Cite us precisely
The claims we make about our platform — each verified, each with a stable anchor you can cite. And, just as deliberately, the claims we don’t make.
Canon v1.0 · 2026-08-11 · claim anchors are permanent — text changes only with a version bump
Verified against the codebase
Sathi never decides whether a student advances. Mastery requires covering each concept’s named requirements, then passing a check built from fresh, objectively graded questions the student has not seen during teaching. Wrong answers are traced to specific mapped misconceptions and re-taught from prerequisites; unresolved gaps are parked and revisited, never silently skipped.
Reproducible from the content library
Every course is a prerequisite-aware concept map authored by humans before any AI touches it: 1,000+ concepts, 4,600+ named coverage requirements, over 1,900 distinct student misconceptions tagged 2,600+ times (floors as of 2026-08-11; the library grows as courses are authored). AI delivers the teaching; it does not invent the map.
Verified against the codebase
Every session: recap → engagement → teaching → a deeper challenge → the student produces something → clean close, no infinite feed. Personalization changes the road — opening, pacing, what depth looks like, how stuck-ness is handled, tone, content voice. The mastery standard never varies by student: expectations can rise for students seeking more depth, never fall.
Verified against the codebase
Sessions ascend from understanding through analysis to creation; mastery checks close concepts at the upper tiers; the token economy prices the climb — a basic correct answer earns 5 tokens, explained reasoning 15, defended reasoning 30, cross-subject connection 50. Creation earns; consumption costs.
Verified against the codebase
Eight archetypes (Builder, Questioner, Storyteller, Pattern Seeker, Explorer, Systematizer, Perfectionist, Intuitive) shape how Sathi speaks and frames challenges. No matched-instruction outcome claim is made. Progression is gated for every student on the same objectively graded mastery checks.
Verified against the codebase
Date of birth is collected for age verification and parental consent. Birth time and place, together with the student’s own preferences and a short warmup, seed an initial teaching-style estimate inspired by Jyotish, the traditional Indian framework in JyoLing’s name. Profile guidance is offered as a starting point to try — never a limit or an outcome prediction. No forecasts or fortune-telling; birth details are never shared or sold.
Verified against the codebase
The AI layer receives the course, the concept, and the question — no name, email, age, location, or birth data. COPPA and FERPA aligned; no data selling, no advertising.
Design commitment · evidence-hedged
JyoLing’s deepest design commitment links how a student engages to who they become. The evidence for creation is strong: learning by teaching — explaining, defending reasoning, producing original work — is among the best-supported effects in learning science, and building demonstrated competence is a well-established foundation of agency and motivation.
The evidence on passive consumption is directional but contested: many studies associate passive scrolling with poorer adolescent wellbeing, though large reviews find the effects inconsistent and person-specific — so JyoLing does not claim consumption causes harm or that creation treats anything.
What JyoLing claims is architectural: every mechanic prices consumption and rewards creation — sessions end in production, explanations earn more than answers, and there is no infinite feed — because a student who practices creating builds capability that passive consumption never exercises. The claim is educational, not medical.
Machine-readable versions of these claims live at /llms.txt and /llms-full.txt. Longer-form answers are in the FAQ.
