Claude Prompts for Physicians (Documentation, Communication, Literature)
20 copy-paste Claude prompts for physicians: SOAP notes, patient education, differential aids, literature reviews, and practice operations. Always verify against clinical guidelines — Claude assists, doesn't diagnose.
In short: This page contains 16 copy-paste ready prompts, organized into 4 categories with a description and pro tip for each. The first 5 prompts are free instantly, no signup needed. Hand-curated and tested by the AI Academy team.
Clinical Documentation
4 promptsSOAP Note from Encounter Notes
1/16✨ What it does
Claude turns [Paste encounter notes] into a SOAP note: Subjective, Objective, Assessment, and Plan, and flags gaps without inventing facts. Add the missing bits and file only what you actually saw.
[Paste encounter notes]. Convert to SOAP format: Subjective (HPI in patient's words, ROS pertinent positives + negatives), Objective (vitals, exam by system, results), Assessment (problem list with reasoning), Plan (per problem, including pt education + follow-up). Stay within my notes — flag anything I should add but didn't document.
Pro tip: Documentation gaps cost RVU + create medico-legal exposure. Asking Claude to flag missing standard elements (ROS, exam by system, MDM components) catches what you forgot before you sign.
Differential Diagnosis Brainstorm
2/16✨ What it does
Claude takes [Patient presentation summary] and ranks a top-5 differential plus three cannot-miss diagnoses, with tests that distinguish them and red flags. Apply your own judgment; this is a brainstorm, not a diagnosis.
[Patient presentation summary]. Generate a structured differential. Output: top 5 diagnoses ranked by likelihood, top 3 "can't miss" diagnoses regardless of likelihood, what additional history/exam/labs would distinguish, red flags requiring immediate workup. I'll integrate with my clinical judgment — this is brainstorm support, not diagnosis.
Pro tip: Use as a "what am I missing?" check, not as primary reasoning. Bias correction tool — catches the obvious diagnosis you anchored away from. Always your call.
Discharge Summary Draft
3/16✨ What it does
Claude drafts a discharge summary from [Paste hospital course notes]: admission diagnosis, course, procedures, consults, condition, meds, follow-up, education, and a patient-readable recap. Reconcile the meds before you send it.
[Paste hospital course notes]. Draft a discharge summary: admission diagnosis, hospital course (chronological, key events), procedures, consultations, condition at discharge, discharge medications (with reconciliation), follow-up plan, patient education provided, pending results. Patient-readable summary at end.
Pro tip: Patient-readable summary at the end is what families actually read. Medical-grade body for the chart; plain-English summary for the human. Both matter.
Procedure Note Template
4/16✨ What it does
Claude builds a procedure-note template for [procedure name] with indication, consent, time-out, anesthesia, technique, findings, complications, specimens, blood loss, condition, plan, and attending presence. Fill every [bracketed prompts] from your case.
Procedure note for [procedure name]. Output template: indication, consent obtained, time-out completed, anesthesia, technique step-by-step, findings, complications (none / list), specimens, estimated blood loss, condition at end, post-procedure plan, attending presence. Fill placeholders with [bracketed prompts].
Pro tip: Templates with bracketed prompts > free-text. Forces every required element. Audits don't care about your prose; they check elements documented.
XML tags are just the start. Learn the full Claude workflow.
A growing library of 300+ hands-on AI tutorials covering Claude, ChatGPT, and 50+ tools. New tutorials added every week.
Patient Communication
4 promptsPatient-Friendly Diagnosis Explanation
5/16✨ What it does
Claude explains [diagnosis] at [reading level / education level] with an analogy, why you think they have it, what it means, the plan, and common questions, in everyday words. Read it aloud and adjust anything that does not match their case.
Explain [diagnosis] to a patient at [reading level / education level]. Output: what it is (analogy), why we think they have it, what it means for their life, what we'll do, common questions. Avoid jargon entirely. Use specific everyday words. Tone: serious but not scary.
Pro tip: Patient at 6th-grade reading level handles 6th-grade vocabulary about complex conditions. Don't equate vocabulary with intelligence — they're scared, not stupid. Plain words = better understanding + retention.
