On a mission to make software development a more productive and enjoyable experience. Make it happen. With Code.
Joined March 2008
- Tweets15K
- Following67
- Followers215K
- Likes8K
Pinned Tweet
Your IDE already knows your codebase. What happens when coding agents can use that knowledge too?
We tested it with Netflix using Claude Code and Codex. One finding stood out: the strongest models gained the most from IntelliJ IDEA’s code intelligence.
We connected IntelliJ IDEA’s code intelligence to Claude Code and Codex, then tested the setup with Netflix.
The first public results are out.
Typical efficiency gains: 20–30%.
Best code-navigation case: ~65%.
These results come from two real codebases. The efficiency metric averages token savings and time savings.
Correctness stayed stable or improved.
Here’s what we actually built.
The code engine behind IntelliJ IDEA ran headlessly, giving agents access to its capabilities through a CLI backed by a daemon.
LSP alone wasn’t sufficient.
Agents needed a convenient way to invoke the tools. The backend also needed to stay running and keep the project index warm between calls.
The idea is straightforward.
An IDE has already mapped the structure of your code and its dependencies — including what’s inside compiled libraries.
An agent can use that knowledge instead of spending time and tokens reconstructing it.
But the most interesting finding was which models benefited most.
The strongest models saw the biggest gains.
Especially at higher reasoning effort.
In these experiments, more capable models were also better at taking advantage of code intelligence.
My takeaway: better models and better tools aren’t competing bets.
You don’t have to choose between investing in model intelligence and giving agents better access to your codebase.
The two can reinforce each other.
Huge thanks to @pbakker and the Netflix team for working with us on this!
When an AI agent fixes a bug, who checks the fix?
Kai’s GameDev Day lesson goes beyond games. Pair agent work with Qodana’s deterministic checks, review the result, and repeat until it meets your quality gate. Bugs don’t need sequels.
Talk and recap: jb.gg/87dro6
Freedom to run any agent. Control over who uses what, and what it costs.
See Air Governance in action with the product team, plus a live Q&A.
November 18, 4:00 pm CET
events.jetbrains.net/registe…
Choose an agent. Start a session. Check what comes back.
In Part 1 of our JetBrains Air in IDEs series, Kristel Cocoli adds advanced search to an app while showing how to track sessions and review the result in IntelliJ IDEA.
#JetBrains #AI
You can read more in the blog below!
blog.jetbrains.com/ai/2026/1…
Setting up your first cloud environment and building agentic automations, step by step in Air Teams
Your AI coding agents will feel right at home in the JetBrains terminal.
Multi-line prompts, light/dark theme matching, and cleaner TUI rendering, all thanks to libghostty 👻
And it’s not just for agents. Neovim and tmux now follow your IDE theme, keybindings work the way the docs say, and ncurses apps, monitors, and dashboards now render borders, colors, and lines cleanly.
On by default in the 2026.3 EAP builds. Learn more 👉 jb.gg/jb-terminal-with-libgh…
The better coding agents get, the more the IDE matters — not for writing code, but for verifying what the agent wrote before you ship.
What is an IDE when you aren't writing the code by hand? Here's @isaacrlevin 's take: jb.gg/why-we-need-ides-x
JetBrains IDE intelligence made coding agents 20%–30% more efficient.
Netflix gave AI agents JetBrains IDE intelligence, ran headless, and measured typical gains on real Java and Kotlin tasks, with no drop in correctness.
Read the full case study results: jb.gg/netflix_ide
Four days to figure out where our AI budget went? No, thanks.
We built Air Governance to solve a problem we faced ourselves.
An agent writes the code now. Do you still need an IDE?
You do if you want to understand and verify what the agent did.
🎥 In our new video, we talk about the role of an IDE now that humans aren't the only ones working on the code. youtu.be/AHFGMkzrfwM
Junie Local now runs on @NVIDIARTXSpark from day one.
Get a full-fledged coding agent on your PC. It reads your code, edits files, and runs tests. There are no tokens or quotas, and no code leaves the machine.
Windows support is stable, too. All you need is a 24 GB Nvidia RTX card.
Try it for free: junie.jetbrains.com/local
ALT Image with a black background features text: "Your RTX Spark just got an agent. Junie Local runs on it from day one." The text is in white and green. The top corners display the logos for Junie and JetBrains. The bottom shows a green command line: "> /local".
Long-term AI adoption depends on driving down token costs. Mellum2.1 is our contribution to that shift – bringing an open-source 12B MoE model into local PyCharm workflows to deliver 140+ T/S without cloud overhead.
Learn more and see it in action:
Meet Mellum2.1 – JetBrains' open-source 12B MoE model built for coding agents and local execution.
🚀 140+ T/S in local testing scenarios
🇪🇺 Ethically trained European open model
💻 Efficient worker model inside IDE agent workflows
Try it locally: huggingface.co/collections/J…
Read the case study 👇
blog.jetbrains.com/ai/2026/1…
We're proud to see @junie_ai, the JetBrains AI coding agent, featured as an official partner in the @figma MCP Catalog! 🎉
Another step toward bridging the gap between design and code, making developers' workflows smoother and more connected.
Excited to be part of this!
Try agentic coding with JetBrains Air and Junie Lite for free in PyCharm 2026.3 EAP 4 👇
Free, fast, and private agentic coding inside PyCharm?
JetBrains Air is live in PyCharm 2026.3 EAP 4, and you can test it for free with Junie Lite – simply sign in with your JetBrains Account. No paid AI subscription required!
🤖 Powered by open-weights Qwen 3.6 27B + JetBrains code intelligence
🔒 Private by design – your code is never used for training
⚡ Perfect for routine tasks, boilerplate, and test generation in Air.
A few AI power users don’t automatically make a whole team more productive.
At @WorldSummitAI, Ciara Byrne of JetBrains shared how teams can make AI agents useful beyond a handful of power users: build skills across the team, agree on shared practices, and automate repetitive work.
See how JetBrains Air can help your team: jb.gg/s9nrn4
Gemini 4 Argon is officially live!
@kristel_tech tasked two agents with building a web-swinging delivery game in a hyper-realistic night city:
• Gemini 4 Argon: $54.41 | 23 mins
• Opus 5.5: $56.97 | 2h 20 mins
Compare their performance yourself in JetBrains Air or Junie.