JetBrains Air: A System of Products for Agentic Software Development

We have put a lot of thought into how we can add value for the workflow you just described. Here's the way I think about it: FSD for a car. Can you imagine trying to sell a car without a steering wheel? I still want to code, I still want the deterministic side, even in cases where I'm letting the machine do the work.

That's a small subset of the functionality you would need if you're actually authoring code. So the IDE maybe be more valuable, but the feature set you need is actually much smaller and can probably be redesigned given your narrow workflow.

Is this accurate?

Unless you are blindly vibe coding everything without an IDE to help navigate what is being generated to review the output, working would be hellish.

And if you are blindly vibe coding everything, I am just glad I don't have to work with you. While LLMs mostly speed me up, they make serious mistakes often enough that a review is necessary.

After using Air in PyCharm, it's some good stuff. It's re-imagined for this hybrid world. But my question for you, honest question: do you think you still want to look at code? How about write code? If so, what are some things you'd do, if you were in charge of our IDEs?

AI can do all of that quite well. If you take your hands off of the wheel, lean into it, start building systems for it, start figuring out where it goes wrong on your codebase and building systems to prevent that... you might get 10x more done. I do, and the results are generally better than anything I'd have coded by hand, because there was never enough time.

I don't look at or try to grok all changes, though. I couldn't get near as much done, otherwise, and I'm not convinced that 1 hr of me looking over it is better than 4 hrs of AI looking over it, and the AI is far cheaper. I look over the code, occasionally, to look for code that's objectively terrible, but I don't fix it directly - I use it as a test-case for improving my AI stack, to make it able to find and fix or prevent that class of terrible.

I probably spend 9 out of 10 credits on review and refinement, not writing fresh code. In spite of that, I'm still producing things way faster than I ever did by hand, with only a single $200/mo Codex plan.

I still keep my JetBrains' subscription, so that agents can use the MCP. I probably spend <5h per month in an IDE myself, though.

Of course, but agents are also opening up new possibilities to do these jobs.

For example, you can do quick first code review with agent, or you can ask agent to add couple of print statements and debug the code until it figures out the issue, also for discovery, you can do discovery with agents and generate nice output with the details you want (although not accurate sometimes)

As a JetBrains user myself, whose organization cancelled the IntelliJ license recently, I can attest things I am doing inside IntelliJ is getting less and less. I am primarily using IntelliJ for code navigation at the moment, which is still the best one

I do feel however they have been neglecting anything non-AI for a while now. I in particular loved their auto complete, and with the new guesswork AI auto complete it's just not the same. I want deterministic behaviour from my IDE.

On the LLM side, I couldn't use the Anthropic subscription with their offerings, so I just use it from a harness outside the IDE, and switch to the IDE for review. This may not be JB's fault, but it still makes their offering useless to me.

I may be one of the few remaining but I also still program myself sometimes (I weigh it based on the task). The IDE has been pushing so much AI it has been getting in my way sometimes, and it is definitely using more resources for stuff I don't use.

I too am on the fence on whether I'll resume my subscription. Luckily for JB I dearly dislike VSCode's code navigation and interface, and would severely miss their debugging tools integration.

I know harnesses (and harness harnesses) have a long way to go and lots of improvements even without models getting “smarter”, I’m rooting for JetBrains but so far IDEA has been more of hindrance in the LLM-era. The CLI TUI’s have become the most important tool I have and the GUI versions haven’t kept pace.

I’d love to live in IDEA instead of the CLI but so far I’ve found that to be too limiting and not as adaptable to our rapidly changing field. Maybe Air will help with that, we will see.

I want something like herdr in IDEA, a way to monitor agents, smart worktree integration, easily visualize changes and use the power of the InteliJ brains to assist in coding (lint/checks/etc).

Right now my IDE gets more in my way than assists me in shipping code.

I really hope that you guys manage to turn the ship around, but after experiencing the decline myself and paying until this year, all my goodwill towards Jetbrains has been used up. At this point, I would never consider paying full price again.

Have you guys discussed (if you're able to share) allowing customers to resume subscriptions, which they've cancelled during the decline years? For me, that would be an important step to rebuilding trust.

Honestly not really.

I mean I am happy that there is some kind of response, but this is just damage control.

And, frankly, you do not need me to fix that. Of that I am certain.

I'm not running any weird setups or something out of the ordinary. If you actually test your software on a normal computer (think: random thinkpad with 8th gen intel cpu), running some random boring linux distribution (think: debian) you will run into these problems.

The bad experiences all so far have been smoke-test-level issues.

Or.. well. Product strategy. Not even bugs or performance issues at all.

__

But, yeah, you had to say something. I understand that, given your role as "developer advocate" (as per the HN account about section). This is your job after all.

But, honestly, sticking ones head in the sand and hoping that this passes might've been the strategically more wise move.

The problems your employer has cannot be fixed by one person taking their time and looking at an individual issue some other vocal guy on the web has. I think we both know that.

I'm sorry, genuinely.

What else can one use?

Excluding VSCode and all those AI-first IDEs I mean. JetBrains' git features have been excellent. I have not yet seen them be reproduced anywhere, but, eventually, they will kill that classic UI plugin. :(

There's so much going on right now, and the push to PaaS is not performing as well in my opinion.

Take a look at how Herdr got viral, and how it exposes protocols that let others come and build with it. Multiplexers are a good bet, though there are plenty of other verticals out there too.

I would say try to chase another ReSharper moment for you guys.

What is the problem with using Codex in Rider, can you please share? It's generally available, with your own Codex subscription or via JetBrains AI.

Hadn't used ACP yet.

1) Import of historical data from agents. I often look up past agent sessions and require search into them as a primary feature of the harness. I know for a fact that historical conversations are not encrypted for both Codex and Cursor on a local filesystem, so Intellij tool could import them into ai assistance plugin even before user is authenticated with either Cursor or Codex. There are few annoying things in search for both Cursor and Codex extensions, so having great search over past conversations could be a great introductory feature

2) Auth .. I am not sure about this one technically because I haven't looked myself into how agent auth is done for Cursor and Codex, but at least for Codex, their IDE extension for vscodium/cursor/zed/etc. is able to use existing authentication from the CLI codex tool, so I do not need to login into every new IDE I try Codex extension in. With Intellij Codex auth did not work at all for me.

3) Cursor authentication worked, though I needed second one for Intellij while being logged in with CLI, but the model reasoning level is not selectable from within ai assistant, one more deal breaker for me unfortunately (I found it stays like this for a long time: https://forum.cursor.com/t/intellij-cursor-acp-reasoning-lev...)

  - Junie
  - Air
  - AI autocomplete
  - AI Assistant
  - AI Chat