Shouldn't something like this be first and foremost for humans ... which also benefits machines as an obvious side-effect?
> I have a dream for the Web [in which computers] become capable of analyzing all the data on the Web – the content, links, and transactions between people and computers. A "Semantic Web", which makes this possible, has yet to emerge, but when it does, the day-to-day mechanisms of trade, bureaucracy and our daily lives will be handled by machines talking to machines. The "intelligent agents" people have touted for ages will finally materialize.
I quoted this from https://en.wikipedia.org/wiki/Semantic_Web since the original reference was a book that is not openly accessible. Also I think it's funny that he's talking about agents in exactly the same way that people do now.
Some websites have the same patch for humans in the form of a "Help" or "About" section that details how the page is to be used/interpreted.
This essentially just places those same instructions into a well-known location, so that LLM-based agents don't first have to crawl the website for such an instructional page (which may or may not exist).
If you have good UX these instructions should be largely moot for both machines and humans, and bring machines on the same page as humans that may have additional context (e.g. where the site was linked; previous visits to the website).
It sounds like that exactly
no because machines can put up with large walls of text but humans need exciting ux to keep their attention.