Healthcare & Wellness

Verified against ChatGPT · 2026-08-12

Draft a post-visit follow-up message that sounds like the clinic, not like a form letter

Writes a follow-up message to a patient after a visit or test result — checking in, confirming next steps, answering a routine question — for the clinician or clinic staff member to review and send under their own name.

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.

Draft a follow-up message to a patient after a recent visit or result. This is a message the clinician or clinic staff member reviews and sends themselves — not something that goes out automatically or under your name.

WHO THIS IS TO AND WHY
Patient who had bloodwork done last week; sending to share that results came back and next steps.

KEY POINTS TO INCLUDE
Cholesterol panel results are back and within normal range. No action needed. Continue current diet and exercise routine. Next annual bloodwork in 12 months unless something changes.

TONE THE CLINIC WANTS
Warm but brief — this patient prefers efficient communication.

ANYTHING SENSITIVE TO HANDLE CAREFULLY
N/A for this one — routine normal result.

HOW TO WRITE IT
Open by referencing the specific visit or result so the patient immediately knows what this is about, rather than a generic greeting. Cover the key points in the order the patient would need them — what's confirmed or resolved first, then anything requiring action from them, then how to reach the clinic with questions. If any key point involves a result or finding, state only what was given in the key points field, in the same terms — do not add interpretation, reassurance language, or severity framing that wasn't explicitly provided, since the person sending this message is the one qualified to characterize the finding, not this draft. Keep sentences short enough to be read on a phone screen. If sensitive content is flagged, handle it plainly and respectfully without being clinical to the point of feeling cold, but do not soften a factual point to the point of changing its meaning.

WHAT NOT TO DO
Do not invent next steps, reassurances, or interpretations beyond the key points given. Do not make the message sound automated — no "this is an automated message" framing, since a real person is sending it after review.

OUTPUT FORMAT
1. Subject line, if this is going by portal message or email.
2. Message body, ready for the sender to review, edit, and personalize before sending.
3. One bracketed note at the end (not part of the message itself) reminding the sender to confirm every clinical detail before sending, since this draft only reflects the key points supplied.

Customize

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

Why this works

Restricting the message to only the key points supplied, in the same terms, is what keeps this a communication-drafting tool rather than something making an independent clinical characterization: if a model is handed "cholesterol results back, within range" and asked to write a warm patient message, its default instinct is to add reassuring color ("great news, nothing to worry about here") that goes slightly beyond what was actually stated, and that small addition compounds badly when the same drafting pattern is reused for an abnormal result, where an unintended reassuring tone could actively undercut a warning the sender meant to convey. Ordering the content by what's resolved, then action items, then contact information reflects how people actually read short messages on a phone — they skim for whether they need to do anything before reading the full context, so front-loading resolved status and burying action items in paragraph three means they're more likely to be missed. The explicit ban on "automated message" framing matters for a specific reason: presenting this as automated would misrepresent the fact that a licensed clinician or staff member is reviewing and personally sending it, which is exactly the accountability structure that makes this drafting tool appropriate to use in the first place — it's a draft awaiting a real person's review, not a system generating patient-facing clinical communication unsupervised. The closing bracketed reminder is placed outside the message body itself so it never accidentally gets copy-pasted into what the patient actually receives.

What you get back

Subject: Your recent bloodwork results Hi [Patient name], your cholesterol panel from last week is back and within normal range — no action needed on your end. Keep up your current diet and exercise routine, and we'll see you for your next annual bloodwork in about 12 months unless anything changes before then. Reach out anytime if you have questions. [Reminder: confirm every clinical detail above matches the actual result before sending — this draft only reflects the key points you supplied.]

Verified against

ChatGPT GPT-5.1 · 2026-08-12

Changelog

  • 2026-08-12 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