AIエージェント

Customer Support Agent Workflow

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

モデル: ChatGPT, Claude
レベル: 上級
バージョン: v0.9

このプロンプトは現在英語で提供されています。画面は選択した言語のままです。

できること

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

最適な用途

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

プロンプト変数

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

システムプロンプト

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

ユーザープロンプト

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.

使い方

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

効果の理由

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

モデル互換性

ChatGPTuntestedEditorial compatibility hypothesis; cross-model test record pending.

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

入力例

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

出力例

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

カスタマイズ方法

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