Writing and content decision
WRITING9
A competent developer can build a useful replacement in ~30 hours using an LLM plus an off-the-shelf grammar checker and standard SaaS components; the vendor’s asserted dataset, user base, and commercial polish are the main nontrivial advantages.
Visit website↗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.
What a replacement has to do
- User submits an essay → system scores by IELTS criteria and highlights errors → returns band estimate, annotated corrections, and improvement suggestions.
What it still won’t have
- Proprietary dataset and algorithms "tested on thousands of essays" (claimed)
- Existing user base and trust signals ("Trusted by 47,755 students")
- Commercial polish, bonuses and integrated extras (speaking simulator, eBook, etc.)
- 100% money-back guarantee and any associated refund handling
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 4 seats.
Money you would actually spend
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
Build a minimal self-hosted IELTS essay checker using Node.js (Express) + React frontend + Postgres. Implement: (1) an essay submission form and authenticated account pages, (2) an analysis pipeline that: sends essay text to an LLM (OpenAI/GPT) with prompts that evaluate IELTS band across task response, coherence, vocabulary, grammar, and returns a band estimate and per-sentence suggestions, (3) a grammar-check step using LanguageTool API and surface fixes inline, (4) store submissions and results in Postgres, (5) Stripe monthly subscription gating for premium unlimited submissions, (6) annotated results UI showing highlighted errors and suggestions. Out of scope: training custom large models or recreating any proprietary datasets. Include error handling, input validation, unit tests for the API, and a small e2e test that submits an essay and asserts a result is returned.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 6 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 · 6
Every page the run actually retrieved.
- official productWriting9 — homepage
- official pricingWriting9 — pricing
- official productWriting9 — trust and scale claims
- official productWriting9 — system testing claim
- open sourcelanguagetool-org/languagetool
- open sourceAutomattic/harper
Integrity checks
What held up, and what did not.
