开发者吐槽 Agent Harness 现状：别指望自动模式直接交付代码
搞 agent 工作流的朋友可以看看这条：Seymour 用 Jev 分类器加验证工具自己搭 harness，思路是把确定性环节留在代码里，而不是全靠模型自动跑。如果你被复杂任务的 agent 跑挂坑过，这套做法可以参考。
Elvis（Seymour）在 X 上分享了他构建一个 agent harness 的思考：把确定性组件原生编码进 agent 工作流，比如把 Jev 分类器和验证工具与 coding agents 混合搭配。他认为目前大多数 harness 试图自动化一切，反而引入更多问题，除少数几个外整体状态不佳。随着越来越多人想搭 software factory，复杂运行中各种问题频出，harness 层面还有大量工作要做。
他的核心观点是：很多人把"coding is solved"误解为可以把 agent 切到 auto mode 直接交付代码。实际上，编码能力在基准测试上的提升不代表真实工程中可靠，确定性验证组件（分类、校验）应该显式嵌入 harness，而不是全部交给概率性模型自动决策。
This thought came from a simple harness I have been trying to build that more natively encodes all these important deterministic components with my agents (e.g., mixing Jev classifier and verification tools with coding agents). I am just tired of all these harnesses that try to automate everything and end up inviting more issues down the road. The state of harnesses has been really bad more recently (with the exception of a few). Plus, more people want to create software factories and complain about all kinds of issues showing up during complex runs. I feel like we still have a lot of work to do on harnesses. Excited to keep experimenting, but I wanted to share how I feel, because I think a lot of people believe that "coding is solved" and mistake that for meaning you can just put your agents to ship code in auto mode.📊 1 ⚡
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Agent, harness, coding agents, prompt engineering.
Source attribution: curated from elvis (@omarsar0).
