What is a workable assembly-to-fine-cut workflow for an AI short: paper edit, selects, versions and interchange, tying Murch's priorities, J/L cuts and OTIO together?

Problem. AI shorts have many generated takes per shot and need an orderly path from script to locked picture. Conditions. A short with dozens of shots; steps are inference stitched from the findings 01-12 and prior ones (paper edits C2-B26-A4-06; J/L cuts and split edits C3-B137-S29-03/05, C3-B164-G58-01..05; dialogue cutting C3-B231-S58-05; pacing C2-B17-A3-02 and C3-B589-04). Method [inference]. (1) Paper edit: write the shot list with beat, emotional purpose, duration target and dialogue; pick the order before generating. (2) Generate to the shot list; name files SHOT-ID_take. (3) Selects: score takes with the six-criteria sheet (P-L1-6-02), mark one hero take per shot and keep alternates as 'B' takes; reject for artefacts early (C3-B586-11). (4) Assembly: lay hero takes in order with placeholder frames for shots not yet made (the OTIO use case suggests placeholder clips with unused names); no polish yet. (5) Rough cut: trim for rhythm, cut at lulls and onset of motion (P-L1-6-03/04), set overlaps as split edits (J/L) so sound leads or trails; do not smooth jump cuts until content is final (Descript advises finishing the rough cut first, P-L1-6-06). (6) Fine cut: match colour (C3-B586-06), reframe, sound sweetening, check against shot-length benchmarks (not repeated here). (7) Versioning: duplicate the timeline for each cut version (v01, v02...), export OTIO/EDL plus a mixdown at each version, and keep a change log (shots added/removed). (8) Regenerate only shots still in the cut, then relink by shot ID (P-L1-6-11). (9) Lock picture, then export for finish with effects baked (P-L1-6-12). Failure modes. Regenerating shots that get cut; loss of lineage between versions. Limitations. This is a suggested workflow, not from a single authority; no source tested it on AI work. Version/date. 2026-10-23. Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources. Limitations: Inference-heavy synthesis. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://opentimelineio.readthedocs.io/en/latest/use-cases/conform-new-renders-into-cut.html",
      "note": "Workflow; Example; Before you start; The Rule of Six; Feature matrix; workflow"
    },
    {
      "url": "https://opentimelineio.readthedocs.io/en/latest/use-cases/shots-added-removed-from-cut.html",
      "note": "Workflow; Example; Before you start; The Rule of Six; Feature matrix; workflow"
    },
    {
      "url": "https://help.descript.com/script-editing/smooth-jump-cuts.md",
      "note": "Workflow; Example; Before you start; The Rule of Six; Feature matrix; workflow"
    },
    {
      "url": "https://blogs.ischool.berkeley.edu/i290-viznarr-s12/the-rule-of-six-walter-murch/",
      "note": "Workflow; Example; Before you start; The Rule of Six; Feature matrix; workflow"
    },
    {
      "url": "https://opentimelineio.readthedocs.io/en/latest/tutorials/feature-matrix.html",
      "note": "Workflow; Example; Before you start; The Rule of Six; Feature matrix; workflow"
    }
  ]
}