Back to Details

errors-mistakes

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Mistakes: errors of intention

错误类型：意图错误

A mistake happens when the user's action matched their intent — but the intent was wrong because their model of the situation was wrong. They misread an alarm; misjudged a chart; chose the wrong option from a menu they misunderstood. Unlike slips, mistakes are usually unrecognized at the moment they happen — the user is confident they're doing the right thing.
The design responses for mistakes work upstream of action: better information, clearer system state, training, conventions that match user expectations.
当用户的操作符合其意图，但该意图因用户对情境的认知模型错误而出现偏差时，就会产生意图错误。比如用户误读警报、误判图表、从误解的菜单中选择错误选项。与操作失误（slips）不同，意图错误通常在发生时不会被用户察觉——用户坚信自己在做正确的事。
针对意图错误的设计应对措施需在用户操作前介入：提供更清晰的信息、明确系统状态、开展培训、采用符合用户预期的设计惯例。

The three mistake subtypes (from the book)

三种意图错误子类型（源自书籍）

Perception mistakes

感知错误

Wrong action because of misread information.
Design responses:
  • Improve situational awareness (clear, distinctive feedback).
  • Show trends and historical data, not just point-in-time values.
  • Provide clear and distinctive feedback at decision points.
html
<!-- Point-in-time only — perception-mistake-prone -->
<p>CPU: 45%</p>

<!-- With trend — clearer -->
<div class="metric">
  <p>CPU: 45%</p>
  <span class="trend trend--up">↑ Rising over last hour</span>
  <canvas class="sparkline"></canvas>
</div>
因误读信息而采取错误操作。
设计应对措施：
  • 提升情境感知能力（清晰、独特的反馈）。
  • 展示趋势和历史数据，而非仅显示实时单点数据。
  • 在决策节点提供清晰、独特的反馈。
html
<!-- 仅显示实时数据——易引发感知错误 -->
<p>CPU: 45%</p>

<!-- 附带趋势信息——更清晰 -->
<div class="metric">
  <p>CPU: 45%</p>
  <span class="trend trend--up">↑ 过去一小时持续上升</span>
  <canvas class="sparkline"></canvas>
</div>

Decision mistakes

决策错误

Wrong action under stress, bias, or overconfidence.
Design responses:
  • Minimize information and environmental noise.
  • Use checklists and decision trees for high-stakes decisions.
  • Train on error recovery and troubleshooting.
  • Reduce time pressure where possible.
A monitoring console for production incidents that surfaces a checklist of likely causes ("Check service X first, then Y, then Z") reduces decision mistakes during stressful incidents.
在压力、偏见或过度自信下采取错误操作。
设计应对措施：
  • 减少信息干扰和环境噪音。
  • 针对高风险决策使用检查表和决策树。
  • 开展错误恢复和故障排查培训。
  • 尽可能降低时间压力。
例如，用于生产事件的监控控制台可展示可能原因的检查表（“先检查服务X，再检查Y，最后检查Z”），从而减少压力场景下的决策错误。

Knowledge mistakes

认知错误

Wrong action because of missing knowledge.
Design responses:
  • Memory and decision aids in context.
  • Standardized naming and operational conventions.
  • Training using case studies and simulations.
  • Mnemonic devices.
A new user encountering an unfamiliar feature for the first time benefits from inline help, walkthroughs, or progressive-disclosure of complexity.
因知识缺失而采取错误操作。
设计应对措施：
  • 提供上下文内的记忆辅助和决策辅助工具。
  • 采用标准化命名和操作惯例。
  • 通过案例研究和模拟开展培训。
  • 使用记忆辅助装置。
首次接触陌生功能的新用户可受益于内嵌帮助、引导流程或逐步展示的复杂功能。

Common mistake-prevention patterns

常见的错误预防模式

Surfacing system state

展示系统状态

Many mistakes flow from invisible system state. The user thinks the system is in mode A; it's actually in mode B; their action is correct for A but wrong for B.
Design response: make state visible. Modal indicators, status bars, breadcrumbs all help.
html
<header class="env-banner env-banner--prod">
  ⚠ Production environment — actions affect live customers
</header>
A visible "PROD" banner on production tools prevents the mistake of running staging-style commands against real customer data.
许多意图错误源于不可见的系统状态。用户认为系统处于模式A，但实际处于模式B；他们的操作对模式A是正确的，但对模式B则是错误的。
设计应对措施：让系统状态可见。模态指示器、状态栏、面包屑导航等都能起到帮助作用。
html
<header class="env-banner env-banner--prod">
  ⚠ 生产环境——操作会影响真实客户
</header>
生产工具上显示醒目的“PROD”横幅，可防止用户针对真实客户数据执行 staging（预发布）环境下的命令这类错误。

Decision trees and guided flows

决策树与引导流程

For complex decisions, walk the user through. Each step narrows the option space.
Are you trying to...
  (•) Fix a customer issue
  ( ) Make a code change
  ( ) Run a migration

[Continue]
Then based on the answer, the next set of options is contextual. The user can't easily make a mistake by picking from a flat list of 30 options because the context narrows the space.
针对复杂决策，引导用户逐步操作。每一步都缩小选项范围。
您想要...
  (•) 解决客户问题
  ( ) 进行代码修改
  ( ) 执行迁移

