Learning Copilot
Learning Copilot is a learner-facing AI tutor. It hints, asks, and retrieves a definition, and it stops short of handing over a finished answer.
| A recorded lesson | Learning Copilot | |
|---|---|---|
| Who the lesson is for | Every student hears the same explanation. | The student explores inside a topic the teacher already set. |
| What the student leaves with | The teacher’s explanation, played back. | A sharper question, a revision, or the next step they still have to take. |
| When the answer appears | The video gives it. | The agent withholds it while the student is still doing the work. |
What this agent is for
Learning Copilot holds a goal for a study session, looks at the learner's work, and takes a short sequence of steps: ask, hint, retrieve a definition, or wait. The product of those steps is a better question from the learner, not a completed assignment.
An agent is a poor tutor when every turn ends in the answer. It is a useful tutor when it can tell a reminder from a struggle that should continue, and when it can use a diagram, a spoken explanation, or a worked step without taking the thinking away.
Planning, tools, and restraint
The technical questions are the ones any education agent has to answer. What is the agent allowed to do on this turn? Which tool is appropriate: a hint, a retrieval from course material, or no tool at all? What should it remember about this learner, and what should it forget when the session ends?
Restraint is a design constraint. A copilot that only answers trains students to stop asking. A copilot that helps them sharpen a question trains a skill they can use when the agent is closed.
What it is not
Learning Copilot is not an answer engine with a tutoring costume, and it is not a claim that any one model already does this well. Essays on the learning theory and the technical limits are published in Writing as they are ready. NexEd describes who does this work on the About page.
Writing on this program
- The Mirror in the Machine: Self-Regulated Learning and the Design of AI Tutors
Self-regulated learning theory shapes how AI agents help students plan, monitor, and reflect on their work. By externalizing progress through open learner models, these systems turn metacognition into a visible, actionable process.
- The Scaffolding Problem: How Vygotsky’s Zone of Proximal Development Shapes AI Tutoring
Vygotsky’s Zone of Proximal Development and the instructional principle of scaffolding provide a necessary framework for AI agents that tutor students or assist teachers, ensuring support is calibrated to ability and withdrawn as competence grows.
- Cognitive Load Theory Meets Generative AI: Keeping Learning Within Working Memory
Cognitive load theory explains how working-memory limits shape learning, especially during problem solving. As generative AI enters classrooms, it can reduce unnecessary mental effort or add distraction. The key question is whether AI supports meaningful processing, preserves human oversight, and keeps instruction centered on learning rather than mere output.
- How to use llama.cpp LoRA fine-tuning
llama.cpp LoRA fine-tuning is the task this tutorial walks through. Learn how to use llama.cpp to apply or merge a trained LoRA adapter with a base model, enabling a lightweight assistant to run offline on a standard laptop.