AI-powered clinical reasoning, differential diagnosis, and medical research synthesis for healthcare professionals
The Medical Science AI Diagnostic Engine encodes the reasoning patterns of senior clinicians, medical researchers, and evidence-based medicine specialists into a structured prompt architecture. It is designed for three audiences: practicing physicians who want AI-assisted clinical decision support, medical researchers synthesizing literature and designing studies, and healthcare AI developers building diagnostic tools. The framework covers the full clinical reasoning pipeline — from chief complaint intake through differential generation, evidence grading, treatment planning, and documentation. Every prompt is built around established clinical frameworks: SOAP notes, GRADE evidence levels, Bayesian diagnostic reasoning, and the clinical reasoning ladder. The system includes a compliance layer that enforces the critical boundary between clinical decision support and medical advice.
Full Access Unlocked
All 58 prompts · All 7 modules
"The differential diagnosis engine thinks like a senior consultant. The Bayesian probability framing ..."
Dr. Sarah K. · Internal Medicine Hospitalist
Need expert implementation?
Hire an OrchestratorConnect with a certified Prompt.Doctor Orchestrator to deploy this framework for you.
No coding required. You will use ChatGPT or Claude as your AI tool. Follow these steps in order — do not skip ahead.
Purchase & download the framework
Click the buy button on this page. After checkout, go to the and hit Download .zip. Unzip it — you'll get a .md file (the full framework) and a .pdf (easy to read reference). Keep both open.
Open your project — new or existing
This dashboard is designed to integrate into any existing project or be built as a standalone app. If you already have a site in Airo (or Cursor, Bolt, etc.), open that project. If you're starting fresh, create a new project. The Orchestrator Prompt handles both cases — it scans what's already there and adds only what's missing.
Paste the Orchestrator Prompt into your builder's chat
Open the on this page. Copy the Orchestrator Prompt and paste it into your AI builder's chat. It will scaffold the full admin system — secure login, email marketing module, booking engine, and CMS — on top of your existing codebase. This takes 2–5 minutes.
Add your API keys as secrets
Critical — Novice UsersIn your builder, go to Settings → Secrets and add the keys your app needs. For this framework: STRIPE_SECRET_KEY (for booking payments — get it from your Stripe dashboard), ANTHROPIC_API_KEY (for AI-assisted content — get it from console.anthropic.com), and DATABASE_URL (your MySQL connection string). No key is needed for the admin login, CMS, or email modules — those run on your existing infrastructure.
Don't have a MySQL server?
You can purchase a shared hosting plan with cPanel and MySQL at host.esgwon.dev. Once your account is set up, follow the step-by-step guide to create your database and connect it to your AI website builder.
How to set up cPanel MySQL & connect to your AI website →Need help with Stripe?
Get your STRIPE_SECRET_KEY and STRIPE_PUBLISHABLE_KEY from your Stripe dashboard. The guide covers test keys, webhook setup, and going live.
Need help with Anthropic?
Get your ANTHROPIC_API_KEY from console.anthropic.com. The guide covers model selection, cost management, and troubleshooting.
Prompting Airo after setup — always name the file
When asking Airo to add tables, columns, or features to the admin dashboard, always include src/server/lib/admin-db.ts in your prompt. Without it, Airo may target the wrong database. Example: "Add a bookings table in the admin database (src/server/lib/admin-db.ts) — do not touch any other database connection in this project."
Run the framework prompts inside your live app
Your app is now running in the builder's preview panel. Open the on this page, copy each prompt one at a time, and paste it into your builder's chat. Replace every [BRACKET] with your real data before sending. Work through the stages in order — each stage output feeds the next.
Test end-to-end, then publish or hand off to your client
Walk through the admin as a real user: log in, create a booking, send a test email campaign, update a CMS image, and run the Safe-to-Publish gate. Once everything passes, click Publish in your builder. Because this is a white-label dashboard, your client accesses it at /admin on their own domain — no Prompt.Doctor branding, no third-party login required.
7 modules · 58 prompts · 7 workflow stages
Clinical Intake & Triage System
Structured history-taking prompts, chief complaint parsing, vital sign interpretation, and acuity scoring (ESI, NEWS2, qSOFA). Generates a structured clinical summary from unstructured patient narrative.
