Use a model responsibly
Using a model responsibly means knowing what it is good at (drafting, explaining, transforming) and what it is unreliable for (facts, arithmetic, anything current).
Your program can now ask an AI model for help. That makes checking the answer your job.
Students call a model from code, request output in a structure their program can actually use, and build in verification — because a confident wrong answer is far more dangerous than an obvious error.
AI-assisted programming is now ordinary professional practice. Doing it responsibly, with checks, is the skill worth having.
Three core ideas, each taught with worked examples and then practised until it feels obvious.
Using a model responsibly means knowing what it is good at (drafting, explaining, transforming) and what it is unreliable for (facts, arithmetic, anything current).
Prompting from code means the prompt becomes part of your program — versioned, tested and consistent, not typed fresh each time.
Evaluating output means checking before using: is it the right shape, within range, and consistent with a source you trust?
Language models are trained to produce plausible text, not true text. Fluency and accuracy are separate properties, which is precisely why they must be checked.
“The AI wrote it, so it works.” Generated code compiles and still gets the logic wrong. You remain responsible for everything you ship.
Sessions 57–64 of the 72-session year, at two one-hour sessions per week.
Where this module fits, what you will build, and a hands-on starter that gets everyone curious about use a model responsibly.
Guided teaching on use a model responsibly, worked through together with the teacher.
Independent practice, small challenges and one deliberate mistake to diagnose.
Guided teaching on prompt from code concept, building directly on the previous two sessions.
Applied tasks that combine use a model responsibly and prompt from code concept in one piece of work.
Evaluate output introduced and practised, completing the toolkit needed for the project.
Guided build session for the module project: AI-assisted study prototype.
Finish, test against the checklist, present the work and explain the decisions behind it.
Every module ends with something the student built themselves and can demonstrate. This is the piece that goes into their portfolio and gets explained out loud at the end of session 64.
Ask a model to write a function, then write your own tests for it before running it. Note whether your tests find anything.
Students finishing Module 8 can:
The vocabulary introduced here, in plain language:
6 quick questions drawn from this module — vocabulary, the project you build, and a myth-or-fact round. Every wrong answer explains itself, so a mistake still teaches you something.
Tell us your child’s class and what they enjoy. We will suggest the closest program fit—no pressure and no upfront payment.