An Agent on a Leash, or why my AI agent doesn't make business decisions

Описание и применение

Создание безопасного AI‑агента для поддержки клиентов, где ИИ интерпретирует намерения, а программное обеспечение применяет правила и требует одобрения человека для высокорисковых действий.

Задача

How to build an AI-powered support agent that can be trusted to make business decisions without risking incorrect actions or data leaks.

Результат

Implemented a safe AI support agent that never executes high-risk actions without human approval, reducing errors and ensuring compliance.

Рабочий процесс

• 1. User sends support message
• 2. AI classifies intent (e.g., refund request)
• 3. Deterministic rule engine evaluates risk tier
• 4. Low/medium risk: AI assists with drafting response or routing
• 5. High risk: AI proposes action with audit trail, queues for human approval
• 6. Very high risk: AI only proposes, human executes manually
• 7. Human reviews queue, approves or rejects action
• 8. Approved action is executed by software
• 9. System logs audit trail and notifies user

Доказательства

The AI interprets intent. The software enforces policy. That's the split, and it's the thesis of everything that follows.

Источник

The system drafts a response, proposes the refund, files it in the approval queue with a full audit trail.

Источник