Fact Sheet

The AI-Powered Knowledge Exploring Library

One concept, fifteen ways to explore it. An engine that generates interactive learning explorations, renders them, tracks every interaction as xAPI, and analyzes the behavior — built for modern education and learning research.

15
KE formats
3
format categories
9
LLM providers
15
analysis frameworks
01

Theory

The library rests on the premise that how knowledge is presented changes what a learner does with it. Each design decision maps to an established school of thought in the learning sciences — not to a claimed result.

Representation shapes cognition

The founding idea: a single concept explored as a network, a chronology, or a Socratic question tree engages different cognitive skills. So the same content is offered in 15 formats rather than one.

In the code → config.keFormats defines 15 formats across 3 categories; a matching template renders each.

Cognitive Load Theory

Managing intrinsic and extraneous load lets working memory focus on understanding. Formats that pace and stage information follow directly from this.

In the code → the Progressive Disclosure and Comprehension-Adapted formats reveal material in graded levels.

Dual Coding & Multimedia Learning

Pairing verbal and visual channels gives learners more than one route to meaning. This motivates the visual and multi-representation formats.

In the code → Concept Map, Timeline, Multi-Modal, and Comparison formats present structure visually alongside text.

Active & Inquiry-Based Learning

Constructing understanding through questions and problems, rather than receiving it, drives the pedagogical formats — including lateral (cross-domain) thinking.

In the code → Question-Driven, Problem-Based, Lateral, and Collaborative Team formats.

The Spacing & Testing Effects

Retrieval at increasing intervals strengthens retention. A dedicated format is built around repeated recall rather than re-reading.

In the code → the Spaced Repetition format is card- and recall-based.

Evidence-Centered Learning Analytics

If learning is behavior, it should be observable and analyzable. Every interaction is captured as a standards-based statement and interpreted against a per-format framework.

In the code → interactions become xAPI statements; an AI analyzer reads them with a format-specific behavior framework.

02

Technology

A Node.js/Express application with a deliberately small set of chokepoints: one gateway for models, one data layer, one place that defines the formats. Client code ships with no build step.

Single LLM gateway

Every model call flows through one dispatch(). Switch providers with a single environment variable.

9 providers → OpenAI, Azure, Mistral, DeepSeek, Groq, Ollama, Anthropic, Google Gemini, Cohere. Default gpt-4o.

GCS-only persistence

No SQL database. Every entity — sessions, explorations, analyses, assessments, users — is a JSON object in a Google Cloud Storage bucket, behind one data layer.

Keyed paths → sessions/ questions/ analyses/ assessments/ cache/ users/

xAPI behavior stream

Learner events are translated to xAPI 1.0.3 statements (mapped to ADL verbs) and posted to a Learning Record Store; reads query the LRS by session.

Standards → xAPI 1.0.3, ADL verb vocabulary, LRS-backed.

Schema-constrained generation

Each format carries a precise JSON contract injected into the prompt, so output always matches what its template can render.

One contract per format → in keGenerator, JSON-mode with fence-stripping.

Variant-pool cache

Requests are hashed by content-defining parameters. Explorations accumulate into a pool; once full, requests draw random variants instead of regenerating.

Default pool 20 → SHA-256 config hash at cache/<hash>.json.

OAuth + 3 role tiers

Bearer tokens are verified against an external OAuth gateway and cached; roles gate the admin, teacher, and student surfaces.

Tiers → admin · teacher · student.

How it works

Generate

Configure & create

Pick a format, domain, and concept. The gateway produces schema-valid content; the pool caches variants.

Render

Explore

A per-format template loads the content by id and renders an interactive experience — with an in-context AI assistant.

Track

Record behavior

Clicks, reveals, confidence changes and submissions stream out as xAPI statements to the LRS.

Analyze

Interpret

An AI analyzer reads the statements against the format's behavior framework and returns a learner profile and metrics.

03

Applications

Where it fits, who uses it, and the 15 formats it ships with — grouped by the cognitive category each serves.

Educators & course designers

Turn any concept into a shareable, interactive exploration in one config. Bundle several into an assessment; embed any of them in an LMS by iframe.

Students & self-learners

Try every format live with no sign-in, then learn with an AI assistant that explains both the content and the method being used.

Researchers & analysts

Collect standards-based xAPI behavior at scale and run AI analysis with per-format frameworks — a testbed for how presentation affects learning.

Linear & Sequential
Linear Tabs
AI Interactive Reading
Progressive Disclosure
Comprehension-Adapted
Visual & Network
Concept Map
Timeline
Comparison
Multi-Modal
Hierarchical Drilling
Adaptive & Pedagogical
Question-Driven
Lateral Exploration
Style-Adapted
Problem-Based Learning
Spaced Repetition
Collaborative Team
04

Impacts

What changes for each audience — framed as mechanisms the design produces, not as measured outcomes.

Educators Author-once, serve-many

  • One config becomes a rendered, linkable, embeddable exploration.
  • The variant-pool cache means a whole class can each receive a different variant of the same config without paying to regenerate every one.
  • A format switch is a one-field change — the same concept, re-presented.

Students Meet the concept where you are

  • No-sign-in demos remove the barrier to trying every format.
  • The in-context assistant is grounded in both the content and the KE-method doc, so it can coach the method, not just the answer.
  • Multiple representations give more than one route to the same idea.

Researchers Behavior you can query

  • Every interaction is a portable xAPI statement in a standard LRS — not locked in a private schema.
  • AI analysis reads that stream against a per-format framework, yielding structured profiles and metrics.
  • 15 formats over shared infrastructure make presentation itself the variable.

Integrators Swap-friendly by design

  • One gateway abstracts 9 model providers behind a single env var.
  • The embed API accepts params four ways (query, JSON, base64-JSON, POST) for iframe or server-to-server use.
  • One data layer over GCS keeps state portable and dependency-light.