Prompt Engineering From Scratch in 5 Days
Course questions · 15 / 15
D1 What a Prompt Is, and Isn't: How the Model Reads Instructions; the Four Elements of Role / Task / Format / Constraints
What exactly is being engineered in prompt engineering, and how does it differ from writing a requirements doc or a design spec?提示词工程到底在工程什么?它和写需求文档、写技术方案有什么本质区别?
Common in ChinaCommon overseasBasic#prompt-basics#mental-model🔒 Unlock D1 to see the answer keys.
What problem does each of the four prompt elements — role, task, format, constraints — solve? If you could keep only three, which would you drop and why?角色、任务、格式、约束四要素各解决什么问题?如果只能保留三个,你会砍掉哪个,为什么?
Common in ChinaCommon overseasIntermediate#prompt-basics#four-elements🔒 Unlock D1 to see the answer keys.
Why do rules belong in the system prompt rather than the user message? Cover adherence, control, and cost, and name what the system prompt cannot guarantee.为什么规则要放系统提示而不是用户消息?请从遵从度、管控和成本三个角度说明,并指出系统提示做不到什么。
Common in ChinaCommon overseasIntermediate#system-prompt#prompt-basics🔒 Unlock D1 to see the answer keys.
D2 Few-Shot, Chain of Thought, Step-by-Step, and Self-Checks; When None of These Work
Why does few-shot prompting work, what goes wrong when you give too many examples, and how do you decide how many to include?few-shot 为什么有效?示例给多了会出什么问题?你怎么决定给几个?
Common in ChinaCommon overseasBasic#few-shot#prompt-techniques🔒 Unlock D2 to see the answer keys.
Where does chain-of-thought prompting help most, where is it a waste, and how does it differ from splitting a task into steps?思维链在什么任务上提升明显,在什么任务上是浪费?它和「分步」有什么区别?
Common in ChinaCommon overseasIntermediate#chain-of-thought#prompt-techniques🔒 Unlock D2 to see the answer keys.
What are the signs of a task that no amount of prompt engineering will fix, and what do you do when you hit one?提示词写得再好也做不对的任务有哪些特征?遇到这类任务你会怎么办?
Common in ChinaCommon overseasIntermediate#prompt-limits#failure-modes🔒 Unlock D2 to see the answer keys.
D3 Structured Output: JSON Schema, Templates and Variables, Multilingual Output
Why should structured output be enforced with a schema instead of a 'please respond in JSON' instruction, and do you still need validation once the schema passes?结构化输出为什么要用 schema 约束,而不是在提示词里写「请输出 JSON」?schema 通过之后还需要校验吗?
Common in ChinaCommon overseasBasic#structured-output#json-schema🔒 Unlock D3 to see the answer keys.
In a prompt template, what should become a variable and what should stay constant, and what goes wrong when you have too many variables?提示词模板里哪些内容该做成变量,哪些该写死?变量多了会有什么问题?
Common in ChinaCommon overseasIntermediate#prompt-template#structured-output🔒 Unlock D3 to see the answer keys.
When the model's JSON fails to parse or validate, how do you design the fallback — how many retries, how do you retry, and what happens after the last failure?模型返回的 JSON 解析或校验失败时,你会怎么设计兜底?重试几次、怎么重试、失败之后怎么办?
Common in ChinaCommon overseasIntermediate#structured-output#error-handling🔒 Unlock D3 to see the answer keys.
D4 Iteration and Evaluation: Small Test Sets, A/B Testing, Version Control, Common Anti-Patterns
How do you build a test set for a prompt? How would you choose ten samples, and where do the expected answers come from?怎么给一个提示词建测试集?十条样本该怎么挑,标准答案从哪来?
Common in ChinaCommon overseasBasic#evaluation#test-set🔒 Unlock D4 to see the answer keys.
How do you version prompts? How does it differ from versioning code, and what is your first move when production misbehaves?提示词版本化怎么做?它和代码版本管理有什么不同?线上出问题你先做什么?
Common in ChinaCommon overseasIntermediate#prompt-versioning#evaluation🔒 Unlock D4 to see the answer keys.
Is using a model to grade another model's output reliable? When is it acceptable, and when must a human look?用模型给模型打分靠谱吗?什么时候可以用,什么时候必须人工看?
Common in ChinaCommon overseasIntermediate#evaluation#llm-as-judge🔒 Unlock D4 to see the answer keys.
D5 Migrating Across Models: Differences Between Claude / GPT / Domestic Chinese Models, Organizing the System Prompt; Where to Go Next — the Claude Course or the Codex Course
When you move a prompt from one model vendor to another, where does it break most often, and how do you tell a prompt problem from a genuine capability gap?同一份提示词从一家模型迁到另一家,最常坏在哪里?你怎么区分是提示词的问题还是模型能力的问题?
Common in ChinaCommon overseasIntermediate#model-migration#cross-model🔒 Unlock D5 to see the answer keys.
How should a system prompt be organized so it ports across models, and how do you decide which block a given sentence belongs to?系统提示应该怎么组织才方便跨模型复用?怎么判断某一句该放哪一块?
Common in ChinaCommon overseasIntermediate#system-prompt#model-migration🔒 Unlock D5 to see the answer keys.
After migrating a prompt, how do you verify nothing regressed, and if the pass rate drops, what is your debugging order?迁移之后怎么验证效果没有退步?如果通过率降了,你的排查顺序是什么?
Common in ChinaCommon overseasDeep dive#model-migration#evaluation🔒 Unlock D5 to see the answer keys.