Blog

I've been writing online at various sites since 2003, mostly about a wide variety of topics including web development, tech, food and whatever else I feel like writing and sharing.

2026-09-30

Migrating this site to EmDash

This site has changed CMS more times than I can count since 2003. This time I moved to EmDash on Cloudflare, and the reason is that most of my building now happens alongside an AI agent.

2026-09-29

Get Butters: A Quick Events Dashboard

I wanted a simple dashboard that showed me events as they happened, so I wrote a quick little Astro app. It grew into Get Butters: a real-time event feed with a REST API, a CLI, insight cards and push alerts.

2026-09-06

The Agentic OS in Practice: Running Multiple Agents Without Losing Control

Once four agents can edit the same repo, architecture stops being the hard problem and coordination starts. The five roles I run and what each one is forbidden to touch, why every handoff goes through a file, a worktree script so agents stop racing, and the failure modes worth naming.

2026-09-03

Your AI Agent Needs a Definition of Done

Saying "done" costs a model nothing, which means it carries no information. A definition of done has four machine-checkable parts: source boundaries, acceptance criteria written as observations, verification commands the agent does not own, and a list of claims it must refuse to make without evidence.

2026-09-02Featured

Setting Up Dozzle with Auth on Coolify

Guide on setting up Dozzle with authentication on Coolify for secure, real-time Docker container logs, CPU, and memory monitoring.

2026-08-30

How to Build an Agent QA Loop That Files Its Own GitHub Issues

A one-shot QA pass is a demo. Put it on a cron and it files the same issue every morning until the qa-bot label is a landfill. Here is the loop that makes the queue drain instead of grow: a spec in version control, fingerprinted issues, a reconciler with no opinions, and auto-close when the flow goes green.

2026-07-23

Context Engineering for Production Agents: Sources, Boundaries, and Evaluation

A practical framework for giving production agents the right evidence, the right limits, and a measurable definition of done.

2026-07-07

Your Astro API Route Can Be an MCP Server

Most MCP tutorials assume a standalone process. Here's how to expose one as just another Astro API route using Streamable HTTP — same auth, same deploy pipeline, no second app to maintain.

2026-07-01

Talk to Your Datastar Chat: Voice Input with the Web Speech API

Extending the Datastar chat widget with the browser's native SpeechRecognition API — no new backend, no transcription service, just one more way to fill the same signal.

2026-06-07

Run the Whole Stack Locally: Datastar + Astro + Ollama, No Cloud Bill

Take the Astro + Datastar + Vercel AI SDK stack from this series and run it entirely on your own machine with Ollama — no API key, no per-token cost, no data leaving your laptop. It's a one-import change.

2026-06-06

Streaming Structured Output into a Datastar UI (a Card That Fills Itself In)

Stream typed, structured data from the Vercel AI SDK and watch a card build itself field by field in a Datastar UI — using streamText with output, the v6 replacement for streamObject. No React.

2026-06-06Featured

How to use Claude Code to QA your website

My dialer QAs itself: Claude Code logs in, dials a list of Twilio test numbers — a voicemail, an IVR, a simulated gatekeeper — records what happened vs. what should have, and files GitHub issues for another agent to fix.

2026-06-05

Giving Your Datastar Chat Real Tools with the Vercel AI SDK v6 Agent

Turn the streaming chat widget into an agent that calls tools — and stream the tool-call status live into the conversation. Astro, Datastar, and the AI SDK v6 ToolLoopAgent, no React.

2026-06-04

Build a Streaming AI Chat Widget with Astro, Datastar, and the Vercel AI SDK

A full multi-turn chat widget with live token streaming — where the server owns the conversation and the DOM is just the view. No React, no useChat, no client framework.

2026-06-03

Add an AI "Summarize This Page" Button to Any Astro Site with Datastar

A small, genuinely useful build: a button that streams an AI summary of the current page into a panel, using Astro, Datastar, and the Vercel AI SDK — no React, no client framework.

2026-06-02

Streaming LLM Responses into a Datastar UI with the Vercel AI SDK

The Vercel AI SDK's useChat only ships React, Vue, and Svelte bindings. Here's the small, reusable pattern for streaming AI tokens into a plain Datastar UI instead — no framework required

2026-06-01

Building AI Apps with Astro, Datastar & the Vercel AI SDK (a 6-Part Series)

The Vercel AI SDK's useChat only ships React, Vue, and Svelte bindings. This six-part series builds real AI apps — chat, agents, structured output, local models — with no client framework at all, using Astro, Datastar, and one small streaming pattern

2026-05-29

How to use VAPID web push notifications with Astro

You don't need OneSignal or Firebase to send push notifications. Web push with VAPID keys is built into every modern browser — here's the full setup in Astro: service worker, subscribe flow, SSR endpoints, and sending from the server.

2026-04-06

Building a Streaming URL Summarizer with Astro, Datastar, and the Vercel AI SDK

How I wired up a tiny TLDR tool that takes a URL, extracts the article, and streams a Markdown summary back to the browser in real time — using Astro SSR, Datastar for reactivity, and the Vercel AI SDK for the model call.

2026-04-02

Why I’m migrating from HTMX + Alpine to Datastar

I've been a big fan of HTMX + Alpine for a long time, the combination just lets you create powerful reactive web apps, but recently I've made the decision to move from HTMX + Alpine to Datastar for various reasons and the result means a better experience for users.