Learning and careers decision

Porosheets

A competent developer can build a useful single-teacher replacement (week board, LLM generation, PDF export) in a multi-week project, but matching the product polish, content coverage, and reliability of the paid service is costly to reproduce and would lack the refinements teachers expect.

Visit website

Built by Hamza, who ships 3 products in this index

You pay

$19.99/mo

$240/yr

Read off the official pricing page.

You’d pay instead

$100one-off115 h to build

$50/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

  • Teacher picks a lesson on a week-board -> send prompt to an LLM to generate worksheet/quiz/slides -> save generated PDF and answer key to lesson card -> optionally transform to variants (support/advanced/translate) -> export/print/share link.

What it still won’t have

  • Product polish and refined UX (tweaks, animations, accessibility)
  • Prebuilt teacher-facing templates and content coverage tuning
  • Ongoing prompt engineering and dataset-informed adjustments
  • Reliability and multi-user scaling and SLA
  • Integrated transforms (support/advanced/translate) tuned for pedagogy and QA

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 single-tenant web app (React + TypeScript frontend, Node.js + Express backend, Postgres) that provides a week-board for one teacher: implement auth with email/password and Stripe subscription (3-day trial then monthly), a week-view UI with five weekday columns and lesson cards, lesson detail view to request generation of a worksheet/quiz/slides via an LLM API, server-side prompt assembly supporting variants (support/advanced/translate), generate PDFs from the returned text (html-to-pdf), store attachments in Postgres and serve shareable links, and simple logging and tests. Out of scope: multi-tenant org billing, advanced analytics, teacher collaboration features, and mobile native apps. Include input validation, error handling, unit and integration tests for core flows, and deployment scripts (Docker + one-click deploy to a managed host).
How we checked2 sources · 2/3 runs agreed · evidence score 56

How the score was reached

  • Partly verdict base52
  • 2 cited sources+1
  • Price verified on pricing page+3
  • Evidence score56

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 · 2

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