The Orchestration Tax is You

Starting additional agents is easy, but running them does not increase available cognitive bandwidth. Steering agents and merging their code into a codebase must still pass through a single serial decision-maker. This creates an orchestration tax when parallelism is assumed to scale like human attention. Hidden asymmetry appears in agentic workflows: launching agents is cheap, while closing the loop requires verification, reconciliation, and integration by the same person. Feeling busy can result from many agents without producing equivalent shipped work. The core issue is architectural rather than disciplinary, requiring deliberate design of how attention is allocated and managed like a concurrent system.

"Starting more agents is easy now. However, more agents running doesn't mean more of you available - your cognitive bandwidth doesn't parallelize. All the judgement to actually steer them and merge the code they write into the codebase still has to route through exactly one serial processor which is just you. Orchestration tax is basically the price you pay for forgetting this and the only real fix is to start architecting your own attention like you architect any concurrent system."

"You can run 20 agents and feel completely busy. But thats not 20 agents worth of shipped work. Earlier in that chat Richard gave this problem a name. "You talked about the orchestration tax" he said. "You can't manage twenty agents successfully in your own brain." He is totally right. I want to breakdown this idea properly because its not a discipline problem. It is an architecture problem."

"There is this hidden asymmetry in agentic workflows. Starting an agent is very cheap. It is just a keystroke or a sentence prompt. But closing the loop on the agent is not cheap at all. Someone has to check if what came back is correct and reconcile it with whatever the other agents touched. That someone is you. And there is exactly one of you."

Read at Addyosmani