{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidvi5zevr5wynxytibkow26fbjymle3qxuslt26fyvuo6mzakfti4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mn6g4jxhu222"
  },
  "path": "/t/how-do-you-forecast-what-an-ai-feature-will-actually-cost-before-you-build-it/1382064#post_2",
  "publishedAt": "2026-05-31T19:52:05.000Z",
  "site": "https://community.openai.com",
  "textContent": "While building (at drawing board) you have some per-call estimate, then you compose and test. Then staging gives you estimates per run (optimistic). Basically, if subjective complexity factor (0-5) * cost per run * 50 < customer cost per run… is the point where you ask your self 2 questions:\n\n  1. Can you divide the costs at least by 2 (better 4)?\n  2. Is it worth bothering?\n\n",
  "title": "How do you forecast what an AI feature will actually cost — before you build it?"
}