{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifl46tfdsctbp3dhq6vj6gyycv4n2q33vks2qhkdss47h4llsvwiu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mftjy7zdxbl2"
  },
  "path": "/t/framework-thought-process-of-diagnosing-prompt-issues/1375261#post_1",
  "publishedAt": "2026-02-27T09:07:04.000Z",
  "site": "https://community.openai.com",
  "textContent": "Often I’d be able to start writing a prompt (or generate one). The result ends up being a mix of some inaccurate tool calls, a little bit too wordy there, ignoring an instruction to bold letters. Since I don’t know why that happens, I’m mostly making uncalculated guesses at which parts to change.\n\nHas anyone come up with a structured method of diagnosing prompts into broad categories ?\n\nI was wondering if there are tell tale signs of certain mistakes, for eg not specifying a full “tool_name” may cause a model to **consistently** make incorrect choices.\n\nBy knowing what’s wrong, we could narrow down some prompting techniques to see if it solves the problem. For eg a category of instruction ignoring, one could use either a system prompt for higher priority, or applying markdown to make rules distinct.\n\n-A junior dev",
  "title": "Framework/Thought Process of Diagnosing Prompt Issues"
}