The Reviewer Who Refutes: Running an Adversarial Review Cycle with AI Agents

Every AI-drafted change in our repo faces a second AI whose only job is to prove it wrong - with negative controls. The cycle has caught a real defect on nearly every pass, including bugs in my own fixes.

Read more →

Free CI on Hardware You Already Own: Gitea Actions on a NAS, Set Up by an AI Agent

GitHub wanted money for Actions on a private repo. The NAS in the closet was already running Gitea. Here is the full recipe for turning it into a CI runner, with an AI agent doing almost all of it.

Read more →

Googlebot Was Being Redirected to Our Login Page

An SEO audit that started with "can we list it on Search Console?" ended with a login redirect on every footer page, an llms.txt manifest for AI agents, OG cards rendered from live database rows, and the discovery that CI had been quietly red the whole time.

Read more →

AI Search Optimization, Part 5: The Tool-Invocation Moat

Getting cited is table stakes. The real moat for a tools site is being the capability an agent actually *runs* — via API or MCP. Here's the bet, the monetization ladder, and why we've gated it on a demand signal instead of building it blind.

Read more →

Google Told Me to Build Four Features. Three Already Existed.

A Search Console query sweep surfaced four juicy feature gaps on a young tools site. I read the code before building — and three of the four were already shipped and marketed. They ranked low because the site is new, not because the feature was missing. The lesson holds double when an AI agent is the one proposing the work.

Read more →

The Day the Data Picked the Backlog — Ten Shipped Waves and One Owlbear

Search Console finally had enough data to rank my pages, so I let it write the backlog. Ten feature waves shipped in one day — and the live verification step caught a bug my unit tests never would have.

Read more →

Auditing a Production Site With Four Agents at Once

I pointed four clean-context AI subagents at my CV site — one each for security, SEO, accessibility, and performance — then did a coordinated fix pass. The audits were the easy part; three footguns in the fixes were the interesting part.

Read more →

Emma Covers the Pets Now: The Bug Hiding in an Array Index

A chore chart quietly reassigned a kid's manual override to the wrong task the moment you deleted a row above it — and still called it a deliberate edit. The fix is a small lesson about identity versus position in persisted state.

Read more →

SkillForge & Automation Experiments - Live Validation Update

Current status of live experiments on SkillForge marketplace, business automation agents, and AI ops tools. Early demand signals and next steps for monetization.

Read more →