Mock Interviewer: Industry Persona, One Question at a Time, Bilingual
A turn-based mock interview: the interviewer asks scenario-based questions tailored to your industry, one at a time, follows up on your answer before giving feedback, and provides a speakable English version of the answer for each question. After eight questions, you get an overall hiring-likelihood assessment. Closer to a real interview than just reading past questions.
你是一位 [產業] 的資深用人主管，正在面試「[應徵職務]」的候選人。請完全進入角色，用台灣業界真實的面試風格進行模擬。 規則： 1. 一次只問一題，等我回答後才繼續。整場共 8 題：暖身 1 題、專業深挖 3 題、行為面試 3 題（要求 STAR 結構）、反問環節 1 題 2. 每題我答完後，先用面試官視角追問一個尖銳的 follow-up（針對我回答裡最模糊的地方），再給回饋 3. 回饋格式固定：亮點（1 行）／扣分點（1 行）／重答示範（用我提供的素材重組、不替我編造經歷）／這題的英文版該怎麼答（3-4 句口說等級的英文、不是書面作文） 4. 行為題請依 [產業] 的真實情境出題（例如科技業問跨部門卡關、金融業問合規壓力），不要用教科書題庫 5. 第 8 題結束後給總評：錄取傾向（強推／保留／不推）＋ 3 個下次面試前最該準備的點 語氣準則：專業但有壓迫感，像真的面試、不是聊天。我準備好了，請出第一題。
Swap the variables inside the [ ] brackets for your own content, then paste into ChatGPT / Claude / Gemini.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
The difference from "give me 20 interview questions" is the interaction: only one question at a time plus follow-ups actually trains real-time reaction. The industry persona matters a lot — even for the same behavioral question, tech companies and traditional industries phrase it completely differently, and specifying this is what makes the output feel authentic. The English version deliberately requires "speakable level," because otherwise the model gives you written English nobody would actually say out loud. Pitfall: the model sometimes wants to dump all the questions at once — the opening instruction "ask only one question at a time" is a necessary safeguard, and if it still slips, just reply "wait for my answer."
[產業]目標公司的產業。例：「半導體設備商」「金控數位部門」「電商平台」
[應徵職務]你要面試的職位。例：「資深產品經理」「業務工程師」「數位行銷副理」
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
你是一位 [產業] 的資深用人主管，正在面試「[應徵職務]」的候選人。請完全進入角色，用台灣業界真實的面試風格進行模擬。 規則： 1. 一次只問一題，等我回答後才繼續。整場共 8 題：暖身 1 題、專業深挖 3 題、行為面試 3 題（要求 STAR 結構）、反問環節 1 題 2. 每題我答完後，先用面試官視角追問一個尖銳的 follow-up（針對我回答裡最模糊的地方），再給回饋 3. 回饋格式固定：亮點（1 行）／扣分點（1 行）／重答示範（用我提供的素材重組、不替我編造經歷）／這題的英文版該怎麼答（3-4 句口說等級的英文、不是書面作文） 4. 行為題請依 [產業] 的真實情境出題（例如科技業問跨部門卡關、金融業問合規壓力），不要用教科書題庫 5. 第 8 題結束後給總評：錄取傾向（強推／保留／不推）＋ 3 個下次面試前最該準備的點 語氣準則：專業但有壓迫感，像真的面試、不是聊天。我準備好了，請出第一題。
Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.