11-Agent Company Earned $0: CLAUDE.md Mistakes Cost Revenue

说明与用途

一项为期30天的11个AI代理实验在完成896项任务后收入为0。操作员发现3-4个代理是最佳配置，而11个代理会导致过多的协调开销。主要失败原因包括因隐藏约束而违反澳大利亚垃圾邮件法。发布了一个包含72个协调和合规教训的开源CLAUDE.md模板。

问题

A 30-day experiment with 11 AI agents completed 896 tasks but earned $0 revenue due to coordination failures, excessive overhead, and legal violations.

结果

The experiment earned $0 revenue after 896 tasks. The operator documented 72 mistakes and identified that coordination overhead and lack of constraint-first prompting were the primary causes of failure. The optimal configuration was found to be 3-4 agents with strict legal and operational constraints defined in the CLAUDE.md file.

工作流

• Define a minimal viable agent team of 3-4 agents (CEO, CTO, Researcher, Sprint Engineer).
• Create a CLAUDE.md file with hard constraints listed first (e.g., no cold email/DM/SMS, no destructive commands without approval).
• Implement shared state memory where every agent reads company/lessons.md and company/credentials.md on every wake.
• Assign specific roles: CEO for strategy, CTO for execution, Researcher for market discovery.
• Mandate immediate documentation of any failure mode in the shared lessons file.
• Kill failing experiments within 48 hours instead of letting them run for days.
• Focus on finding one distribution channel before building multiple products.

证据

11-agent company experiment earned $0 after 896 tasks.

来源

Optimal agent count: 3-4, not 11

来源

Australian spam law violated due to buried constraints

来源