{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiewjwmpqytkbz5bxigxzq3jtprlqpcxwghdyow75mxy6qvwueveza",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mn6mtqxgig32"
  },
  "path": "/t/how-do-you-forecast-what-an-ai-feature-will-actually-cost-before-you-build-it/1382064#post_4",
  "publishedAt": "2026-05-31T20:46:48.000Z",
  "site": "https://community.openai.com",
  "textContent": "Personally, I saw cost exploding when the context window was not thought through. Stacking and compressing is not the best approach (at least for what I usually do).\n\nI prefer what I call “composition”, where the context is processed in small tasks separately, then results from there are assembled into “answer context” and finally the model gets you the answer you attach to the conversation.\n\nBut it’s me who pulls the context from the conversation, so I have more control there.",
  "title": "How do you forecast what an AI feature will actually cost — before you build it?"
}