AI Tutoring
10 articles in series
Ten essays on building AI tutors that actually teach — answer-suppression and the Socratic move, why pedagogy is a skill and not a bigger model, spaced repetition, feedback without rewriting, assessment loops, grounding against real tools, Bloom’s 2-sigma at scale, and assembling a four-skill tutor stack from the marketplace.
The AI Tutor That Refuses to Give the Answer
The single hardest thing to make an AI tutor do is not answer. Withholding the solution and asking the next guiding question — the Socratic move — is the core design constraint that separates a tutor from an answer key.
AI Tutoring Is a Skills Problem, Not a Model Problem
A smarter base model doesn't automatically make a better tutor. Pedagogy is a behavior you install — a SKILL.md that tells the agent when to question, when to scaffold, when to assess — not something you get from more parameters.
The Assessment Loop: Use AI to Write the Test, Not Take It
Point AI at assessment instead of answers and it becomes a formative-assessment engine — generating quizzes, blueprints, and retrieval practice that reveal what a learner doesn't yet know.
Build Your Tutor Stack: Four Skills, Not Forty
You don't need forty education skills. A working AI tutor is four composable behaviors — question, explain-and-ground, drill, and assess — assembled from the marketplace. Here's the stack.
Explain It Like I'm Twelve: The Analogy Engine and Its Failure Mode
LLMs are extraordinary analogy engines — the core of a good explainer. They're also confidently wrong in ways a novice can't catch. Great AI explanation is analogy plus grounding, never analogy alone.
Feedback Without Rewriting: The Hardest Move in AI Tutoring
An AI that rewrites the student's essay teaches nothing. The skilled move is rubric-based feedback that diagnoses without doing the work — preserving the struggle where the learning actually lives.
Grounding the Tutor: Why an AI Teacher Needs Tools, Not Just Talk
A hallucinating tutor is worse than no tutor — it teaches errors with authority. Grounding a tutor in real tools (a math engine, references, a code runner) is a safety requirement, not a nice-to-have.
Metacognition Is the Real Curriculum
The durable win from an AI tutor isn't the physics answer — it's teaching the learner how to plan, self-test, and manage anxiety. Metacognition, not content, is what compounds.
Spaced Repetition Is the One Ed-Tech Idea That Survived
Most ed-tech fads died. Spaced repetition — testing yourself at widening intervals against the forgetting curve — didn't. Here's why it's the highest-leverage thing to wire an AI tutor into, and the skills that do it.
Bloom's 2-Sigma and the Tutor in the Room
Bloom's 2-sigma problem — that one-on-one tutoring beats classroom instruction by about two standard deviations — was a scaling impossibility for 40 years. Personalized AI tutors are the first plausible answer, with real caveats.