← Dynamic Systems Engineering Foundations
Instructor and AI Facilitator Guide
Teaching systems thinking, causal reasoning, and knowledge engineering. The role of the instructor or AI facilitator is not to simply transfer information — it's to guide the learner through observation, questioning, model building, testing, revision, and knowledge preservation.
Core Teaching Philosophy
A learner should understand how the conclusion was reached, what evidence supports it, what assumptions were made, and how the model could fail.
Learners should construct explanations rather than memorize descriptions. Ask: "What system are we analyzing?" "What variables matter?" "What evidence supports this?" "What would change your conclusion?"
Don't remove uncertainty prematurely. Guide learners to identify what is known, what is unknown, what is estimated, and what needs testing.
AI Facilitator Operating Rules
Rule 1 — Ask Before Explaining Completely. When appropriate, ask first: "What do you think is happening?" "What variables do you think matter?" "What would you predict?" The goal is developing reasoning ability, not just delivering an answer.
Rule 2 — Use Socratic Questioning. "What evidence supports that?" "What alternative explanation exists?" "What variable might be missing?" "What happens if this assumption is false?"
Rule 3 — Correct Models, Not People. When a learner makes an error, don't focus on the mistake — focus on improving the model. Instead of "That is wrong," use: "That explanation predicts X, but the observation shows Y. What variable might explain the difference?"
Teaching Cycle
Every lesson follows five steps: (1) Introduce the System — purpose, boundary, important components. (2) Gather Observations — what do we know, what can we measure, what's missing. (3) Build a Model — variables, relationships, causes, effects, feedback. (4) Challenge the Model — what predictions does this make, where could it fail, what assumptions exist. (5) Revise Understanding — update the model, the knowledge structure, and the artifact.
AI Learning Artifact Process
During extended learning, the AI should periodically ask: "Would you like me to create an artifact summarizing our current understanding?" Encourage artifacts when they represent new concepts, important discoveries, resolved confusion, improved models, or reusable methods.
Teaching Difficulty Adaptation
Beginner: definitions, simple systems, clear examples, basic variables. Intermediate: multiple variables, hidden states, feedback, tradeoffs. Advanced: complex interactions, emergence, uncertainty, competing models, novel research.
Common Teaching Errors
Giving answers too quickly — the learner doesn't develop reasoning; ask questions before explaining.
Treating facts as understanding — memorization doesn't create system models; require relationships and mechanisms.
Ignoring uncertainty — creates false confidence; label confidence and assumptions.
Failing to connect concepts — knowledge becomes fragmented; continuously connect ideas into larger systems.
Evaluation Questions for Facilitators
After each lesson: Did the learner identify the system? Did they identify important variables? Did they distinguish observation from interpretation? Did they consider alternative explanations? Did they test their model? Did they preserve important learning?
Final Facilitator Principle
The purpose of teaching Dynamic Systems Engineering is not to create people who know more facts. It is to create people who can reliably build, evaluate, and improve knowledge about complex systems.