I think their agentic cloud stuff is their best product right now. This makes sense to me. We still have subs because its nice to have something that works when Claude doesn't, it was already approved, and Composer actually is a decent value. I will sometimes use the cloud agent to put up a PR when I'm not at my computer and I remember it exists.

So a few people started using grok bot and I'll probably regret that some day, but honestly the deployment model they have here for custom agents is kind of appealing to me, much more than BigLang.

I still use Cursor and am still very happy with it.

I've found the grok-4.5+ variants to be quite suitable for powerhouse work, and I have a legacy plan with a Third Party model allowance, so I can throw the occasional harder planning tasks at e.g. Fable when needed.

I like that I can run any model from the major labs (or anything on Bedrock), instead of being fully tethered to a single vendor. I'll occasionally run the same task through several models/vendors to understand what's most cost effective to achieve a given outcome (and also to keep my grok calls -- which are very cheap through Cursor -- honest and within the limits of what it can do well).

I run most tasks through Cloud agents, with exceptions for Mac-native stuff (iOS builds, app store I/O etc).

SpaceX-stans (god i can't believe i just typed that) use it, there's a whole subculture grokking (heinlein is turning in his grave) their way towards the same vibe coded nonsense as the rest of us.

the tab era was the right mix for me. I retained all the mental context of what was going on and I could quickly ascertain if it had made a mistake. they just killed cmd+k for who knows why. Everything is agent or nothing 'easy' button slot machine pulls.