{"version":"2.1.232","anchor":"claude-told-not-to-invent-a-pending-subagent-s-result","canonical_anchor":"claude-told-not-to-invent-a-pending-subagent-s-result","heading":"Claude told not to invent a pending subagent's result","tier":"notice","area":"Subagents","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232\/e\/claude-told-not-to-invent-a-pending-subagent-s-result","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.232","markdown":"### Claude told not to invent a pending subagent's result\n\nClaude no longer makes up results for background subagents that haven't finished yet.\n\n**What**\n\nDelegation guidance now says subagents run in the background, that a completion notification will arrive on its own, and that Claude must not fabricate or predict results. If you ask before the notification lands, it should say the agent is still running.\n\n**Details**\n\n- Added to both the fork wording and the background-agent wording.\n\n**Evidence**\n\n`Never fabricate or predict a pending agent's results \\u2014 the notification is never something you write yourself; if the user asks before it arrives, say it's still running.`\n\n- Area: Subagents\n- Tier: You'll notice\n- Useful: 4\/5\n- Signal: 3\/5"}