Teaching students prompt literacy

The day before a Secondary 3 history project deadline, a class teacher collects twenty reports and notices seven share the same opening sentence about how Hong Kong's port changed trade patterns, right down to one statistic that does not appear in any government yearbook. When she asks how they did it, someone mutters: "I just asked AI."

Prompt literacy is not about teaching students to ask AI better questions. It is about keeping them thinking while they use it. This lesson follows lesson 10 and covers how students write prompts, verify claims and handle integrity when they operate AI themselves.

---

The one move students know

The problem is often not a plagiarism detector catching a copied paragraph. It is that the student knows exactly one move — paste the question in unchanged, hand the output back unchanged. It has never occurred to him that he could follow up, ask the AI to list figures that need checking, or ask it to flag which claims are uncertain.

Give the same student this instead and the work looks completely different:

Role: you are a discussion partner, not a ghostwriter.
Task: I am writing a Secondary 3 history project on "trade changes in nineteenth-century Hong Kong". List five key figures or events I should verify myself, and two common claims that may not hold up.
Output format: two columns — "items to verify" and "type of source to check (archives, yearbook, academic work)" — then three items under "claims worth doubting".
Constraints: do not write any of my prose. For any figure you are unsure of, write "student to verify" rather than supplying a number.

What he hands in is written in his own sentences, with three checked sources he did not have before. This lesson teaches him to write that kind of prompt.

Three role switches

What an AI gives you depends largely on what you cast it as. Treat it as an answer machine and it produces answers; treat it as a discussion partner, an opponent or a proofreader and it produces questions, counter-examples and suggested edits. Same model — the difference is one role line, which is exactly what the role, task, context, format framework is about. Nobody has ever taught students this.

The second thing students do not know: confidence of tone tells you nothing about reliability. A model predicts one token at a time, and fluency and truth are separate properties. You do not need to explain architecture in class — one failed demonstration does the work. Ask the AI for the clause number of a Hong Kong ordinance or a specific statistic, then have the class look it up on the official site together. Two or three times in ten it will not match. The underlying explanation lives in where hallucination and bias come from.

The third thing is integrity. Students cannot tell "AI helped me think" from "AI wrote it" — not because they are devious but because nobody has ever drawn them a line. So the second half of this lesson is not technique. It is rules.

The goal is not students who use AI better but students who are still thinking while they use it.

A lesson you can run as written

Below is a forty-minute flow. You need a device you can project from and a printed worksheet. If students have no devices for the verification stage, run the AI output in advance, print it, and have them do only the checking.

First five minutes: Run the same project topic through two prompts — "paste the question unchanged" and "discussion partner" — and project both outputs.

Next ten minutes: Groups discuss the differences and write three points. Hold back the "who is doing the thinking" point until the end.

Fifteen minutes on verification: Students use the worksheet prompt to get five claims to check, split up to verify them on named sites, and record hits and misses.

Eight minutes on integrity: Vote on the four scenarios below — allowed, declare, or not allowed — then converge on a panel rule.

Final two minutes: Issue the declaration box and say it goes on every assignment from this week.

Three prompts for the worksheet

Breaking down the project

Print this on the worksheet for students to copy, leaving the bracket blank for their own topic.

Role: you are my research discussion partner, not a ghostwriter.
Task: my project topic is [                    ]. Break this topic down and tell me what I should be verifying myself.
Output:
1. Three sub-questions this topic splits into.
2. Five key facts or figures I need to verify myself, each with the kind of source to check it against (government statistics, academic report, news coverage).
3. Three common claims about this topic and why each might not hold up.
Constraints: do not write any prose or conclusions for me. For any figure you are unsure of, write "student to verify" rather than supplying a number. Do not mention personal details of any real individual.

Checking AI claims

Verification only happens if it is a fixed routine. This prompt lowers the starting cost by having the AI itself list what needs checking.

Role: you are a fact-checking assistant.
Task: below is a passage I am considering citing. List every checkable factual claim it contains.
Output format: list each item — "what the passage claims", "type of claim (year, figure, name, legal clause, quotation)", "where to verify it". After the list, one line naming the claim most likely to be wrong.
Constraints: do not judge whether the content is correct and do not add new information. Your job is only to identify what needs checking. Mark any sentence you cannot classify as "for teacher or student to judge".
[paste the passage to be checked]

Pair this with one simple rule for students: a claim is verified when you find the same sentence or the same figure in the original source. Finding another website that says the same thing does not count.

Organising the AI-use declaration

Declarations must be specific. This prompt helps a student organise what he actually did before copying it into the box.

Role: you are an academic integrity assistant.
Task: I will describe how I used AI on this assignment. Turn it into a clear use declaration.
Output format: one declaration of no more than four sentences covering three things — at which stage I used AI, what I asked it to do, and what I changed or verified myself.
Constraints: do not polish or soften my description; organise only what I actually wrote. Do not add verification steps I did not describe. If what I describe may already exceed what the assignment permits, say so directly and tell me to ask my teacher first.
My description: [                    ]

A declaration that passes looks like this: "At the planning stage I asked AI to list three possible lines of argument and chose one. The trade figures in the essay I looked up myself on the Census and Statistics Department site. I drafted paragraph two myself, then asked AI to point out awkward sentences, and the final wording is my own edit."

Four integrity scenarios

Do not read out the rules. Let students take a position first and they will remember it. Each scenario asks the same question — allowed, declare, or not allowed?

1. Using AI to split my topic into three sub-questions. Most students say allowed, and that is reasonable — this is planning, not content.
2. Using AI to find five figures to verify, which I then check myself. This is the use we want to promote, and it should be declared, because it shaped the direction of the work.
3. Writing a paragraph myself, then asking AI to flag grammar problems which I fix. Usually declare. The line is who wrote the final words, not who read them.
4. Asking AI to write a paragraph and changing a few words. Not allowed. Put one question to the student here: if your teacher asked why you chose this argument, could you answer? If not, the paragraph is not yours.

Afterwards write the class's conclusions as three lines on the wall, and make sure the rest of the panel uses the same three. What students find hardest to accept is different teachers drawing different lines.

Where people go wrong

• Stating the rule without demonstrating it. Students hear "AI makes mistakes" ten times and still believe it, because they have never seen one. Self-check: did this lesson include a live failure where the AI got a checkable fact wrong in front of the class?
• Vague declarations. "AI was used to assist with this assignment" says nothing. Self-check: does the declaration name the stage, the request and the student's own changes? If any of the three is missing, it fails.
• Teaching verification as "ask the AI again". The student asks "is this figure right", the AI says yes, and he considers it checked. Self-check: did you require the student to write down a source URL or document name that is not another AI?

Try it once

Choose the topic for your next project or extended writing assignment. Run the "break down the project" worksheet prompt once (or run it in advance and print the output), then complete the verification stage yourself.

What to do: From the five items the AI lists, verify at least two — one you find in an official or original source, one you cannot find or that does not match what the AI said. Run the fact-checking prompt on one paragraph the AI gave you and see whether it flags the item most likely to be wrong.

What to hand in: A short record — (1) one verified item with its source; (2) one failed or mismatched item with what you found; (3) an AI-use declaration of no more than four sentences describing how you used AI in this exercise.

How you know it worked: You have at least one piece of evidence that AI cannot replace verification, and the declaration is specific enough that someone reading it knows at which stage you used AI, what you asked for, and what you changed yourself.

For how students test the boundary in tutor mode, see scaffolded tutor prompts. For what the school has to do at platform level, see the safety net for student AI use and privacy, bias and copyright ethics.