Chief Product Officer of Air Platform at JetBrains - AI and Agentic Systems
Amsterdam, The Netherlands
Joined May 2009
- Tweets680
- Following731
- Followers441
- Likes508
Nick Frolov retweeted
Air Governance is the org layer of Air.
Pick the agents your teams can use: Claude Agent, Codex, Junie, or any ACP agent. Set credit limits per user, team, or service account. See which models drive the bill.
With the internet melting over the PHP2Shell vulnerability, seeing PHP all over the news actually brings me back to great times. If not for PHP, I might never have started my software development career.
I was 16 or 17, making pocket money freelancing and doing psd2html work (yes, the kind of tasks you can now vibecode in 5 minutes). One of my customers asked me if I knew PHP. "Of course," I said... Well, I didn’t.
Back then, my internet wasn't even fast enough to download a local server or the documentation. So I went to a store, bought a physical CD with PHP on it (photo of the CD attached!), and opened up the manual. Fortunately, I had a printer at home, so I printed out about 100 A4 pages of PHP syntax and documentation.
That weekend, I had to take a train to the countryside to visit my grandma. I took that stack of 100 pages with me and read it the entire train ride - and kept reading at my grandma's house, since there was literally nothing else to do there besides hugging her and having a quick catch-up.
Two days later, I came back home, pinged my client on ICQ, and said: "Give me more details about this PHP project of yours." And just like that, my software engineering career began.
Things snowballed quickly from there:
Later that same year, I landed my first full-time PHP developer job at Warecorp and spent a couple of years there as a Lead PHP Developer, largely because my English was good enough to talk directly to American clients.
Next, I joined Oxagile (which is where the team photo is from!). Our whole PHP crew decided to get officially certified together, and we all passed our Zend PHP certifications.
From there, I moved to EPAM. At the time, EPAM was heavily focused on massive Java enterprise projects and didn't really have a PHP practice. I ended up leading a team of ~20 PHP developers, building high-traffic platforms for MTV Entertainment - including MTV dot com, UFC, and Comedy Central.
I had no idea back then where it would all lead, but following what genuinely sparks your curiosity pays off if you just keep showing up and building on that path.
P.S. Speaking of PHP... it’s probably a great time to go update your WordPress blogs. 😉
Excited to share that I’ve been promoted to Chief Product Officer of Air Platform at @jetbrains
The future of AI-native software engineering isn’t just a single coding agent—it’s a unified system where developers, teams, and agents work together seamlessly.
Here is what we’re building next 🧵👇
We’re bringing all of JetBrains’ AI and agentic experiences together into Air Platform—one cohesive, open system across:
All surfaces: IDEs, web, mobile, Slack, voice, CLI & CI/CD
• All harnesses: Junie, Claude, Codex, Pi & other agents (local + cloud)
• The enterprise & context stack: routing, shared memory, governance & scale
🧵👇
Air Platform unlocks what I’m most excited about next: the AI Software Factory.
Faster individual developers don’t automatically make a faster organization—and unchecked "dark factories" only produce AI slop.
We’re rethinking software development methodology itself. More on the AI Software Factory soon
Junie now runs local LLM models on Nvidia RTX Spark laptops 🔥
RTX Spark platform pairs a Blackwell RTX GPU with ARM-based Grace CPU allowing to use unified memory on the laptop.
Don’t have RTX Spark powered laptops yet? We also support Apple M5 and NVIDIA RTX 3090, 4090 and 5090.
Install @junie_ai and run /local, and you have a full coding agent on your RTX Spark. It reads your code, edits files, and runs your tests. No token charges, no quotas, and your code never leaves the machine.
blog.jetbrains.com/junie/202…
Nick Frolov retweeted
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".
Nick Frolov retweeted
Your GPU. Your code. No token bill.
Junie Local runs on NVIDIA RTX Spark from day one. Windows support is stable, too.
Reads code. Edits files. Runs tests. All locally.
Try it free → junie.jetbrains.com/blog/jun…
🤖 Made with AI
In our testing on the RTX Spark, Junie Local reached generation speeds of up to 55 tokens per second for Qwen 27b model
Nick Frolov retweeted
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!
Nick Frolov retweeted
We want you to know that Air lets you run agents in the cloud, too.
Initially, we recorded this demo on a small project, but it felt like cheating. So we re-shot it on the real IntelliJ IDEA repository, where the team works every day.
Nick Frolov retweeted
Automated debugging by AI agents in Air with IntelliJ IDEA. Such a quality-of-life improvement!
Big Day for @jetbrains IDEs and for @junie_ai .
A completely new agentic experience is open today in our IDEs - we call it JetBrains Air. And the best part - Junie provides free baseline intelligence tier - Junie Lite.
In JetBrains Air you have a professional control plane over your agents (plug-in any agent you already love), agents work in parallel, you can link sessions with each other, delegate inline comments from code or md files to agents and many more.
Read the details here: blog.jetbrains.com/ai/2026/1…
Nick Frolov retweeted
We've reimagined JetBrains IDEs to become the ultimate agentic workbench.
Air is an open hub for agents inside your IDE:
-Any agents to run (Claude, Codex & many more)
-Agents are more efficient with IDE intelligence
-Free Junie Lite agent bundled
-Cloud runs via Air Teams
⬇️
The Evolution of Voice as UI:
1. Hardcoded Intents: TTS and STT have been largely solved for years, but early assistants like Siri and Alexa relied on rigid, prescripted intent mapping.
2. Raw Transcription: Voice input just captured verbatim speech filler words, false starts, awkward pauses, and all.
3. LLM Cleaners: Tools like Whisper Flow arrived, using LLMs as a harness to turn messy human speech into structured, coherent text prompts.
4. Multimodal Local Agents: Systems like Codex integrated voice with vision and direct on-device action.
5. Remote Agent Control: With Meta Muse and OpenAI's latest agentic workflows, the compute is entirely remote. Hardware like Meta RayBans or your phone becomes pure audio I/O, an ambient steering wheel for an agent running a full computer in the cloud.