After-Visit Summary
6/16✨ What it does
Claude writes a one-page after-visit summary for diagnoses [list] and plan [list]: what you discussed, numbered home steps, warning signs, next visit, questions, and prescription wording. Print or portal it after you check the instructions.
Patient-readable after-visit summary. Diagnoses today: [list]. Plan: [list]. Output: what we discussed (plain English), what to do at home (numbered, specific), warning signs (call back if), next appointment, questions to bring next time, prescription instructions in patient terms. Under 1 page.
Pro tip: Patients forget 50% of what you said by the time they hit the parking lot. Written summary = compliance jumps. Make warning signs visually distinct (bold, separate section).
Difficult News Conversation Script
7/16✨ What it does
Claude writes a SPIKES-aligned script for [difficult news]: setting, perception, invitation, knowledge in chunks, emotion, strategy, plus pause points. Use the pauses in your conversation; do not rush the news.
Help me prepare to deliver [difficult news] to a patient. Output: SPIKES protocol-aligned script — Setting prep, Perception check, Invitation, Knowledge sharing (warning shot then info in chunks), Emotion response, Strategy + summary. Specific words. Where to pause for patient response.
Pro tip: SPIKES is taught for a reason. The "warning shot" + chunked info pattern lets the patient process. Dumping everything at once = patient hears word 1 and goes deaf for the rest.
Patient Email Response
8/16✨ What it does
Claude drafts a portal reply to [paste message] that answers the concern, names what email can and cannot do, and suggests a visit when an exam is needed. Send it only after you would stand behind the advice.
Patient sent: [paste message]. Draft a clinically appropriate response. Address their concern, set expectations on what email is for vs what needs a visit, document plan. Tone: warm but boundaried. Avoid promises or definitive remote advice for issues needing exam. Suggest visit if appropriate.
Pro tip: Email = communication, not consultation. Patients sometimes describe emergencies in casual emails. Draft response should triage — does this need a visit, ER, or just info?
Literature + Decision Support
4 promptsLiterature Quick Review
9/16✨ What it does
Claude critiques [Paste abstract or full paper] for practice: design, whether the population matches yours, absolute effect, guidelines, and whether you would change care. Decide yourself; the critique is input, not a protocol.
[Paste abstract or full paper]. Critique this study for clinical practice integration. Output: study design strengths/weaknesses, population (does it match my patients?), effect size in absolute terms (NNT), conflicts of interest, where this fits with current guidelines, would I change practice based on this? Honest take.
Pro tip: Effect size in absolute terms (NNT) > relative risk reduction. RRR misleads. NNT tells you how many patients you'd treat to benefit one. Often unimpressive when stated honestly.
Guideline Reconciliation
10/16✨ What it does
Claude compares [Paste guideline A] and [paste guideline B] on [clinical question]: where they agree, why they differ, and what to weigh when they conflict. Apply it to your patient; do not treat the write-up as the order.
Two guidelines say different things about [clinical question]. [Paste guideline A] vs [paste guideline B]. Output: where they agree, where they diverge + why (different evidence base, different risk tolerance, different population), what to do when they conflict, my judgment factors. Don't just pick one — illuminate.
Pro tip: Different specialties weight evidence differently. AHA vs ACC vs ACP often diverge. Knowing WHY they diverge = clinical judgment. Picking the one that matches your specialty's preference = lazy.
Drug Interaction Brainstorm
11/16✨ What it does
Claude brainstorms interactions for meds [list] plus new [drug], including kinetic and dynamic risks and factors [age, renal, hepatic], and tells you to verify. Check the pharmacy database before you prescribe.
Patient med list: [list]. New rx considering: [drug]. Brainstorm interactions: pharmacokinetic (CYP, renal, hepatic), pharmacodynamic (additive effects, antagonism), specific ones to verify in pharmacy database before prescribing. Patient-specific factors: [age, renal, hepatic]. Always verify against database.