[继续]
然后根据用户的选择，展示下一组上下文相关的选项。用户不会轻易从30个选项的扁平列表中选错，因为上下文已经缩小了选择范围。

Trend-aware displays

趋势感知型展示

Replace point-in-time displays with trend-aware ones. The single number "23%" hides a trajectory; the sparkline reveals it.
将实时单点展示替换为趋势感知型展示。单一数字“23%”隐藏了变化轨迹，而迷你折线图（sparkline）则能揭示这一轨迹。

Checklists

检查表

Borrowed from aviation and medicine. A checklist forces the user to verify each prerequisite explicitly. Surgical "time-out" checklists, pilot pre-takeoff checklists, and software pre-deployment checklists all prevent decision and knowledge mistakes by externalizing memory.
源自航空和医疗领域。检查表强制用户明确验证每个前提条件。手术中的“暂停确认”检查表、飞行员起飞前检查表以及软件部署前检查表，都通过外部化记忆来防止决策错误和认知错误。

Conventions and standards

设计惯例与标准

When users encounter unfamiliar systems, they apply conventions from familiar ones. If your system honors conventions (cmd-K opens command palette, Esc closes overlays), users transfer prior knowledge correctly. If you violate them, users transfer prior knowledge incorrectly — knowledge mistakes ensue.
当用户接触陌生系统时，会套用熟悉系统的惯例。如果您的系统遵循惯例（如cmd-K打开命令面板、Esc关闭弹窗），用户就能正确迁移已有知识。如果违背这些惯例，用户就会错误迁移已有知识——进而引发认知错误。

Inline help in context

上下文内嵌帮助

Don't rely on documentation pages users won't visit. Surface help in the moment: a "?" icon next to ambiguous fields with a tooltip, an info-banner explaining a section's purpose, contextual onboarding hints.
不要依赖用户不会访问的文档页面。在关键时刻展示帮助：模糊字段旁的“?”图标及提示框、解释某部分用途的信息横幅、上下文引导提示。

Mistake-prone contexts

易引发意图错误的场景

  • Novel situations — the user's model doesn't apply.
  • Ambiguous information — multiple plausible interpretations.
  • High-stakes decisions under stress — judgment narrows.
  • Cross-domain transfers — applying conventions from one domain to another that doesn't share them.
  • Edge cases — situations the user hasn't seen before.
  • First-time users of any feature — knowledge gap.
  • 全新场景——用户的认知模型不适用。
  • 模糊信息——存在多种合理解读。
  • 高压下的高风险决策——判断力受限。
  • 跨领域迁移——将某一领域的惯例应用到不兼容的另一领域。
  • 边缘情况——用户从未遇到过的场景。
  • 首次使用某功能的用户——存在知识缺口。

Anti-patterns

反模式

  • Hidden system state. User assumes the system is in one state; it's actually in another.
  • Cryptic error messages that don't help the user understand what's wrong.
  • Conventions violated without warning. A "Save" button that doesn't save, or saves to a different location.
  • Onboarding for new users that's just a tour. Watching demo videos doesn't transfer knowledge as well as guided practice.
  • Single-point-in-time displays for trending phenomena. Hides the trajectory.
  • 隐藏系统状态。用户认为系统处于某种状态，但实际并非如此。
  • 晦涩的错误提示——无法帮助用户理解问题所在。
  • 无预警地违背惯例。比如“保存”按钮不执行保存操作，或保存到其他位置。
  • 仅为新用户提供演示式引导。观看演示视频的知识迁移效果远不如实操引导。
  • 针对趋势性现象仅展示实时单点数据——隐藏了变化轨迹。

Heuristics

启发式原则

  1. The "what's the user's model?" check. Before designing a flow, ask what model the user is likely to bring. Designs that match it prevent mistakes; designs that violate it cause them.
  2. The state-visibility audit. What state are users in right now? Can they see it? If not, they can mistake.
  3. The novel-situation walkthrough. For unfamiliar features, walk a new user through. Note where their model diverges from the system; design responses there.
  1. “用户的认知模型是什么？”检查。在设计流程前，先思考用户可能持有的认知模型。与其匹配的设计可防止错误；与之相悖的设计则会引发错误。
  2. 系统状态可见性审核。用户当前处于何种系统状态？他们能否看到该状态？如果不能，就可能引发错误。
  3. 全新场景走查。针对陌生功能，引导新用户走查流程。记录用户认知模型与系统不符的地方，并在这些位置设计应对措施。

Related sub-skills

相关子技能

  • errors
     (parent).
  • errors-slips
     — the complementary error type; execution rather than intention.
  • mental-model
     — mistakes flow from wrong models; mental-model design prevents them.
  • expectation-effect
     — when the system violates expectation, mistakes follow.
  • visibility
     — system state must be visible to be reasoned about.
  • mimicry
     — borrowing conventions reduces knowledge-mistakes.
  • errors
    （父项）。
  • errors-slips
    ——互补的错误类型；属于执行错误而非意图错误。
  • mental-model
    ——意图错误源于错误的认知模型；认知模型设计可防止此类错误。
  • expectation-effect
    ——当系统违背用户预期时，就会引发错误。
  • visibility
    ——系统状态必须可见才能被用户正确判断。
  • mimicry
    ——借鉴惯例可减少认知错误。