Brian Mwangi

So agents are quite good now,what remains for humans

11/02/2026

I have been doing a bunch of coding, experimenting and just generally ai/agentic related stuff, and once in a while when i am struggling with something i will probably try and think of a way out with agents. So i did such this week, i had been using the chrome dev tool with claude code for a while when iterating the look on a website, and i had always struggled with making a great UI, it either turned out to be…

Read more...

Authenticating and Tracing AI Agents: A Protocol-Level Approach

04/24/2026

Oauth solved human identity, JWT’s solved API authentication, But neither was designed for agents. Agents are entities that act autonomously, persist across sessions and accumulate permissions over time and can be compromised without anyone noticing. Agent Auth is the first protocol i have read so far that treats agent identity as a first class problem. The Problem Nobody Has Solved … Yet The problem has three…

Read more...

Building in Public: from 3D NeRFs to safer AI agent harnesses

04/14/2026

I’m Brian Mwangi — a software engineer and AI infrastructure engineer based in Nairobi, Kenya. This blog is where I’ll share what I’m building and what I’m learning as I go: the systems behind agents, practical AI infrastructure, and the occasional deep dive into tools that feel “too magical” until you open them up and see the moving parts. This first post is an orientation: a snapshot of the technical threads I’m…

Read more...