The Orchestrator's Tax
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Martin Fowler article on orchestrator tax in subagent systems, directly addresses multi-agent architecture tradeoffs.
Rahul Garg argues that in long-running multi-agent workflows, the orchestrator's working memory—not parallelism—is the scarce resource, and subagents should be treated as tools to protect that context rather than to speed execution. Analyzing a real Claude Code session on a .NET codebase, he found the largest cost came from the orchestrator's own token consumption when it checked on subagents, not from the subagents themselves. The piece ends with open questions about giving orchestrators explicit delegation rules rather than adding more governance.
Rahul Garg