{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiddfwwyvaipvlpx53g3nskhcwdgrwtmp2xhnwvxvlknperra7pmqm",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlfibk5jolt2"
  },
  "path": "/t/do-you-use-function-calling-or-use-intent-recognition-internal-orchestration/1380376#post_2",
  "publishedAt": "2026-05-09T03:41:03.000Z",
  "site": "https://community.openai.com",
  "textContent": "For production workflows, I’d usually let the LLM handle intent and parameter extraction, then keep state, retries, permissions, and side effects in deterministic orchestration. Tool calling is still a good contract, but I wouldn’t make the model the workflow engine for anything business-critical",
  "title": "Do you use Function Calling or use Intent Recognition + Internal Orchestration?"
}