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

Description and use

Adding a dedicated reviewer step to the support ticket workflow improved reliability by catching policy violations, tone issues, and missing information that a single prompt could not consistently handle.

Problem

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.

Outcome

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

Workflow

• 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.

Evidence

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

Source

One prompt was doing four jobs badly

Source