Ask HN: How do you verify front-end code in agentic LLM coding loops?
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. 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. How are you closing the loop on front-end verification? 2 comments on Hacker News.
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. 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. How are you closing the loop on front-end verification?
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. 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. How are you closing the loop on front-end verification? 2 comments on Hacker News.
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. 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. How are you closing the loop on front-end verification?
Hacker News story: Ask HN: How do you verify front-end code in agentic LLM coding loops?
![Hacker News story: Ask HN: How do you verify front-end code in agentic LLM coding loops?]()
Reviewed by Tha Kur
on
November 29, 2025
Rating:
No comments: