Healthcare & Wellness

Verified against ChatGPT · 2026-08-08

Build a question list for a doctor's appointment that won't dissolve the second you sit down

Turns a jumble of symptoms, worries, and half-remembered questions into a short, prioritized list to bring into an appointment, ordered so the most important items get asked even if time runs short.

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 someone prepare for an upcoming medical appointment by turning their scattered notes into a short, prioritized question list they can actually use in the room.

APPOINTMENT TYPE AND REASON
15-minute follow-up with my primary care doctor after a knee injury three weeks ago.

WHAT'S BEEN GOING ON
Swelling has gone down but there's still a clicking sound going up stairs, and I can't fully straighten the leg first thing in the morning.

QUESTIONS AND WORRIES SO FAR
Should I get an MRI? Is it okay to keep running? Why does it click? Is this going to need surgery? Can I go back to the gym next week?

TIME LIKELY AVAILABLE
15 minutes

RULES
1. Rank every question by what would actually change a decision if answered, not by how worried it makes the person — a question about a scary-sounding symptom that turns out to be minor still ranks below a question that affects an active treatment choice.
2. Cut every list down to fit realistically inside the stated appointment length, assuming roughly two minutes per substantive question once the clinician's own agenda is accounted for; put anything that doesn't fit into a clearly separate "if there's time" section instead of silently dropping it.
3. Rewrite vague worries into a specific, answerable question — "is this normal" becomes something the clinician can actually respond to in one exchange.
4. Where the raw notes describe a symptom, keep the description factual (what, when, how often, what makes it better or worse) and do not editorialize about what it might mean.
5. If the same underlying concern appears more than once in different words, merge it into one question instead of asking it twice.

OUTPUT FORMAT
Top questions (ranked, fits the stated time): numbered list, each one phrased as it would actually be asked out loud.
If there's time: a second short list.
One line at the end reminding the person to write down the clinician's actual answers during the visit, since this list is only meant to prepare for the conversation and is not a substitute for what the treating clinician tells them directly.

Customize

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

Why this works

Ranking by decision-relevance rather than by anxiety level is the core mechanism here, because left unguided a model asked to prioritize "worries" will over-weight whatever sounds most alarming in the raw text rather than whatever is most likely to change what the clinician actually does — a scary-sounding but low-stakes question about clicking joints will otherwise crowd out a question that genuinely affects a return-to-activity decision. The explicit two-minutes-per-question budget forces a real cutoff instead of an open-ended list that looks thorough on paper but is impossible to get through in a 15-minute slot, which is the single most common reason patients report leaving appointments having forgotten their most important question — it got buried in a long list rather than surfaced first. Rewriting vague worries into specific, answerable questions matters because "is this normal" invites a generic reassurance response from any clinician working quickly, whereas a specific version ("is a clicking sound going up stairs at three weeks post-injury expected, or does it need imaging") gets a real, checkable answer in the same amount of time. Merging duplicate concerns keeps the list from padding itself with restated variations, which otherwise eats into the same fixed time budget the ranking rule is trying to protect. The closing instruction to write down the clinician's actual answers reinforces that this list is scaffolding for the conversation, not a replacement for whatever the treating clinician says once asked.

What you get back

Top questions (fits 15 min): 1. Is the clicking when going up stairs expected at three weeks, or does it warrant an MRI now? 2. Is running safe to resume, and if not yet, what's the timeline? 3. Based on today's exam, does this look like something surgery would ever be on the table for? If there's time: Is the gym (non-running exercise) okay to resume next week? Remember to write down the doctor's actual answers — this list is only meant to prepare for the conversation.

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