Customer Support Agent Workflow

Define a bounded support-agent decision loop with tool use and human escalation.

모델: ChatGPT, Claude
난이도: 고급
버전: v0.9

이 프롬프트는 현재 영어로 제공됩니다. 인터페이스는 선택한 언어로 유지됩니다.

프롬프트 기능

Define a bounded support-agent decision loop with tool use and human escalation.

프롬프트 변수

[PRODUCT_POLICY][TOOLS][ESCALATION_RULES][CUSTOMER_MESSAGE]

시스템 프롬프트

You design safe support workflows. Policies and tool permissions are authoritative; never promise an action that a tool did not confirm.

사용자 프롬프트

OBJECTIVE:
Handle [CUSTOMER_MESSAGE] using [PRODUCT_POLICY], available tools [TOOLS], and [ESCALATION_RULES].

INPUTS:
PRODUCT_POLICY: [PRODUCT_POLICY]
TOOLS: [TOOLS]
ESCALATION_RULES: [ESCALATION_RULES]
CUSTOMER_MESSAGE: [CUSTOMER_MESSAGE]

OUTPUT CONTRACT:
JSON containing intent, facts, missing information, planned tool calls, policy checks, response, escalation status, and audit note.

사용 방법

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.

효과적인 이유

The blueprint separates authority, task context, evidence limits, and the output contract so requirements can be checked independently.

모델 호환성

ChatGPTuntestedEditorial compatibility hypothesis; cross-model test record pending.

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

입력 예시

PRODUCT_POLICY: [PRODUCT_POLICY]
TOOLS: [TOOLS]
ESCALATION_RULES: [ESCALATION_RULES]
CUSTOMER_MESSAGE: [CUSTOMER_MESSAGE]

출력 예시

A structured deliverable following the listed output contract, with assumptions and missing evidence clearly marked.

수정 방법

Replace every variable with specific, non-sensitive information. Remove irrelevant sections and add one representative example when tone or classification matters.