Lit Ladder is an adaptive expert system - not a chatbot. It emulates the moment-to-moment decisions of a skilled tutor - what should this student work on right now? - using a knowledge graph and the cognitive-science learning strategies with the strongest research evidence: mastery learning, spaced repetition, and interleaved practice.
Every topic in the course is a node, connected by weighted prerequisite edges. “Reading Short Words” points back to “Short Vowel Sounds”, which points back to “Letter Sounds”, and so on up through word families, context clues and main idea. The graph is what lets the system reason about your reading instead of just recording scores.
Instead of testing all topics, the diagnostic bisects the graph. Each question targets the topic of median depth among the still-undecided ones. Answer correctly and the topic plus every prerequisite beneath it is marked known; miss it and the topic plus everything built on it is marked unknown. A handful of questions places the whole graph and finds your knowledge frontier.
You only get a lesson when every one of its prerequisites is mastered, and you must score at least 75% on a lesson's practice to master it. No moving on with gaps - gaps are what make later reading feel impossible.
And when you miss a question, the system doesn't just show the answer and move on. It re-teaches the rule with a worked example and immediately hands you a fresh question of the same type to work - active correction, right at the moment of the mistake, before you continue.
Each mastered topic has a repetition number; every successful review raises it and roughly doubles the time until the next review (2 → 4 → 8 → 16 days…). Fail a review and the topic comes back immediately.
Crucially, reading is hierarchical: working out a word from its prefix and suffix is practice of the base word underneath. So when you advance a topic, fractional credit trickles down its prerequisite edges (scaled by each edge's weight), postponing reviews of skills you just practiced implicitly. You never waste time reviewing something you used five minutes ago inside a harder word.
Every time you ask for work, the engine picks the highest-value task:
| Review | Overdue spaced reviews come first - up to three topics interleaved in one task, which is harder but builds far more durable memory than blocked practice. |
| Quiz | After every six lessons, a mixed cumulative check revisits recent material. Each completed unit adds a 12-item quiz, and balanced course assessments appear at 25%, 50%, 75%, and 100% mastery. Missed topics get targeted remediation. |
| Lesson | Otherwise, the next frontier topic - always something you have the prerequisites for, never something you've already shown you know. |
One rung is calibrated to roughly one minute of focused work. You set a daily rung goal; hitting it every day builds a streak. Progress is measured in work completed, not time spent staring at the screen.
Word-level work - phonemic awareness, phonics, morphology, spelling, grammar - is generated from a stated rule of English. Exactly one option satisfies the rule and every distractor breaks it in a named way, so the item is machine-checkable and the supply of fresh practice is unlimited.
Passage work - main idea, inference, theme, structure, author's purpose - is hand-authored. A comprehension question cannot be verified by recomputation the way an arithmetic answer can, so each one is written with a single defensible answer and the reason recorded alongside it. The passages are original, written for this course, and checked against the grade level they claim.
Every early item carries a read-aloud button that uses the browser's own speech synthesiser - no audio files, no network request, no third-party voice service.
This is not a convenience feature. Without it, a listening comprehension question for a five-year-old measures decoding, and the placement report tells a family their child cannot comprehend when in fact they cannot yet decode. Those are different problems with different answers, and the whole product is built on being able to tell them apart.