[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-how-to-write-clear-ai-prompts-zh":3,"article-related-how-to-write-clear-ai-prompts-zh":30,"series-research-26b9fc63-b522-49ae-a07f-4a03e032027c":80},{"id":4,"slug":5,"title":6,"content":7,"summary":8,"source":9,"source_url":10,"author":11,"image_url":12,"cover_image":12,"category":13,"language":14,"translated_content":11,"related_article_id":15,"keywords":16,"key_takeaways":22,"views":26,"created_at":27,"published_at":28,"topic_cluster_id":29},"26b9fc63-b522-49ae-a07f-4a03e032027c","how-to-write-clear-ai-prompts-zh","怎麼寫清楚的 AI 提示詞","\u003Cp data-speakable=\"summary\">這篇教你把\u003Ca href=\"\u002Fnews\u002Fprompt-engineering-vague-asks-usable-outputs-zh\">模糊\u003C\u002Fa>的 AI 問題改寫成可驗證、可追蹤、較安全的研究提示詞。\u003C\u002Fp>\u003Cp>這篇給學生、研究者和辦公室工作者看，目標是讓 AI 回答更貼題、更好查證，也更適合拿來做研究\u003Ca href=\"\u002Fnews\u002Fmumbai-news-live-big-stories-shaping-city-zh\">整理\u003C\u002Fa>、寫作與找資料。\u003C\u002Fp>\u003Cp>照著做完，你會得到一套可重複使用的提示詞流程，包含角色、任務、格式、來源檢查與自我檢討，之後每次提問都能直接套用。\u003C\u002Fp>\u003Ch2>開始之前\u003C\u002Fh2>\u003Cul>\u003Cli>一個 AI 帳號，例如 \u003Ca href=\"https:\u002F\u002Fgemini.google.com\u002F\">Google Gemini\u003C\u002Fa>、\u003Ca href=\"https:\u002F\u002Fcopilot.microsoft.com\u002F\">Microsoft Copilot\u003C\u002Fa> 或 \u003Ca href=\"https:\u002F\u002Fchat.openai.com\u002F\">ChatGPT\u003C\u002Fa>\u003C\u002Fli>\u003Cli>一個可查證來源的入口，例如圖書館資料庫、Google Scholar，或可信出版社網站\u003C\u002Fli>\u003Cli>一台可正常上網的裝置與現代瀏覽器\u003C\u002Fli>\u003Cli>一個筆記工具或文件，用來保存提示詞與回覆\u003C\u002Fli>\u003Cli>一個明確的研究題目、作業要求，或待回答問題\u003C\u002Fli>\u003Cli>提示詞中不包含姓名、證號、密碼、健康資料或其他敏感資訊\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Step 1: 定義研究目標\u003C\u002Fh2>\u003Cp>目的：先說清楚你是誰、要做\u003Ca href=\"\u002Fnews\u002Fwhat-large-language-models-are-how-they-work-zh\">什麼\u003C\u002Fa>、為什麼要做，讓 AI 把回答對準你的情境，而不是只給通用說明。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779341762085-silz.png\" alt=\"怎麼寫清楚的 AI 提示詞\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>你可以先寫一句身份，再接一個具體任務，例如「我是護理系學生，正在研究飽和脂肪與人體健康。請整理支持與反對它有害健康的主要論點。」\u003C\u002Fp>\u003Cp>驗收：你應該看到回答更貼近主題，且不會大量跑到不相干的背景介紹。\u003C\u002Fp>\u003Ch2>Step 2: 加上明確限制\u003C\u002Fh2>\u003Cp>目的：用可解析的條件減少誤解，讓 AI 知道你要的範圍、格式與篇幅，降低模糊回覆的機率。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779341759036-xg87.png\" alt=\"怎麼寫清楚的 AI 提示詞\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>把任務拆成「主題 + 動作 + 輸出格式 + 限制」四段，並明確寫出字數、條列數量或語氣要求。\u003C\u002Fp>\u003Cpre>\u003Ccode>我是歷史系學生，要寫一篇關於法國大革命成因的短文獻回顧。請用 5 點條列整理主要成因，使用白話中文，並把答案控制在 250 字以內。\u003C\u002Fcode>\u003C\u002Fpre>\u003Cp>驗收：你應該看到更短、更有結構的回答，而且能遵守字數與格式要求。\u003C\u002Fp>\u003Ch2>Step 3: 指定可查證來源\u003C\u002Fh2>\u003Cp>目的：要求 AI 提供可打開、可比對的來源，避免它用看似合理但其實無法驗證的內容充數。\u003C\u002Fp>\u003Cp>你可以直接指定來源類型與時間範圍，例如近五年的同儕審查論文、政府報告，或知名學術出版社的專書。\u003C\u002Fp>\u003Cp>驗收：你應該看到連結、引文或具名來源，且能逐一打開核對；如果來源對不上主張，就先視為未驗證。\u003C\u002Fp>\u003Ch2>Step 4: 要求自我檢討\u003C\u002Fh2>\u003Cp>目的：讓 AI 自己檢查回答中的偏誤、缺口與推論弱點，補出第一輪回覆常漏掉的地方。\u003C\u002Fp>\u003Cp>在第一版答案後追問：「如果你是審稿研究者，會怎麼批評這個回答？有哪些偏誤、缺漏或未支持的主張需要再查？」\u003C\u002Fp>\u003Cp>驗收：你應該看到 AI 主動指出不確定性、缺少證據，或其他觀點，而不是只是重複原答案。