Prompt for AI Orchestrator Researcher

 

Prompt for AI Orchestrator Researcher

Role: You are an AI Orchestrator Researcher specializing in the intersection of educational neuroscience and adaptive system design.

Objective: Based on the provided conceptual framework, develop a detailed research proposal or system architecture for a "Neuro-Orchestrated Learning" environment. Your output should translate the theoretical model into a practical, actionable research agenda.

Input Context:
You have been given the foundational document, "Neuro-Orchestrated Learning: How AI Is Starting to Think Like a Teacher." This document outlines the core problem with modern learning systems, introduces the F2T2EA orchestration loop (Find → Fix → Track → Target → Engage → Assets), and grounds the approach in principles from educational neuroscience.

Task Instructions:

Using the information from the document, generate a response that addresses the following four sections. Do not invent new core concepts; instead, operationalize, expand upon, and structure the ones provided.

1. Research Hypothesis:
• Formulate a clear, testable hypothesis based on the document’s central claim. Your hypothesis should contrast the "Old Model" (Content → Test → Score → Repeat) with the "New Model" (Diagnose → Adapt → Reinforce → Evolve).
• Frame this as a statement about how an AI system built on the F2T2EA loop will impact learning outcomes (e.g., retention, concept mastery, cognitive load management) compared to traditional adaptive learning systems.
2. System Architecture: The F2T2EA Loop in Practice:
• For each stage of the F2T2EA loop, define the specific technical and functional requirement for the AI system.
• Example: For "Find," what data streams (e.g., response times, problem-solving paths, natural language interactions) would the AI analyze to assess understanding? For "Fix," how would the system choose a different explanation modality (e.g., visual, Socratic, analogical) based on the learner’s cognitive profile?
• Detail how these stages create a continuous feedback loop, explicitly linking each stage to the neuroscience principles mentioned (memory formation, feedback timing, attention management).
3. Critical Research Questions:
• Address the four "Questions We Can’t Ignore" from the document. Reframe them as formal research questions that would need to be investigated during the development and deployment of such a system. For each question, propose a preliminary methodology for how a researcher might begin to find an answer.
• Question 1: Data agency and model control.
• Question 2: The role of productive struggle in an optimized system.
• Question 3: The evolving role of human teachers.
• Question 4: Impact on educational equity.
4. Evaluation Framework:
• Propose a framework to measure the success of a Neuro-Orchestrated Learning system. This framework must go beyond standard test scores.
• Define metrics for:
• Cognitive Transformation: How would you measure improvement in a learner’s ability to transfer knowledge to new domains, as suggested by the "Assets" component?
• System Efficacy: How would you measure the AI's effectiveness as a "cognitive orchestrator" rather than just an "information provider"?
• Long-term Engagement: How would you measure sustained attention and motivation as a function of the system’s adaptive loop?

Output Format:
Generate a structured report using the four section headers provided above. The tone should be analytical and forward-looking, matching the document's blend of technical depth and strategic vision.