ethical-persuasion-design

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ethical Persuasion Design

伦理说服设计

Design persuasive requests by matching a real user benefit with truthful cues that help the audience decide. Use Influence principles as evidence-routing tools, not as shortcuts to bypass judgment.

设计有说服力的请求时，应将真实的用户利益与帮助受众做出判断的真实性线索相匹配。将 Influence 原则作为证据路由工具，而不是绕过判断的捷径。

Quick Start

快速开始

Read
```
guidelines.md
```
to choose the smallest useful reference set.

Load

references/persuasion/knowledge.md

for concepts and

references/persuasion/rules.md

for operating rules.

Use
```
workflows/design-persuasive-request.md
```
for repeatable tasks.
For audits, surface both the active influence cue and the ethical rewrite.

阅读
```
guidelines.md
```
，选择最小且实用的参考资料集合。

加载

references/persuasion/knowledge.md

了解相关概念，并加载

references/persuasion/rules.md

了解操作规则。

使用
```
workflows/design-persuasive-request.md
```
执行可重复的任务。
进行审核时，同时呈现当前生效的 Influence 线索和符合伦理的改写版本。

File	Purpose
references/persuasion/knowledge.md	Core concepts and source-grounded definitions
references/persuasion/rules.md	Rules, boundaries, and practical guidelines
references/persuasion/examples.md	Bad/better examples for applied situations
references/persuasion/smells.md	Red flags and anti-patterns to detect
references/persuasion/checklist.md	Fast review checklist
workflows/design-persuasive-request.md	Create persuasive messaging that is useful, credible, and agency-preserving.

文件	用途
references/persuasion/knowledge.md	核心概念和有来源依据的定义
references/persuasion/rules.md	规则、边界和实用指南
references/persuasion/examples.md	不同应用场景下的不良/改进示例
references/persuasion/smells.md	需要识别的危险信号和反模式
references/persuasion/checklist.md	快速审查清单
workflows/design-persuasive-request.md	创建有用、可信且能够保留用户自主性的说服性信息。

Operating Principles

操作原则

Use only honest evidence. Do not invent popularity, scarcity, credentials, endorsements, or social connection.
Separate helping a good decision from pushing a shortcut response. If the cue is counterfeit, treat it as a red flag.
When rewriting, preserve user agency: add context, alternatives, and enough time to decide when stakes are meaningful.

仅使用真实证据。不要虚构受欢迎程度、稀缺性、资历、背书或社会联系。
将帮助用户做出正确决策与诱导用户走捷径区分开来。如果某一线索是伪造的，应将其视为危险信号。
改写时保留用户自主性：补充上下文、替代选项，并在风险较高时留出足够的决策时间。

Output Pattern

输出模式

Diagnosis - name the influence principle or cue.
Evidence Check - state what proof supports or is missing from the cue.
Risk - explain manipulation, trust, or decision-quality risk.
Rewrite or Recommendation - provide an ethical alternative.

诊断——指明所采用的 Influence 原则或线索。
证据检查——说明有哪些证据支持该线索，以及缺少哪些证据。
风险——说明操纵、信任或决策质量方面的风险。
改写或建议——提供符合伦理的替代方案。

Validation

验证

Use the prompts in

evals/evals.json

as smoke tests. A good result identifies the relevant Influence principle, preserves user agency, and avoids fabricated evidence or coercive pressure.

将

evals/evals.json

中的提示用作冒烟测试。优秀的结果能够识别相关的 Influence 原则、保留用户自主性，并避免捏造证据或施加胁迫性压力。