This tool analyzes text using 8 heuristic signals that research and observation suggest differ between human and AI-generated writing. These include: sentence length burstiness, AI-typical buzzword density, transition word overuse, vocabulary richness (type-token ratio), passive voice frequency, hedging language patterns, structural uniformity, and filler phrase density.

Each signal produces a score (0–100%). A weighted average gives the final AI likelihood score. No machine learning model or external API is used — all analysis runs locally in your browser.

The detector is calibrated against text produced by large language models including ChatGPT (GPT-4/3.5), Claude, Gemini, Llama, and Mistral. These models share characteristic patterns: lower sentence length variance, overuse of transition words ("Furthermore", "Moreover"), and reliance on certain buzzwords ("nuanced", "delve", "leverage", "pivotal").

The detector works best on English text. It may give unreliable results for other languages, highly technical text, poetry, dialogue, or very short passages.

Heuristic AI detection without a trained model is inherently probabilistic. This tool will produce false positives (human text scored as AI) and false negatives (AI text scored as human). Consider it one signal among many, not a definitive verdict.

Accuracy improves with longer texts (100+ words) and degrades for heavily edited AI text, paraphrased content, or text in non-English languages. The detector is designed to be a quick first-pass screen, not a forensic tool.

No. All analysis runs entirely in your browser using JavaScript. Your text never leaves your device — there is no server, no API call, and no data storage. You can even run this tool offline once the page has loaded.

Burstiness refers to the variance in sentence lengths. Human writers naturally alternate between short punchy sentences and long complex ones — this creates high burstiness. AI models tend to produce more uniformly-sized sentences, resulting in lower burstiness.

The detector measures the coefficient of variation (CV = standard deviation / mean) of sentence lengths. A high CV suggests human writing; a low CV suggests AI.

Type-Token Ratio (TTR) is the ratio of unique words to total words. A higher TTR means more diverse vocabulary. AI models trained on massive corpora often settle into frequent, "safe" word choices, producing slightly lower TTR scores — though this signal is weaker than phrase density and burstiness.

The buzzword and phrase databases are built for English text only. Sentence length burstiness and vocabulary richness signals work for any language, but the phrase-based signals will be largely inactive for non-English text, reducing reliability significantly.

We recommend at least 100 words for meaningful results. Below 50 words, statistical signals are too noisy to be useful. The tool will warn you if your text is too short and display lower confidence accordingly.