This site is live. Here's what it's for.
Build logs, playbooks, and case studies from AI systems that actually run in production. Written by the one person who builds and operates all of them.
This site had a coming-soon page for longer than I would like to admit, because the systems it documents kept eating the time I meant to spend documenting them. Fair trade. The systems are the product; the site is the paper trail.
Here is what you will find as it fills in:
- Case studies from AI systems I built and personally operate in production: a document pipeline that processes 600 vehicle titles a week, the tooling that lets one engineer run a 37-server voice fleet, and a one-person newsroom that publishes daily.
- Playbooks on running AI with infrastructure discipline: telemetry, gated writes, drafts-only email, backups you have actually restored.
- Build logs, failures included, because the failure is usually the useful part.
- A free guide to the video pipeline that turns one weekly livestream into a week of short-form content.
The rule for everything published here: I only write about systems I actually run. If that sounds useful, subscribe below, and if your business has a workflow that deserves this treatment, that is what I do.
