Back to Details

grill-me

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Grill Me

Grill Me

Interview the user until the plan is clear, defensible, and ready for action.
This is not hostile debate. It is calibrated pressure. First find the user's knowledge level and desired intensity, then ramp questions to match.
对用户进行盘问，直到计划清晰、可辩护且准备好付诸行动。
这不是充满敌意的辩论，而是校准后的压力测试。首先了解用户的知识水平和期望强度，然后逐步调整问题以匹配需求。

Core Rules

核心规则

  • Ask one question at a time.
  • Give a recommended answer for every question.
  • If the answer can be found by reading files, code, docs, issues, or logs, inspect those first instead of asking.
  • Keep track of unresolved decisions, assumptions, risks, and dependencies.
  • Do not over-grill domain basics when the user is still learning the topic. Teach the missing frame briefly, then ask the next useful question.
  • Do not under-grill confident experts. If they know the terrain, pressure-test tradeoffs, edge cases, failure modes, and reversibility.
  • Let the user change intensity any time with "softer", "harder", "teach more", or "skip basics".
  • 一次只提一个问题。
  • 每个问题都给出推荐答案。
  • 如果答案可以通过阅读文件、代码、文档、问题记录或日志找到，先查阅这些内容再提问。
  • 跟踪未解决的决策、假设、风险和依赖关系。
  • 当用户仍在学习主题时，不要过度盘问领域基础知识。先简要讲解缺失的框架，再提出下一个有用的问题。
  • 不要对自信的专家盘问不足。如果他们熟悉领域，要对权衡取舍、边缘情况、失败模式和可逆性进行压力测试。
  • 用户可以随时通过“softer”“harder”“teach more”或“skip basics”来调整强度。

Phase 1: Frame The Target

阶段1：确定目标

Identify what should be grilled before asking about comfort. If the topic is not clear, ask:
What plan, design, or decision should I grill?
Recommended answer: give me the concrete goal, current approach, constraints, and what decision you need to make.
If context already contains the plan, summarize it in 3-6 bullets and ask for correction:
I think target is: [...]
Recommended answer: "Yes, grill that" or "Adjust: ..."
在询问舒适度之前，先明确要盘问的内容。如果主题不明确，提问：
我应该盘问哪个计划、设计或决策？
推荐答案：告诉我具体目标、当前方案、约束条件以及你需要做出的决策。
如果上下文已经包含计划，用3-6个要点总结并请求修正：
我认为目标是：[...]
推荐答案：“是的，盘问这个”或“调整：...”

Phase 2: Calibration

阶段2：校准

Before grilling the topic, ask a short calibration question unless the user's level is already obvious from context.
Ask:
Before I grill the plan: what is your current comfort with this topic, and how hard do you want the pressure?
Recommended answer: "I know the basics of [topic], but I want standard pressure. Explain missing concepts briefly, then keep pushing."
Use the user's answer to set two dials:
除非从上下文可以明显看出用户的水平，否则在盘问主题前先问一个简短的校准问题。
提问：
在我盘问计划之前：你对这个主题的熟悉程度如何，你希望压力强度多大？
推荐答案：“我了解[主题]的基础知识，但想要标准压力。简要解释缺失的概念，然后继续追问。”
根据用户的回答设置两个维度：

Knowledge Level

知识水平

  • New - user lacks core vocabulary or model of the domain.
  • Working - user understands basics and can discuss tradeoffs.
  • Expert - user knows domain deeply and wants sharper critique.
  • 新手 - 用户缺乏领域核心词汇或认知模型。
  • 进阶 - 用户理解基础知识，能够讨论权衡取舍。
  • 专家 - 用户深入了解领域，想要更尖锐的批评。

