I stopped babysitting my support bot when I added a reviewer agent prompt after every draft

说明与用途

在支持工单流程中加入专门的审核步骤，显著提升了可靠性，捕捉了单一提示无法持续处理的政策违规、语气问题和缺失信息。

问题

A single GPT call that tried to classify, draft, enforce policy, and check tone produced unreliable support replies that were technically correct but rude, overconfident, or missing key information.

结果

Adding a dedicated reviewer step dramatically improved reliability, catching policy violations, tone issues, and missing information that a single prompt could not consistently handle.

工作流

• 1. Classify the ticket type using a classifier agent.
• 2. Draft the reply with a draft agent based on the classification.
• 3. Review the draft with a reviewer agent that checks policy, tone, and completeness.
• 4. Escalate to a human if confidence is low or errors are found.

证据

That extra review step caught policy misses, weird tone, and missing fields before anything went out.

来源

One prompt was doing four jobs badly

来源