9 min read
Subagents vs. Agent Teams: Two Ways to Split a Job
Subagents delegate and report back. Agent teams coordinate and talk to each other. A practical guide to choosing between them, and to supervising the autonomy you just bought.
Writing
Field notes
Platform engineering, DevOps, and building with AI coding agents — the practical version.
Showing all 17 posts
Filter by tag
8 min read
The Tokens I Don't Have
Every long-lived credential in your CI secrets is a standing liability you re-accept every day. Here's replacing them with short-lived, identity-based auth: OIDC trusted publishing to npm, letting the vendor CLI own its own login, and an honest list of the ones I haven't killed yet.
10 min read
What Should an AI Agent Be Allowed to Write Down?
Putting an agent between a voice recording and a git repo is easy. Deciding what it may commit is the hard part, and the rules that sound most responsible are the ones that fail first.
8 min read
The Monitoring You Set Up During an Outage Is the Wrong Monitoring
Observability is the thing everyone agrees matters and nobody installs until after it would have helped. Here's what actually goes in the box, why the alert thresholds are the hard part, and the three alerts that watch the monitoring itself.
9 min read
You Can't Sanitize a Sentence: Why Prompt Injection Is Still Unsolved
Prompt injection held the top spot in OWASP's 2026 LLM Top 10, published this month. But the entry that moved tells the real story: Excessive Agency jumped from sixth to third. The vulnerability didn't get worse. We handed it more to work with.
9 min read
Migrating Off a Platform That's Fighting You: WordPress to Astro
A real WordPress + Elementor site rebuilt as a static Astro site: preserving five years of URLs, rewiring 1.7 GB of images that pointed at three different dead hosts, and the last step nobody talks about, which is destroying the old server.
10 min read
It's Not Skynet, and It's Not Reading Your Mind
What ChatGPT, Claude, and Gemini actually are, in plain English. Why they aren't plotting anything, why one of them knew about your family, and where the real risks actually live.
8 min read
RAG Is Context Engineering, Not a Chatbot Trick
Most explanations of RAG stop at 'chat with your PDF.' For a long-running agent, retrieval isn't a one-shot lookup: it's how you decide, at every step, what belongs in a limited context window and what gets left out.
6 min read
Kill Your Public Management Ports: Zero-Trust Access with Tailscale
Every open port on a droplet is a standing bet against the entire internet. Here's how I stopped taking that bet: the real Tailscale setup behind this site's own analytics stack, the three things that broke before it worked, and the one port I still haven't closed.
6 min read
One File to Govern Them All: A Policy Layer for Every AI Agent
Every project I own has its own CLAUDE.md, and none of them can override the one thing that actually matters. How a three-layer policy hierarchy turns AI governance into filesystem permissions instead of a promise.
7 min read
I Built My Own Consulting ERP
Generic invoicing tools don't fit a solo consultant's actual pipeline, so I built Helm: a local-first back office where proposal, SOW, invoice, and tax set-aside all live in one connected model. This is the dogfooding story, and the decision that almost shipped it as the wrong kind of app.
6 min read
Push to Main, Ship to Prod: The Bug That Ate a Deploy
GitOps promises that merging to main quietly becomes a live deploy. Here's the merge that looked perfect everywhere except in production, the exact error that explained it, and the boring fix that makes sure it can't happen twice.
6 min read
Should Your AI Agent Be Able to Edit Its Own Guardrails?
Should an AI agent be allowed to edit its own guardrails? The answer is yes, if you separate the control plane from the data plane. Here's how, and why it's the safety.
7 min read
No, I'm Not Vibe Coding
The critics of AI-generated code are mostly right, and that's exactly why 'vibe coding' doesn't describe how I work. The whole line is: who reads the code?
15 min read
From Sand to Sorcery: How LLMs and AI Agents Actually Work
A working engineer's ground-up map of how LLMs, tool use, and AI agents actually operate. No hype: just a stateless next-token function, wrapped in a loop.
6 min read
Two Ravens, Two Wolves, and a High Seat
I run two dozen GitHub repos as one estate with five small CLIs named for Odin's ravens and wolves. Here's the pack, and why the myth is really just good ops.
5 min read
Your AI Coding Agent Is an Over-Eager Intern
AI coding agents are brilliant, tireless, and eager to a fault, which is exactly what makes them dangerous. Why speed quietly defeats review, and how a handful of automated guardrails keep an over-eager agent from merging something regrettable.
No posts match your search or filter.