Last updated: July 2026
ORDO has no footage library and doesn't store your video files anywhere but your own drive. When a clip is classified, only the individual frames needed for that classification are sent out — never the full file, never your archive, never stored server-side afterward. Full details below.
ORDO does not import or copy your footage into any internal library. It works directly on the video files already on your computer or an external drive, tagging each clip and moving it into the bucket (folder) you've defined — in place, on your own storage.
When you run a sort, ORDO extracts a small number of still frames from each clip locally on your machine, in order to classify what the clip contains. Those frames — not the original video file — are sent to our classification service for analysis.
Frame classification is powered by Anthropic's Claude models, accessed through Anthropic's commercial API. Under Anthropic's commercial terms, data sent through the API is not used to train future models by default. ORDO does not opt into any data-sharing or model-training program with Anthropic, and does not pool or share classification data across ORDO users.
When ORDO classifies a clip, it writes the resulting tags directly into that file's own metadata (and as macOS Finder tags), so the tags travel with the file wherever it goes — copied to another drive, dragged into an editing project, shared with someone else. Any existing metadata your camera wrote (creation date, camera model, GPS location, etc.) is preserved, not overwritten, in this process.
Creating an ORDO account requires an email address and password. We use this to authenticate you and manage your subscription. We do not sell or share account data with third parties for advertising or marketing purposes.
If this policy changes in a way that affects how your data is handled, we'll update this page and note the change date at the top.
Reach out at sam@ordo.video with any questions about this policy or how your data is handled.