[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-function-calling":3},{"tag":4,"articles":11},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":10},"ca60fdc2-a0c8-4354-bd01-a201ba3eaff8","function calling","function-calling",3,"Function calling 是讓模型不只產生文字，而是依規則呼叫 API、查資料、寫入系統或觸發工作流的介面層。從即時語音代理到 MCP 這類工具協定，都在解決同一件事：把模型輸出接到可控、可審核的外部動作。","Function calling is the interface layer that lets a model move beyond text generation to invoke APIs, query data, write records, or trigger workflows under defined rules. It matters for assistants, voice agents, and protocols like MCP, where control and auditability are as important as model output.",[12,21,29],{"id":13,"slug":14,"title":15,"summary":16,"category":17,"image_url":18,"cover_image":18,"language":19,"created_at":20},"bcb80586-e23e-4822-b98e-d92b65870928","5-reasons-to-use-kimi-k2-5-on-cloudflare-en","5 reasons to use Kimi K2.5 on Cloudflare","5 reasons Kimi K2.5 fits agentic apps on Cloudflare, from a 256k context window to tool calling, vision, and structured outputs.","industry","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780769864414-tqp9.png","en","2026-06-06T18:17:17.730869+00:00",{"id":22,"slug":23,"title":24,"summary":25,"category":26,"image_url":27,"cover_image":27,"language":19,"created_at":28},"99b4197b-3e94-475d-bb05-7a4fa6927b3f","benchlm-agent-tool-use-benchmarks-2026-en","BenchLM ranks the best AI agent models for 2026","BenchLM’s 2026 rankings compare 49 models across agentic tasks like tool use, browsing, terminal work, and computer control.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780317186915-pe39.png","2026-06-01T12:32:38.172799+00:00",{"id":30,"slug":31,"title":32,"summary":33,"category":34,"image_url":35,"cover_image":35,"language":19,"created_at":36},"171dca3d-20d5-4205-a20d-406cd426fc6d","how-to-build-harness-for-ai-agents-en","How to Build a Harness for AI Agents","Harness engineering defines the control system that lets an AI agent perceive, act, and verify output.","ai-agent","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1779844562168-ar28.png","2026-05-27T01:15:29.046272+00:00"]