Writing
Working notes on building with AI, in public.
Essays on applied AI, agentic development, observability, and the infrastructure underneath. Published on Substack — these link straight through.
Subscribe on Substack →You Cannot Bullshit a Soldering Iron
Blender and 3D animation has always had too steep a learning curve and I have consistently fallen short of making headway in learning these skills.
The Long Way Around
Five and a half years from network automation into AI — what worked, what cost me a year I'd like back, and the number I wish someone had handed me.
POSTMORTUM: Token Black Holes
A junior dev's postmortem, from a 30 round PR review.
What Does an Observability Platform Actually Help You Do?
What building Milhouse is teaching me about signals, context, and learning whether a change really helped.
Introducing Milhouse: Observability For The Way I Actually Build Software Now
What would it look like if my development workflow, production systems, AI coding agents, deploys, bugs, alerts, and weekly operating feedback all lived inside one observability loop?
Hammerspace at AI Field Day 8: Unification, Not Centralization
Disclosure: I attended AI Field Day 8 as a Tech Field Day delegate.
Distributed Filesystems in Agentic Work
and the Signs You Need One
The Pipeline Is the Product
What Selector showed at AI Field Day 8 — and why trustworthy AI in the NOC starts well below the LLM
Tech Field Day
The Room Where Vendors Have to Be Real
Why Your AI Stack Needs a Model Router
The Case for Infrastructure Thinking
How We Skipped the Dashboard: A Case Study in Agent-Native Commerce
By Ryan Booth | April 24, 2026
How the Hotdog Is Made: MCP vs. Smart API from the code
Last post was for the room where decisions get made and plans get drawn.
Customers Don’t Want MCP. They Want Your API to Think.
Breaking down the hype of MCPs and why properly designed APIs are still the right approach.
Building an AI-Discoverable Portfolio with the A2A Protocol
A hands-on introduction building your A2A-enabled personal portfolio.
When the Agents Went Off the Rails (And What I Learned)
What happens when overconfidence meets orchestration and how to prevent it.
Bring a Spec, Not a Vibe
PRD fundamentals for agentic teams (spec‑first, test‑gated, read‑only by default).
Vibes don't ship.
Spec‑first, TDD workflows for skeptical engineers.
Welcome to Reliable AI Workflows
Where PRDs, tests, and tools learn to play nice.
New essays land on Substack first.
Subscribe →