Capture evidence of a URL hosting impersonating or stolen content: independent archive snapshot, retrieval timestamp, SHA-256 of the exact bytes, and a PDQ perceptual fingerprint of any image. Returns a typed evidence manifest. Run this FIRST, before the content is taken down or changed.

Get the takedown playbook for a platform: legal bases, report-form URLs, documented email intakes, required fields, ID requirements, and response times. Every fact carries a primary-source citation with a retrieval date; unverifiable facts are marked UNVERIFIED, never guessed. Platforms: meta, youtube, tiktok, x, google.

Draft a platform-correct takedown notice from captured evidence. Statutory fields are computed deterministically; the result is a DRAFT the human must review and file themselves (the draft includes the form URL or documented email intake, plus step-by-step instructions). Use capture_evidence first to get an evidenceManifestId, and get_playbook to pick the right reportPathId.

Check whether content matches a registered authentic work in the Official AI registry. Query by sha256 (exact bytes) or pdq (perceptual fingerprint from capture_evidence). Returns the registry record or an honest 'unknown'; absence of a record is not a judgment about the content, and perceptual matches require human confirmation.