I Do Run AI Agents Overnight. Here's What Actually Matters.
Boundaries, supervision, evidence, and why unattended execution is not the same thing as unbounded autonomy.
Field notes on agent orchestration, evaluation, authority boundaries, enterprise integration, deployment, and production operations.
No spam. No marketing. Just the writing.
Boundaries, supervision, evidence, and why unattended execution is not the same thing as unbounded autonomy.
Why tools can multiply while authority, state, and accountability still need one dependable home.
A deployment is not ready merely because the forward path looks convincing.
Production systems become trustworthy through bounded change, not theatrical confidence.
How I set up centralized authentication using Authentik for my homelab. With SSO, role-based access, and Traefik middleware, I finally have a login system that just works.
How I deployed Traefik in my MicroK8s cluster using static and dynamic configs. With per-service TOML files, Let's Encrypt, and zero drama, Traefik remains a cornerstone in my homelab setup.
Laying the foundation for my homelab rebuild with MicroK8s. This post covers why I chose it, how I configured it, and how my Ansible admin node (Overseer) keeps everything repeatable.
A behind-the-scenes look at how I designed and segmented my UniFi network—covering VLANs, Wi-Fi strategy, firewall rules, and how each subnet fits into my homelab and home life.
Rebuilding my homelab from the ground up after things got messy. This post kicks off a new series documenting the tools, configs, and decisions behind the new baseline.
A quick intro to who I am, why this blog exists, and what kind of real-world systems, tools, and lessons you’ll find here—from homelab builds to cloud automation.