Compliance workflow
AI detector for compliance
Compliance-oriented AI detection reports that separate watermark, provenance, classifier, and limitation signals.
Run a signal check
No detector model loads until you press Check.
Current support
Compliance workflows need audit trails and signed reports, but the MVP already normalizes detector evidence and limitations.
What this checks
- Reports preserve timestamped detector outputs and recommended next steps.
- C2PA and provenance checks are stronger compliance signals than text-only likelihood.
- API and bulk job previews share the same report schema.
What this does not prove
- The MVP is not yet a legal compliance system.
- Audit logs, account roles, and signed reports are still production work.
- Classifier scores alone should not be used as compliance determinations.
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.