Your Multi Agent Pipeline Not Slow Because of the Model
I run Suhail, my own Claude Code orchestrator, against real repos most days. The first time I timed a full run (an indexer plus a trivial two-part plan), it took 22 minutes. My instinct was to blame the model: swap to a faster tier, shave a few seconds per call, ship it. That instinct was wrong. I pulled the actual dispatch counts, and the bottleneck wasn’t model latency at all. It was how many times I was cold-starting a subagent to re-read context it had already seen. ...