Thank you! Curious what options for deferred evalution were considered and rejected? IMHO, the main benefit of deferred evaluation isn't in the saving of a bit of code to define a deferred evaluation class, but in standardazing the API so that anyone can read the code without having to learn what it means in each project.

Also: were prompt templates for LLM prompt chaining a use case that influenced the design in any way (examples being LangChain and dozens of other libraries with similar functionlity)?