I’m a software engineer. I started out in security research, moved on to Android and Flutter, and eventually landed on the backend. These days I mostly work on AI/LLM platforms, RAG, and agents.

I like bringing new technology back down to real problems: how to swap models, how to make document search accurate, how to recover when a workflow fails. I care less about showing that something runs than about whether the system is still easy to maintain down the road, and whether the next person to pick it up can make sense of it.

What I write about here

This is where I document my hands-on work with AI agents, RAG, backend systems, and security, along with the pitfalls I ran into and the trade-offs I made along the way. Topics range from workflows for AI coding assistants and source-code deep dives into open-source tools to security attack chains reconstructed from public evidence. You’ll also find notes from tech talks and a few side projects of my own. I sometimes write about Android and Flutter too; that experience didn’t disappear just because I started writing Python and Go.

Most posts start from a concrete question. I link to the original sources, note the version I checked whenever I can, keep verifiable facts separate from my own judgment, and spell out where that judgment applies.