Pro tip: Brainstorm tool, not source of truth. Use Claude to surface candidates ("what could I be missing?") then verify in Lexicomp/Epocrates. Hallucinated interactions exist; verification non-negotiable.
Risk Stratification Helper
12/16✨ What it does
Claude risk-stratifies for [condition/procedure] using [details]: which validated tools apply, inputs to confirm, risk band, what would change management, and tool limits. Confirm the inputs, then decide with your patient.
Risk stratify this patient for [condition/procedure]. Patient: [details]. Output: validated risk tools applicable (mention which), input variables I need to confirm, estimated risk band, what changes management, where the tool's limitations matter for this patient. Frame for clinical decision-making.
Pro tip: Risk calculators have validated populations. Asian/elderly/pregnant often poorly represented. Tool's output ≠ this patient's actual risk. Knowing the tool's population matters more than knowing the tool exists.
These prompts give you the what. Tutorials give you the why.
Learn when to use extended thinking, how to build Claude Projects, and workflows that compound. 300+ tutorials and growing.
Practice + Workflow
4 promptsInbox Triage Protocol
13/16✨ What it does
Claude builds an inbox triage protocol for volume [#/day] and staff [describe]: what the MA can close, what nursing reviews, what is yours, escalation, and response times. Train your staff on the rules and adjust after a week.
Build an inbox triage protocol for my practice. Volume: [#/day]. Staff support: [describe]. Output: messages MA can resolve, messages requiring nurse review, messages requiring me, escalation criteria, response time targets per category. Specific rules — not vague guidance.
Pro tip: Untriaged inbox = physician burnout fuel. Specific rules ("MA handles X, escalates if Y") = staff actually act. Vague rules = everything ends up on physician.
Pre-Visit Planning
14/16✨ What it does
Claude preps tomorrow from [paste schedule with chief complaints]: what to review, pending results, refills, overdue screening, and 5-10 minute efficiency moves. Glance the list the night before your clinic, not for half an hour.
Pre-visit prep for tomorrow's schedule: [paste schedule with chief complaints]. For each patient: what to review beforehand, likely workflow (results pending, refills due, screening overdue), efficiency moves (combine visits, hand off to MA, prep orders). 5-10 min total prep — not 30.
Pro tip: Pre-visit prep saves more time than it takes. 5 minutes the night before = 15 minutes per visit reclaimed. Not prepping = reactive scrambling all day.
Coding + Documentation Audit
15/16✨ What it does
Claude audits [Paste de-identified note] for E/M support, missing elements, risk justification, and time documentation if you bill by time. Fix documentation gaps; this is a compliance check, not advice to code up.
[Paste de-identified note]. Audit for E/M coding: which level does the documentation support, which elements are missing for higher level (if appropriate), what risk-of-complication justification is in the note, is the time documented if billing time-based. Compliance check, not coding-up advice.
Pro tip: Down-coding from missed documentation is the silent revenue loss. Regular self-audit = catch the patterns. Don't code up beyond what's documented; document up to what you actually did.
Burnout Check-In
16/16✨ What it does
Claude walks a burnout check-in: exhaustion, cynicism, accomplishment, sleep, exercise, vacation, and life outside work, then reflects the pattern. Answer honestly and act on one of your numbers that is off.
Walk me through a self check-in on burnout. Ask sequentially: emotional exhaustion (1-10), depersonalization (do I feel cynical about patients?), personal accomplishment (do I feel effective?), sleep, exercise, last vacation, last social connection outside work. Reflect what I share — pattern, not just data.
Pro tip: Maslach Burnout Inventory dimensions matter. Exhaustion alone is normal; exhaustion + cynicism + low accomplishment = burnout. Naming the specific dimension = pointed intervention.
Free tool
Prompt Optimizer
Turn a rough idea into a structured, professional AI prompt.
Frequently Asked Questions
Prompts are the starting line. Tutorials are the finish.
A growing library of 300+ hands-on tutorials on ChatGPT, Claude, Midjourney, and 50+ AI tools. New tutorials added every week.
7-day free trial. Cancel anytime.