About Me

I'm Raj Chettri — I currently serve in a technical role with the U.S. Army, and I'm a builder and lifelong student of how things work and how they break.

My path into technical work started with hands-on systems, troubleshooting under pressure, and learning to respect the details that keep complex things running. Thirteen years in, the work still comes down to the same thing: understand the system, find the edge, and work the problem.

What I'm working on

My center of gravity right now is agentic AI and applied LLM workflows. I'm building with Claude Code, MCP servers, the Anthropic SDK, LangChain, and ChromaDB — automating real work, not demoware. I write tooling that sits between humans and models, and I care about the boring parts: reliability, evals, cost, and whether the thing actually ships.

The cyber side of my brain hasn't gone quiet either. I'm interested in where AI lives on the attack surface — model abuse, agent security, supply chain risk, and the governance gap that's opening faster than anyone's closing it.

Why this site

This is my working notebook. I write here to force clarity on what I'm learning, leave a trail others can use, and keep myself honest about what I actually understand versus what I've only skimmed. Teaching is the best way to learn, and public writing is the fastest way to find out what you got wrong.

You'll find: notes on agentic AI and MCP, security deep dives, hands-on walkthroughs, tool reviews, and the occasional piece on process, ops, and how I run my own life as a system.

Off the clock

Outside work, I'm a husband and dad of three (2 kids and one dog) who enjoys outdoors, movies, music and good beer. I read more nonfiction than I probably should, take the long drive when I can, and keep my coffee strong and my backups automated.

If any of this resonates, get in touch. I'm always up for a real conversation — about cyber, AI, entrepreneurship, or anything in between.

---