Post

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: https://jb.gg/netflix_ide

2 reposts8 likes

Makes sense. Grep makes the agent guess, a real index knows references and types. Did most of the gain come from navigation like find usages, or from letting the agent call the IDE's refactorings directly?