Kembali ke galeri

Agen AI

Customer Support Agent Workflow

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

Model
ChatGPT, Claude
Tingkat
Mahir
Versi
v0.9

Prompt ini saat ini tersedia dalam bahasa Inggris. Antarmuka tetap menggunakan bahasa pilihan Anda.

01

Fungsi prompt

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

02

Terbaik untuk

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

03

Variabel prompt

[PRODUCT_POLICY][TOOLS][ESCALATION_RULES][CUSTOMER_MESSAGE]
Prompt Sistem
You design safe support workflows. Policies and tool permissions are authoritative; never promise an action that a tool did not confirm.
Prompt Pengguna
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.

Cara menggunakan

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

Mengapa berhasil

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

Kompatibilitas model

ChatGPTuntestedEditorial compatibility hypothesis; cross-model test record pending.

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

05

Contoh masukan

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

06

Contoh keluaran

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

Cara menyesuaikan

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

Kesalahan umum

Do not paste secrets or personal data. Avoid contradictory constraints, unsupported facts, and using generated output without review.

Catatan pengujian

Editorial blueprint awaiting recorded cross-model evaluation. It is visible for review but is not labeled as tested.

Why is this blueprint not marked as tested?

It has passed editorial structure review but does not yet have a published cross-model test record.