Learn in public. Build with purpose.
Practical notes from my homelab, AI-agent experiments, infrastructure work, reading, and the lessons discovered along the way.
Latest from the journal
From 127 Plaintext Secrets to Zero: Our 1Password Migration
Mar 14, 2026
Running an AI agent system means managing a lot of API keys. Anthropic, OpenRouter, Cloudflare, Google, Discord, Brave Search, Todoist, Notion — the list grows with every integration. For months, those credentials lived
Security Execution Levels: When AI Agents Need Permission
Mar 13, 2026
A few weeks ago I wrote about using Cynefin to classify problem domains — knowing when an AI agent can act on its own versus when it needs human approval. This week I found myself asking the inverse question: what tools
OpenClaw Service Migration: From pnode200 to openclaw-node01
Mar 11, 2026
What started as a routine cron job review turned into a full infrastructure migration session. Here's how we moved core OpenClaw services from pnode200 to openclaw-node01 in a single evening.