大部分候选人带着 2-3 个故事进行为面试，剩下都是临场——所以答案听着空。修复方法是系统挖矿：提取近 1-3 年事件、按主题聚类、识别缺口、把覆盖 90% 行为题的 8-12 个故事练熟。下面 15 个模板让挖矿变得结构化而不焦虑。
适合哪些场景
准备行为面试重度的 loop（Amazon、Meta、Google、头部咨询），项目记忆变模糊的工程师 / PM，需要把非传统经历翻译成可讲故事的转行者。
什么时候不建议这样写 Prompt
不足 6 个月工作经验的不用——素材太少。目标 loop 纯技术、零行为题的也不用。
Prompt 结构公式
故事挖掘类 Prompt 一定要带这六个要素：
- 角色：让 AI 扮演谁（recruiter、HR、职业教练、同级面试官）。
- 上下文：目标岗位、行业、级别、地区、你的背景、你在回应的 JD 或邮件。
- 目标：一个具体可交付物——改写后的 bullet、关键词排序、STAR 答案、follow-up 邮件。
- 限制：AI 不能做什么（别编造指标、别改事实、别堆我答不出的术语）。
- 输出格式：编号清单、markdown 表格、并排对比、带打分的排序。
- 示例 / 信号：1-2 段你自己的真实语气，或一份”好输出”参考。
这套 Prompt 适合用在哪
- 从 1-3 年工作中搭故事库
- 从非传统 / 非线性履历里翻出可转移故事
- 已知 loop 偏行为面试时补主题缺口
- 简历隐藏了故事时回忆具体事件
- loop 前预演 8-12 个故事，避免临场即兴
15 个可直接复制的 Prompt 模板
1. 一年回顾记忆倾倒
从这条开始——先要原始材料，再做结构。
Help me do a memory dump of the past 12 months at work. Ask me 10 prompting questions, one at a time, that surface concrete events: a difficult decision, a conflict, a stretch project, a failure, a moment of leadership, a learning, a cross-functional fight, a launch, a mentor moment, a politically tricky moment. Wait for my answer after each question — do NOT batch all 10.
Start with question 1.2. 从 bullet 还原故事
Below is one resume bullet. Help me reconstruct the story behind it by asking 6 targeted questions: who was involved, what was the trigger, what alternative paths existed, what I chose, what surprised me, what I would do differently. Wait for my answers before producing the STAR. Then format into STAR (≤200 words).
Bullet: "{paste}"3. 主题聚类
Below are 15 raw events from my last 2 years. Cluster them into 8 behavioral themes: leadership, conflict, failure, ambiguity, impact, learning, ethics, cross-functional, growth, prioritization, influence-without-authority, customer-obsession, decision-under-uncertainty. For each cluster, mark the strongest event. List clusters with 0 events — those are gaps.
Events:
{paste 15 short descriptions}4. 主题缺口检测
I have stories for these themes: {list}. The target loop is at {company / role family}, which typically asks heavily about {their LP / values}. Map my current story coverage against their LP. Output a table: LP / theme | story I have | strength (Strong / Weak / Missing). Rank top 3 gaps to fill.5. 一个事件三种视角
I have ONE story (paste below). Rewrite it 3 ways for 3 different behavioral question themes: e.g., once for "leadership", once for "dealing with ambiguity", once for "learning from failure". Same facts, different emphasis. Mark which themes the same event genuinely supports vs which would be a stretch.
