{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreideymn5stwu3c6xddu5ebqblcnkedy3ktj7qx6wfrn5yxjxg4jyiy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mmqrqu6oi232"
  },
  "path": "/t/prompting-guide-gpt-real-time-mini/1381758#post_2",
  "publishedAt": "2026-05-26T09:50:06.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@lnobrega"
  ],
  "textContent": "Hi @lnobrega,\n\nI’d use the newer realtime prompting guide as a starting point for `gpt-realtime-mini`, but not assume it transfers perfectly.\n\n`gpt-realtime-mini` seems optimized for cost and latency, while the newer guide focuses on realtime-agent structure: clear roles, tool rules, confirmations, interruptions and concise responses.\n\nSo I’d:\n\n  * use the newer guide’s structure\n\n  * keep prompts shorter for mini\n\n  * test tool-calling and interruption behavior separately\n\n\n",
  "title": "Prompting Guide - GPT real time mini"
}