Our AI approved the invoice. But nobody could tell us why.

说明与用途

AI 代理自动批准发票，但未记录决策原因，导致审计困难。改进后，每个决策记录输入、规则和模型版本、置信度以及简明理由，并由独立服务执行硬限制。

问题

The AI agent approved supplier invoices automatically but did not record the reasoning behind each decision, leaving finance unable to explain why an invoice was approved.

结果

The system now provides traceability for each approved invoice, enabling finance to audit decisions, while maintaining high throughput for most invoices.

工作流

• 1. Invoice arrives. 2. Agent matches invoice to purchase order and decides approve/reject. 3. Agent writes a record of the decision, including inputs, rule version, model version, confidence, and reason. 4. Agent proposes the decision to a separate service. 5. The service checks hard limits (amount threshold, new supplier, exact match). 6. If limits are met, the proposal is posted to the ledger; otherwise it is sent to a human for review. 7. Access to data is limited to approved queries and actions. 8. Matching rules and prompts are versioned and reviewed like code.

证据

We logged the outcome, not the decision

来源

Now, whenever the agent approves or rejects something, it writes down the inputs it used, the rule version, the model version, its confidence, and a plain‑language reason

来源

The agent no longer posts anything itself. Instead, it proposes, and a separate, boring, well-tested service checks that proposal against hard limits before anything touches the ledger

来源