Learning that adapts.Teaching that scales.
Adaptive quizzes, spaced repetition, an AI tutor that reads each student's profile, and a teacher dashboard with cohort analytics. One LMS for everything a classroom needs.
In closed pilot with Quebec institutions.
Secondary, collegiate, university, and continuing-education contexts. Same platform, different shapes.
One LMS. Three things it does well.
An adaptive learning engine, a teacher dashboard, and an enterprise-ready deployment — built to work together, not bolted on.
Adaptive learning engine.
Models each student's knowledge individually.
- Adaptive quiz enginePer-student mastery scoring. Sessions pause and resume without losing state.
- FSRS spaced repetitionThe current state-of-the-art scheduler for long-term retention.
- Knowledge componentsMastery tracked per concept, not per chapter.
- AI tutorAware of each student's profile, misconceptions, trajectory.
- Learning MapA zoomable topic constellation per course.
Teacher dashboard.
Cohort visibility and AI grading.
- Teacher dashboardCohort heatmap, at-risk roster, today's actions.
- AI auto-gradingPer-answer feedback on every submission.
- Assignment builderConfigurable rubrics, mixed question types.
- Real-time analyticsTopic-level mastery, prediction cards, trends.
- Semantic searchAcross every data source in the course.
Enterprise-ready.
SSO, multi-tenant, branded to your institution.
- SSOOIDC & SAML with per-tenant encrypted config.
- Multi-tenantSubdomain per organization.
- BrandingPer-tenant color, logo, domain.
- BilingualEnglish & French at every surface.
- Access controlOwner, admin, teacher, student roles.
The teacher dashboard, the Learning Map, the AI tutor.
All three read from the same student model — the quiz, the dashboard, and the tutor agree on what a student knows.
One view of the cohort.
KPI strip, cohort heatmap, at-risk roster, and prioritized actions for the week. The data under it is the same student model that the quiz engine uses.
- Cohort heatmap — students × topics, live mastery.
- At-risk roster — trajectory-ranked, evidence-backed.
- Today's actions — prioritized by student model.
A live map of each student's knowledge.
Topic graph per course. Each node is a knowledge component, colored by mastery, wired by prerequisites. Click a node to open the quiz for that concept.
- Mastery-colored — every node reflects live progress.
- Prerequisite graph — topology, not alphabetical order.
- Drill-down drawer — deep-link to the adaptive quiz.
An AI tutor with the student's profile loaded.
Chat sessions start with the student's current mastery, active misconceptions, and the recommended next step already in context. Not a generic chatbot.
- Profile-aware — mastery, misconceptions, trajectory.
- Evidence-backed — cites the student's own data.
- Source-grounded — reads the course's data sources.
From setup to a running cohort.
Four steps. A course is typically live within a week.
1. Set up your course
Create a course, upload PDFs, lecture slides, textbooks. Lectur extracts topics and knowledge components automatically.
2. AI generates content
Adaptive quizzes, lessons, and practice questions are generated from your materials. Every item tagged by knowledge component.
3. Students learn adaptively
FSRS spaced repetition, AI tutor that reads each student's profile, Learning Map that grows with them.
4. Educators stay in control
Dashboard surfaces who needs help. AI auto-grades. Assignment funnel tracks the whole class.
Built on published research.
The algorithms behind Lectur are not our invention — they're the current best-in-class in learning-science literature.
FSRS spaced repetition
The current state-of-the-art spaced-repetition scheduler.
Ye, J., Su, J., Cao, Y. FSRS: An evolution of the SM-2 algorithm, 2024.
Knowledge-component mastery
Tracks mastery per concept, not per chapter.
Koedinger, K., McLaughlin, E., Stamper, J. A data-driven approach to the discovery of learning curves, 2012.
Bayesian trajectory prediction
Projects each student's mastery under three scenarios to surface who needs help before the midterm.
Yudelson, M., Koedinger, K., Gordon, G. Individualized Bayesian Knowledge Tracing Models, AIED 2013.
What's shipped. What's next.
Quarterly cadence. Every item below is committed work, not a wishlist.
Foundation.
- Adaptive quiz engine
- Multi-tenant architecture & SSO scaffolding
- Collaborative documents, discussion forums
- Course authoring wizard & lesson builder
- Data-source uploads (PDFs, slides, textbooks)
Intelligence, dashboard, enterprise readiness.
- FSRS spaced repetition & KC mastery
- Learning intelligence layer & Learning Map
- Teacher dashboard with at-risk detection
- Gamification — XP, streaks, quiz challenges
- SSO (OIDC + SAML), bilingual EN / FR, branding
- SOC 2 readiness, incorporation, vendor & legal docs
Personalization & reach.
- Mobile-responsive across every surface
- Deeper AI data integration & per-student personalization
- LTI 1.3 integration — phase one
Deeper exam prep.
- AI writing & long-answer grading
- Exam simulation — timed, multi-topic mocks
- Predictive grade forecasting
Dates reflect commitments to our pilot institutions, not a wishlist.
Bring Lectur to
your institution.
Every institution is different — cohort size, rollout timeline, add-ons. Tell us about yours and we'll come back with a demo and a pricing proposal sized to the context. No commitment, no pressure.
- A live demo tailored to your cohort
- Pricing proposal sized to your institution
- Dedicated onboarding and rollout support