commitment-ladder-design

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Commitment Ladder Design

承诺阶梯设计

Design commitments that help users act on real intent, not commitments that trap them into defending a decision. The consistency drive is useful when it supports identity-aligned action and risky when it hides changing terms.
设计有助于用户基于真实意愿行动的承诺机制,而非将用户困在为决策辩护的陷阱中。一致性驱动力在支持符合用户身份的行动时是有益的,但在隐藏条款变更时则存在风险。

Quick Start

快速开始

  1. Read
    guidelines.md
    to choose the smallest useful reference set.
  2. Load
    references/commitment/knowledge.md
    for concepts and
    references/commitment/rules.md
    for operating rules.
  3. Use
    workflows/build-commitment-ladder.md
    for repeatable tasks.
  4. For audits, surface both the active influence cue and the ethical rewrite.
  1. 阅读
    guidelines.md
    以选择最实用的参考资料集。
  2. 加载
    references/commitment/knowledge.md
    获取相关概念,加载
    references/commitment/rules.md
    获取操作规则。
  3. 使用
    workflows/build-commitment-ladder.md
    完成可重复任务。
  4. 进行审核时,同时明确当前的影响提示语以及符合伦理的改写版本。

Contents

目录

FilePurpose
references/commitment/knowledge.mdCore concepts and source-grounded definitions
references/commitment/rules.mdRules, boundaries, and practical guidelines
references/commitment/examples.mdBad/better examples for applied situations
references/commitment/smells.mdRed flags and anti-patterns to detect
references/commitment/checklist.mdFast review checklist
workflows/build-commitment-ladder.mdCreate a sequence of small, authentic commitments that lead toward a meaningful user goal.
文件用途
references/commitment/knowledge.md核心概念及基于来源的定义
references/commitment/rules.md规则、边界及实用指南
references/commitment/examples.md应用场景下的反面/优化示例
references/commitment/smells.md需要识别的危险信号及反模式
references/commitment/checklist.md快速审核清单
workflows/build-commitment-ladder.md创建一系列小型、真实的承诺,逐步引导用户达成有意义的目标。

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。不得虚构受欢迎程度、稀缺性、资质、背书或社交关联。
  • 将助力合理决策与诱导快速响应区分开。若提示语存在虚假成分,需将其视为危险信号。
  • 改写时需保留用户自主权:当决策涉及重大利益时,补充背景信息、替代选项,并给予充足的决策时间。

Output Pattern

输出模式

  1. Diagnosis - name the influence principle or cue.
  2. Evidence Check - state what proof supports or is missing from the cue.
  3. Risk - explain manipulation, trust, or decision-quality risk.
  4. Rewrite or Recommendation - provide an ethical alternative.
  1. 诊断 - 明确所采用的影响原则或提示语。
  2. 证据核查 - 说明支持或缺失该提示语的证据。
  3. 风险 - 解释操纵、信任或决策质量方面的风险。
  4. 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.
使用
evals/evals.json
中的提示作为冒烟测试。优质结果应能识别相关的影响原则、保留用户自主权,且避免伪造证据或施加强制压力。