Development
访谈我
提取用户真正想要的东西,而非他们以为自己应该想要的东西。通过每次只问一个问题的访谈来实现,直到达到约 95% 的确信度。
人们所要求的与他们真正想要的是两回事。这个技能在差距造成任何代价之前就将其弥合。
使用场景
- 请求至少缺少以下之一:谁、为什么、成功是什么样子,或起约束作用的限制条件
- 请求流于俗套而非具体("给我做个 X"、"让它更快")
- 你忍不住想从尚未摆上台面的假设开始动手
- 用户明确触发:"访谈我"、"拷问我"、"压力测试我的想法"
流程
第 1 步:提出假设,并附上确信度数字
在提出任何问题之前,先写下你当前的最佳判断,外加一个诚实的确信度数字(0–100%):
HYPOTHESIS: You want a way to answer "how are we doing?" in standup, and "dashboard" was the convention that came to mind.
CONFIDENCE: ~30% — missing: who it's for, what "metrics" means, and what success looks like
第 2 步:每次只问一个问题,每个问题都附上一个猜测
Q: <one focused question>
GUESS: <your hypothesis for the answer, with reasoning>
为什么一次只问一个,而非一次性抛出一批:
- 如果你把假设埋在一个列表里,用户就无法对它们做出反应
- 第三个问题往往取决于第一个问题的答案
- 用户用心思考的精力是有限的
为什么要附上一个猜测:
- 相比从零开始组织答案,用户对一个错误的猜测反应更快
- 它让你押注于一个可能被明显证伪的假设
第 3 步:留意"想要 vs. 应该想要"
注意:
- 那些只会套用最佳实践话术、却缺乏具体内容的回答
- 那些诉诸惯例的回答("标准做法")
- 把流行词当作目标——"现代化"、"可扩展"、"健壮"
当你听到这些时,就问:
"如果你不必向任何人解释这件事,你究竟会想要什么?"
第 4 步:用用户自己的话复述意图
当确信度较高时,把你认为用户想要的东西写回去:
Here's what I now think you want:
- Outcome: <one line>
- User: <one line — who benefits>
- Why now: <one line — what changed>
- Success: <one line — how we know it worked>
- Constraint: <one line — the binding limit>
- Out of scope: <one line — what we're explicitly not doing>
Yes / no / refine?
第 5 步:确认——明确的"是",而非"随你怎么想都行"
关卡是一个明确的"是"。以下都不算"是":
- "随你觉得怎么好都行。" → 用两个具体选项重新提问
- "听起来不错。" → 追问:"有什么你想调整的吗?"
- "行,那就开始吧。" → 这往往是礼貌性的搪塞,而非认可
95% 确信度的停止点
当你能对以下问题回答"是"时,你就完成了:
我能否预测用户对我接下来要问的三个问题的反应?
如果能,你们就达成了共识。停止访谈,并产出那份复述。
示例
User: build me a dashboard for our metrics
Agent:
HYPOTHESIS: You want a way to answer "how are we doing?" in standup.
CONFIDENCE: ~30% — missing: who it's for, what "metrics" are, success criteria
Q: When you say "how are we doing?", who's asking — you alone, the team, or up the chain?
GUESS: engineering team in standup, because "we" usually scopes that way
User: It's actually for me. I keep losing track of which experiments are running.
Agent:
Updated read: not a team dashboard. It's a personal experiment tracker. Confidence: ~60%
Q: Is the gap that you don't know which experiments exist, or that you can't see their results in one place?
GUESS: the second one. Results live in five different tools.
User: First one actually. I literally don't have a list.
Agent: Two questions in, the actual ask isn't "a dashboard." It's "a list."
验证
应用 interview-me 之后:
- 在第一轮就陈述了一个带确信度数字的假设
- 问题是每次一个、并附带猜测提出的
- 已将一份具体的复述写回给用户
- 用户以一个明确的"是"做了确认
- 在停止点,代理能够预测用户对接下来三个问题的反应