aactingintern·prompting
A self-paced tutorial / ≈ 35 minutes / Internal Medicine

How to actually use AI
in clinical practice.

A short, hands-on tutorial built around a real H&P with 22 deliberate errors — the kind of mistakes a tired intern, or a confident model, will quietly make at 2 a.m.

For residents

You already know how to write an H&P. This teaches you how to supervise a model writing one — what to trust, what to catch, what to throw out.

The arc

Learn, then do, then reflect.

10 min · read

Setup

How LLMs work — tokens, context, hallucination — and how to prompt them like you'd sign out to a colleague.

  • · how-llms-work
  • · prompting
★ The exercise

Audit a real admission H&P.

Find the planted errors. Compare what different models and different prompts catch — and what they miss. 15 minutes of close reading you'll actually remember.

22
errors planted
4
models compared
15m
close reading
10 min · read

Debrief

What just happened, why models fail in predictable ways, and how to choose one for the task in front of you.

  • · failure-modes
  • · choosing-a-model

Most learners skip the reading. Don't — the prompting chapter is what makes the exercise work.

After 35 minutes

You'll leave with three habits, not three tools.

The model landscape will change again next quarter. The way you supervise it shouldn't have to.

01

Frame the task.

Tell the model who it is, who you are, and what counts as a good answer — before you paste anything.

02

Read the output like a chart.

Verify numbers, dates, doses, and pronouns. Treat fluency as suspicious, not reassuring.

03

Pick the right model.

Match latency, reasoning depth, and privacy posture to the clinical question — not to the brand on the tab.