I built Brightstar for my own daughter. When I show other parents an AI tool that marks children's writing, the first sensible question is always some version of "how much should I trust this?" This page is my honest answer.
What the AI actually does
Brightstar uses Claude, an AI assistant made by Anthropic, for two features. Everything else on the site — the practice questions, the worksheets, the practice tests — involves no AI at all.
1. AI Writing Feedback
Your child writes a response to a prompt. When they submit it, the text is sent to Claude along with instructions to mark it against the ten official NAPLAN criteria. Claude returns a score for each criterion, one piece of specific praise, and one thing to improve. That comes back to your child's screen in a few seconds.
2. AI Reading Comprehension
Your child picks a topic — dinosaurs, netball, quokkas, anything. Claude writes an original passage at a suitable reading level, plus five comprehension questions covering literal, inferential and vocabulary understanding.
What it does well
✓ Genuine strengths
- It's structured against the real criteria. The score ranges are the actual NAPLAN ones — Audience 0–6, Sentence Structure 0–6, Paragraphing 0–2 for narrative and 0–3 for persuasive, totalling 47 or 48. Many tools use a made-up scale.
- It's specific. Feedback quotes your child's own words rather than offering generic advice.
- It's fast. A few seconds instead of a week. Feedback given while the writing is still fresh is far more useful.
- It's consistent about weaknesses. Even when a score varies slightly, the advice on what to improve tends to be stable — and that's the part that helps.
- It never gets tired or impatient. Your child can submit at 8pm on a Sunday without anyone sighing.
What it can't do
This is the part most companies leave out.
✗ Real limitations
- It is not an official assessment. Our scores carry no standing whatsoever. They're practice guidance, nothing more.
- It may differ from a trained marker. Real NAPLAN markers apply detailed descriptors for every score point and go through moderation to keep marking consistent nationally. We can't replicate that. Expect our score to be in the right neighbourhood, not identical.
- It isn't perfectly repeatable. Submit the same piece twice and a criterion may score a point differently. AI models vary slightly between runs.
- It can't see handwriting. Year 3 sits the real writing test on paper. We assess typed text only, so we can't tell you anything about legibility or handwriting stamina.
- It can't judge a child's whole ability. It sees one piece of writing on one day. It knows nothing about your child's progress, effort, or the things they do brilliantly elsewhere.
- It can't diagnose anything. If you suspect dyslexia, a language delay, or another learning difficulty, no AI tool is the right instrument. Speak to your child's teacher or a qualified professional.
- It can occasionally be wrong. AI models make mistakes. If feedback ever looks plainly incorrect, trust your judgement over ours — and please tell us.
The honest summary: our AI is a good practice coach and a poor examiner. Use the score to see roughly where things stand, and use the tips to decide what to work on next. Don't use it to predict your child's NAPLAN result — nobody can do that, including us.
Things we're often asked to clarify
| Concern | The reality |
|---|---|
| "Does the AI write for my child?" | No. Your child writes every word. The AI reads the finished piece and comments on it — it never drafts, rewrites or completes work. |
| "Are these real NAPLAN questions?" | No. Every question and prompt on Brightstar is original, written in a NAPLAN-style format. ACARA's actual test material is copyright and we don't reproduce it. |
| "Is my child's writing stored?" | No. The text is sent for marking and returned. It isn't stored on our servers, and under Anthropic's API policy it isn't used to train models. |
| "Do you know who my child is?" | No. There are no learner accounts, and we don't ask for a name, school or location — the request carries the writing text, the prompt and the year level. Anything your child types is sent, so please keep identifying details out of the writing. |
| "Is this endorsed by ACARA?" | No. Brightstar is completely independent and has no affiliation with, endorsement from, or approval by ACARA. |
| "Will it replace a teacher?" | No, and it shouldn't. It's practice between lessons, not a substitute for one. |
Other limitations worth knowing
- Progress is saved on one device only. Because there are no accounts, streaks and progress live in that browser. Switching devices starts fresh. That's the price of not collecting data, and we think it's worth paying.
- AI features have daily limits. Writing feedback is capped at a few submissions a day. Running these features costs real money, and the cap is what keeps Brightstar free for everyone.
- Our question bank isn't exhaustive. It covers the curriculum broadly, but no free tool covers everything.
- We have had bugs, and will again. When parents and teachers have found errors in our questions, we've fixed them quickly and publicly. We'd rather be told than not.
What we promise instead
- We'll be accurate about NAPLAN. Current terminology, correct criteria, real score ranges — and corrections when we get something wrong.
- We won't collect your child's data. No accounts, no tracking of children, nothing sold, ever.
- We won't fabricate anything. No invented testimonials, no inflated numbers, no claims of endorsement we don't have.
- We'll stay free. No paywall appearing once you're invested.
- We'll tell you what we can't do. This page exists because you deserve to know before you rely on us.
For teachers and schools
If you're considering pointing families to Brightstar, there's a page covering what it includes, how Brightstar creates and reviews educational content, and exactly what data is and isn't collected — plus a printable one-pager and newsletter text you're welcome to use: Brightstar for schools.
Found something wrong?
Please tell us. Every error a parent or teacher has reported has been fixed, usually within a day or two. That feedback has made Brightstar meaningfully better, and it's the main reason to trust it.
Try it and judge for yourself
Free writing feedback on all 10 NAPLAN criteria. No signup and no cost. See how we handle data. Make up your own mind.
Try AI writing feedback →Frequently asked questions
Is AI writing feedback as accurate as a real NAPLAN marker?
No. Our feedback is an estimate designed to help a child improve. Trained markers apply detailed descriptors and national moderation that we can't replicate. Treat our score as a guide to what to work on, not a prediction of the official result.
Will the AI give the same score twice for the same writing?
Not always. AI models vary slightly between runs, so a criterion may score a point differently on a second submission. The advice about what to improve is usually consistent — and that's the part that matters.
Which AI model does Brightstar use?
Claude, made by Anthropic. We use their faster model so feedback arrives in seconds rather than minutes, which matters for children's attention spans.
Is it safe for my child to use unsupervised?
There's no chat, no open-ended conversation, and no way for a child to talk freely with the AI. They submit writing or choose a topic, and receive structured feedback. There's nothing to sign up for and no way to contact anyone.
What if the AI says something wrong?
Trust your own judgement, and please let us know or email hello@brightstarprep.com. We fix reported errors quickly.