{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicbwmbeoqjm7gaqcjsxkllwfavfirt4a3fj5grqm3crm3zkw3lpau",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mmadnb3bf2i2"
  },
  "path": "/t/prompt-engineering-the-protocol-of-intent-the-theoretical-foundation/175880#post_7",
  "publishedAt": "2026-05-19T20:13:08.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "seperating logic and reueable knowledge alows one to make better prompt based tools. which is great.\n\nthe problem with your overall responce is that it assumes that LLMs are just chat boxes, and they are not.\nshifting things in to a cognitive runetime is simply a codebase architecture, which whie we are talking about programs, this does not take in to account how agents actually work.\n\nwhile there is room for backround logic routines agents still need INTRUCTIONS. and these instructions come in the form of conversation. and where there is conversation there is room for intent ambiguity. and there are 2 paths to follow from here\n\n  1. turn the agent in to an automation bot\n  2. learn to be better at giving instructions and maintaining better communication flow.\n\n\n\nat its very nature, a LLM is a black box. as it breaks down words in to semantic context, and then generates a response out of semantic context. the fact that this works at all is amazing, the fact that it works reliably and consistently is a mundane miracle.\nthere is only so much that can be done directly with algorithms.\n\nmy point here is that the path forward involves many diverging paths, not just 1.",
  "title": "Prompt Engineering - The Protocol of Intent: The Theoretical Foundation"
}