Opus 5.5 builds a dashboard animation and reviews its own frames
The author moves quality checks out of his head and into files: CLAUDE.md rules, a check.py numeric validator, and a second model as reviewer, so Opus 5.5 can turn a still image into a dashboard animation and read its own frames before handing it over.
Everyone gets the same first result from a new model. It's good. So is the fifth one. And they're still sitting there, watching every render. Why? Because nothing else in the process can tell a good result from a bad one. The model stopped being the bottleneck. You are. You're the only quality check, and you don't scale. So I moved the check out of my head and into files: CLAUDE.md: rules read on every run check. py: numbers the model can't argue with a reviewer: a second model that didn't make the work /goal: keeps going until all of it passes Then it stops at a draft and waits for me. The dashboard in this video started as one still image. Opus 5.5 built it and read its own frames before I saw it. The full studio, file by file, in the article 👇
This post quotes another post: x.com/averix_official/status/2110711923968778244