Surprised that’s your take considering Diamond is one of the code review bots that are ahead of the pack. Curious why you think that’s the case? Is it a technical limitation? Or something about human code review that is just fundamentally hard to copy?
AI will certainly make human code review easier — the goal being to keep up with the velocity of changes to existing large systems.
"Code review" as defined as a human in the loop getting the final say on whether a change will be made to the system will be the absolute last thing to go. That process may look very different as both the inputs massively increase in scale and the methods get disrupted by AI.
>"Code review" as defined as a human in the loop getting the final say on whether a change will be made to the system will be the absolute last thing to go. That process may look very different as both the inputs massively increase in scale and the methods get disrupted by AI.
I know this is probably not something you can divulge but I look forward to how your team at Graphite plans to solve this! (Would also love your personal take!)
We've already soft launched the next step toward this to some existing Graphite users, so I'm fine sharing!
We're adding an agentic chat sidebar to the pull request that can help you gather context to understand a PR and make pre-merge changes without needing to leave the PR page. Open beta next week.
We're only going to spend more and more time looking at diffs as the amount of them increases, so the tools that we use here need to evolve as well. "AI code review" should be an interactive experience that directly builds on how code is reviewed today, not just a bot that comments on your PRs.