Articles
Higher-Order Attacks on AI Code Agents
Direct prompt injection is just the beginning. Higher-order attacks manipulate agents into producing malicious code, propagating intent across systems, and …
When Your AI Code Agent Becomes an RCE Engine
If your AI code agent treats repository content as instructions, any contributor can execute commands. This article maps the direct injection attack surface and …
Javable: generate Java-friendly wrappers for Kotlin with KSP
Javable is a KSP2 processor that generates Java-friendly wrappers for Kotlin classes, turning suspend functions into CompletableFuture, Flow into Stream, and …
kotlinx-schema: Three Ways to Generate JSON Schemas from Kotlin Code
Every time you rename a Kotlin function parameter, the hand-written JSON schema your LLM reads is wrong — and it fails silently. kotlinx-schema derives the …
Mokksy: a mock server that actually streams — and why your AI app needs integration tests
Why unit tests alone won’t save your LLM application in production, and how Mokksy — a Kotlin mock server with true SSE and streaming support — fills the …
Open source deserves better than 'Move Fast'
Open-source libraries may power critical systems where failures have severe consequences. AI tools now eliminate the excuse of insufficient testing time, but …
Introducing Kotlinx-schema: generate JSON Schema from Kotlin types and functions
Generate JSON Schema for Kotlin Multiplatform models and API functions, so your schema stays in sync with your code.
Weekend hack: Kotlin Symbol Processing Maven plugin
KSP only works with Gradle, leaving Maven users out in the cold. I built ksp-maven-plugin to fix that - minimal setup, auto-discovers processors, integrates …
The cookie story: when build failures became sweet accountability
A deceptively simple rule transforms a chaotic development team: break the build, buy cookies. What starts as lighthearted motivation evolves into a …
LLM evaluation testing with promptfoo: a practical guide
This article shows how to implement automated testing for LLM applications using promptfoo with a real application server, addressing the challenge that …