Text risk signals
AI text detector
Analyze text for AI-writing risk signals, burstiness, repetition, and available classifier support without claiming proof.
Run a signal check
No detector model loads until you press Check.
Current support
Browser text features are available now; heavier model checks are advanced or server-side depending on device and plan.
What this checks
- Lightweight text features run after Check without loading a detector model first.
- Advanced local model analysis stays behind an explicit post-Check stage.
- Reports explain uncertainty and conflicting signals.
What this does not prove
- Short text is hard to classify.
- Human editors can make AI text look human and vice versa.
- Classifier output is probabilistic.
FAQ
- Can this prove whether content was written by AI?
No. AI Detect reports signals such as provenance metadata, watermark support status, and statistical text risk. It does not claim legal or authorship proof.
- Does text leave my browser during a local check?
Browser-default checks run local text features and provenance checks after you press Check. Server enhanced checks are separate and will be labelled before use.
- Why can a result be unknown?
Many providers do not expose public watermark detectors, and metadata can be absent or stripped. Unknown is a valid result when no reliable public signal exists.
Workflow upgrade
Need repeatable reviews?
Move from one-off checks to saved reports, batch review, and API-ready signal records when the workflow needs it.