the code reviews can't be effective because the LLM does not have the tribal kno... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		asdev 7 months ago \| parent \| context \| favorite \| on: Learnings from building AI agents the code reviews can't be effective because the LLM does not have the tribal knowledge and product context of the change. it's just reading the code at face value

theonething 7 months ago [–]

Isn't it possible to feed that knowledge and context to it? Have it scan your product website and docs, code documentation, git history, etc?

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact