Yep yep that's why I didn't like it when I was originally using MS Clarity. It was just summarizing stuff that was obvious (and more importantly after the issues happen). RJ here is built mainly for a single focus of being really automated. Of course, if you want the classic product analytics like replay, crashes, api, heatmaps, that also exists in the RJ dashboard but that's more for human validation of the issues spotted.
Wow Turing Scholars! you guys are like the navy seals of CS at UT lol. Yes I appreciate the insight and will actually hand write it (and copy some parts of this post, but it is a bit too goofy to just use the post straight up). One thing you mentioned, I've never heard of Readmes including a history of the project, because I thought Readmes were like a small intro doc with a bunch of hyper links only.
Did you look at them, or did you just tell Claude to look at them? /s
Seriously, though — if the history is valuable and interesting, include it. If it provides context in general, include it; if it’s just overconfident marketing fluff straight from the parrot’s mouth, drop it. I like my READMEs to open with the ‘why’ of the project: why I built it and why you might need it too.
Thanks for the encouragement! Yes, he's been sharing with his friend family groups. Early feedbacks are pretty good, he's ecstatic that he can actually make this happen!
Great Question! We have a few options when it comes to how we process a 100s of session replays that each can be a few MBs or greater. The main concept here is that we initially use a grouping system that groups the same signals (such as rage taps or dead taps) that occurred on the same app or website page for many sessions, and admit a random sample of that group into deeper analysis, which is an LLM of choice. We also have other tricks up our sleeves such as reusing session context we already put the effort into processing before among other things. We're working on improving this system though so let us know what suggestions you have!