[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-tool-calling":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"5c0c1205-0e79-40c5-b6ab-4b53460b5d4f","tool calling","tool-calling",4,"Tool calling 指的是讓 LLM 依照結構化介面呼叫 API、查資料庫、觸發工作流或執行外部函式，是 agent 與生產系統接軌的核心。這個主題也涵蓋 JSON 合約、錯誤處理、迴圈控制與評估。","Tool calling is the mechanism that lets an LLM invoke APIs, query databases, trigger workflows, or run external functions through structured contracts. It sits at the center of agent systems, where JSON schemas, error handling, loop control, and evaluation shape reliability.",[12],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"f8c44ca5-e1b5-4b51-a7e5-61cdf8fa5ab9","prompt-engineering-agents-structured-outputs-zh","Agent 與結構化輸出提示詞實戰","LLM 進到生產環境後，提示詞不再是寫得漂亮就好。這篇拆解推理、長上下文、JSON 合約與 agent 迴圈，講清楚怎麼把 GPT、Claude 和本地模型用得更穩。","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1775164928194-j63i.png","zh","2026-04-02T21:21:45.59991+00:00"]