From the archive
Monday, 9 November
Folded from 18 sources that day.
Sorted by quality and by how many sources covered it, the same for everyone.
-
How LinkedIn Uses AI to Review 40,000 Pull Requests a Week
LinkedIn built a multi-agent AI code reviewer that covers over 40,000 PRs weekly, with most reviews posted before a human reviewer opens the PR. The article covers the architecture, evaluation, and lessons learned.
-
CodeRabbit scales agentic software development and ships 20x more
CodeRabbit uses OpenAI models to govern AI-generated code and Codex to speed up development. It reports shipping 20 times more software with the same engineering team.