做 AI 代理开发的团队，如果遇到长任务执行效率低或复杂任务难以分解的问题，Subagentmaxxing 提供了一种递归监督的实用思路，值得尝试。
Phil Schmid 提出了一种名为 Subagentmaxxing 的方法，通过 /goal 命令结合子智能体（subagents）来提升 AI 代理处理复杂任务的能力。核心思想是当代理需要执行更长时间或更复杂的任务时，用另一个代理替代人工监督，并让子代理之间形成递归监督结构。这种方法自然演化自尝试最大化代理运行时长或解决更复杂问题的实践。Peter Steinberger 补充强调，开发者不应再手动提示编码代理，而应设计循环来驱动代理。
Subagentmaxxing or /goal + subagents (^2 depth). You should naturally evolve towards this when you...
Subagentmaxxing or /goal + subagents (^2 depth). You should naturally evolve towards this when you try to max your agents run for longer or solve more complex task. You replace your oversight with another agent, and then their oversight with another agent around. Peter Steinberger 🦞 @steipete Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore. You should be designing loops that prompt your agents. 🔗 View Quoted Tweet 💬 6 🔄 1 ❤️ 9 👀 475 📊 6 ⚡