About this curriculum

This site is a hands-on AI curriculum for Stanford Internal Medicine residents and fellows. It pairs short explainers with practice you actually do — comparing model outputs, iterating prompts with feedback, red-teaming for failure modes, adopting skill-preserving habits, and using AI as a research tool.

Course directors: Kevin Keet, MD (Hospitalist · APD); Poonam Hosamani, MD (Hospitalist · APD).

Why this exists. A 2025 Stanford IM needs assessment found 91% of residents had used at least one AI tool clinically, but mean self-rated AI competence was 2.6 / 5. Existing curricula focus on tool selection and output quality. None train trainees to interact with AI in skill-preserving ways — the gap this site is built to close.

Companion exercise. The H&P error-finding exercise at prompting.actingintern.com is a deeper version of what Module 2 introduces.

Email: kevinkeet@gmail.com.