[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-why-prompt-engineering-is-dead-for-ai-agents-zh":3,"tags-why-prompt-engineering-is-dead-for-ai-agents-zh":35,"related-lang-why-prompt-engineering-is-dead-for-ai-agents-zh":45,"related-posts-why-prompt-engineering-is-dead-for-ai-agents-zh":49,"series-ai-agent-8a126231-b5e1-4c89-a338-73d1d73148ff":86},{"id":4,"title":5,"content":6,"summary":7,"source":8,"source_url":9,"author":10,"image_url":11,"keywords":12,"language":19,"translated_content":10,"views":20,"is_premium":21,"created_at":22,"updated_at":22,"cover_image":11,"published_at":23,"rewrite_status":24,"rewrite_error":10,"rewritten_from_id":25,"slug":26,"category":27,"related_article_id":28,"status":29,"google_indexed_at":30,"x_posted_at":10,"tweet_text":10,"title_rewritten_at":10,"title_original":10,"key_takeaways":31,"topic_cluster_id":10,"embedding":10,"is_canonical_seed":21},"8a126231-b5e1-4c89-a338-73d1d73148ff","為什麼 AI Agent 時代，Prompt Engineering 已經死了","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fai-agent\">AI Agent\u003C\u002Fa> 的可靠性不靠更會寫提示詞，而靠上下文管理：選對資訊、控制長度、維持狀態。\u003C\u002Fp>\u003Cp>\u003Ca href=\"\u002Ftag\u002Fprompt-engineering\">Prompt engineering\u003C\u002Fa> 對 \u003Ca href=\"\u002Ftag\u002Fai-agents\">AI agents\u003C\u002Fa> 來說已經不是主戰場，因為真正決定成敗的不是措辭，而是上下文管理。Chroma 在 2025 年 7 月針對 18 個模型的研究，包含 C\u003Ca href=\"\u002Fnews\u002Fbest-solana-api-providers-for-devs-and-ai-agents-zh\">la\u003C\u002Fa>ude 4、GPT-4.1 與 \u003Ca href=\"\u002Ftag\u002Fgemini\">Gemini\u003C\u002Fa> 2.5，顯示 context 一拉長，表現就下滑，而且連簡單的檢索任務都會受影響。這代表問題不是模型「突然變笨」，而是它在錯的時間看到太多錯的資訊。\u003C\u002Fp>\u003Ch2>第一個論點\u003C\u002Fh2>\u003Cp>對 AI \u003Ca href=\"\u002Ftag\u002Fagents\">agents\u003C\u002Fa> 而言，prompt 只是包裝，真正的產品是整包上下文：指令、工具、記憶、檢索文件與任務狀態。只要這包內容雜亂，agent 就會失手，即使 prompt 寫得再工整也一樣。很多團隊把心力花在字句修飾，卻忽略了系統輸入本身才是主要變因。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778184658982-xgnl.png\" alt=\"為什麼 AI Agent 時代，Prompt Engineering 已經死了\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>Chroma 的結果之所以重要，是因為它說明退化不是線性的。context 變長不等於資訊變多、答案就更好；相反地，模型的注意力會被競爭中的 token 分散，連原本很簡單的 retrieval 任務也會變差。這不是文案問題，而是系統設計問題。\u003C\u002Fp>\u003Ch2>第二個論點\u003C\u002Fh2>\u003Cp>真正能交付穩定 agent 的團隊，不會只靠一段萬用指令。他們做的是管線：先選資料、再排序、再壓縮、再更新 context，最後才交給模型回應。這就是為什麼 context engineering 比 prompt engineering 更接近實戰：它把模型視為系統的最後一步，而不是整個系統本身。\u003C\u002Fp>\u003Cp>以客服自動化為例，把完整工單歷史、產品文件、政策全文與前一次工具輸出一次塞進去，常常比不上只給它「當前問題、相關政策片段、上一輪動作摘要」的精簡版本。這裡的關鍵不是少，而是準。對 agent 來說，正確的 300 個 token，常常勝過錯置的 3,000 個 token。\u003C\u002Fp>\u003Ch2>反方可能怎麼說\u003C\u002Fh2>\u003Cp>prompt engineering 的支持者不是完全錯。對於範圍很窄的工作流，一段精準的 system prompt 確實能大幅改善行為；清楚的格式、明確的限制、挑對的 few-shot 範例，都有實際效果。很多今天上線的 pr\u003Ca href=\"\u002Fnews\u002Fsoderbergh-ai-lennon-doc-meta-zh\">od\u003C\u002Fa>uction agent，仍然離不開這些基本功。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778184648786-twoz.png\" alt=\"為什麼 AI Agent 時代，Prompt Engineering 已經死了\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>另一個合理顧慮是，context engineering 聽起來很對，但工程成本也很高。