\u003C\u002Fp>\u003Ch2>Step 5: 修正並驗證輸出\u003C\u002Fh2>\u003Cp>目的：把提示詞變成可重複的測試流程，當答案太廣、太窄或不準時，就根據結果改寫再試一次。\u003C\u002Fp>\u003Cp>必要時可交叉比對不同工具，最後再用圖書館資料庫、\u003Ca href=\"\u002Ftag\u002Fgoogle\">Google\u003C\u002Fa> Scholar 或權威網站核對核心主張，並把提示詞、回覆與查核筆記一起存檔。\u003C\u002Fp>\u003Cp>驗收：你應該得到一版更清楚的提示詞、一個更貼題的回答，以及一份可追溯的來源清單。\u003C\u002Fp>\u003Ctable>\u003Cthead>\u003Ctr>\u003Cth>指標\u003C\u002Fth>\u003Cth>基準／優化前\u003C\u002Fth>\u003Cth>結果／優化後\u003C\u002Fth>\u003C\u002Ftr>\u003C\u002Fthead>\u003Ctbody>\u003Ctr>\u003Ctd>回答相關性\u003C\u002Ftd>\u003Ctd>泛泛而談或偏題\u003C\u002Ftd>\u003Ctd>貼合角色、主題與目標\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>來源品質\u003C\u002Ftd>\u003Ctd>沒有引文或只有弱連結\u003C\u002Ftd>\u003Ctd>可直接核對的具名來源\u003C\u002Ftd>\u003C\u002Ftr>\u003Ctr>\u003Ctd>輸出可靠度\u003C\u002Ftd>\u003Ctd>可能有幻覺或缺少脈絡\u003C\u002Ftd>\u003Ctd>自我檢討能揭露缺口與不確定性\u003C\u002Ftd>\u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\u003Ch2>常見錯誤\u003C\u002Fh2>\u003Cul>\u003Cli>把個資或敏感資料寫進提示詞。修法：送出前先刪掉姓名、證號、健康細節與機密內容。\u003C\u002Fli>\u003Cli>只問「請告訴我這個主題」。修法：補上角色、任務、格式與來源限制。\u003C\u002Fli>\u003Cli>看到第一版答案就直接使用。修法：先開連結、核對主張，再和圖書館資料庫或可信出版社比對。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>接下來可以看什麼\u003C\u002Fh2>\u003Cp>當你能穩定寫出清楚提示詞後，可以進一步做可重用模板，例如文獻回顧、找來源、腦力激盪與草稿回饋，之後就能把同一套結構套到不同 AI 工具與不同作業題目。\u003C\u002Fp>","這篇教你把模糊的 AI 問題改寫成可驗證、可追蹤、較安全的研究提示詞。","campbellsville.libguides.com","https:\u002F\u002Fcampbellsville.libguides.com\u002FAI-as-a-research-tool\u002Fprompt-engineering",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779341762085-silz.png","research","zh","130a23e8-0358-48c7-a9f8-536298f29a50",[17,18,19,20,21],"AI 提示詞","研究查證","來源驗證","提示詞工程","Google Scholar",[23,24,25],"先寫清楚角色、任務與限制，AI 才會對準你的需求。","要求可查證來源與自我檢討，能降低幻覺與錯引風險。","把提示詞、答案和核對結果一起保存，方便重複使用與改寫。",7,"2026-05-21T05:35:30.418713+00:00","2026-05-21T05:35:30.283+00:00","0c35a120-52fc-41fc-afa3-d404eb934158",{"tags":31,"relatedLang":39,"relatedPosts":43},[32,34,36,37,38],{"name":17,"slug":33},"ai-提示詞",{"name":21,"slug":35},"google-scholar",{"name":18,"slug":18},{"name":20,"slug":20},{"name":19,"slug":19},{"id":15,"slug":40,"title":41,"language":42},"how-to-write-clear-ai-prompts-en","How to Write Clear AI Prompts","en",[44,50,56,62,68,74],{"id":45,"slug":46,"title":47,"cover_image":48,"image_url":48,"created_at":49,"category":13},"f374155a-c29e-478c-b7a5-679cad1c51e4","crdts-keep-replicas-in-sync-without-locks-zh","CRDT 讓副本不用鎖也能同步","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781011086259-4p4k.png","2026-06-09T13:17:34.493426+00:00",{"id":51,"slug":52,"title":53,"cover_image":54,"image_url":54,"created_at":55,"category":13},"4b3b5a50-45b7-4238-a38b-160f82e323ff","post-deterministic-systems-autonomous-infra-zh","後決定性分散系：自治基礎設施新框架","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781010194792-5ogb.png","2026-06-09T13:02:32.717551+00:00",{"id":57,"slug":58,"title":59,"cover_image":60,"image_url":60,"created_at":61,"category":13},"04e45398-9814-4907-b416-fcb5b8d69508","causal-learnability-formal-language-tasks-zh","用因果法量化任務可學性","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780987696075-l4g0.png","2026-06-09T06:47:34.438642+00:00",{"id":63,"slug":64,"title":65,"cover_image":66,"image_url":66,"created_at":67,"category":13},"75bcc569-5e89-45c8-b809-6f169e929f4b","rl-training-hands-off-control-gradually-zh","RL 