The method: how The Learning Harness teaches

The rules the harness runs, in the order a learner meets them, and the evidence behind each one.

By Ojasvi YadavPublished 12 September 2026

One record for each learner

The harness keeps everything it knows about you in one database inside your study folder. The record holds the concepts you have, the answers you gave when it placed you, the topics on your path and their order, every quiz and explain-back with its result, the questions you asked while learning, and the cards it wrote. Every lesson, quiz and grade reads from that record and writes back to it. Nothing depends on a chat transcript, so a new session opens exactly where the last one ended, and a lesson written next month is pitched at what you know next month.

This is the property a chat window lacks and the reason the harness is an app rather than a prompt. The four rules that follow only work when the AI can remember what happened yesterday. How to learn properly with AI gives the reasoning.

Step 1. It asks what you know

Before the first lesson of a topic, the harness lists the concepts that lesson will lean on and asks about them, one at a time. Three broad questions come first, because three is enough to place you without fatigue. Only if real gaps remain does it ask a second round of up to six targeted questions, each aimed at the exact uncertainty the first three exposed. The questions ask what you know and in which vocabulary; they never hint at an answer and never turn into a test.

Every answer is stored against the concept it concerns. Later lessons, the lesson reviewer, and the quiz all inherit the same prior, so you are asked once.

Step 2. Follow one ordered path to the smallest next step

Every topic sits on one ordered path. Two rules decide the order. The hard rule is that the harness teaches nothing before its prerequisites, because a lesson with a missing prerequisite cannot be taught. The soft rule is that among the teachable lessons, the next one is the smallest step from what you already know.

What you want to learn falls into one of three cases, and the path handles each. Some of it is already inside what you know, and the lesson connects concepts you have. Some of it is one or two concepts away, and the lesson teaches those first. Some of it is far off, and the harness builds a short course in order over several days, each lesson the smallest step from the last.

Step 3. Read a reviewed lesson written for you

The harness writes each lesson as a self-contained page for one reader. It fetches sources for the lesson and cites them. It uses the prior from Step 1, carries one worked example through every part, draws a diagram wherever a mechanism has parts, and uses the field's own terminology so that later reading in the field feels familiar. It renders the page and looks at it before it hands it over, because a diagram that overlaps its labels teaches nothing.

A second AI pass then reviews the lesson against the sources, the prior, and the workspace's prose rules, and fixes what it finds. Only the reviewed page reaches you. A randomized trial at Harvard found that an AI tutor built around teaching practices produced more than double the learning gains of an active-learning class, in less time (Kestin and colleagues, 2025); the lesson rules above are the harness's version of those practices.

Step 4. A quiz the same day

The quiz starts after you say you have finished reading, never in the same message as the lesson. It is multiple choice, one question at a time, with the right option in a random position and no hints. A multiple-choice pass measures recognition, so the harness treats it as provisional: it records the result per concept and moves the concept on to the explain-back, which is where recall is proven. Practice testing is one of the two techniques rated high utility in the largest review of learning techniques (Dunlosky and colleagues, 2013), and a same-day test raised one-week retention above rereading in Roediger and Karpicke (2006).

A passed quiz moves the concept to "currently learning" and schedules the explain-back for the next day. A reminder arrives the next morning if you have reminders switched on.

Step 5. Explain it back after sleep on the next day

The next day, with the lesson closed, you explain each concept in your own words and the harness grades the explanation against the lesson. It marks the mechanism, not the vocabulary. The delay is deliberate. After five minutes, restudying beats testing. After two days the order reverses, so a same-day test cannot tell short-term memory from learning. A night of sleep consolidates declarative memory (Diekelmann and Born, 2010), and the next-day test measures what survived it.

A concept that fails the explain-back is re-taught on the spot, at the exact gap, and explained again the next day, every day until it passes. It is never marked understood on the strength of the same-day quiz alone. The full protocol, with a prompt for people who use a general chat model, is in the Feynman technique with AI.

Step 6. Add spaced-repetition cards across concepts

Once a concept passes both tests, the harness writes two to four cards for it: the definition, the trap, one mechanism or number, plus one card for every question you asked while learning it. Each card asks one question with one gradable answer, in the field's official terms, and stands alone. Cards for a question you asked keep your own wording on the front, because the question you actually had is the best prompt for the answer that resolved it.

The harness orders its queue of unseen cards so that each day covers several concepts instead of many cards from one, and it paces new material so that daily reviews stay near 50 cards. From then on it reads the review history, the intervals and lapses of each card, as the measure of retention. It uses that history when it judges later quizzes. Distributed practice is the second high-utility technique in Dunlosky's review, and spaced study beat massed study at every interval in Cepeda and colleagues (2006). The card rules are in spaced repetition with AI.

What the harness refuses to do

It will not give you the answer during an exercise; it gives hints in steps and grades the attempt. It will not quiz you in the same message as the lesson. It will not write a card for a concept that has not passed both tests. It will not teach a topic before its prerequisites, and it will not mark a concept understood because you say you know it. A claim of prior knowledge earns a short verification quiz, and the explain-back still follows. Each refusal removes a shortcut that makes a concept look learned when it is not. The field experiment by Bastani and colleagues (2025) measured what the first refusal is worth: a hint-only AI removed a 17% exam loss caused by an AI that handed over answers.

What it runs on

The Learning Harness is a native macOS app. It keeps your next step, lessons, chat, roadmaps, progress, topics, and card reviews in one interface. A lesson stays open beside Chat, and the built-in flashcards use spaced repetition to manage your daily reviews. Your flashcards stay on this Mac. The app is in a closed beta; the FAQ has the current requirements.

Sources

1. Kestin, G., Miller, K., Klales, A., Milbourne, T., & Ponti, G. (2025). AI tutoring outperforms in-class active learning. Scientific Reports, 15, 17458. https://doi.org/10.1038/s41598-025-97652-6
2. Dunlosky, J., Rawson, K. A., Marsh, E. J., Nathan, M. J., & Willingham, D. T. (2013). Improving Students' Learning With Effective Learning Techniques. Psychological Science in the Public Interest, 14(1), 4–58. https://doi.org/10.1177/1529100612453266
3. Roediger, H. L., & Karpicke, J. D. (2006). Test-Enhanced Learning: Taking Memory Tests Improves Long-Term Retention. Psychological Science, 17(3), 249–255. https://doi.org/10.1111/j.1467-9280.2006.01693.x
4. Diekelmann, S., & Born, J. (2010). The memory function of sleep. Nature Reviews Neuroscience, 11, 114–126. https://doi.org/10.1038/nrn2762
5. Cepeda, N. J., Pashler, H., Vul, E., Wixted, J. T., & Rohrer, D. (2006). Distributed practice in verbal recall tasks: A review and quantitative synthesis. Psychological Bulletin, 132(3), 354–380. https://doi.org/10.1037/0033-2909.132.3.354
6. Bastani, H., Bastani, O., Sungu, A., Ge, H., Kabakcı, Ö., & Mariman, R. (2025). Generative AI without guardrails can harm learning. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.2422633122