A22

Dependency mapping

Get the prerequisite structure of a topic drawn out, and locate yourself on it before you start.

When to use this: When something feels wrong
Learning impact: Strong change
Learning evidence: Credible with caveats
Where you are with the topic: Building understanding
How often to use it: Build and keep as a habit

When to use it

You are stuck on this week's problem and suspect the real gap is earlier.
You re-read the chapter and still cannot say what is missing.
The idea only makes sense when you can see it, and your notes are all prose.

What to ask AI

Type something like: “I'm about to study …. Before I start: map its dependency structure”.

Ask it to generate material for you to attempt, problems, cues, or a schedule, not finished answers.

Ask it to find gaps in what you wrote, without rewriting the whole explanation for you.

Keep the hard part on your side: you retrieve, attempt, explain, or decide before you ask for help.

How it helps

Cumulative subjects fail cumulatively.

A gap three levels down doesn't announce itself, it produces unpredictable failures at the top that look like difficulty with the current topic.

Students respond by working harder on the current topic, which cannot possibly help.

Mapping in advance converts that from a mystery into a sequence.

It also tells you something a syllabus never does: which topics are load-bearing and which are leaves. A concept that four later things depend on deserves more of your time than one that nothing depends on, and the syllabus gives them equal chapter weight.

How to run it

Name a concrete target for dependency mapping (narrower than a whole chapter).
Use the copyable prompt below, filling in your topic.
Do the cognitive work yourself before you ask AI to continue.
Stop when you can point to what you can now do that you could not do before.

Example exchange

You

I'm about to study eigenvalues. Before I start, map what this topic depends on, not a lesson, just the dependency structure.

Eigenvalues typically rest on matrices and matrix-vector multiplication, determinants or characteristic polynomials, and the idea of a basis. Which of those three would you be least happy to be tested on tomorrow?

You

Determinants. I can compute two-by-two ones, but I don't know what they mean.

Put determinants first on your study path. We won't touch eigenvalues until you can explain what a determinant tells you about a linear system.

Copyable prompt

I'm about to study [TOPIC/MODULE]. Before I start: map its dependency structure
three or four levels down: what rests on what. Mark which nodes are
load-bearing (several things depend on them) and which are leaves. Then give me
one diagnostic question per node so I can mark which I can already do.

The Tell

Here is how you know this method has flipped: every node is load-bearing. Then the map is too coarse, ask for it deeper, and the structure will separate.

In that moment the AI (or the schedule, or the story) did the thinking, and you only recognised a finished product.

Tighten the prompt for dependency mapping so you attempt, decide, or retrieve before anything is handed to you.

Principle evidence

Strength of the underlying learning idea, not a claim about AI products.

The underlying learning idea is rated moderate. Prerequisite / dependency trees are knowledge-structure representations used in curriculum design, knowledge space theory, and intelligent tutoring domain models. Mapping “where I sit” is metacognitive + diagnostic. Principle moderate for the structural idea; AI-built trees can invent false dependencies, speculative delivery.

AI delivery evidence

Whether an AI tutor delivers this method well is a separate question.

The learning principle may be moderate, but that does not prove an AI session delivers it well. Treat AI delivery as speculative unless a study of tutoring with this method is named, and none is claimed here.