Zurück zur Galerie

KI-Agenten

Customer Support Agent Workflow

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

Modelle
ChatGPT, Claude
Stufe
Fortgeschritten
Version
v0.9

Dieser Prompt ist derzeit auf Englisch verfügbar. Die Oberfläche bleibt in der gewählten Sprache.

01

Was dieser Prompt leistet

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

02

Geeignet für

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

03

Prompt-Variablen

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

Anwendung

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

Warum es funktioniert

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

Modellkompatibilität

ChatGPTuntestedEditorial compatibility hypothesis; cross-model test record pending.

ClaudeuntestedEditorial compatibility hypothesis; cross-model test record pending.

05

Beispieleingabe

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

06

Beispielausgabe

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

Anpassen

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

Häufige Fehler

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

Testnotizen

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.