In Part 1 I explained why I built a 13-model BKT architecture instead of the standard single-model approach. In Part 2 I described how I mapped Piaget's cognitive development stages onto that architecture's parameters. But that was still the "engine in the background." In this post I describe how I turned that engine into the BILGE mentor character on the child's screen, the mission system, and classroom-oriented scenarios.

When I started designing the learning engine for AfetAkademi 8-16 — I knew I wanted to use Bayesian Knowledge Tracing. BKT is elegant, interpretable, and grounded in decades of research going back to Corbett & Anderson (1995). "But the more I thought about what I actually needed to model, the more I realized: one model per skill wasn't going to be enough." This is the story of why I ended up with 13.

Traditional disaster drills provide theoretical knowledge but consistently fail to activate the psychomotor speed and decisional agency required under high-stress crisis conditions. This failure leads to the "Knowledge-Action Gap," where individuals experience a paralyzing response during actual seismic events. This article examines an XR-based and AI-driven "Intelligent Disaster Learning Architecture" designed to reprogram human cognition under pressure. Our systemic approach utilizes a Distributed Cognition model to mitigate cognitive overload, operationalized through characters representing Jungian functions of consciousness. At the architecture's core, a Bayesian Knowledge Tracing (BKT) algorithm analyzes learner performance at 60 FPS, distinguishing between momentary slips and genuine knowledge gaps. By moving beyond subjective self-reports, the study utilizes Stealth Assessment to record millisecond latencies and decision-making patterns, providing an evidence-based model for predicting real-world survival performance.