Event: {paste}6. 失败故事挖掘
Help me surface a failure story I can use in interviews. Ask 5 questions one at a time to extract a real failure that meets: (1) I owned the outcome, (2) it had consequences, (3) I learned and changed behavior, (4) I can tell it without blaming others, (5) it is not so catastrophic it kills the loop. Wait between questions.7. 冲突故事挖掘
Help me surface a conflict story. Ask 6 questions to extract: who was the conflict with (peer, manager, cross-functional), what was the substantive disagreement (not personality), what I did to understand the other side, what we changed, what the outcome was, what principle I extracted. Wait between questions.8. 模糊情境决策故事挖掘
Surface an ambiguity story. Ask 5 questions covering: what was unclear (goal / data / stakeholders / timeline), how I narrowed the unknowns, what I committed to despite gaps, what the outcome was, what I would commit to faster next time. One question at a time.9. 无 authority 跨职能影响故事
Surface a story about influencing someone I had no authority over. Ask 6 questions to extract: who, what I needed from them, why they resisted, what evidence I used, what I changed in my approach, what happened. End with a 1-line principle. Wait between questions.10. 资深岗位”扩展 scope”故事
For senior-and-above interviews, mine a story where I expanded scope beyond my role. Ask 5 questions: what gap I noticed, why nobody else was filling it, what I did without explicit permission, how I socialized the work, what changed structurally. Wait between questions.11. 客户至上故事（Amazon LP 风格）
Surface a customer-obsession story. Ask 6 questions: who the customer was (internal or external), what their unmet need was, how I learned about it, what I built / changed, what data showed the impact, what I would do differently. One question at a time.12. 带人成长故事
Surface a story about growing another person. Ask 5 questions: who they were, what they needed, what I did consistently over time (not one-off), what evidence shows they grew, what I learned about my own management style. Wait between questions.13. 故事新鲜度审计
loop 前 1 周跑。
Below is my story bank. For each story, score on 4 dimensions (0-3 each): (A) clarity in 90 seconds, (B) quantification or specificity, (C) theme fit, (D) my comfort delivering it. Rank from strongest to weakest. Flag any story <2 on dimension (D) — I should swap or rehearse.
Story bank:
{paste}14. 故事时长压缩
Below is one of my behavioral stories at full length (paste). Compress to: (A) 30-second screen version, (B) 90-second standard version, (C) 3-minute deep-dive version with optional add-ons. All three must hit STAR — situation, task, action, result. Mark which details to add when interviewer probes.
Full story:
{paste}15. 故事库覆盖矩阵
最后跑；给你 loop 级覆盖视图。
Below is my full story bank (8-12 stories). Map them against a matrix of behavioral question types: {failure, conflict, leadership, ambiguity, impact, learning, ethics, customer, cross-functional, prioritization, influence, growth}. Output a matrix: rows = stories, columns = themes, cells = strong / partial / no. Highlight stories that cover 3+ themes — those are your workhorses.
Stories:
{paste}容易踩的坑
- 先聚类后挖矿——只能找到已经符合你心智模型的故事。
- 让 AI 编故事而不是挖你自己的——追问下守不住细节。
- 只有 2-3 个故事硬塞所有问题——面试官一眼看穿。
- 不做新鲜度审计——6 个月前写的故事和现在的讲法已经漂移。
- 压得太短——30 秒版没空间落到 principle。
- 压得不够——5 分钟故事烧掉面试官时间预算。
- 只在最近一年里挖——更早的 stretch 项目影响力往往更大。
优化技巧
- 挖矿要写下来，别在脑子里。记忆 + AI 提问比纯回忆多 3 倍事件。
- 搭 8-12 个故事，每个覆盖 2-3 主题——比 20 个单主题强。
- 先把 result 一句话写出来。一句话写不出，故事还没成型。
- 出声预演、独自计时。口述时长和书面感觉完全不同。
- 记”故事日记”——每周记一个面试可用事件，一年就是组合拳。
- 每个故事预测 3 个追问，每个写 30 秒答案。
- 找朋友或同梯候选人试讲。如果对方问”然后呢”，result 还不够强。
FAQ
- 准备多少故事够？: 8-12 个，每个覆盖 2-3 主题。少于 6 个会明显复用；多于 15 个保持不住新鲜度。
- 故事要多近期？: 大多数近 2-3 年。1 个更早的高影响力故事可以；超过 5 年就显得旧。
- 学校 / 副业可以拿来讲吗？: 应届可以；有工作经验的，副业 scope 得跟正职可比才行。
- 结果不好的故事怎么讲？: 失败故事很值钱——前提是你能讲出 learning 和行为改变。没有 learning 就没有故事。
- AI 应该直接生成完整 STAR 吗？: AI 应该把你的原料结构化成 STAR，不应该编细节。每一条都要确保你能守住。
- 故事库多久刷新一次？: 每 6-12 个月一次，或开新 loop 时一次。旧故事和你当前语气会漂移。