CiZen: The Knowledge Topology Engine (KTE)

Mission

CiZen exists to transition education from passive consumption to Active Knowledge Construction.

Traditional educational platforms fail because they treat knowledge as a static sequence of content. The Knowledge Topology Engine (KTE) treats knowledge as a dynamic, interconnected graph. We map individual skill acquisition by identifying the "Structural White Spaces"—the gaps between what a user has studied and what a user has actually demonstrated through project-based work.

The Thesis: "Grounded Insight"

We operate on a simple, verifiable hypothesis: Intelligence is not just the possession of facts; it is the density and quality of the connections between them.

CiZen leverages a Hybrid Graph/Vector/BKT Architecture to ground AI diagnostic feedback in real-world project data. By ingesting project artifacts (code, logs, process notes), we generate a mastery signature that is verifiable, scalable, and—above all—accurate.

Core Architecture

• The Memory Map (Neo4j): Our graph layer that stores nodes (User, Task, Concept, Artifact) and their structural relationships.
• The Context Brain (Vector DB): Our semantic layer that allows the engine to interpret the "meaning" of unstructured project data.
• The Progress Tracker (BKT): Our Bayesian logic layer that treats skill mastery as a probabilistic model, evolving with every task completed.

The Path Forward

We are currently in our Initialization Phase, documenting our research process in public. This repository serves as our "Public Lab Notebook," where we iterate on the ingestion pipelines, schema definitions, and diagnostic prompts that comprise the engine.

Our goal is not just to build software; it is to build a new standard for diagnostic, portfolio-based development.

CiZen: The Knowledge Topology Engine (KTE)

Roadmap

• Phase 1: Foundation (Current)
• Phase 2: Super Journeyman Engine
• Phase 3: Diagnostic Engine (White Space Detector)

Architecture Overview

• The Memory Map (Neo4j): Stores nodes (User, Task, Concept, Artifact) and their relationships.
• The Context Brain (Vector DB): Provides semantic context for project data.
• The Progress Tracker (BKT): Bayesian model for tracking skill mastery.

Latest Research Log

• Day 1: Repo initialized and mission established.