The examples in the article seem awfully contrived. Can someone please explain what a real-world use case for something like this would be? Why not just do it all in Go? Or is the point of it to be able to use existing JS scripts within a Go application?
a) non-technical users describe, in plain English, what they would like from the data; b) an LLM with lots and lots of prompt-engineering massaging translates the English into JS, c) the JS gets executed in a sandbox, d) the results get returned to the user