先接管再放手","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780986786312-03yo.png","2026-06-09T06:32:32.849589+00:00",{"id":69,"slug":70,"title":71,"cover_image":72,"image_url":72,"created_at":73,"category":13},"e3ecab4b-7cc7-4246-baf6-e1c170d86ca5","omnigamearena-vlm-game-agent-benchmark-zh","OmniGameArena 讓 VLM 遊戲代理更好比","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780985893022-70pl.png","2026-06-09T06:17:32.189729+00:00",{"id":75,"slug":76,"title":77,"cover_image":78,"image_url":78,"created_at":79,"category":13},"6f25a29c-cbb8-4f53-9af7-1656b394333a","turboquant-cuts-kv-cache-memory-6x-google-tests-zh","TurboQuant 在 Google 測試中省下 6x KV 快取","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780906682236-sqe2.png","2026-06-08T08:17:21.878314+00:00",[81,86,91,96,101,106,111,116,121,126],{"id":82,"slug":83,"title":84,"created_at":85},"f18dbadb-8c59-4723-84a4-6ad22746c77a","deepmind-bets-on-continuous-learning-ai-2026-zh","DeepMind 押注 2026 連續學習 AI","2026-03-26T08:16:02.367355+00:00",{"id":87,"slug":88,"title":89,"created_at":90},"f4a106cb-02a6-4508-8f39-9720a0a93cee","ml-papers-of-the-week-github-research-desk-zh","每週 ML 論文清單，為何紅到 GitHub","2026-03-27T01:11:39.284175+00:00",{"id":92,"slug":93,"title":94,"created_at":95},"c4f807ca-4e5f-47f1-a48c-961cf3fc44dc","ai-ml-conferences-to-watch-in-2026-zh","2026 AI 研討會投稿時程整理","2026-03-27T01:51:53.874432+00:00",{"id":97,"slug":98,"title":99,"created_at":100},"cf046742-efb2-4753-aef9-caed5da5e32e","adaptive-block-scaled-data-types-zh","IF4：神經網路量化的聰明選擇","2026-03-31T06:00:36.990273+00:00",{"id":102,"slug":103,"title":104,"created_at":105},"53a0dc54-0371-4e40-8d5e-74e94a73840c","geometry-aware-similarity-metrics-for-neural-representations-zh","超越距離測量：用微分幾何重新理解神經網路","2026-03-31T06:01:01.241968+00:00",{"id":107,"slug":108,"title":109,"created_at":110},"fee7d472-a775-4b1d-bbc2-1e8bca1bbf8b","on-the-fly-repulsion-in-the-contextual-space-for-rich-divers-zh","讓AI繪圖更有創意：用排斥力提升生成多樣性","2026-03-31T06:01:25.439673+00:00",{"id":112,"slug":113,"title":114,"created_at":115},"a9901203-d69b-447b-8854-15d14eab32b4","vision-aided-beam-prediction-cnn-eca-zh","影像輔助波束預測升級 CNN","2026-04-01T10:00:25.8073+00:00",{"id":117,"slug":118,"title":119,"created_at":120},"b55e7dd4-0a24-4b3d-804d-b0309a03f498","triple-band-fss-mimo-antenna-sub-6-ghz-zh","三頻 FSS MIMO 天線瞄準 sub-6 GHz","2026-04-01T13:18:36.857305+00:00",{"id":122,"slug":123,"title":124,"created_at":125},"f68290bd-e7f3-4b30-ba22-dcd4e0130a66","openclaw-1299-repos-eight-weeks-analysis-zh","OpenClaw 1299 個 Repo 的資料解讀","2026-04-02T05:03:45.208411+00:00",{"id":127,"slug":128,"title":129,"created_at":130},"ed9f80eb-eb02-4d35-8ad4-0ddf428751dd","beam-coherence-aware-combining-mmwave-mimo-zh","毫米波 MIMO 的雙階合併法","2026-04-02T05:27:26.897188+00:00"]