[atomon]

This looks very cool, will try it out on my next project.

There have been a number of solutions popping up to address this problem, and I think the need is very real. Decomposing these LLM tasks into subtasks seems to be one of the best ways to work around the shortcomings of LLMs in production apps (hallucinations, context window limits, etc). But then you end up with complicated pipelines that are difficult to debug, improve, reason about, etc.

[antonap]

Indeed - decomposition improves reliability but also makes the testing more challenging. That’s why we made the framework modular! Let us know of any feedback as you try it out!