Just setup my team with Cursor. They actually got back to me on an enterprise plan (Claude keeps ignoring me). Cloud Agents have been great for keeping multiple streams going at the same time. Adding in computer use has been great for actually testing out features and showing they work for PRs. Bugbot so far has been the best AI reviewer I've tested. Composer 2.5 is great, though still using Opus for planning.

I can do most of this with Claude Code, but there's definitely a cost in maintaining it for the whole team.

I stopped using Cursor because of how terribly optimised it is (worse than VSCode despite being a fork). It would routinely take up 50% of the CPU resources on my MacBook M4 and gigabytes of RAM for absolutely no reason.

I switched to Zed, and I'm never going back to Electron/non-native IDEs.

Still do. Composer 2.5 is a beast. But even with Opus (and Fable for a few days) their harness is many times faster. The main reason for me to use CC is the $200 subsidized pro max plan.

Also their computer use in the cloud agents (when it works) is a game changer. No need to keep your laptop open / get a Mac mini if it runs in the cloud.

It's still my primary at work (data engineering/platform engineering), running a mix of GPT-5.5 and Composer 2.5. We also have Claude Code subscriptions. I find myself preferring Cursor for most tasks.

70% of the time I use AI agents on a pretty tight leash. I often reject edits and ask it to change things. The IDE integration is really efficient for this workflow compared to Claude (yes, I've tried the Claude extensions).

Autocomplete is still the best available (I've tried both Copilot and Zed); though admittedly it's not as important as it was circa last year.

For the 30% simpler or very well-specced tasks their cloud agents are last I compared way better than Claude Code's/Codex's version of the concept. @cursor for quick fixes in Slack works quite well. Don't get me wrong, it's still quite under-documented, but the others are worse. The integrations with linear, Slack and github are well executed

Composer 2.5 is really fast in their harness at code search/explanation/Q&A tasks (much faster than Sonnet/Opus). It's also really good at debugging, very proactive compared to other models in the same size/prices class IMO. Just due to the speed I actually prefer it to almost any other model for these tasks. I suspect at least some of this may be due to the harness and good codebase indexing.

I don't know why people are down on the Cursor harness. It's good. The main advantage of Claude Code/Codex are the token subsidies; but according to their dashboard I am costing my employer between $100-200/month on Cursor, so the overall price is comparable and only narrowing now that Anthropic is switching many enterprises to API usage.

I also don't understand the people complaining about VSCode bloat and in the same sentence praising Claude Code. Claude Code often uses MORE RAM than Cursor, has a super unstable UI (on my home machine there is input lag when typing ANYTHING in Claude Code) and the desktop app version of CC barely works. The Codex TUI is genuinely nice and snappy, on the other hand.

It's my primary. Claude Code for personal stuff on the weekends. I really just prefer the GUI of having the changes easily highlighted. If I can get something to apply that with Claude Code or Codex or OpenCode or whatever, I'd swap over without thinking.

I was on Claude Code the past year, now I use chinese models, but I've used Cursor and they have an ok pricing offering today because of their mix of sota models with usage based pricing along with their Kimi based Composer model with generous limits. I think it makes a lot of sense for the enterprise market, which is the real moat, and not the capabilities/features of the forked ide or app/tui/github bot anyone can come up with today.

I use Cursor for work, but claude code for personal development. I think Cursor is still useful but the most value really is access to latest models

My company gave me cursor license after I had already been using Codex CLI for months and VS Code for a decade.

I had absolutely no interest in their VS Code fork. The Agent Window was okay but buggy (eg wouldn’t load branches on Ubuntu via WSL2).

Overall used it a couple of times but still use Codex CLI as my main driver. Might try CC in the future esp. if they unban Fable.

I switched back to VSCode with Codex and Claude extensions. Just more stable.

I'm still on their old 500 requests/month plan and the value is simply unbeatable for $20. I've been able to use agents without worrying about usage for my job and personal projects paired with the $20 codex sub and I dread the day when they finally get rid of the requests plan.

to be fair "nobody" is using grok either

Development is moving away from the IDE to agentic long running workers. I've been using their SDK in this mode - which then forces you to use cursor as model provider. I use a mix of harnesses for different types of agentic tasks and Cursor gets the best results.

Earlier this year I had used it because I would rather have a IDE-like exp and be able to actually look at the code. However, recently switched to using claude code VS code extension and it's basically the same thing (plus at Amazon we can only use Claude Code)

I use Cursor, but funny enough it's 98% just using the codex plugin - I kept cursor around on the grand fathered $20 / 500 requests plan, if they un-grandfather me or things change too much I'll zip over to vscode.

Fully on Cursor at work and I love it over CC, OpenCode and Pi that I use for personal work.

Zed with Claude code is the best of both worlds

I used their agent view yesterday and the file tree does not update when you add new files.

Yes. Do the heavy lifting in Claude code , Codex.

Basic tasks in cursor. It's decent and damn fast.

All my team members also use it.

Yes, unlike Claude it has excellent response rate and i can leverage their speedy models

We use the bugbot. Best code review agent we've seen.

I use it because their pro plan is free for students

Cursor became obsolete pretty quickly as Claude has improved. Good on them to find an out before they collapsed. $60 billion is a huge overpay.

if you use hn you probably don't speak to actual people tho

I use Cursor for coding. I like to review the changes via the UI. Plan mode is also really strong in Cursor. It bugs me less about needing to search through files and basic coding tasks. I find it also saves the company a ton of money compared to Claude, Claude burns through tokens with no regard.

I typically use Claude for interacting with MCPs and skills to operate on live systems.

Plenty of enterprises are still using Cursor, though they are facing plenty of pressure because Anthropic and OpenAI bundle Claude Code and Codex which can make it hard to justify an additional license for a third-party harness (why spend that money there when you can buy the underlying tokens instead).

I use Cursor every day.

I have seen a few codebases lately with AI-bullish teams. Code produced by Cursor reeks of low quality. I’ve tried it but never got hooked.

AFAIK their market is pseudo-technical people who haven’t found the terminal yet.