[Ethee]

This is where I feel like we've solved a third-order problem. If you're sorting all PRs into those two buckets then you should probably take a step back and redefine what a PR is for your organization, as both 1 and 2 make the assumption that the PR is too big to review in a single sit down or that the author didn't put in enough effort to craft their PR. Both of these should just be rejected outright in favor of doing things in a smaller more manageable way, instead of having an AI sort through something that a human should have started with. Obviously this is more of an ideal situation and a lot of companies don't work on the ideal which is why I think your product will find good use because companies don't want to invest in slowing down, only going faster.

[akshaysg]

Interesting. At my previous company there was a debate about smaller PRs vs bigger PRs and the end conclusion was that there are tradeoffs in being able to deal with 2-5 bite-sized PRs vs one large PR. The largest one being that it's hard to grasp the totality of the pull request and how the different PRs work together.

> companies don't want to invest in slowing down, only going faster.

I do think this is the way things are going to go moving forward, for better or for worse!

[mystickphoenix]

> you should probably take a step back and redefine what a PR is for your organization

I agree with this wholeheartedly if you are in a role that allows you to redefine what a PR is. In almost every organization that I've worked for, the PR is defined several levels above my pay grade and suggesting changes/updates/etc is usually seen as complaining.