Scientifically backed adaptive learning

Every topic gets an Elo rating, the system that ranks chess players [1] and a proven model of learners in adaptive education [2]. Each attempt is a game between you and the problem, rated on the same scale as LeetCode's contests.

Your mastery is your expected score on a typical Medium. 77 means you solve one at interview pace with a hint at most: you're at the bar. 95 and up is Mastered. Every result moves your rating by how surprising it was, so the same solve moves a beginner far more than an expert, and a hard problem proves more than an easy one.

Mastery is tracked separately for every topic, so a strong record in arrays never hides a gap in graphs. That gap is exactly what an interviewer finds if it goes unmeasured. A problem can usually be solved more than one way, so we credit the topics your solution actually used, not every topic the problem is tagged with. When your code is accepted, an AI reviewer reads it, identifies which topics it draws on and how heavily, and moves each topic's mastery by its share.

Each attempt's evidence is your time against an interview benchmark, any hints or wrong submissions, and whether the accepted solution hits the optimal time complexity, which the same reviewer checks against the problem's editorial. Finishing always beats giving up. More help never scores higher. Repeating a problem counts once.

Every problem in the bank has its own rating on the same Elo scale as your topics, from real contest results, so even problems at the same official level are ordered from easiest to hardest. Your rating in a topic picks the next problem: the one you're expected to solve well 70% of the time. While a topic is new, Spot aims harder, near 60%, where one result says the most about your level, as adaptive tests do [3]. A handful of problems place you; then the target eases to 70%.

The target is desirable difficulty: practice that is effortful but achievable, which improves long-term learning even though it feels harder in the moment [4]. Research on optimal training finds that learning is fastest when some attempts fail, not when every one succeeds [5]. Spot aims for the point where most attempts succeed and some don't, and the level you pick at sign-up is only a starting point that a few problems correct.

Spreading practice out over time improves retention compared with massing it together [6]. Problems you've solved come back for review at growing intervals, and the ones you solved cleanly wait longest.

Failures come back sooner. Making a mistake and then correcting it is a powerful way to learn [7], so a problem you gave up on returns before one you solved.

Recognizing which technique a problem calls for is often the hardest part of an interview. Flashcards train that skill directly: each card shows a problem statement, and you retrieve the approach and its complexity from memory against a timer, while an AI grader either passes the card or gives you a Socratic nudge. Retrieving an answer from memory strengthens it far more than re-reading it does [8, 9].

Cards follow a spaced schedule: missed cards come back quickly, and cards you know return at growing intervals. In a review of the evidence on common study techniques, practice testing and distributed practice were the two rated highest-utility [10].

Every company gets its own Elo rating, set by how selective it is, and that sets its bar: the mastery at which you solve its typical question at interview pace. Your readiness is how far each topic the company asks has come from scratch to that bar, weighted by how often the topic comes up.

Reach 100% and you're ready for that company, in every topic it asks.