{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifpeq6prt55usadv5jcp444ktshaa7uhjwlc3ztonni33dq2zjz2a",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mptd2t6cwsn2"
  },
  "path": "/t/how-to-curb-gpts-ambition-to-become-a-leader/1385720#post_1",
  "publishedAt": "2026-07-04T13:44:24.000Z",
  "site": "https://community.openai.com",
  "textContent": "I built a multi-agent workflow primarily using the `agent-team` feature in Claude Code.\nGiven the project’s complexity—and the fact that I have comprehensive documentation—I organized the agents into three tiers, with specific “domain owners” responsible for their respective areas.\nThe main agent’s role is simply to activate them and monitor the process for any issues.\n\nI clearly outlined everyone’s responsibilities in `agent.md` and `workflow.md`, explicitly stating that the main agent should _not_ assign tasks to sub-agents or define their scope.\nYet, every time I start a new session, unless I specifically reiterate these points, the agent invariably assigns tasks to those owners.\nI’ve revised the instructions countless times; this information is repeated across multiple documents.\n\nBut it insists on grandstanding with its own “insights” and assigning tasks to the sub-agents anyway.",
  "title": "How to Curb GPT's Ambition to Become a Leader"
}