Exam Stress Before UASA: Signs in Your Child and How to Help

Learn Coding

Hafiz Rahman
Coding Curriculum Team, Algonova Malaysia

Prompt writing for kids is the part of AI that survives the next tool change. Chat windows will look different in three years; asking precisely for a method, a constraint and a check will not. A child aged 9 and up can learn the 4-part structure below in one sitting, and it takes about two weeks of small daily use before it becomes automatic.
Role, task, constraint, check. Every prompt worth writing has those four pieces, and children remember them faster than adults do.
| Part | What it does | Example wording |
|---|---|---|
| Role | Sets who is answering | "You are a patient maths teacher" |
| Task | Says what to produce | "Explain how to add fractions" |
| Constraint | Limits the answer | "For a 10 year old, in under 100 words" |
| Check | Forces verification | "Then ask me two questions to test I understood" |
The check is the piece almost everyone skips, and it is the one that turns a chatbot into a study partner. Without it, the child reads an answer. With it, the child has to produce something.
A lazy prompt asks for the answer. A directed prompt asks for the process. Same tool, completely different outcome for the child.
| Lazy | Directed |
|---|---|
| "What is 3/4 plus 2/5?" | "Show me the steps to add 3/4 and 2/5, without the final answer" |
| "Write an essay about recycling" | "Give me three angles for an essay on recycling, then critique my opening line" |
| "Is this right?" | "Do not tell me if it is right. Show me how to check it myself" |
| "Explain photosynthesis" | "Explain photosynthesis to a 9 year old, then quiz me on it" |
Show your child the left column once, then the right column, and ask which one taught them more. Most children pick correctly without being told.

Start with these, in this order. Each one teaches a different move, and together they cover most of what a student needs.
Number seven changes the dynamic completely, because the child has to respond instead of read. Number eight is the one that builds scepticism, which is the habit worth having most.
Younger children need the constraint written for them; older ones write it themselves.
| Age | What they can do | What the adult supplies |
|---|---|---|
| 7 to 8 | Say what they want in one sentence | The role, the constraint and the check |
| 9 to 10 | Use the four parts with a written reminder | Occasional correction |
| 11 to 13 | Write full prompts and refine after a bad answer | Nothing, mostly |
| 14 to 17 | Chain prompts, compare outputs, spot invented sources | Nothing |
The jump between 10 and 11 is noticeable. Before it, children accept the first answer. After it, with practice, they start pushing back and asking for a different explanation, which is exactly the behaviour you want.
Reading the answer critically matters more than writing the prompt. A perfect prompt followed by blind acceptance teaches nothing.
The second last point is a good weekend exercise. Two different answers to the same question, side by side, shows a child that this is a text generator rather than an oracle. Nothing you say achieves that as quickly.
Directing a tool precisely is the same skill as writing a clear brief, and it shows up in every job that exists now. Children who practise it get three things at once:
This is why prompting sits next to coding in our AI classes for kids rather than on its own. Directing software without understanding how software behaves tends to stall at the first unexpected result.
Under 13 there is no personal account, so practise the thinking with tools built for children. The structure transfers even when the interface does not.
The paper version is the best one and costs nothing. Children discover for themselves that "draw a house" produces ten different houses, which is the entire lesson about constraints.

If day six of week two works, the skill has landed. Being able to explain the structure without the card is the honest test, and it takes most children about two weeks of small daily use.
Prompting is a multiplier, not a substitute. A child who does not understand fractions will get a fluent explanation of fractions and still be unable to do the homework, because reading an explanation is not the same as practising. When that gap shows up, the answer is a teacher watching the working, not a better prompt.
Worth reading next: ChatGPT for kids, AI and homework and our coding programme.
Prompt writing is asking an AI tool precisely enough to get something useful back, which turns out to be the same skill as writing a clear brief for a person. It matters for children because it is the part that survives the next tool change. Chat windows will look different in a few years, but stating what you want, setting a constraint and building in a check will still work. There is a second benefit most parents notice before the first: children who practise it get better at saying what they actually mean, which is something plenty of adults do badly.
Four parts: role, task, constraint and check. Role sets who is answering, such as a patient maths teacher. Task says what to produce, such as explain how to add fractions. Constraint limits the answer, for example for a 10 year old in under 100 words. Check forces verification, such as then ask me two questions to test that I understood. The check is the piece almost everyone skips and the one that matters most, because without it the child just reads an answer, and with it the child has to produce something.
Around 9 is the comfortable starting point for the full structure, though younger children can practise the thinking without any AI at all. At 7 or 8, an adult supplies the role, the constraint and the check while the child says what they want. From 9 to 10, children use the four parts with a written reminder nearby. From 11, most write full prompts and refine them after a weak answer. From 14, they chain prompts, compare outputs and start noticing invented sources. Remember the main chat services set 13 as their own minimum age for a personal account.
Use tools built for children, since the structure transfers even when the interface does not. Teachable Machine lets a child define categories, feed examples and watch the model get confused by sloppy input, which is constraint and check in physical form. Scratch teaches the same discipline by making a sprite do exactly what it is told. The cheapest exercise needs no screen at all: one child writes instructions for drawing a shape and another follows them literally. Half of them draw something wrong, and the lesson about vague instructions lands harder than any explanation.
A lazy prompt asks for the answer, a directed prompt asks for the process. Instead of what is three quarters plus two fifths, a directed version asks for the steps without the final answer. Instead of is this right, it asks the tool to show how to check it. Instead of explain photosynthesis, it asks for an explanation aimed at a nine year old followed by a quiz. The tool is identical in both cases; what changes is whether the child ends up with a finished answer or with something they had to work through.
It helps a child get a better explanation faster, which is real but limited. Prompting is a multiplier rather than a substitute. A child who does not understand fractions will receive a fluent explanation of fractions and still be unable to finish the homework, because reading an explanation is not the same as practising one. That distinction is worth saying out loud at home. When the gap keeps appearing on the same topic, better prompts will not close it, and a teacher who watches the working will.
Ask them to teach you the four parts from memory, without the card on the desk. That is the honest test and it usually takes about two weeks of small daily use to pass. Two more signals are worth watching. The first is whether they refine a prompt after a weak answer instead of accepting it, which shows they understand the tool responds to how they ask. The second is whether they check numbers by hand without being reminded, which shows the scepticism has taken hold.
No, and teaching that is more valuable than the prompting itself. Three exercises make the point faster than any lecture. Ask the tool the same question twice in separate chats and compare how the answers differ. Give it a correct sum, insist it is wrong, and watch it apologise and switch to a wrong answer. Ask it for a source and then try to find that source together. Children who do these three once stop treating the output as fact, which is the habit that protects them long after this particular tool is gone.
Not really, which is why we teach it alongside coding rather than as a standalone subject. Directing software without any understanding of how software behaves tends to stall at the first unexpected result, because the child has no model of what went wrong. Coding supplies that model: variables, sequences, conditions and the habit of debugging. A child with both can ask precisely and then judge whether the answer makes sense, and that combination is considerably more useful than either half alone.
Through projects rather than lists of tips. Children build something small, hit a point where the tool gives an unhelpful answer, and learn to restate the request with a clearer constraint. The teacher watches the process rather than the output, which is where the actual correction happens. Prompting sits next to coding in every level, so children learn to direct a tool and to understand what the tool is doing. The free trial class shows within an hour whether your child takes to this way of working.
Blog



Start your child's tech journey
Book your free 60-minute trial class with an Algonova certified tutor. No payment, no obligation, just discover what your child can build.