Provenance and content credentials
AI provenance checker
Check files and text for provenance signals, C2PA metadata, watermark support, and AI-writing risk with honest uncertainty.
Run a signal check
No detector model loads until you press Check.
Current support
File provenance checks are supported through C2PA metadata inspection; text-only provenance remains limited without original generation context.
What this checks
- C2PA manifests can identify content credentials when files preserve them.
- Provider and model claims are recorded separately from detector signals.
- The report separates provenance metadata from AI text likelihood.
What this does not prove
- No manifest found is not proof that a file is human-made.
- Screenshots, exports, and social platforms can strip provenance metadata.
- Pasted text usually lacks enough provenance context for direct verification.
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.