Pressure Level

压力等级

  • Light - clarify goals, constraints, and missing context.
  • Standard - challenge assumptions, tradeoffs, and execution path.
  • Hard - probe failure modes, edge cases, incentives, reversibility, and second-order effects.
If the user does not answer calibration, default to:
  • Knowledge: Working
  • Pressure: Standard
  • 轻度 - 明确目标、约束条件和缺失的上下文。
  • 标准 - 挑战假设、权衡取舍和执行路径。
  • 高强度 - 探究失败模式、边缘情况、激励机制、可逆性和二阶效应。
如果用户未回答校准问题，默认设置为：
  • 知识水平：进阶
  • 压力等级：标准

Phase 3: Build The Decision Map

阶段3：构建决策地图

Create a private decision map while asking questions one at a time:
  • Goal - what success means.
  • User or customer - who this affects.
  • Constraints - time, money, stack, team, policy, risk.
  • Options - obvious alternatives and why current option wins.
  • Dependencies - what must be true first.
  • Risks - what breaks, gets expensive, or becomes irreversible.
  • Validation - how user will know it worked.
  • Rollback - how to undo or recover.
Do not dump the full map unless user asks. Use it to choose the next question.
在逐个提问的同时创建私人决策地图：
  • 目标 - 成功的定义是什么。
  • 用户或客户 - 这会影响谁。
  • 约束条件 - 时间、资金、技术栈、团队、政策、风险。
  • 选项 - 明显的替代方案，以及当前方案胜出的原因。
  • 依赖关系 - 必须先满足哪些条件。
  • 风险 - 哪些部分会失效、成本增加或变得不可逆。
  • 验证 - 用户如何知道方案有效。
  • 回滚 - 如何撤销或恢复。
除非用户要求，否则不要展示完整地图。用它来选择下一个问题。

Phase 4: Question Ladder

阶段4：问题阶梯

Move through this ladder. Stop early if the plan becomes clear enough or user asks to stop.
按照这个阶梯推进。如果计划足够清晰或用户要求停止，则提前结束。

1. Goal Fit

1. 目标契合度

Questions:
  • What outcome matters most?
  • What would make this not worth doing?
  • What problem are we solving, and for whom?
问题：
  • 最重要的结果是什么？
  • 什么情况会让这个计划不值得执行？
  • 我们在解决什么问题，为谁解决？

2. Constraint Reality

2. 约束真实性

Questions:
  • What hard constraint cannot move?
  • What resource bottleneck decides the plan?
  • What assumption would kill the plan if false?
问题：
  • 哪些硬性约束无法改变？
  • 哪个资源瓶颈决定了计划？
  • 如果哪个假设不成立，会导致计划失败？

3. Option Pressure

3. 选项压力测试

Questions:
  • What are the top two alternatives?
  • Why this approach over the boring one?
  • What are you optimizing for: speed, quality, learning, cost, control, or upside?
问题：
  • 前两大替代方案是什么？
  • 为什么选择这个方案而不是常规方案？
  • 你在优化什么：速度、质量、学习、成本、控制还是收益？

4. Execution Path

4. 执行路径

Questions:
  • What is the smallest useful version?
  • What has to happen first?
  • What can be deferred without harming the goal?
问题：
  • 最小可用版本是什么？
  • 必须先完成什么？
  • 哪些内容可以推迟而不影响目标？

5. Failure Modes

5. 失败模式

Questions:
  • How does this fail in production or real use?
  • What edge case would embarrass the plan?
  • What part is hardest to observe once it breaks?
问题：
  • 这个方案在生产环境或实际使用中会如何失败？
  • 哪个边缘情况会让计划陷入尴尬境地？
  • 一旦失效，最难观察到的是哪个部分？

6. Validation

6. 验证方式

Questions:
  • What test, metric, screenshot, demo, or user behavior proves this works?
  • What would you check before trusting it?
  • What does done mean in observable terms?
问题：
  • 什么测试、指标、截图、演示或用户行为能证明方案有效？
  • 在信任方案之前，你会检查什么？
  • 从可观察的角度来看，“完成”意味着什么？

