Teaches AI agents to write idiomatic Kotlin (data classes, val, scope fns, Kotest) AND to make the right stack choices on JVM: Kotlin 2.3 + JDK 21 + Gradle Kotlin DSL, Ktor for HTTP, kotlinx-coroutines, DJL for ML inference, JavaCV for vision, Koog for AI agent orchestration.
95
95%
Does it follow best practices?
Impact
95%
1.23xAverage score across 10 eval scenarios
Passed
No known issues
kotlin("jvm") version "2.3.0") — the latest stable, picks up the type-inference and coroutine fixes that downstream libraries (Koog, Ktor 3.4, kotlinx-coroutines 1.10) build againstjvmToolchain(21)) — the current LTS; required by JavaCV 1.5.13's native libs and recommended by Koogbuild.gradle.kts, settings.gradle.kts) — Groovy DSL only for legacy projects you didn't start./gradlew) committed to the repo so a fresh clone runs without a system Gradle installgradle/libs.versions.toml) when there are more than ~5 dependencies; inline implementation("group:artifact:version") is fine for tiny projectssrc/main/kotlin/, src/main/resources/, src/test/kotlin/main() per file when each file is independently runnable (CLI tools, demo stages); use application plugin + per-stage JavaExec tasks rather than a single fat mainapply plugin: 'kotlin' in a build.gradle Groovy file when starting fresh