ClipWhat can I filter by?
Open the filter picker to see available fields, values and counts for the current folder or project view. Combine subjects, ratings, flags, technical metadata and controlled logging fields. Pick several values within one field to match any of them; add another field to narrow the results further. Free-form notes and descriptions are searchable text rather than lists of filter choices. Try the directory picker.
Can I separate what the AI found from what I decided?
Yes, two ways. The Log status facet is a tri-state (Unlogged, AI-suggested, Confirmed), so "show me everything still waiting on review" is one click. And every reasoning result carries provenance (local / your API / Rush), so cloud-derived values are identifiable per clip via the provenance badge.
Is there a search box grammar?
Yes. Combine free text with supported field filters, or choose the available fields and values from the picker. Search indexed filenames, notes, transcripts and text seen in footage. Semantic discovery finds related meaning, and visual discovery finds related appearances when the required models and indexes are ready. Your reviewed log is searchable inside ClipLogger and can also supply filters, filenames and supported exports.
How do I find the best takes fast?
Sort the grid by Quality (best shot), which is the on-device aesthetics score, or filter on the quality-score range and the cull-candidates flag to sweep the junk the other way. Combine with your own flags and ratings; the AI score is a lens, your flag is the decision.
Are searches saveable?
Yes, as smart bins. A smart bin is a project-hosted saved query that evaluates live on each machine; pin clips into it to keep them regardless of the query, or exclude ones that match but don't belong. Because bins are query views, a saved search never moves or copies a file.