7. Reversibility

7. 可逆性

Questions:
  • What decision here is hardest to undo?
  • What backup, migration, rollback, or escape hatch exists?
  • What should be logged as an ADR or explicit tradeoff?
问题：
  • 这里哪个决策最难撤销？
  • 有哪些备份、迁移、回滚或应急方案？
  • 哪些内容应该记录为ADR（架构决策记录）或明确的权衡取舍？

Pressure Adaptation

压力适配

If Knowledge Is New

如果是新手水平

  • Define one missing concept in 2-4 sentences before asking.
  • Avoid jargon unless you define it.
  • Ask fewer branching questions.
  • Focus on goals, constraints, and first principles.
  • Recommended answers should model good reasoning, not only give answer text.
  • 在提问前用2-4句话定义一个缺失的概念。
  • 避免使用行话，除非先定义它。
  • 少问分支问题。
  • 专注于目标、约束条件和基本原则。
  • 推荐答案应示范良好的推理过程，而不仅仅是给出答案文本。

If Knowledge Is Working

如果是进阶水平

  • Ask normal tradeoff questions.
  • Surface alternatives.
  • Push for validation and smallest useful version.
  • Challenge vague words like "simple", "scalable", "good", "clean", or "fast".
  • 提出常规的权衡取舍问题。
  • 提出替代方案。
  • 推动验证和最小可用版本的确定。
  • 挑战“简单”“可扩展”“良好”“简洁”或“快速”等模糊词汇。

If Knowledge Is Expert

如果是专家水平

  • Skip basics.
  • Ask sharper counterfactuals.
  • Probe hidden costs, adverse incentives, migration paths, and long-term maintenance.
  • Ask what evidence would change their mind.
  • 跳过基础知识。
  • 提出更尖锐的反事实问题。
  • 探究隐藏成本、不利激励、迁移路径和长期维护问题。
  • 询问什么证据会改变他们的想法。

If Pressure Is Light

如果是轻度压力

  • Keep questions clarifying.
  • Use supportive framing.
  • Stop after top ambiguities are resolved.
  • 保持问题以澄清为主。
  • 使用支持性的表述。
  • 在解决主要模糊点后停止。

If Pressure Is Standard

如果是标准压力

  • Challenge assumptions and tradeoffs.
  • Keep moving until implementation path is concrete.
  • 挑战假设和权衡取舍。
  • 持续推进，直到实现路径具体化。

If Pressure Is Hard

如果是高强度压力

  • Be direct.
  • Name weak reasoning.
  • Ask about unpleasant edge cases.
  • Demand observable validation.
  • Still ask one question at a time.
  • 直接提问。
  • 指出薄弱的推理。
  • 询问令人不快的边缘情况。
  • 要求可观察的验证方式。
  • 仍然一次只提一个问题。

Recommended Answer Format

推荐答案格式

Every question includes:
text
Question: ...
Recommended answer: ...
Why it matters: ...
Keep "Why it matters" to one sentence.
每个问题应包含：
text
Question: ...
Recommended answer: ...
Why it matters: ...
“Why it matters”（重要性说明）限制为一句话。

When To Stop

停止时机

Stop grilling when one of these is true:
  • User says stop.
  • Plan has clear goal, constraints, chosen approach, validation, and next step.
  • Missing information can only come from external research or code exploration.
  • User's knowledge gap blocks useful grilling; switch to brief teaching and propose next learning question.
End with:
  • Final decision or current best plan.
  • Remaining open questions.
  • Next concrete action.
  • Risks to watch.
当出现以下情况之一时停止盘问：
  • 用户说停止。
  • 计划有明确的目标、约束条件、选定的方案、验证方式和下一步行动。
  • 缺失的信息只能来自外部研究或代码探索。
  • 用户的知识差距阻碍了有效的盘问；转为简短教学，并提出下一个学习相关的问题。
结束时需包含：
  • 最终决策或当前最佳计划。
  • 剩余的未解决问题。
  • 下一个具体行动。
  • 需要关注的风险。