Simon Willison’s Weblog

--- +++ @@ -49,7 +49,7 @@ ## Parallel subagents -This Explore subagent is the simplest example of how subagents can work, with the parent agent pausing while the subagent runs. The principle advantage of this kind of subagent is that it can work with a fresh content in a way that avoids spending tokens from the parent’s available limit. +This Explore subagent is the simplest example of how subagents can work, with the parent agent pausing while the subagent runs. The principle advantage of this kind of subagent is that it can work with a fresh context in a way that avoids spending tokens from the parent’s available limit. Subagents can also provide a significant performance boost by having the parent agent run multiple subagents at the same time, potentially also using faster and cheaper models such as Claude Haiku to accelerate those tasks.

--- +++ @@ -60,13 +60,19 @@ ``` For tasks that involve editing several files - and where those files are not dependent on each other - this can offer a significant speed boost. -#### Subagents with different roles +## Specialist subagents +Some coding agents allow subagents to run with further customizations, often in the form of a custom system prompt or custom tools or both, which allow those subagents to take on a different role. +These roles can cover a variety of useful specialties: -While useful, Subagents should be thought of mainly as a power user feature. They can often speed up work, but it's rare that a subagent workflow will be able to achieve something that could not have been achieved without them. +- A **code reviewer** agent can review code and identify bugs, feature gaps or weaknesses in the design. +- A **test runner** agent can run the test. This is particularly worthwhile if your test suite is large and verbose, as the subagent can hide the full test output from the main coding agent and report back with just details of any failures. +- A **debugger** agent can specialize in debugging problems, spending its token allowance reasoning though the codebase and running snippets of code to help isolate steps to reproduce and determine the root cause of a bug. -#### Official documentation +While it can be tempting to go overboard breaking up tasks across dozens of different specialist subagents, it's important to remember that the main value of subagents is in preserving that valuable root context and managing token-heavy operations. Your root coding agent is perfectly capable of debugging or reviewing its own output provided it has the tokens to spare. + +## Official documentation Several popular coding agents support subagents, each with their own documentation on how to use them: