We gave our AI agent fleet a credit limit, and it hit it the same day

说明与用途

一组十个自治 AI 代理被限制在 5 小时滚动窗口内 100 美元的预算。系统将共享事件日志视为交易日志，重新播放到双重会计账簿中，测量并计价劳动力，触发预算阈值警报，并在支出低于上限前自动暂停新任务调度，从而实现实时成本控制，无需人工干预。

问题

Uncontrolled AI agent fleet spending exceeded budget, risking runaway costs and loss of control.

结果

The fleet’s spending was capped at $100 over a rolling 5‑hour window, automatically pausing new tasks when the cap was exceeded and resuming as spend aged out. The system provided real‑time audit, alerts, and control without manual intervention.

工作流

• 1. Replay board events into three hledger journals (money, promises, labour).
• 2. Verify ledger parity with hledger check and independent replay.
• 3. Query outstanding obligations via mesh-promises.
• 4. Measure spend with mesh-labor over a rolling 5‑hour window.
• 5. Price spend using token counts and a rate table.
• 6. Alert on budget thresholds with mesh-labor-alert (edge‑triggered).
• 7. Throttle new task dispatch with mesh-pace when spend exceeds cap.
• 8. Allow operator overrides via Telegram and direct command channels.
• 9. Auto‑resume dispatch as spend ages out of the rolling window.
• 10. Update budget cap in environment file and re‑source when needed.

证据

The board gets replayed into three separate double‑entry hledger journals, each tracking a different commodity: money, promises, labour.

来源

mesh-labor --budget … spent: $43.23 / cap $200 / remain $156.77 …

来源

mesh-pace holding, new dispatch stopped … operator raises the cap to $200 → spend $152.38 < $200 → dispatch resumes

来源