Make sense of a parent's medical records before a doctor visit with ChatGPT
Beginner-friendlyNo logins, payments or coding needed. Low risk: paste the prompt and you should get something useful.
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Improved prompt
Our fuller version of the source's prompt, or one written to avoid a problem in the source. Not tested by the poster. It doesn't change what happened in the source.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Turn a family member's medical records into a plain-language summary and a list of questions for the next doctor visit. Questions to ask me first: - Who is the summary for, and how much medical background do they have? - When is the next appointment, and with which kind of doctor? - Is there anything specific we're worried about? Inputs (fill in or confirm): - Records with names, dates of birth and ID numbers removed: [RECORDS] - Current medication list: [MEDICATIONS] - Upcoming appointment: [DOCTOR / DATE] - Our main worries: [CONCERNS] Rules: - Summarize each document in plain words, without jargon; explain any medical term you must use. - Point out patterns or changes over time, and recommendations that show up in more than one record. - Never diagnose, change a medication or give dosing advice; anything that sounds urgent goes to the doctor. - If part of a page is unreadable, say so instead of guessing. Checkpoint: Show me the summary of the first document and wait for me to confirm it's readable and accurate before doing the rest. If you get stuck: If records seem to disagree, list both versions and add it to the questions for the doctor. Verify before you finish: Check every finding points back to a specific document and date, and that no personal identifiers appear. Output: A one-page overview, a short summary per document, and a numbered list of questions to bring to the appointment. Done when: We walk into the appointment understanding the records and knowing what to ask.
Customize this prompt
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Turn a family member's medical records into a plain-language summary and a list of questions for the next doctor visit. Questions to ask me first: - Who is the summary for, and how much medical background do they have? - When is the next appointment, and with which kind of doctor? - Is there anything specific we're worried about? Inputs (fill in or confirm): - Records with names, dates of birth and ID numbers removed: [RECORDS] - Current medication list: [MEDICATIONS] - Upcoming appointment: [DOCTOR / DATE] - Our main worries: [CONCERNS] Rules: - Summarize each document in plain words, without jargon; explain any medical term you must use. - Point out patterns or changes over time, and recommendations that show up in more than one record. - Never diagnose, change a medication or give dosing advice; anything that sounds urgent goes to the doctor. - If part of a page is unreadable, say so instead of guessing. Checkpoint: Show me the summary of the first document and wait for me to confirm it's readable and accurate before doing the rest. If you get stuck: If records seem to disagree, list both versions and add it to the questions for the doctor. Verify before you finish: Check every finding points back to a specific document and date, and that no personal identifiers appear. Output: A one-page overview, a short summary per document, and a numbered list of questions to bring to the appointment. Done when: We walk into the appointment understanding the records and knowing what to ask.
Scroll to see the whole prompt. Your answers show in green.
4 blanks are still empty: Records with names, dates of birth and ID numbers removed; Current medication list; Upcoming appointment; Our main worries. They'll stay in brackets in your prompt, so the chat tool may ask you about them.
What you type stays in this browser tab. We don't send it or save it, and it's gone when you leave the page. If you use a "Try this in" button, your answers go to that tool as part of the prompt.
Try this in:
This prompt has blanks to fill in, like [RECORDS]. We'll copy it instead of filling it in, so you can edit it before you send.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
The prompt they actually used
The exact prompt from the source.
You are a skilled health communicator who explains complex medical information in simple, plain language for a non-medical caregiver. I have uploaded anonymized medical records. Before starting, please ask me any clarifying questions you need to give me the most accurate, useful, and easy-to-understand output. Once you have my answers, please: Summarize each document in clear, plain language without medical jargon Highlight any key findings, patterns, or trends over time Identify any consistent recommendations across the records Suggest a list of questions I could ask the healthcare provider based on this information Organize the information so it is easy to review before an appointment
AI tool
Outcome
After Heather Lambert-Shemo's dad spent time in the ICU, the family faced dozens of pages of records and a dozen medications. Lambert-Shemo photographed the pages, blacked out identifying details and asked ChatGPT to translate them into plain language, find trends and list questions for the primary care doctor. It gave the family a clearer picture of what led to the hospital stay and turned up a significant diagnosis the dad had misunderstood. Lambert-Shemo later shared the exact prompt in the post's comments.
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Source
- Posted
- by Heather Lambert-Shemo
- Last checked
- Method:
- How we verify
Context: Lambert-Shemo removed identifying details before uploading. Nothing here replaces the doctor; use the summary to ask better questions.
Related cases
Find out why two Medicare Advantage plans have different deductibles with ChatGPT
Comparing 2027 Medicare Advantage plans, John Major found two from one company with nearly identical features and premiums and copays within $10, but plan E had a $2,000 deductible on non-routine care and plan S had none. Major couldn't find a benefit to explain it and asked ChatGPT. It admitted it couldn't find an explanation either, but on its own it compared the 2026 versions: then, plan E's deductible was $1,500 with an out-of-pocket maximum $2,750 lower than plan S. Major concluded the company was 'apparently squeezing existing plan E customers', counting on them to renew without looking.
PersonalChatGPTWorkedRecreated promptEvidence: Described by posterView CaseExplain retirement money ideas simply and prepare for a planner meeting with ChatGPT
Therese M., a retiree who isn't a financial professional, uses ChatGPT between appointments with a financial planner, not instead of them. Therese asks it to 'explain these concepts to me like I'm in fifth grade'. Before meetings with an accountant or certified financial planner, Therese says what the meeting should achieve and asks ChatGPT for targeted questions. When Therese was thinking about redoing a bathroom, ChatGPT ran the numbers and the pros and cons, and Therese decided to just fix the leaky faucet. One firm rule: no real account numbers, Social Security number or identifying details go into the chat.
PersonalChatGPTWorkedRecreated promptEvidence: Article or interviewBeginner-friendlyView CaseSpot a jury duty scam targeting your spouse with ChatGPT (partial)
On July 21, men posing as sheriff's deputies told Kimberly Fudge, 38, a Florida finance manager, that Fudge had missed federal jury duty and faced arrest. Fudge spent nearly 10 hours driving and feeding $25,000 into cryptocurrency machines as 'bail'. Following the callers' script, Fudge texted spouse Jonathan for money, and Jonathan sent $3,000. At a second request, Jonathan asked ChatGPT why a spouse would make such a demand. It listed ordinary explanations, then flagged a possible scam, and Jonathan called 911. The money already sent is gone; reports went to the sheriff's offices, the FBI's Internet Crime Complaint Center and the FTC, but the family is 'not counting on recovery.'
PersonalChatGPTPartialRecreated promptEvidence: Article or interviewView Case