Healthcare & Wellness

Verified against ChatGPT · 2026-08-08

Turn a rushed doctor's-visit debrief into a summary the rest of the family can actually use

Converts a caregiver's messy notes or voice-memo transcript from a loved one's appointment into an organized visit summary the whole family can read in two minutes — flagged everywhere as a personal record for the family, not a clinical document.

ChatGPT (GPT-5.1)4 fillable variables
Scope for this category: Organizational, educational and communication support only — no diagnosis, treatment recommendation, or medication guidance. Every prompt states plainly that a qualified clinician must review anything before it is acted on.

The prompt

Ready to copy — highlighted parts are example details you can swap.

You are helping a family caregiver turn their own notes from a relative's medical appointment into a short, organized summary to share with siblings or other family members who couldn't be there.

WHO THE VISIT WAS FOR
My mother, 78, saw her cardiologist for a follow-up after a hospital stay in June.

RAW NOTES OR VOICE-MEMO TRANSCRIPT
Dr. Patel said the swelling in her ankles is 'much better than last time,' adjusted the water pill to a lower dose, wants a follow-up echo in 6 weeks, mentioned something about 'BNP levels' trending down.

WHAT THE FAMILY NEEDS TO KNOW
My brother wants to know if she's stable enough to travel for Thanksgiving; my sister wants the medication change in writing.

UPCOMING DECISIONS
Whether to schedule the follow-up echo for the week of Sept 14 or wait until after the family visit.

HOW TO STRUCTURE IT
Open with one line stating who the appointment was with and why, in plain terms, before any detail. Group the rest of the raw notes into what actually happened at the visit, what the doctor said in their own words wherever the notes captured something close to a direct quote (mark paraphrases clearly as paraphrases, not quotes, if the notes weren't verbatim), and what changed as a result — a new medication, a referral, a follow-up test. If the raw notes contain a term or abbreviation you can't confidently expand from context, list it under a short 'terms to ask the doctor's office to clarify' section rather than guessing at what it means. Do not infer a diagnosis, prognosis, or severity assessment that isn't explicitly stated in the notes themselves — if the notes are ambiguous about how serious something is, say the notes don't specify rather than filling in an assumption. Keep the tone matter-of-fact; this is a family status update, not a reassurance exercise, so don't add comforting language that isn't grounded in what was actually said at the visit.

WHAT NOT TO DO
Do not turn this into a to-do list for the caregiver themselves — that's a separate document. Do not speculate about what a lab result or scan finding might mean beyond what the notes already say the doctor concluded.

OUTPUT FORMAT
1. One-line visit summary (who, with whom, why).
2. What happened / what was said (bulleted, paraphrases marked as such).
3. What changed (new meds, referrals, tests, dosage changes).
4. Pending decisions the family should weigh in on, tied to the dates given.
5. Terms to clarify with the doctor's office, if any.
6. A closing line stating plainly that this summary is a personal family record based on one caregiver's notes, not a medical record, and that any decision about care should be confirmed directly with the treating clinician.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

The instruction to mark paraphrases as paraphrases rather than quotes directly counters a specific failure mode of language models summarizing informal notes: given a loosely worded fragment like "much better than last time," the model's default behavior is to smooth it into a confident, quote-like clinical statement, which misrepresents the certainty of what was actually said and can mislead family members who weren't present to judge tone or hedging themselves. Explicitly forbidding inference of diagnosis or severity from ambiguous notes matters because GPT-5.1 is otherwise very good at pattern-completing a plausible-sounding medical interpretation from partial information — a term like "BNP levels trending down" invites exactly the kind of confident elaboration a caregiver has no way to fact-check, so the prompt forces the gap to surface as a flagged unknown instead of a filled-in guess. Routing unclear abbreviations into a dedicated "terms to clarify" section rather than silently expanding them prevents a second, subtler failure: a wrong expansion of an abbreviation reads exactly as confidently as a correct one, and family members downstream have no signal to distinguish the two. The closing disclaimer is placed at the very end, after the substantive content, specifically so it reads as a genuine boundary statement about the document's status rather than legal boilerplate skimmed past at the top — its function is to make sure nobody in the family thread treats this caregiver's paraphrase as equivalent to the actual chart note.

What you get back

Visit summary: Mom saw Dr. Patel (cardiology) for a post-hospital follow-up on Aug 5. What happened: Ankle swelling described as much improved since last visit. Water-pill dose was lowered. A follow-up echo was scheduled for 6 weeks out. What changed: Furosemide dose reduced (exact new dose not captured in the notes — confirm with pharmacy). Echo ordered. Terms to clarify: what "BNP levels trending down" means for her specific case. This is a personal family summary based on one caregiver's notes, not a medical record — confirm any care decision directly with Dr. Patel's office.

Verified against

ChatGPT GPT-5.1 · 2026-08-08

Changelog

  • 2026-08-08 Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
All Healthcare & Wellness prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY