7 Claude Code agents held 24 board meetings. Revenue: $0

Description and use

A set of seven AI agents running unattended failed to generate revenue due to mis‑defined success, missing human steps, and resource limits. Implementing artifact checks, publishing OAuth consent, and rate‑limiting improved reliability, yet revenue stayed at zero.

Problem

Unattended AI agents failed to produce real business outcomes due to mis‑defined success, missing human steps, and resource limits.

Outcome

The unattended system produced 16 articles, 18 Shorts, 3 Dev.to posts, 5 proposals, and 3 digital products but generated $0 revenue. Key failures were artifact mis‑checks, OAuth token expiry, and resource overuse. Improvements included artifact validation, human‑task logging, OAuth publishing, and rate‑limiting.

Workflow

• Define agents and slash command
• Schedule daily run via Task Scheduler
• Run agents in order: research → decide → write → design → publish → review → repeat
• Check artifact existence, modification time, and content
• Log success or NG
• Post outputs to platforms
• Run daily self‑check comparing scheduled vs. actual outputs
• Iterate on agent definitions based on meeting decisions

Evidence

The runner that launches each unattended command wrote OK to its log when the process exited 0 and printed something. That definition of success failed three separate ways in three weeks.

Source

The Shorts pipeline is the only fully unattended business. It stopped on September 12 at 06:45 because the YouTube refresh token expired.

Source

The runner now takes the path of the file the command is supposed to produce and checks that it exists, was modified after the run started, and contains the heading the command always writes.

Source