{"version":"2.1.224","anchor":"guidance-on-when-multiagent-is-worth-it-and-a-corrected-docs","canonical_anchor":"guidance-on-when-multiagent-is-worth-it-and-a-corrected-docs","heading":"Guidance on when multiagent is worth it, and a corrected docs link","tier":"notice","area":"Agent SDK Docs","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224\/e\/guidance-on-when-multiagent-is-worth-it-and-a-corrected-docs","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.224","markdown":"### Guidance on when multiagent is worth it, and a corrected docs link\n\nMultiagent docs gained a staged guide on when extra agents are actually worth it.\n\n**What**\n\nThe multiagent docs gained a step-by-step section with Python examples: start with a roster of just `{\"type\": \"self\"}`, move reading-heavy sub-tasks to a cheaper worker model, and only then add dedicated specialists. The overview and skill entry point now point fan-out shaped work here.\n\n**Details**\n\n- The URL fetched for live docs was wrong and is corrected from `multi-agent.md` to `multiagent-orchestration.md`.\n\n**Evidence**\n\n`https:\/\/platform.claude.com\/docs\/en\/managed-agents\/multiagent-orchestration.md`\n\n- Area: Agent SDK Docs\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5"}