Decision models are going to make video production way faster. This is a decision model reading every frame of the Matrix rooftop scene. It's fast enough to keep context from frame to frame, so it can catch things an LLM would take forever to check. Check out this skill

Read this if you make videos with Claude. I built a skill that cut my QA cost on this video from $127 to 16 cents. It was made with Claude in Remotion. It's called SageCut. It swaps the LLM out of frame-by-frame QA and uses a multimodal decision model, Sage (@levantolabs), instead. I'm the only video guy at Levanto. I run 3 Claude plans and have been making Remotion videos since early this year, with BlenderMCP in the mix, so the output is pro-grade with very little babysitting. The problem: it burned through my Max plan, and a video could take 2 days. When I dug into the workflow, the reason was that Claude subagents were reviewing every single frame. That cost a ton and added 4+ hours per video. SageCut hands that step to Sage. Sage is great at spotting defective frames, and only those get passed to Opus 5.5 to fix. Across 6 A/B tests the output was exactly the same, at 1/10 the QA cost and 1/4 the QA time. On this video, Sage read all 3,153 frames for 16 cents. If you make Remotion videos, try it. The link to skill is below. How long does a Remotion video take you right now with Claude?

It's hard to use a decision model for your average claude code operator. Sage makes your work in coding harnesses faster and use less of your max plan. What are your results using Sage wisdom? Love the ascii artwork on this 🔥