# Letting Claude See Video: A 4x4 Grid Trick
Claude (and most multimodal LLMs) can look at images. They cannot watch video. If you generate an MP4 in a session — Sora, Runway, Kling, Veo — and want the assistant to *see* what it made, you hit a wall: there's no `Read` tool for video frames.
The fix is one ffmpeg command and a habit.
## The clip we're working with
We started with a still, generated by gpt-image-2 from a profile photo as character reference. Forest scene, green lightsaber, beaver dam, blooming meadow:
Then we asked Sora-2 for 4 seconds of motion — the *release* the still only implies. Trees falling, dam bursting, water surging through into the meadow:
<video controls preload="metadata" style="max-width:100%;height:auto;" poster="https://askrobots.com/files/public/34b5101c-23b6-4df0-ba53-cabed41e675e/">
<source src="https://askrobots.com/files/public/744c8222-eabd-4b7e-b2b9-215dc036edc6/" type="video/mp4">
Your browser does not support the video tag. <a href="https://askrobots.com/files/public/744c8222-eabd-4b7e-b2b9-215dc036edc6/">Download the MP4</a>.
</video>
The video came back. The model couldn't see it.
## The trick
Extract evenly-spaced frames from the video, tile them into a single image, then `Read` that image. Sixteen frames in a 4x4 grid is enough to read the motion arc of a short clip without making each thumbnail too small to parse.
```bash
# For a 4-second video, 4 fps × 4 sec = 16 frames in a 4x4 grid:
ffmpeg -i video.mp4 -vf "fps=4,scale=320:-1,tile=4x4" -frames:v 1 collage.jpg
```
That's it. The output is one ~80KB JPEG that the model can look at directly.
## What it looks like
Here's the collage of the same 4-second clip:
Reading top-to-bottom, the story is right there:
- **Row 1** — character mid-swing, trees on the dam, golden hour light
- **Row 2** — trees crashing, splash, dam breaching
- **Row 3** — pull-back, water rushing through the breach
- **Row 4** — wide meadow, river flowing free, full bloom
You don't need to watch it. The grid IS the watching.
## Tuning the grid to clip length
Don't blindly use 4x4. Match the grid to your duration so each thumbnail represents a meaningful slice of motion.
| Clip length | Grid | Frame interval |
|---|---|---|
| 4s | 4x4 (16) | 0.25s |
| 8s | 4x4 (16) | 0.5s |
| 12s | 4x6 (24) | 0.5s |
| 20s | 5x6 (30) | 0.67s |
The math: pick `fps = grid_cells / duration`. Drop `fps` below 1 if you have to — a 60-second clip in a 5x6 grid is `fps=0.5` (one frame every 2 seconds), still totally readable for slow-changing scenes.
If your clip is fast-cut or has rapid camera motion, scale up the grid. If it's a slow drone shot, scale down — you don't need 30 thumbnails of the same hillside.
## Why this matters more than it sounds
Generative video tools cost real money. Sora-2 runs ~$0.10/sec. Runway, Kling, Veo are similar or higher. If you generate a clip and *can't see it*, you have two options: render frames manually (slow), or trust the model to iterate blind (expensive).
The collage trick collapses both into one cheap ffmpeg call. The assistant can now:
- Verify the clip matches the prompt before you ship it
- Catch issues (wrong character, missing element, weird artifact) without you watching every render
- Suggest concrete edits ("the dam breach is in row 3 not row 2 — try a tighter prompt")
- Decide whether a re-render is worth the spend
It changes the loop from *generate → human reviews → maybe re-prompt* to *generate → assistant reviews → propose next move*.
## Where to put it
Save the workflow somewhere the assistant will reach for it next time. In Claude Code that's a memory file. In a custom agent it's a tool definition or system prompt. The point is: don't make the model rediscover the trick on every video.
The barrier to "AI can see video" turned out to be a one-line shell command and a habit of using it. Most accessibility wins look like this — not new capabilities, just removing friction from existing ones.