The course reduces the choice to one question: does the intermediate work matter to the main thread? If only the final result matters, delegate to a subagent; if the main thread must see or react to what is found along the way, keep the work there.1

Where delegation works

Use caseWhy it fits
Research and exploration, such as locating JWT validation in an unfamiliar codebaseMany files searched, one location and explanation returned1
Code reviewFresh context without the creation history; the system prompt can encode project review standards1
Tasks that need a different system prompt: copywriting (audience, tone, voice), styling (design-system files loaded first)The difference comes from the instructions and context, which the main conversation lacks1

Anti-patterns

Anti-patternWhy it fails
Empty expert personas (“Python expert”)The main conversation already has that knowledge; isolation helps only with a real difference such as a custom prompt, focused context, or controlled tools1
Sequential pipelines of dependent steps (reproduce → debug → fix)Each handoff compresses away discoveries the next step needs; pipelines suit only independent tasks1
Test-runner subagentsDiagnosis needs full failure output, and a summary like “tests failed” hides it; the course reports this pattern performed worse among the configurations tested1

All three are cases of context isolation costing more than it saves.

Footnotes

  1. Introduction to Claude Code Subagents (study guide) 2 3 4 5 6 7