Estimate the share of AI-generated vs human-written text in your document. Uses a lightweight on-device language model to flag likely AI segments and produce an overall likelihood score.
Your text never leaves your device. Detection runs locally with an on-device model. Results are approximate — use as a signal, not proof.
Runs entirely in your browser. Your data never leaves your device.
When you click Analyze Content, the following happens — all locally, all in your browser:
No. This AI content detector runs entirely in your browser using WebAssembly. Your text never leaves your device.
We use Xenova/roberta-base-openai-detector, a distilled RoBERTa model trained by OpenAI. It performs well on formal writing, essays, and news articles.
Yes, after the first use. The model weights (approximately 130MB) are downloaded once and cached in your browser's IndexedDB.
We benchmarked the heuristic detector against 200 text samples — 100 human-written essays and 100 AI-generated passages.
| Metric | Value |
|---|---|
| Agreement with neural detectors | ~82% (vs GPTZero on same samples) |
| False positive rate | ~11% (human flagged as AI) |
| False negative rate | ~9% (AI flagged as human) |
| Per-paragraph analysis time | <1ms (pure JS) |
| Model download | 0 MB — instant execution |
| Recommended min input | 50+ characters, multi-paragraph for best signal |
Last verified: September 2026. Heuristics are intentionally lightweight — they sacrifice some precision for zero-latency, zero-download analysis.