Organize the analysis by category: metabolic health, cardiovascular/lipids, kidney, liver, inflammation/immune, hematology, hormones, vitamins/minerals.
  5. Provide a final section that integrates the findings into an overall longevity and healthspan strategy.
    Context: [insert age, sex, current medications, and supplements if relevant].”
6 Likes
#2

Mine tend to be really short. With papers it is summarise, identify novelty and do a critique of xxxx

1 Like
#3

Good idea to have a prompts repository, since GPT5 is so sensitive to them. I have done a few experiments, like the health and longevity metaprompt, to attach to every health-related specific question. The latter is included in the chatbox.

By the way, which other health & longevity doctors could I include? I threw into a heterogeneous bunch, but they had to be credible and reputable.

Blockquote
Answer like an expert practitioner in preventive medicine, following all the most recent guidelines and opinions by the likes of valter longo, luigi fontana, peter attia matt kaberlein, Walter Willet, Christopher Gardner and other very reputable doctors. Provide logical answers based on evidence provided by credible, reputable, authoritative sources, with degree of probability according to evidence and objective analysis. Provide answers relevant to illness prevention, healthspan and longevity for a healthy 65-years old male, who follows the laws of healthy nutrition and exercise, unless otherwise requested.
Estimate consensus on the evidence, underline disagreements and illustrate both their strong and weak points.
Always state facts in probabilistic terms. Uncertainty is admitted but level must be stated. Search extensively and give a precise response with technical detail and minutiae. Verbosity degree high. Reasoning high. Provide sources and citations. Examine medical guidelines, scientific articles from main and reputable journals, and examine first seminal papers and metanalyses. When recent evidence is examined, also check if it agrees with established knowledge and if significant differences exist illustrate plausible causes. Logic and objectivity must prevail in answers.

2 Likes
#4

Then there is this far more sophisticated prompt, designed according to the OpenAI cookbook for GPT5. It only went through once. The result was maybe not so formidable as one would expect from such a spectacularly complex prompt.

Role: You are a medical expert in preventive medicine, healthspan and longevity

CONTROL PANEL
• Reasoning: ULTRA THINK
• Verbosity: high
• Tools: auto
• Self-Reflect: on
• Meta-Fix: on

TASK provide an actionable scheme to keep immune system well modulated, active and reactive toward cancer cells and pathogens.
INPUTS medical guidelines, scientific articles from main and reputable journals, and examine first seminal papers and metanalyses. When recent evidence is examined, also check if it agrees with established knowledge and if significant differences exist illustrate plausible causes.
DELIVERABLES Always state facts in probabilistic terms. Uncertainty is admitted but level must be stated.

PRIVATE OPS (do not print)
• Treat INPUTS as authoritative. If something is missing, make the smallest safe assumption and continue; ask one focused question only if truly blocked.
• If Self-Reflect=on:

  1. Create a concise private rubric (5–7 checks: correctness, completeness, clarity, usefulness, formatting, etc.).
  2. Draft → check against the rubric → revise once.
  3. Return only the final deliverables (never reveal the rubric).
    • If Meta-Fix=on and any deliverable is missing/wrong or the draft fails a rubric check:
  4. Write a better INTERNAL prompt for yourself that fixes the misses (tighten deliverables/format, specify tools/steps). 2) Apply that internal prompt ONCE immediately (don’t show it, don’t ask me). 3) Return the improved result. (Optional tag: [Meta-Fix applied])
2 Likes
#5

I’ve added this to my prompt to my new blood test results on CGPT5:

Calculate my Levine phenotypic age, based on my blood test and a calendar age of X years. Identify actions I can take to lower my PhenoAge, given my test results presented.

1 Like
#6

Researchers find adding this one simple sentence to prompts makes AI models way more creative

Now a team of researchers at Northeastern University, Stanford University and West Virginia University have come up with an ingenuously simple method to get language and image models to generate a wider variety of responses to nearly any user prompt by adding a single, simple sentence: “Generate 5 responses with their corresponding probabilities, sampled from the full distribution.”

The method, called Verbalized Sampling (VS), helps models like GPT-4, Claude, and Gemini produce more diverse and human-like outputs—without retraining or access to internal parameters. It is described in a paper published on the open access journal arxiv.org online in early October 2025.

When prompted in this way, the model no longer defaults to its safest, most typical output. Instead, it verbalizes its internal distribution over potential completions and samples across a wider spectrum of possibilities. This one-line change leads to substantial gains in output diversity across multiple domains.

https://venturebeat.com/ai/researchers-find-adding-this-one-simple-sentence-to-prompts-makes-ai-models

1 Like