Patient portal replies you review instead of write
In Basket volume has grown so much that health systems now pipe GPT-4 draft replies directly into Epic. The UC San Diego Health trial found drafts did not shorten reply time but reduced the burden of starting from a blank box — and a separate analysis found 35-45% of erroneous drafts were sent completely unedited, which is exactly the failure mode a disciplined prompt and review habit prevents.
You draft replies to patient portal messages for a busy {{specialty}} clinic. Draft a reply I can edit and send. Patient's message (de-identified): {{patient_message}} What I want to communicate: {{my_answer}} Rules: - Under 120 words, written at a 6th-8th grade reading level: warm, direct, no medical jargon without a plain-word explanation. - Communicate only the clinical content I gave you. Do not add advice, reassurance about symptoms, medication changes, or interpretations I did not state. - If my answer does not fully address something the patient asked, list it under "UNANSWERED" below the draft instead of improvising. - Never include a drug dose unless I stated it. - If the message describes any potentially urgent symptom, open with a clearly worded safety-net line ("If X worsens or you develop Y, call 911 or go to the ER"). - End with a concrete next step: what the patient should do and when to expect follow-up. - No "as an AI" language — this is sent from my clinic account under my name.
Fill in your details and the prompt updates live — then copy.
Thank you for tracking your blood pressure so carefully — that information really helps. Your readings are higher than our goal, so please increase your lisinopril the way we discussed at your visit. Keep checking your blood pressure and send me your numbers in 2 weeks. If you get a severe headache, chest pain, trouble breathing, or vision changes, call 911 or go to the ER right away. And yes — please complete your lab work before your next visit so we can review it together. UNANSWERED: none.
The full workflow
- Copy the patient's question without identifiers, and decide your clinical answer first — the AI words it, you decide it
- Run the prompt and check the draft says exactly what you intended, nothing more
- Resolve anything under UNANSWERED yourself before sending
- Send from the EHR, and escalate to a call or visit when the thread needs one
Watch out for
HIPAA: consumer chatbots have no BAA — de-identify the message or use your health system's EHR-integrated drafting tool, which is covered.
Studies show clinicians send a meaningful share of erroneous drafts unedited. Read every word before sending — the reply is medical advice under your name.
AI drafts trend long and overly polite; cut them down or patients stop reading your messages.
Where this comes from
Every use case on this site is grounded in real reports from working physicians — not invented by us.