AI Content Detector

Check text for AI-generation signals

Telling whether text was written by a human or a model is increasingly relevant, for educators, editors and publishers. This tool analyses text for patterns commonly associated with AI generation, such as perplexity signals, giving an indication rather than a verdict.

Why detection is inherently uncertain

AI text detection looks for statistical signatures, text that is unusually smooth and predictable, low in the surprising word choices a human makes, which is roughly what perplexity measures. But these signals are imperfect: capable models produce human-like text, humans sometimes write predictably, and editing blurs the line. So any detector gives a probability, not proof, and false positives, flagging genuine human writing, are a real and serious risk. The honest use is as one weak signal among several, never as a sole basis for an accusation, which is a limitation worth stating plainly.

A signal, not a verdict

The tool runs entirely in your browser, so nothing you paste, prompts, outputs or documents, is uploaded, which matters when the input is sensitive AI data or your own content.

Related tools

• AI Prompt Leakage Analyzer — Paste a system prompt and a hostile user input to see whether the prompt holds secrets and whether the input carries injection patterns. Local, instant.
• LLM Data Exposure Checker — Check if text contains data likely to be memorized or exposed by LLMs.
• AI Usage Policy Generator — Generate an acceptable use policy for AI tools in your company.
• Model Hallucination Estimator — Estimate risk of hallucinations based on task type and temperature.