Learning and careers decision

NT School Reports

A single competent developer can build and run a useful, pay-as-you-go NTBOS-aligned comment generator and workspace; the vendor's value is tuning, content and convenience rather than irreplicable moats, so self-build is realistic.

Visit website

Built by Pieter van Wyk, who ships 10 products in this index

You pay

$10/mo

$120/yr

Read off the official pricing page.

You’d pay instead

$100one-off40 h to build

$50/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 6 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 and achievement level → choose length/tone → enter brief notes/strengths → system consumes one token and calls an LLM with NTBOS-tuned prompt → present editable draft for teacher approval/export.

What it still won’t have

  • Pre-tuned NTBOS prompt library specifically crafted for Northern Territory reporting
  • Privacy-first workplace policy and wording from the vendor ('We never collect real student names or personal information') as presented
  • Included content resources, blog posts, and example comment library
  • Priority support (noted as included on the Full Year pack)

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 6 seats.

Paid seatsseats

Money you would actually spend

Keep paying
—

Subscription price × seats × 12

Build it
—

AI build —APIs + hosting —

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

Not run yet
Build a minimal NT School Reports replacement using Next.js (React) for frontend, PostgreSQL for storage, Node.js/Express API, Stripe for one-off token purchases, and OpenAI for text generation. In scope: user registration and login (email), store teacher workspace with student nickname codes, token balance management, Stripe checkout for buying token packs (50/150/500), prompt template management keyed by subject/year/achievement (NTBOS scales), server-side OpenAI integration that consumes a token per generation, an editor UI to show/edit generated comments and export to PDF/clipboard, basic privacy behavior (store nicknames not real names), logging and error handling, and automated tests for payments and LLM calls. Out of scope: training custom models, multi-jurisdiction curriculum tuning, formal privacy certification, multi-tenant school billing. Provide end-to-end tests, error handling for payment and API failures, and deployment scripts (Docker + Vercel/Heroku instructions).
How we checked3 sources · 2/3 runs agreed · evidence score 84

How the score was reached

  • Build verdict base78
  • 3 cited sources+3
  • Price verified on pricing page+3
  • Evidence score84

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.

Integrity checks

What held up, and what did not.

✓ Price read off the page! 2 of 3 runs agreed; the verdict is the majority✓ Citations limited to fetched pages! 1 moat recorded