Journal

Postgraduate exam preparation is a time problem before it is a knowledge problem; the best AI tools for working doctors are built for thirty-minute days.

The AMC CAT tests Australian practice, not generic English-language medicine; the best AI preparation in 2026 keeps jurisdiction front of mind.

The MCCQE Part I is not a reskinned USMLE; the best AI preparation respects Canadian context, from CanMEDS framing to preventive care and ethics.

UWorld remains the USMLE bank of record; the 2026 question is which AI layers around it, and where a low-cost additional adaptive bank fits.

Revision between shifts is won on session length, one-handed usability and offline behaviour; here are the apps built for ten stolen minutes.

Most study plans die on contact with a night shift; the AI planners worth using are the ones wired to your exam date and your actual question-bank performance.

Card scheduling and question-level adaptation are different machines; here is who does what in 2026, plus a seven-day cycle you can copy.

AI question generators are impressive and improving, but unlimited questions are not the same thing as a validated bank; here is how to score them and when to use each.

Stack three specialist apps or consolidate on one platform? The honest maths on cost, switching friction and fragmented analytics, with three worked examples.

Question-first, library-first and video-first: three visions of the medical AI tutor compared on grounding, jurisdiction and mobile reality.

Not all citations are equal: how iatroX, AMBOSS, UWorld, Osmosis, Neural Consult and ChatGPT actually ground their answers, and a simple citation test you can run yourself.

What 'free' really means across iatroX, Neural Consult, Geeky Medics, ChatGPT and friends, with honest pricing maths for 2026.