Goland (2022-2024)-> Cursor(November 2024 to February 2026) -> Claude Code (& VSCode or Cursor for manual edits)
The Claude Code setup is interesting, I use the terminal or GitHub for diffs. I do open an editor to do manual edits, especially when I am doing something new( that the LLM hasn't been trained on) or debugging something.
Potential improvements
Stripe Projects ( creating API keys from CLI) as something that I have wanted in the past as with LLMs sometimes with a project the slowest part seems to be deployment / bringing all the keys. I also don't enjoy the fact that I can't push a job to the web when I am leaving work. Worktrees aren't fun as I can't run the services on different ports that easily for testing, further managing different TMUXs is painful. I am curious what tools people here are using, also what do people do while the LLM generates.
VSCode/GH copilot -> windsurf -> Zed/Claude code -> Zed/codex -> Zed/opencode -> Antigravity/opencode
I'm only using antigravity cause they have good limits for now .. (but it we be matter of time before it will go away and then go back to Zed)
2025: Stopped writing so much Java, so used VSCode exclusively for Python, TS etc, with Claude Code or Cline.
2026: Time is split between Codex App (40%), Claude App (30%) and VSCode with Claude Code (30%).
Some other thoughts:
* Overall I feel like opening an IDE in the traditional sense is coming to an end.
* Tech-stack wise I am much more open to trying out new things than before since LLMs will help with the setup and debugging.
* For small teams like ours, code reviews are the bottleneck, and we constantly have to decide what code we review vs what we don't.
* Building seems easy these days, but (1) so much competition no in every field, (2) much more product polish is expected than before, and (3) most products compete with Claude if they realize this or not.
When I'm using an LLM to generate technical debt, it's Visual Studio Code and GitHub's AI tool, that I can't remember the name of.