Learning and careers decision

WorkbookPDF

A single competent developer can reproduce the core product (personalized PDF workbook generation, payments, and delivery) in about a week; there are no evident durable moats on the site to prevent a rebuild.

Visit website

Built by Marc Lou, who ships 32 products in this index

You pay

Not priced

No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.

You’d pay instead

$100one-off40 h to build

$50/mo4 h/mo upkeep

No published price to break even against.

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

  • User selects language, level and topics → system generates exercises via an LLM → render exercises into a styled PDF → deliver to user and record generation for access

What it still won’t have

  • Company polish, marketing, and existing customer base
  • Built-in refund/workflow and support the vendor provides
  • The product's pre-tuned prompt library and any proprietary prompt engineering
  • Illustration assets and curated examples unless recreated or licensed

What remains hard

  • Product polish and ongoing maintenance
Read the build prompt

First-year cost

No published price

WorkbookPDF does not publish a price we could read, so there is nothing to compare against. What building costs is below.

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 WorkbookPDF clone: use Next.js (React) for the frontend, Node.js + Express for API, Postgres for metadata, Amazon S3 for PDF storage, Stripe for one-time payments, and OpenAI (or another LLM) for exercise generation. Core features in scope: language/level/topic selection UI; prompt templates and LLM integration to generate exercise items and answers; HTML/CSS templates and Puppeteer (or Playwright) to render downloadable printable PDFs with optional illustration placement; entitlement check so only paid users can create new workbooks; store workbook metadata and generated PDF files; error handling, input validation, and basic unit/integration tests. Out of scope: building a mobile app, implementing a full spaced-repetition study system, or licensing a large proprietary illustration library.
How we checked2 sources · 3/3 runs agreed · evidence score 83

How the score was reached

  • Build verdict base78
  • 2 cited sources+1
  • 3/3 assessment runs agreed+4
  • Evidence score83

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.

✓ 3 independent runs, one answer✓ Citations limited to fetched pages! 1 moat recorded