Study Guide
Your notes, turned into a plan you can actually finish.
Layered paper strata lit from below, each layer a week of remembered material.
Upload a syllabus or a pile of notes and get a spaced, retrieval-first study plan that adapts to what you keep getting wrong.
X-ray the interface. See the engineering.
The challenge
Students do not lack material, they lack sequence. Every study app either dumped a flashcard deck or a calendar. Neither told the learner what to do in the next twenty minutes.
Architecture decisions
- 01A scheduling engine built on spaced repetition intervals with a retrieval-first session builder.
- 02Notes stay in one document model; sessions are generated views over that model.
- 03Adaptive difficulty from per-card latency and confidence, not self-report.
Build process
Stack
- Client
- React Native · Expo
- Scheduling
- SM-2 variant, tuned intervals
- Ingest
- PDF & photo extraction pipeline
- Storage
- SQLite local-first, synced
From the codebase
// The session is a view over the notes, never a second copy
buildSession({ notes, due, budget: 22 }) // → 14 cards, hardest firstMeasured results
22m
median session, finished
3.1×
more retrieval reps per week
89%
plan completion in week one
Principles in play
The technical layer holds the challenge, the architecture decisions, the week-by-week build and the numbers. Open it when you want to judge the engineering, not the screenshots.