Agentic VideoEngine

A terabyte of footage from Japan, 4,584 clips, and no way to find anything in it. So I taught a machine to watch all of it.

4,584clips indexed from one trip
~$6.50total compute to embed the library

The problem

We came back from Japan with a terabyte of footage across 4,584 clips, spread over nine shoot locations. Filenames were IMG_2532.MOV. Folder names were dates.

Finding the shot you remember in that is not a search problem, it is an archaeology problem, and it silently kills a content pipeline: the footage exists, and the cost of locating it exceeds the value of using it.

What it does

I describe a shot the way I would describe it to a person, and it hands me the clip. “Morning light on a tea field” returns the Kakegawa pans.

How it works

Every clip is sampled, described by a vision model, and embedded alongside a CLIP embedding of the frame itself. Both go into a local vector store. A query is embedded the same way and matched against the library.

The part worth stating plainly is the cost.

An index that costs six dollars is one you re-run whenever the model improves. An index that costs six hundred is one you build once, regret, and never touch again.