[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"article-claude-code-dynamic-workflow-ai-harness-en":3,"article-related-claude-code-dynamic-workflow-ai-harness-en":30,"series-ai-agent-5efa67dd-b9f7-4a2f-8c68-3a4bc6a6b7d9":82},{"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},"5efa67dd-b9f7-4a2f-8c68-3a4bc6a6b7d9","claude-code-dynamic-workflow-ai-harness-en","Claude Code 动态工作流：AI 自写 Harness","\u003Cp data-speakable=\"summary\">\u003Ca href=\"\u002Ftag\u002Fanthropic\">Anthropic\u003C\u002Fa> 正在把 \u003Ca href=\"\u002Ftag\u002Fclaude-code\">Claude Code\u003C\u002Fa> 的调度逻辑交给模型自己写，想用动态 Harness 替代写死流程。\u003C\u002Fp>\u003Cp>Anthropic 正在把 \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002F\" target=\"_blank\" rel=\"noopener\">Anthropic\u003C\u002Fa> 的 \u003Ca href=\"https:\u002F\u002Fwww.anthropic.com\u002Fclaude-code\" target=\"_blank\" rel=\"noopener\">Claude Code\u003C\u002Fa> 工作流往“动态 Harness”方向推：让模型不只负责生成答案，还参与决定怎么调度任务、怎么拆分步骤、怎么执行工具调用。文章判断，这不是单纯的模型能力问题，而是单上下文窗口同时承担规划和执行带来的架构限制。\u003C\u002Fp>\u003Ch2>What changed\u003C\u002Fh2>\u003Cp>作者把 Anthropic 过去一系列定制流程放在同一条线上看：Research、安全审计、\u003Ca href=\"\u002Ftag\u002Fagent\">Agent\u003C\u002Fa> Teams、\u003Ca href=\"\u002Fnews\u002Fopen-code-review-ai-code-review-misses-en\">Code Review\u003C\u002Fa>，这些都不是通用聊天接口，而是为特定任务写死的调度逻辑。它们本质上是在模型外面加一层控制器，避免模型在同一个上下文里既做计划又做执行，导致信息挤爆、步骤混乱或工具调用失控。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781035372495-9czj.png\" alt=\"Claude Code 动态工作流：AI 自写 Harness\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>现在的变化是，\u003Ca href=\"\u002Ftag\u002Fclaude\">Claude\u003C\u002Fa> Code 被讨论成更像“自己写 Harness”的系统：模型先生成工作流，再按工作流去跑任务，而不是只在一个大提示词里硬扛到底。这样做的目标很明确，就是把固定流程变成可适配流程，让不同任务类型有不同执行路径。\u003C\u002Fp>\u003Cul>\u003Cli>Research、审计、Agent Teams、Code Review 都属于定制 Harness。\u003C\u002Fli>\u003Cli>这些流程的共同点，是把规划和执行拆开。\u003C\u002Fli>\u003Cli>问题核心不是模型不会做事，而是上下文窗口不够同时装下全部决策。\u003C\u002Fli>\u003Cli>动态工作流想让模型参与调度，而不是只产出文本。\u003C\u002Fli>\u003C\u002Ful>\u003Ch2>Why it matters\u003C\u002Fh2>\u003Cp>对开发者来说，这意味着 Agent 设计的重点可能从“提示词怎么写”转向“控制层怎么搭”。如果模型能生成适合当前任务的执行路径，工具链就不必为每一种场景手工固化一套流程，Agent 的复用率和可维护性都会更高。\u003C\u002Fp>\n\u003Cfigure class=\"my-6\">\u003Cimg src=\"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781035388045-de5t.png\" alt=\"Claude Code 动态工作流：AI 自写 Harness\" class=\"rounded-xl w-full\" loading=\"lazy\" \u002F>\u003C\u002Ffigure>\n\u003Cp>对市场来说，这也是 Anthropic 在把 Claude Code 从单点编码助手，往更通用的任务编排系统推进。真正的分水岭不是模型是否更会写代码，而是它能不能稳定决定“先做什么、后做什么、何时调用什么工具”。\u003C\u002Fp>\u003Cp>这篇文章的核心问题很直接：当 AI 连工作流本身都能生成时，下一层竞争就不再是回答质量，而是控制权谁来写、谁来改、谁来审。\u003C\u002Fp>","Anthropic 正在把 Claude Code 的调度逻辑交给模型自己写，想用动态 Harness 替代写死流程。","zhuanlan.zhihu.com","https:\u002F\u002Fzhuanlan.zhihu.com\u002Fp\u002F2045777882824325082",null,"https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1781035372495-9czj.png","ai-agent","en","ef96a410-24bd-4e35-8536-439f21f820e6",[17,18,19,20,21],"Claude Code","Anthropic","Agent","Harness","工作流",[23,24,25],"Anthropic 正在把 Claude Code 的调度逻辑往动态 Harness 方向推进。","Research、审计、Agent Teams、Code Review 都是为特定任务写死的控制层。","关键矛盾不是模型能力，而是单上下文窗口同时承担规划和执行。",0,"2026-06-09T20:02:22.33375+00:00","2026-06-09T20:02:22.322+00:00","fe05efaa-cfe8-4382-afd9-6583471c8a11",{"tags":31,"relatedLang":41,"relatedPosts":45},[32,34,36,38,40],{"name":33,"slug":33},"agent",{"name":35,"slug":35},"harness",{"name":17,"slug":37},"claude-code",{"name":18,"slug":39},"anthropic",{"name":21,"slug":21},{"id":15,"slug":42,"title":43,"language":44},"claude-code-dynamic-workflow-ai-harness-zh","Claude Code 動態工作流：AI 自寫 Harness","zh",[46,52,58,64,70,76],{"id":47,"slug":48,"title":49,"cover_image":50,"image_url":50,"created_at":51,"category":13},"2bd28e0e-0f4b-4987-a961-28763c1e1926","agent-orchestration-enterprise-ai-layer-en","Agent orchestration is the missing layer for enterprise