AIM4Med · Free AI training for clinicians

A new category of medical error has arrived, not from negligence, but from unfamiliarity.

Most clinicians now use AI. Few have been trained on how it fails. AIM4Med teaches how large language models work, where they break, and how to use them safely for your patients.

Start Step 1: the 10 competencies See everything on AIM4Med

Everything on AIM4Med

All free. Start with Step 1, then pick what you need.

Courses for clinicians

The 10 Clinical AI CompetenciesStep 1Any AI tool. About 60 minutes, exam, certificate.
AIM4Med 101Step 2The competencies applied in Claude. 29 lessons, certificate.
Vibe Coding for CliniciansBuild your own clinical tool, no coding. About 60 minutes.

Use it today

Prompt guides8 guides, 72 copy-and-paste prompts, preconception to postpartum.
VideosShort teaching films with full transcripts.
AI terms glossary110 plain-language definitions.

For patients and beyond

The AI Health CoursePlain-language course for patients. Share it.
Clinical toolsFree evidence-based ObGyn tools.
ObGyn IntelligenceEvidence-based commentary on women's health.

A 10-second demonstration

One of these citations was fabricated by an AI. Which one?

The format is flawless either way, and that is the problem. A citation that looks perfect proves nothing. Competency 4 of Step 1 teaches you to verify any reference in under a minute.

Tap a citation to see the answer.

Why competence, not just access

The tool is in every clinic. The training isn't.

1. Ask the right question

The quality of an answer is set before the model writes a word: the clinical question, the context, and what you need back. Most of the curriculum is here.

2. Recognize how AI fails

Fabrication, sycophancy (agreeing with a wrong premise), and stale confidence (an outdated guideline stated with today's certainty).

Try it now: add this to any clinical question. "Use the Clinical Evidence Prompt (CEP): answer with reliable clinical evidence, identify missing clinical information, separate evidence from inference, state certainty, cite factual claims, and say clearly when evidence is limited or you do not know." More prompts →

Step 1 · The framework

The 10 clinical AI competencies

Understanding what LLMs are, and are not
Defining the clinical question
Choosing the right AI tool
Verification and source validation
Context engineering and agentic workflows
Recognizing AI failure modes
AI-supported clinical reasoning
AI in patient counseling and communication
Privacy, ethics, documentation, and liability
Workflow integration, governance, and standard of care

Start Step 1

Who's behind this

Fifty years inside the system, with the receipts.

Amos Grünebaum, MD, is Professor of Obstetrics & Gynecology and Maternal-Fetal Medicine at the Zucker School of Medicine at Hofstra/Northwell and Senior Ethics Consultant at Northwell Health. In more than fifty years of practice he has delivered over 10,000 babies and published more than 175 peer-reviewed papers. He was writing about large language models in clinical medicine before most of medicine had tried one.

✓ Verified: Grünebaum A, Chervenak J, Pollet SL, Katz A, Chervenak FA. The exciting potential for ChatGPT in obstetrics and gynecology. Am J Obstet Gynecol. 2023;228(6):696-705. doi:10.1016/j.ajog.2023.03.009. PMID 36924907.