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!

Blogpost: jb.gg/air-ide-blog JetBrains Air isn't just model-agnostic. It's harness-agnostic, so is Air in IDEs. Mix and match Codex, Claude Agent, Junie, Pi, Cursor, Copilot, and 50+ more to get the best result. Work with them your way: in Terminal or Chat UI.