AI","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780984981174-08mj.png","2026-06-09T06:02:31.384174+00:00",{"id":53,"slug":54,"title":55,"cover_image":56,"image_url":56,"created_at":57,"category":13},"95684312-23dc-4a78-a917-df14d132c5fa","ai-agents-use-blockchain-trust-layer-en","AI agents use blockchain as a trust layer","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780980506080-ki4s.png","2026-06-09T04:48:01.710214+00:00",{"id":59,"slug":60,"title":61,"cover_image":62,"image_url":62,"created_at":63,"category":13},"0208e47f-7d4c-4473-a0f9-4cd193b5c139","8-rag-patterns-demos-into-prod-en","8 RAG patterns that turn demos into prod","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780971552707-qpl7.png","2026-06-09T02:18:36.760049+00:00",{"id":65,"slug":66,"title":67,"cover_image":68,"image_url":68,"created_at":69,"category":13},"b413d484-6786-4c32-abdc-77f010ac7eba","fine-tuning-beats-rag-style-not-facts-en","Fine-tuning beats RAG when the goal is style, not facts","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780924681800-5xji.png","2026-06-08T13:17:25.701649+00:00",{"id":71,"slug":72,"title":73,"cover_image":74,"image_url":74,"created_at":75,"category":13},"57beb8b4-c233-400f-b95b-a97be1cf9d02","openclaw-small-business-ai-staff-en","OpenClaw shows how small businesses use AI staff","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780904882032-yp13.png","2026-06-08T07:47:27.730921+00:00",{"id":77,"slug":78,"title":79,"cover_image":80,"image_url":80,"created_at":81,"category":13},"9cfe6784-bd41-452f-979b-8b4b763239a8","litellm-rust-minimal-ai-gateway-en","LiteLLM launches a minimal Rust gateway for agents","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1780899487143-uhga.png","2026-06-08T06:17:33.570272+00:00",[83,88,93,98,103,108,113,118,123,128],{"id":84,"slug":85,"title":86,"created_at":87},"03db8de8-8dc2-4ac1-9cf7-898782efbb1f","anthropic-claude-ai-agent-task-automation-en","Anthropic's Claude AI Agent: A New Era of Task Automation","2026-03-25T16:25:06.513026+00:00",{"id":89,"slug":90,"title":91,"created_at":92},"045d1abc-190d-4594-8c95-91e2a26f0c5a","googles-2026-ai-agent-report-decoded-en","Google’s 2026 AI Agent Report, Decoded","2026-03-26T11:15:23.046616+00:00",{"id":94,"slug":95,"title":96,"created_at":97},"e64aba21-254b-4f93-aa21-837484bb52ec","kimi-k25-review-stronger-still-not-legend-en","Kimi K2.5 review: stronger, still not a legend","2026-03-27T07:15:55.385951+00:00",{"id":99,"slug":100,"title":101,"created_at":102},"30dfb781-a1b2-4add-aebe-b3df40247c37","claude-code-controls-mac-desktop-en","Claude Code now controls your Mac desktop","2026-03-28T03:01:59.384091+00:00",{"id":104,"slug":105,"title":106,"created_at":107},"254405b6-7833-4800-8e13-f5196deefbe6","cloudflare-100x-faster-ai-agent-sandbox-en","Cloudflare’s 100x Faster AI Agent Sandbox","2026-03-28T03:09:44.356437+00:00",{"id":109,"slug":110,"title":111,"created_at":112},"04f29b7f-9b91-4306-89a7-97d725e6e1ba","openai-backs-isara-agent-swarm-bet-en","OpenAI backs Isara’s agent-swarm bet","2026-03-28T03:15:27.849766+00:00",{"id":114,"slug":115,"title":116,"created_at":117},"3b0bf479-e4ae-4703-9666-721a7e0cdb91","openai-plan-automated-ai-researcher-en","OpenAI’s plan for an automated AI researcher","2026-03-28T03:17:42.312819+00:00",{"id":119,"slug":120,"title":121,"created_at":122},"fe91bce0-b85d-4efa-a207-24ae9939c29f","harness-engineering-ai-agent-reliability-2026","Harness Engineering: From Bridle to Operating System, The Missing Link in AI Agent Reliability","2026-03-31T06:36:55.648751+00:00",{"id":124,"slug":125,"title":126,"created_at":127},"7a09007d-820f-43b3-8607-8ad1bfcb94c8","mcp-explained-from-prompts-to-production-en","MCP Explained: From Prompts to Production","2026-04-01T09:24:40.089177+00:00",{"id":129,"slug":130,"title":131,"created_at":132},"116d5ee9-a4f1-4b5a-aac5-5d035dd22bbe","amazon-bedrock-agents-multi-agent-workflows-en","Amazon Bedrock Agents Gets Multi-Agent Workflows","2026-04-01T09:30:30.197685+00:00"]