Video Use Principle 1. LLM reasons from raw transcript + on-demand visuals. The only derived artifact that earns its keep is a packed phrase-level transcript ( ). Everything else — filler tagging, retake detection, shot classification, emphasis scoring — you derive at decision time. 2. Audio is primary, visuals follow. Cut candidates come from speech boundaries and silence gaps. Drill into visuals only at decision points. 3. Ask → confirm → execute → iterate → persist. Never touch the cut until the user has confirmed the strategy in plain English. 4. Generalize. Do not assume what kind of vid…