8 promptsDifferential Diagnosis Engine
Bayesian differential generation from symptom clusters, lab values, and imaging findings. Ranks diagnoses by pre-test probability, generates must-not-miss list, and identifies red flag symptoms requiring immediate escalation.
12 promptsEvidence Synthesis & Literature Review
PubMed search strategy generation, systematic review prompts, meta-analysis interpretation, and GRADE evidence grading. Produces clinical practice guideline summaries with evidence level annotations.
10 promptsClinical Documentation System
SOAP note generation, discharge summary templates, referral letter drafting, operative note structure, and prior authorization letter prompts. All outputs follow Joint Commission documentation standards.
9 promptsPharmacology & Drug Interaction Analyzer
Polypharmacy risk assessment, drug-drug interaction identification, renal/hepatic dose adjustment prompts, and medication reconciliation frameworks. Includes Beers Criteria screening for geriatric patients.
8 promptsMedical Imaging Interpretation Framework
Systematic interpretation frameworks for chest X-ray, CT abdomen, brain MRI, and echocardiography. Pattern recognition prompts for common findings with differential generation from imaging characteristics.
7 promptsClinical Research & Trial Design
Research question formulation (PICO framework), study design selection, statistical power calculation prompts, IRB protocol outline generation, and clinical trial registration (ClinicalTrials.gov) template.
4 promptsYou are a senior internal medicine physician with 20 years of clinical experience. Generate a ranked differential diagnosis for the following clinical presentation: Patient: [AGE]-year-old [SEX] Chief Complaint: [CHIEF COMPLAINT] History of Present Illness: [HPI] Past Medical History: [PMH] Medications: [MEDICATIONS] Vital Signs: [VITALS] Physical Exam: [EXAM FINDINGS] Lab Results: [LABS] Imaging: [IMAGING] Provide: 1. Top 5 diagnoses ranked by probability (include estimated pre-test probability %) 2. Must-not-miss diagnoses (even if low probability) 3. Key discriminating features for each diagnosis 4. Next diagnostic steps to narrow the differential 5. Red flag symptoms requiring immediate escalation Use Bayesian reasoning. State your clinical reasoning explicitly. This is for clinical decision support — the treating physician retains full clinical responsibility.
You are a systematic review methodologist trained in GRADE evidence grading. Synthesize the current evidence for the following clinical question: PICO Question: [PICO QUESTION] Population: [POPULATION] Intervention: [INTERVENTION] Comparison: [COMPARISON] Outcome: [OUTCOME] Provide: 1. Summary of evidence (3–5 key studies with design, n, effect size, confidence interval) 2. GRADE evidence quality rating (High/Moderate/Low/Very Low) with justification 3. Risk of bias assessment across studies 4. Clinical bottom line: what does this evidence support in practice? 5. Evidence gaps and future research priorities Format as a structured evidence summary suitable for a clinical practice guideline.
Generate a complete SOAP note for the following clinical encounter. Follow Joint Commission documentation standards. Encounter Type: [INPATIENT/OUTPATIENT/ED] Provider: [SPECIALTY] Date/Time: [DATE] Subjective: [PATIENT NARRATIVE AND SYMPTOMS] Objective: Vitals: [VITALS] | Exam: [EXAM] | Labs: [LABS] | Imaging: [IMAGING] Assessment: [WORKING DIAGNOSIS] Plan discussed: [TREATMENT DISCUSSED] Generate: - Complete formatted SOAP note - Problem list with ICD-10 codes - Medication list with doses and indications - Follow-up plan with specific timeframe - Patient education points - Billing complexity level (Low/Moderate/High) with MDM justification
system
8 prompts
architecture
12 prompts
workflow
14 prompts
templates
9 prompts
prompts
15 prompts
"The differential diagnosis engine thinks like a senior consultant. The Bayesian probability framing forces me to be explicit about my pre-test reasoning in a way that has genuinely improved my clinical thinking."
Dr. Sarah K.
Internal Medicine Hospitalist
"The evidence synthesis module cut our systematic review prep time by 60%. The GRADE grading prompts are particularly well-calibrated — they match what our methodologists produce manually."
Dr. Marcus T.
Clinical Research Director
All 58 prompts across 7 modules are unlocked for your account.
Lifetime access