Learning with AI

Your personal tutor, not your autopilot

AI can accelerate your learning like nothing else - or wreck it if it writes everything for you. This track teaches you to turn it into a tutor: effective prompts, Socratic mode, tailored quizzes, guided debugging and critical thinking.

Foundations

Beginner - the basics, step by step

• What is generative AI?Discover what an LLM is, how it is trained, and why it seems to know everything.
• What AI does well… and what it gets wrongLearn to spot hallucinations, outdated knowledge, and the overconfidence of assistants.
• Anatomy of a good promptStructure your requests with the 4 ingredients - context, task, constraints, format - to get genuinely useful answers.
• The copy-paste trapUnderstand why having your code generated destroys learning, and adopt the golden rule: the AI explains, you write.
• Choosing and configuring your assistant wellSurvey the major assistants on the market, protect your data, and set up learning-oriented custom instructions.

Progression

Intermediate - build real things

• Turning the AI into a private tutorWrite a tutor-prompt that forces the AI into a role, strict rules, and adaptation to your level.
• The Socratic method: getting questionedLearn to ask for questions and progressive hints rather than ready-made answers.
• Getting custom quizzes and exercises made for youHave the AI generate multiple-choice quizzes, open questions, and exercises of increasing difficulty with commented corrections.
• Getting a concept or a piece of code explainedUse explanation levels, analogies, and rephrasing to deeply understand a concept or a piece of code.
• Getting your exercises corrected without being handed the answerFrame the AI so it evaluates your work through hints and a grading scale, without ever rewriting your code for you.

Advanced

Proficient - advanced patterns and performance

• Debugging with AI: understand before you fixUse AI to break down an error message and build a diagnostic method, instead of begging for a fix you won't understand.
• AI code review: get critiqued, then defend your choicesTurn the AI into a demanding reviewer on readability, bugs, and security, and sharpen your judgment by defending your choices against its remarks.
• Getting calibrated mini-projects generated for you - without the codeMake the AI a client who writes a spec at your level, with milestones and verifiable success criteria, but never the code.
• Advanced prompting techniques: role, constraints, examples, reasoningCombine an expert role, strong constraints, few-shot examples, step-by-step reasoning, and iteration to get answers that genuinely make you learn.
• Verifying AI answers: documentation, tests, hallucinationsAdopt the three reflexes of the practitioner - cross-check against official documentation, test it yourself, hunt for hallucination signals - before integrating anything.

Mastery

Expert - architecture, internals and edge cases

• Building your AI-driven learning programTurn AI into a personal tutor: honest diagnosis, a week-by-week plan, spaced repetition and measurable tracking of your progress.
• AI on a real project without losing your edgeSet up reasoned pair programming with explicit personal rules and no-go zones so that assistance never turns into dependency.
• Learning by explaining to AI: the Feynman techniqueUse AI as a skeptical student and then as an examiner to pinpoint, to the word, where your understanding breaks.
• Ethics, bias and confidentialityKnow exactly what you send, what generated code is worth legally, and how model biases steer your technical decisions.
• The developer in the AI era: staying critical and employableIdentify the skills that gain value as code generation becomes commonplace, and equip yourself to cultivate them deliberately.