LearnOS turns learner interactions into evidence, evidence into an evolving learner model, and learner state into the next best learning experience.
The unit of intelligence is a decision loop: what do we know, what evidence supports it, and what should happen next?
Strong at delivery, administration and reporting. Usually weaker at representing why a learner succeeded, failed, forgot, transferred or became independent.
The platform continuously closes the loop. Each response can change the system's belief and its next action.
The intelligence layer is separated from content delivery. Each engine has explicit inputs, outputs and state changes.
Aarav is in Grade 3. Goal: understand multiplication and use it confidently in unfamiliar situations.
The system does not label Aarav “weak at multiplication”. It keeps competing explanations alive until the next evidence separates them.
A response is not a conclusion. LearnOS captures the event, validates it, links it to knowledge and estimates what the event can legitimately support.
Architecture note: xAPI uses structured statements for learning events and an LRS for storing and sharing records; profiles can constrain event vocabularies and contextual models can roll raw activity into meaningful learner states.
“Mastered” is not one number. A learner can understand an idea but retrieve it slowly, solve familiar tasks but fail transfer, or perform correctly while being poorly calibrated.
How well the learner can perform the target knowledge or skill.
How strong the system's belief is, based on evidence quality and consistency.
How likely performance is to survive time and spacing.
Whether the learner can use the knowledge beyond the practiced surface form.
What the system does not yet know — and therefore what it should test next.
This is the level of explanation the product should expose to teachers, designers and engineers.
4 × 3 is tagged to multiplication facts and equal-groups meaning.
Response, time, retries and interaction context become an event.
Error is linked to the knowledge unit; evidence quality and hypotheses are stored.
A high-information diagnostic is selected instead of generic extra worksheets.
Retrieval uncertainty changes; intervention and future schedule change too.
It chooses an intervention from the learner's current state, not simply the next item in a content sequence.
Meaning: strong
Fact retrieval: uncertain
Transfer: developing
Confidence: moderate
Concrete groups · array · retrieval probe · worked example · mixed transfer problem
Array → prediction → map array to 4 × 3 → immediate retry → capture evidence.
AI does not decide what learning means. LearnOS supplies the blueprint and validates the generated experience.
The intelligence layer does not replace the operational layer. Identity, enrolment, courses, content, assessment, communication and administration remain essential.
Accounts, roles, guardians, organisations, consent, permissions and session security.
Classes, cohorts, schedules, curriculum mapping, assignments and progress.
Lessons, media, question banks, knowledge links, versions and localisation.
Submissions, scoring, rubrics, grading policies and records.
Evidence, learner model, diagnostics, pedagogy, mastery, retention and transfer.
Notifications, reminders, teacher feedback, parent communication and alerts.
Learner, class, school and platform views with traceable explanations.
Tenancy, billing, integrations, audit logs, governance and operational controls.
Aarav sees a clear task. The teacher sees the evidence and the reason for the next action. Engineers can inspect the trace underneath.
Teacher can accept, adjust, add an observation or override. Human input becomes evidence too.
A scaffold that remains forever can create dependence. LearnOS measures what happened after help, not just the final answer.
“What do the four groups represent?”
“Try drawing the four groups.”
Show one group and ask Aarav to complete the rest.
Explain why 4 groups of 3 maps to 4 × 3.
New surface form with no support. Stronger evidence.
The system tests whether learning survives time, changes context and becomes increasingly self-directed.
The system surfaces what matters, why it believes it, what it recommends and where uncertainty remains.
Teacher adds classroom evidence the digital system cannot see.
System presents evidence and hypotheses rather than pretending certainty.
Teacher accepts, modifies or overrides a recommendation.
Intervention outcomes feed the platform learning loop.
One learner loop operates inside a second loop that evaluates interventions across cohorts, with privacy and governance controls.
A pilot does not need Kubernetes, a private foundation model or a giant content library. It needs clean contracts between learning engines.
The architecture is a dependency graph, not a checklist. A learner model cannot be trustworthy if knowledge units, evidence contracts and event capture are undefined.
Planning ranges, not vendor quotes. The major cost is not only software; it is building and validating the learning intelligence.
Not a bigger content catalogue. Not just a chatbot. A learning system that observes, reasons, acts, measures and learns.