Learning and careers decision
NSW School Reports
A focused replacement that generates NESA-aligned comments and implements token purchases is realistic for a competent developer using open-source tooling and LLM APIs, but reproducing the vendor's tuned prompts, product polish, and support/brand experience would be costly.
Visit website↗Built by Pieter van Wyk, who ships 10 products in this index
$10/mo
$120/yr
Read off the official pricing page.
$100one-off120 h to build
$15/mo4 h/mo upkeep
On cash alone, building overtakes the subscription at 3 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- Teacher selects student/subject/achievement level, enters brief notes, system generates a NESA-aligned draft comment which the teacher edits and exports; purchase one-off token packs to allow generation.
What it still won’t have
- Vendor-tuned NESA / NSW curriculum prompt engineering and iterative quality improvements
- Priority support and product polish (demo, UX adjustments, content library, resources)
- Token marketplace trust and pre-purchased token economics as marketed
- Any proprietary training data or closed prompt recipes the vendor uses
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 3 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal NSW-aligned report comment generator using Next.js (React) frontend, Node.js/Express backend, Postgres for de-identified workspace data, Stripe for one-off token purchases, and OpenAI-compatible LLM API for generation. Core features in scope: account sign-up and login (email), dashboard showing token balance, purchase flow for token packs, form UI to select student/subject/year/achievement/tone/length and enter teacher notes, server-side prompt templating that maps selections to curriculum-aligned prompts, call to LLM API with retries and rate-limit handling, save generated drafts and allow edit/export as DOCX (use docxtemplater) and copy-to-clipboard. Out of scope: training proprietary models, long-term analytics dashboards, multi-school admin billing, integrations with SENTRAL. Require input validation, error handling, unit tests for backend routes and prompt generation, and a README with deployment steps for a single small server (Heroku/Render) and estimated monthly costs.
How we checked
How the score was reached
- Partly verdict base52
- 3 cited sources+3
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score62
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productNSW School Reports — Home
- official pricingNSW School Reports — Pricing
- official docsNSW School Reports — Features
Integrity checks
What held up, and what did not.
