Learning and careers decision

darayuth hang

A competent developer can build and run a useful replacement in about a week using existing PDF parsers and an LLM API; the product shows no evident durable moats that prevent DIY.

Visit website

Built by dhang, who ships 4 products in this index

You pay

$9.99/mo

$120/yr

Read off the official pricing page.

You’d pay instead

$100one-off38 h to build

$20/mo6 h/mo upkeep

On cash alone, building overtakes the subscription at 3 seats.

Open-source builds that already do this

Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All darayuth hang alternatives, with the arithmetic →

What a replacement has to do

  • Upload or paste text/PDF → extract key concepts → call an LLM to generate quiz questions and answers → present interactive study UI and allow exports.

What it still won’t have

  • Polished UI/UX and visual design polish of the hosted product
  • Built-up trust/brand and existing user base/support channels
  • Any proprietary model fine-tuning or vendor-specific optimizations the product may use
  • Potentially exact export behavior, edge-case handling, and prebuilt templates

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 AI quiz generator web app using Django + Postgres for the backend, React for the frontend, and OpenAI-compatible LLM API for generation. In scope: file upload and text extraction (PDF/Docx), backend endpoints to send extracted text to the LLM and persist generated quizzes, a React study UI (multiple choice / true-false / fill-in-the-blank) with progress tracking, export endpoints for JSON, QTI and CSV, Stripe one-time pass payments, basic user auth, error handling, and unit/integration tests for parsing, LLM integration, and export generation. Out of scope: advanced UI theming, course/LMS multi-tenant features, and model fine-tuning. Provide retry/failure handling for uploads and API calls, input validation, and automated tests covering parsing, generation pipeline, and exports.
How we checked3 sources · 2/3 runs agreed · evidence score 89

How the score was reached

  • Build verdict base78
  • An open-source build was found+5
  • 3 cited sources+3
  • Price verified on pricing page+3
  • Evidence score89

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