Tag: multi-agent

Everything tagged this way, in Developer.

ProjectOctober 25, 2026
orchestration
I spent weeks building a Claude Code plugin that split one goal across many agents behind gates, then a pre-registered trial showed plain Opus passing the same hidden tests in 7 minutes for $2.46 (notional) against the plugin's 149 minutes and $14.88. This is how I built and tested it, why I retired it, and how to run the same trial on your own tooling.
ProjectOctober 22, 2026
agentic-label-engineering (ALE)
I built a public CLI in which only `ale verify`, after running a task's acceptance commands itself, can mark an agent's work done. It rejected work in 13 of 26 real runs, but under my /work process it took 53 minutes and $8.92 (notional) where plain Opus took 7 minutes and $2.46 for the same hidden-test result, so I retired it.

orchestration