[verdict][curated prompt][source: wasitaigenerated.com]
Can I vibecode WasItAIGenerated?
// the value is the network, the data or the infrastructure
The interface is a text box; the product is a fine-tuned classifier. Detection quality does not come from a clever prompt. It comes from training a model on a labelled corpus and tuning it until the error rate is low enough to act on, which is months of work against a target that moves every time a new generator ships. Asking a general model "is this AI-written?" produces confident, unreliable answers, and in an academic-integrity setting that means falsely accusing real students. A one-shot build gets you the UI and none of the responsibility.
confidence: high
what it is: Detection API and tools for AI-generated text, images, audio and video, plus a thesis review
Buildability index · an editorial game
- Price 9.99 $/month weight: plus 1
- Time not a true replacement; consolation build in one sitting weight: minus 1
- Category ai writing no weight
- Moat proprietary models · proprietary data · compliance and regulation weight: minus 6
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site wasitaigenerated.com (si apre in una nuova scheda) no weight
It is not close. The prompt below rebuilds a piece, not the product.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Build a private workspace that pastes in text, asks one general model for an AI-likelihood judgement with reasoning, stores results, and exports them.
what you need
- OpenAI or Anthropic API key in .env
- Node.js 22
- SQLite database
- A README stating plainly that the output is a guess, not a detector, and must never be used to accuse anyone
The text box is trivial. The trained classifier and its measured false-positive rate are the product.
The prompt
The verdict is NOT REALLY, and the prompt stays anyway: it does not replace the app, it rebuilds the part that really is code. The rest is the moat.
Build the closest honest consolation tool inspired by WasItAIGenerated. Do not claim it detects AI writing.
Use exactly this stack: Next.js 15 + TypeScript + SQLite.
Primary job: paste text, send it to one general language model, and record that model's opinion on how machine-like the writing reads, with its reasoning.
Start from an empty folder and create the complete working project.
Single-user and private by default; store everything locally.
Put every secret in .env and provide .env.example.
Show the result as an opinion with reasoning, never as a score, a percentage or a verdict - the whole point of this build is that it cannot measure what the paid product measures.
Put a permanent, non-dismissable notice in the UI and the README: this is one model's guess, it has no measured error rate, and it must never be used to accuse anyone of anything.
Include clear empty, loading, validation, success and failure states.
Add export so the user is not trapped in the app.
Accessible keyboard navigation, labels, focus states and sensible contrast.
Deliberately exclude these paid-product advantages: a trained classifier, a labelled corpus, a published false-positive rate, image/audio/video detection, per-sentence attribution.
Do not fake accuracy claims, benchmarks or compliance statements.
Write unit tests for the data model and one end-to-end smoke test of the core loop.
Create a README with setup, architecture, data location and an explicit limitations section.
Run the tests and build before finishing, then fix what fails.Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.
What you lose
- a trained classifier and the labelled corpus behind it
- a measured false-positive rate you can quote to an institution
- detection for images, audio and video, not just text
- per-sentence highlighting instead of one document-level guess
- retraining as generators change
Why people still pay
Institutions do not buy a verdict, they buy a defensible one. A university that flags a student needs a documented error rate, an audit trail and a vendor who will stand behind the number. That is a measurement problem, not an interface problem, and it is why every serious buyer in this category asks about false positives before features.
moat: Proprietary models Proprietary data Compliance and regulation what a moat is
trained classifier, labelled corpus, published error rates
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Binoculars (opens in a new tab) — Zero-shot LLM text detection using perplexity ratios between two models.
- DetectGPT (opens in a new tab) — Curvature-based zero-shot detection of machine-generated text.
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
