Tell AI what you are learning and ask it to pose one question at a time. Have it wait for your answer, then give a hint before showing the full solution. Ask for a changed example next so you must apply the idea rather than memorize one answer. Check its feedback against a trustworthy source or teacher because AI can mark a correct answer wrong or explain a wrong answer confidently.
Tell AI what you are learning and give it the source material it should use. Ask for a short pre-test, one question at a time, without immediate answers. After you respond, have it identify the specific gap, offer a hint, and ask you to try again before revealing its explanation.
Finish with a changed scenario and an explanation in your own words. That is more useful than a series of easy questions that only reward recognition. Treat AI's feedback as coaching to inspect, not an infallible grade; verify disputed answers against the source or a teacher.
