{"version":"2.1.314","anchor":"workflow-agents-structured-output-handback-tool-report-revi","canonical_anchor":"workflow-agents-structured-output-handback-tool-report-revi","heading":"Workflow agents' results are now always reviewed when a run ends","tier":"internal","area":"Workflows","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.314\/e\/workflow-agents-structured-output-handback-tool-report-revi","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.314","markdown":"### Workflow agents' results are now always reviewed when a run ends\n\nWhen a workflow agent finishes, Claude Code now reviews its report of the tools it used, even if it never used the handback tool\n\n**Unclear.** It is not clear what switches this handback behaviour on for an agent.\n\n**What**\n\nA workflow agent is a helper agent that Claude Code runs as one step of a larger task. Some hand their result back through a special handback tool. Claude Code now gives that tool only to agents it confirms are meant to hand results back, and it keeps track of each structured result they return. When the run ends, Claude Code reviews the agent's report of the tools it used, even if the agent never used the handback tool. Before, that review came only from the handback tool itself.\n\n**Why**\n\nThis changes how the results of workflow helper agents get checked.\n\n- Area: Workflows\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}