Learning and careers decision

School Reports QLD

A competent developer can build a working tokenized comment generator and workspace in about a week, but reproducing the vendor's curriculum tuning, privacy practices, and support polish would require more effort and ongoing curation.

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-off36 h to build

$30/mo3 h/mo upkeep

On cash alone, building overtakes the subscription at 4 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, enters short notes, system generates a curriculum-aligned comment draft using prompt templates; teacher edits and exports/comment consumes one token.

What it still won’t have

  • Locally tuned, curriculum-specific prompt bank and any proprietary prompt improvements
  • Priority support and any operational guarantees
  • The vendor's claimed privacy review and operational practices (de-identified workspace by default)

What remains hard

  • Brand trustBuilt for Queensland teachers — not a generic chatbot
Read the build prompt

First-year cost

Keep paying

Paying is—cheaper in year one.

On cash alone, building overtakes the subscription at 4 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 single-tenant web app (React frontend, Node/Express backend, Postgres DB) that lets a teacher register, purchase one-off token packs via Stripe, enter anonymised student notes, and generate curriculum-aligned report comments via OpenAI's API. In scope: auth, token accounting, payments, a prompt template system configurable per subject/year, generation endpoint with rate/usage tracking, editable rich-text comment editor, export (PDF/CSV), and basic admin pages for token packs. Out of scope: multi-school billing, formal school integrations (OneSchool), advanced analytics, and custom model training. Include error handling, input validation, unit tests for backend endpoints, and CI to deploy to a single small cloud instance (e.g., DigitalOcean or AWS t3.micro equivalent).
How we checked3 sources · 2/3 runs agreed · evidence score 58

How the score was reached

  • Partly verdict base52
  • 3 cited sources+3
  • Price verified on pricing page+3
  • Evidence score58

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 quoted from the page