{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibuzcjjfaspgmocumbcrwxlidmajo4n4tgotsnho33ye3fdl2lrra",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mgtyj2ow3si2"
  },
  "path": "/t/experimental-protocol-proposal-testing-the-prompt-coherence-engine-pce/174041#post_11",
  "publishedAt": "2026-03-12T06:18:31.000Z",
  "site": "https://discuss.huggingface.co",
  "textContent": "Hi Nyrok,\n\nFollowing your suggestion about structuring prompts into explicit semantic blocks, I experimented with restructuring the PCE prompt framework into a more explicit XML-like format.\n\nThe goal is not to change the axiomatic content itself, but to make the structure of the system prompt easier to read, inspect, and reproduce during experimental runs.\n\nThe axioms are now placed inside a dedicated <pce_framework> and <axiomatic_core> block so that the role and constraint structure becomes explicit rather than embedded in a flat prose prompt.\n\nThis also makes it easier to compare Condition B (long neutral baseline) and Condition C (PCE) in the protocol while keeping the prompt architecture clearly defined.\n\nI’m curious whether this kind of structure aligns with the semantic-block approach you described with flompt.\n\nThanks again for the suggestion — it helped clarify the prompt architecture for the experimental setup.",
  "title": "Experimental Protocol Proposal: Testing the Prompt Coherence Engine (PCE)"
}