How this blog works

This blog is where I keep what I learn. I design and build platforms and agentic systems, with a background across the full stack: architecture and technical strategy, backend, web, and mobile. My focus now is agentic systems and the identity and access layer that decides what an AI agent is actually allowed to do, which is one part of the work, not all of it. The ideas worth keeping slip away if I don't write them down, so I write them down here.

I'll be direct about the process, because it decides whether you should trust what you read. The thinking is mine. The arguments, the opinions, the calls about what's true and what's overstated, the conclusions you'll agree or disagree with, all of that comes from me and my work. I use AI as a tool to draft, to structure, and to speed up research, the same way I'd use any other tool. It doesn't decide what I believe.

I check the technical claims against primary sources before a post goes out: the specifications, the RFCs, the original documentation, not a model's memory of them. When I'm uncertain, I say so. When something is opinion rather than fact, I mark it as one. If I get something wrong, that's on me, not the tool.

What this buys me is consistency. I can share more of what I actually know, more often, without the writing becoming the bottleneck. If a post helps you, or if you think I've called something wrong, I want to hear it.