Sub-agent
A Sub-agent is a separate agent with one clear, limited task. It has its own context and a result to return.
Another example
A lead assigns accessibility review and API analysis to separate agents. The lead checks both reports before deciding.
Main parts
- 01User intent and context
- 02Model or tool decision
- 03Grounded result and fallback
Use it when
Use one for independent, limited work when parallel work or special context truly helps.
Do not use it when
Avoid overlapping edits, vague tasks, excess coordination, and accepting claims without checking evidence.
Name used in code
bounded task + isolated context + returned result Before you ship
Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback.
Outcome: Use or evaluate Sub-agent to make AI behavior measurable and tied to evidence. User context: A lead assigns accessibility review and API analysis to separate agents. The lead checks both reports before deciding. AI method or concept: Sub-agent. Why it fits: Use one for independent, limited work when parallel work or special context truly helps. Do not use it when: Avoid overlapping edits, vague tasks, excess coordination, and accepting claims without checking evidence. AI requirements: Define the input and source evidence. Set model and tool permissions. Use versioned evaluation data and measures. Define failure, decline-to-answer, privacy, speed, and cost limits. Operational safeguards: Keep a clear trace and hide sensitive log data. Show users a safe fallback. Mark steps that need human review. Define how to roll back the model or prompt. Acceptance criteria: Record baseline and target measures on a versioned evaluation set. Test edge cases and hostile inputs. Verify fallback, monitoring, permissions, and rollback. Evidence and limits (evidence boundary): No single official standard controls the whole term. Its meaning may change across teams, platforms, or frameworks. Unknowns to confirm: Target task, model and version, evaluation owner, source data, risk limit, tool permissions, and production fallback.
Check this request
Review the current use of Sub-agent. Definition: A Sub-agent is a separate agent with one clear, limited task. It has its own context and a result to return. Release checks: Check the model and prompt versions, source data, versioned evaluation set, and measures. Verify links to evidence, tool permissions, privacy, common failures, decline-to-answer and fallback behavior, human review, monitoring, cost, speed, and rollback. Before changing code, report the evidence you found, gaps, severity, and the smallest safe fix.