Free browser-first checker
AI detector and watermark checker
Check text and files for AI watermark, provenance metadata, and AI-writing risk signals with clear limitations.
Run a signal check
No detector model loads until you press Check.
Current support
Checks C2PA/provenance and lightweight text signals now; model-specific watermark support depends on public provider availability.
What this checks
- C2PA and metadata checks can run locally after the user presses Check.
- Text analysis starts with lightweight browser-side features.
- Advanced local model checks are lazy-loaded only after Check and only when the browser is suitable.
What this does not prove
- No detector can prove authorship from text alone.
- No watermark found does not mean content is human-written.
- Short or heavily edited text produces weaker signals.
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.