Content Creation

How SageCut Uses a Decision Model to Cut Opus 5.5 Video Review Costs

Built by Shann³ · · Source: X

Quick answer

A Remotion video workflow where code and a cheap multimodal decision model check every rendered frame, and Opus 5.5 only reviews the flagged frames and fixes the video code. SageCut, built by Chris at Levanto, is one implementation of it.

Result: According to the posts, video review costs fell 90% and review time fell 75%. On one video, QA cost dropped from $127 to $0.16, with Sage reading 3,153 frames.

What they built

Shann³ describes a way to make AI-generated videos cheaper to review. Videos are built with Claude Opus 5.5 and rendered with Remotion. Instead of having Opus 5.5 check thousands of frames itself, code and a cheaper "decision model" check the frames first. Opus 5.5 only looks at the problems they flag. The example they point to is SageCut, a skill built by Chris (@bigironchris), the only video person at Levanto. It uses Levanto's multimodal decision model, Sage.

Chris says the old approach had Claude subagents reviewing every single frame. That burned through his Max plan, added 4+ hours per video, and meant a video could take 2 days.

How it works

  • Build: Opus 5.5 gets the idea, brand book, assets and references, then works through the storyboard and animation. Remotion renders the code into a video.
  • Automated checks: Code checks things you can measure, like text size, blank or frozen frames, and colours against brand rules. The decision model reads the frames and answers specific questions to find problems.
  • Fix: Selected frames and check results go to Opus 5.5. It investigates, edits the video code, and the video is re-rendered and checked again.
  • Human review: A person watches the finished video for pacing, sound, transitions and whether it matches what they wanted.

The posts don't give step-by-step setup details beyond this. Chris links to the skill in his post.

The result

According to Shann³, review costs fell 90% and review time fell 75%. Chris says 6 A/B tests produced the same output at 1/10 the QA cost and 1/4 the QA time. On one video, Sage read 3,153 frames for $0.16, down from $127. Shann³ notes that this figure only covers frame reading and that rendering still takes time.

How to build something similar

  • Split your QA into deterministic checks (scripts) and visual judgment (a cheaper vision model). Save your most expensive model for fixing things.
  • Ask the vision model narrow yes/no questions about each frame instead of open-ended ones.
  • Test the pipeline on a video you've already reviewed by hand, and check that it catches the same problems.
  • Compare cost and time against your current process before you switch.

The original post

how to get faster and cheaper videos from Opus 5.5 using a decision model for frame checks reduced video review costs by 90% and review time by 75% when you create videos with Claude Opus 5.5, checking thousands of frames can consume a lot of time and tokens you can set this up so a decision model checks the frames, while Opus 5.5 reviews the flagged issues and fixes the code here's how it works: 1. build your video with Opus 5.5 give it your idea, brand book, assets and references, then work through the storyboard and animation if you're using Remotion, it renders the code into a video 2. separate the repeated checks from the creative work use code to check measurable requirements and a decision model to inspect the frames > code checks things like text size, blank or frozen frames and colours against your brand rules > the decision model reads the frames and answers specific questions to help identify problems > selected frames and check results go to Opus 5.5 for further review 3. have Opus 5.5 investigate and fix the problems it reviews the selected frames and edits the video code where needed render the changes and run the checks again this reduces the amount of frame-by-frame review you ask Opus 5.5 to do 4. review the finished video yourself watch the pacing, sound, transitions and whether the video matches what you wanted to create the automated checks help find defects, while you review the creative decisions and overall quality SageCut is one implementation of this for Remotion videos in the example Chris shared, Sage (decision model) read 3,153 frames for $0.16 (the frame-reading cost, not the full production cost) the savings come from the review stage, rendering still takes time start with a video you've already reviewed and check whether it catches the problems you found then compare the review cost and time with your existing process [Quoted post from @bigironchris]: 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?
Shann³ (@shannholmberg) · October 19, 2026 · View on X

Want to build something like this?

Join the Shipping Skool community free. Paid members get live bootcamp calls every week.

Join Shipping Skool — Free

More use cases

← All AI agent use cases