若每個 agent 都要加 retrieval、memory m\u003Ca href=\"\u002Fnews\u002Fwhy-solana-developer-hiring-should-stop-treating-skills-as-s-zh\">ana\u003C\u002Fa>ger、summarizer 和 ranking service，團隊可能還沒做出產品，就先被基礎設施拖住。對小產品來說，強 prompt 仍然是最快的起步方式。\u003C\u002Fp>\u003Cp>但這些都是限制，不是反駁。prompt quality 是必要條件，卻不是充分條件；一旦 agent 要跨多步驟、多工具、或多個真實資料來源行動，核心問題就會變成選擇與控制，而不是修辭。Chroma 的研究也把邊界講得很清楚：context 越長，表現越差，所以真正的解法是工程化 context window，而不是繼續堆字。\u003C\u002Fp>\u003Ch2>你能做什麼\u003C\u002Fh2>\u003Cp>如果你是工程師，別再把 prompt 當成主要抽象層，改做 context pipeline：少抓資料、提高排序品質、積極摘要、並且只保留當前步驟真的需要的記憶。如果你是 PM 或創辦人，請用真實 context 負載下的任務成功率評估 agent，不要只看 demo 好不好看。問題從來不是「提示詞寫得夠不夠聰明」，而是「agent 有沒有在正確的時間拿到正確的證據」。\u003C\u002Fp>","AI Agent 的關鍵不在於把提示詞寫得更漂亮，而在於把上下文選對、排好、壓縮好；context engineering 才是可靠性的核心。","pub.towardsai.net","https:\u002F\u002Fpub.towardsai.net\u002Fprompt-engineering-is-dead-for-ai-agents-here-is-what-actually-works-541ceda072de?gi=afda2de8cc66",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778184658982-xgnl.png",[13,14,15,16,17,18],"AI agents","prompt engineering","context engineering","retrieval","context window","LLM reliability","zh",2,false,"2026-05-07T20:10:24.866536+00:00","2026-05-07T20:10:24.66+00:00","done","55810bc9-ae36-4608-b26f-12e6aeab9eb2","why-prompt-engineering-is-dead-for-ai-agents-zh","ai-agent","33341479-794d-446c-aa4e-7b8aa61c72d0","published","2026-05-08T09:00:14.75+00:00",[32,33,34],"AI agents 的主要瓶頸是上下文管理，不是提示詞措辭。","context 變長會帶來注意力分散與表現退化，尤其在檢索任務上。","可靠的 agent 需要 context pipeline，而不是更長更花俏的 prompt。",[36,38,39,41,43],{"name":14,"slug":37},"prompt-engineering",{"name":16,"slug":16},{"name":15,"slug":40},"context-engineering",{"name":17,"slug":42},"context-window",{"name":13,"slug":44},"ai-agents",{"id":28,"slug":46,"title":47,"language":48},"why-prompt-engineering-is-dead-for-ai-agents-en","Why Prompt Engineering Is Dead for AI Agents","en",[50,56,62,68,74,80],{"id":51,"slug":52,"title":53,"cover_image":54,"image_url":54,"created_at":55,"category":27},"38406a12-f833-4c69-ae22-99c31f03dd52","switch-ai-outputs-markdown-to-html-zh","怎麼把 AI 輸出改成 HTML","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778743243861-8901.png","2026-05-14T07:20:21.545364+00:00",{"id":57,"slug":58,"title":59,"cover_image":60,"image_url":60,"created_at":61,"category":27},"c7c69fe4-97e3-4edf-a9d6-a79d0c4495b4","anthropic-cat-wu-proactive-ai-assistants-zh","Cat Wu 談 Claude 的主動式 AI","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778735455993-gnw7.png","2026-05-14T05:10:30.453046+00:00",{"id":63,"slug":64,"title":65,"cover_image":66,"image_url":66,"created_at":67,"category":27},"e1d6acda-fa49-4514-aa75-709504be9f93","how-to-run-hermes-agent-on-discord-zh","如何在 Discord 執行 Hermes Agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778724655796-cjul.png","2026-05-14T02:10:34.362605+00:00",{"id":69,"slug":70,"title":71,"cover_image":72,"image_url":72,"created_at":73,"category":27},"4104fa5f-d95f-45c5-9032-99416cf0365c","why-ragflow-is-the-right-open-source-rag-engine-to-self-host-zh","為什麼 RAGFlow 是最適合自架的開源 RAG 引擎","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778674262278-1630.png","2026-05-13T12:10:23.762632+00:00",{"id":75,"slug":76,"title":77,"cover_image":78,"image_url":78,"created_at":79,"category":27},"7095f05c-34f5-469f-a044-2525d2010ce9","how-to-add-temporal-rag-in-production-zh","如何在正式環境加入 Temporal RAG","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778667053844-osvs.png","2026-05-13T10:10:30.930982+00:00",{"id":81,"slug":82,"title":83,"cover_image":84,"image_url":84,"created_at":85,"category":27},"10479c95-53c6-4723-9aaa-2fde5fb19ee7","github-agentic-workflows-ai-github-actions-zh","GitHub 把 AI 代理放進 Actions","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1778551884342-8io7.png","2026-05-12T02:11:02.069769+00:00",[87,92,97,102,107,112,117,122,127,132],{"id":88,"slug":89,"title":90,"created_at":91},"4ae1e197-1d3d-4233-8733-eafe9cb6438b","claude-now-uses-your-pc-to-finish-tasks-zh","Claude 開始幫你操作電腦","2026-03-26T07:20:48.457387+00:00",{"id":93,"slug":94,"title":95,"created_at":96},"5bede67f-e21c-413d-9ab8-54a3c3d26227","googles-2026-ai-agent-report-decoded-zh","Google 2026 AI Agent 報告解讀","2026-03-26T11:15:22.651956+00:00",{"id":98,"slug":99,"title":100,"created_at":101},"2987d097-563f-46c7-b76f-b558d8ef7c2b","kimi-k25-review-stronger-still-not-legend-zh","Kimi K2.5 評測：更強，但還不是神作","2026-03-27T07:15:55.277513+00:00",{"id":103,"slug":104,"title":105,"created_at":106},"95c9053b-e3f4-4cb5-aace-5c54f4c9e044","claude-code-controls-mac-desktop-zh","Claude Code 也能操控 Mac 了","2026-03-28T03:01:58.58121+00:00",{"id":108,"slug":109,"title":110,"created_at":111},"dc58e153-e3a8-4c06-9b96-1aa64eabbf5f","cloudflare-100x-faster-ai-agent-sandbox-zh","Cloudflare 的 AI 沙箱跑超快","2026-03-28T03:09:44.142236+00:00",{"id":113,"slug":114,"title":115,"created_at":116},"1c8afc56-253f-47a2-979f-1065ff072f2a","openai-backs-isara-agent-swarm-bet-zh","OpenAI 挺 Isara 的 agent swarm …","2026-03-28T03:15:27.513155+00:00",{"id":118,"slug":119,"title":120,"created_at":121},"7379b422-576e-45df-ad5a-d57a0d9dd467","openai-plan-automated-ai-researcher-zh","OpenAI 想做自動化 AI 研究員","2026-03-28T03:17:42.090548+00:00",{"id":123,"slug":124,"title":125,"created_at":126},"48c9889e-86df-450b-a356-e4a4b7c83c5b","harness-engineering-ai-agent-reliability-2026-zh","駕馭工程：從「馬具」到「作業系統」，AI Agent 可靠性的終極密碼","2026-03-31T06:42:53.556721+00:00",{"id":128,"slug":129,"title":130,"created_at":131},"e41546b8-ba9e-455f-9159-88d4614ad711","openai-codex-plugin-claude-code-zh","OpenAI 把 Codex 放進 Claude Code","2026-04-01T09:21:54.687617+00:00",{"id":133,"slug":134,"title":135,"created_at":136},"96d8e8c8-1edd-475d-9145-b1e7a1b02b65","mcp-explained-from-prompts-to-production-zh","MCP 怎麼把提示詞變工作流","2026-04-01T09:24:39.321274+00:00"]