Ask HN: How do you verify front-end code in agentic LLM coding loops?
7 points
2 days ago
| 1 comment
| HN
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?

▲
dantodor
2 days ago
[-]
chrome mcp
reply
▲
eugene-kim
1 day ago
[-]
will check this out. thank you!
reply