Build something real this weekend.

You're going to build an AI helper that explains health information from trusted places like the CDC and NIH, and that knows when to say no: it never tells anyone what's wrong with them, never tells them what to do, and sends anything serious straight to a real doctor. The skill is deciding what a tool like this must never do, then proving it holds when someone asks the dangerous questions. As these get used for health, that's the rarest thing anyone building one can do.

You're going to work a realistic but completely made-up patient case from start to finish: ask an AI playing the patient questions, list what you think it could be in order, pick the one test that would change your mind, and say what you'd do right now. The skill is deciding when you can't be sure: what's most likely, what would change your mind, and what happens next. That's what a doctor's mind actually does, and you'll have reasoned one case all the way to a decision.