How I Taught an AI to Do My Bookkeeping
Living in Germany with financial ties to Ukraine means three bank accounts, two countries, two currencies, and a lot of monthly bookkeeping nobody wants to do. For years I’ve tracked every …
Read more →Chrome Now Speaks MCP Natively — Here's What That Means
Six months ago, debugging a website with an AI coding assistant meant launching a separate browser instance, connecting it through a Node.js bridge, and hoping everything held together. As of Chrome …
Read more →I Built an OpenTelemetry Extension for Pi Coding Agent
A few days ago I wrote about setting up observability for Claude Code with the Grafana stack. Claude Code ships with OTEL support baked in — set some env vars, data flows. Easy. Pi is a different …
Read more →Your Second Brain Has a New Reader
Yesterday I gave a talk at the DevOps Meetup in Freiburg, hosted at JobRad. The title: Your Second Brain Has a New Reader. The core thesis is simple: most of us have spent years building personal …
Read more →What I Learned at AWS Frugality Training
Yesterday I attended an AWS GameDay on Frugality, organized by Automate-it. If you haven’t done a GameDay before — it’s AWS’s hands-on competitive format where teams get a real AWS …
Read more →How I Set Up Observability for Claude Code with the Grafana Stack
AI coding assistants are becoming standard engineering tools. But here’s a question most teams aren’t asking yet: how much are they actually costing us, and are they making us faster? I …
Read more →1Password Environments: The End of Plaintext .env Files?
I counted six .env files on my laptop last week. AWS keys, database URLs, API tokens for three different services. All plaintext. All “protected” by .gitignore. We all know this is bad. We …
Read more →Securing OpenClaw with 1Password: No More Plaintext API Keys
I’ve been running OpenClaw on my home server for a few weeks now. It connects to Discord, Telegram, ElevenLabs for TTS, various LLM providers — and every single API key was sitting in plaintext …
Read more →Tracing the Thoughts of a Language Model: What Anthropic Found Inside Claude
Anthropic just published something remarkable — they built an “AI microscope” that traces what actually happens inside Claude’s neural network during inference. Not what the model …
Read more →Agent Client Protocol: LSP for AI Coding Agents
Remember when every text editor had to build custom integrations for every programming language? Syntax highlighting, autocomplete, go-to-definition — all reimplemented from scratch for each …
Read more →