# How do I evaluate a subagent separately from the main loop?

Grade the subagent's own final message, carried back to the parent as the Agent tool's result, rather than whatever the parent agent says afterward. A subagent's intermediate tool calls and reasoning stay inside its own isolated context and never reach the parent; only that one final message crosses the boundary, and the parent is free to summarize or rephrase it before it reaches the user, so a check run on the parent's reply is really grading the parent's paraphrase, not the subagent's actual work.

Messages carry a `parent_tool_use_id` field that ties them back to the subagent that produced them, which is what lets a grader pull just that subagent's output out of the stream instead of the whole session. A subagent's transcript is also stored separately from the parent's and can be resumed on its own, so a failing case can be replayed at the point the subagent actually went wrong. [Grading one node of a LangGraph graph](/answers/langgraph-evals/how-do-i-grade-one-node-of-a-langgraph-graph) is the same idea applied to a different framework's unit of delegation.

---

Sources:
- Claude Docs: Subagents in the SDK: https://code.claude.com/docs/en/agent-sdk/subagents (fetched 2026-09-13)

Source: https://tessary.ai/answers/claude-agent-sdk-evals/how-do-i-evaluate-a-subagent-separately-from-the-main-loop
More on Claude agent sdk evals: https://tessary.ai/answers/claude-agent-sdk-evals
From Tessary, agent reliability for AI agents in production: https://tessary.ai