More parallel subagents made my pipeline slower. Here's the data. (opens in new tab)

Adding a 7th subagent pushed my orchestrator latency from 22s to 31s — the opposite of what I expected. I'd been running a fanout pattern in my ad-creative analysis SaaS: spawn N subagents in parallel, collect results, merge into one verdict. The parallel part worked fine. Individual subagents finished in 9–12 seconds regardless of how many I spawned. The problem was everything after that. With 8 subagents, each returning ~800 tokens of analysis, the orchestrator was assembling a 6,400-token ...