Ask HN: 你们如何在基于 Agent 的 LLM 编码循环中验证前端代码？
1 分•作者: eugene-kim•7 个月前
当 LLM 能够运行测试来验证其工作时，自主编码循环效果很好。对于后端代码，这很简单——编写一个测试，运行它，然后迭代。<p>对于前端工作，我还没有找到一个好的工作流程。我尝试过 Playwright MCP 和 Google Antigravity，后者集成了 Chrome，但效果参差不齐。<p>您是如何在前端验证中闭环的？
查看原文
Agentic coding loops work well when the LLM can run tests to verify its work. For backend code, this is straightforward - write a test, run it, iterate.<p>For front-end work, I haven't found a good workflow. I've tried Playwright MCP and Google Antigravity which has a Chrome integration with mixed results.<p>How are you closing the loop on front-end verification?