{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiavlpbw3w346cflqqphfzoaicx4lwykfnzymf3ghnhjpnkgrjabpu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mn6mtv4muz42"
  },
  "path": "/t/how-do-you-forecast-what-an-ai-feature-will-actually-cost-before-you-build-it/1382064#post_3",
  "publishedAt": "2026-05-31T20:42:00.000Z",
  "site": "https://community.openai.com",
  "textContent": "I just build, deploy, monitor and tune iteratively.\n\nIn Production, if you can limit the population that is processed initially you can work out the cost for a smaller set, then optimise and finally broaden the population when you are satisfied with the behaviour and cost on the smaller set.",
  "title": "How do you forecast what an AI feature will actually cost — before you build it?"
}