Learning and careers decision

ACT School Reports

A capable developer can build a narrow, self-hosted token-based report-comment generator (the core workflow) in a few weeks, but reproducing the polished curriculum tuning, content library, and teacher-facing UX of the paid product would take more effort and refinement.

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-off46 h to build

$20/mo6 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

  • Generate a curriculum-aligned comment by selecting a student/subject, choose achievement level and tone, supply short teacher notes, then call an LLM to produce an editable comment and decrement a local token balance.

What it still won’t have

  • Built-in ACT / ACARA prompt tuning and pre-authored curriculum templates
  • Existing token-shop UX and one-off token purchase flows tailored for teachers
  • Any priority support and existing content library and resources
  • Brand trust and moderation tuned to ACT reporting expectations

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 3 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 self-hosted ACT School Reports replacement using Next.js (React) frontend, Node/Express backend, Postgres database, Stripe for one-off token purchases, and an LLM provider (OpenAI-compatible). Core features in scope: user signup/login (email), token wallet with purchase flow (Stripe Checkout), frontend UI to select student/subject/year/achievement level/tone and paste short teacher notes, a prompt-template engine mapping ACARA/BSSS achievement scales to parameterized prompts, an LLM integration that generates an editable comment and decrements tokens, persistent storage of generated comments and token balances, and basic export/print. Out of scope: multi-school admin billing, marketplace of templates, advanced moderation workflows, and training proprietary models. Include error handling for payment and LLM failures, unit tests for token accounting and prompt templating, and end-to-end tests for the main generation flow.
How we checked3 sources · 3/3 runs agreed · evidence score 62

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.

Integrity checks

What held up, and what did not.

✓ Price read off the page✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded