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

Описание и применение

Автономный флот из десяти ИИ‑агентов получил ограничение бюджета в $100 за 5‑часовой скользящий период. Система использует журнал событий как транзакционный лог, воспроизводит его в двойной бухгалтерии, измеряет и ценит труд, оповещает о превышении лимита и автоматически приостанавливает новые задачи, пока расходы не уменьшатся. Это обеспечивает контроль расходов без ручного вмешательства.

Задача

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

Результат

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.

Рабочий процесс

• 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.

Доказательства

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

Источник

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

Источник

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

Источник