What I’ve Learned Building on the Web
Twenty-plus years of building on the web, all of it in here. Up front: the current work – AI systems, SEO, and WordPress at scale, written from what I’ve actually shipped. Further back: the e-commerce years and a quieter chapter spent writing about meditation. And threaded through everything, the Library of Laughs – the funny stories that, according to my own analytics, are the real headliners here.
Latest Posts
NotebookLM: Where the Context Lightbulb Went On
For a stretch, NotebookLM was the tool I opened most. It answers only from the documents you give it and shows you the passage. That one rule is where it clicked for me that context, not the model, is the product. Here's what it does, who it's for, and what I did with the lesson.
Vector Databases: What Running One Across Five Sites Taught Me
Every AI chat that answers from your own content has a vector database somewhere underneath. I run one behind five sites. Here is what it does, why it is the last thing my engine checks, and the maintenance problem the tutorials leave out.
Designing Tools for AI Agents: What Building MCP Servers Taught Me
An agent is only as good as the tools it can call. I build MCP servers and run a WordPress adapter that hands Claude about thirty of them. These are the six rules I follow now, each one learned from a tool that went wrong.
On-Page SEO: The Short Version After Twenty-Five Years
I've been doing on-page SEO since the title tag was the whole game. Most of what has been written about it since can be thrown away. Here are the seven things that still move pages, and the one thing that's new.
Google Gemini: The Bench Player With Home-Field Advantage
In my AI stack post, Google Gemini got half a sentence. It deserves more. Here's the honest account of a model I respect, use occasionally, and haven't made load-bearing - and why it might be the right starter for you.
Google Search Console: What Google Really Thinks of Your Site
Google Analytics tells you what readers do. Google Search Console is the only place Google tells you what it thinks - which pages it indexed, which queries you appear for, and what broke. Here are the three reports worth your time, from someone who steers by them.
ChatGPT: The Second Opinion in My AI Stack
ChatGPT is the most famous AI on earth and the fifth most important tool in my stack. That's not an insult - it's the most honest review I can give it. Here's what the world's default AI is actually for when it isn't your daily driver.
Claude AI: The Model That Runs My Working Day
Every tool spotlight so far has been about software I use. This one is about the AI underneath most of it. Claude AI runs my working day across three surfaces - a chat workspace, a terminal agent, and the API inside my own engine. Here's the honest review.
Google Analytics: The Instrument That Decides What I Work On
Google Analytics doesn't write a word of my content, but it decides what gets written. Here's how one 90-day report reordered my priorities, the two reports I actually open, and my honest take on GA4 - from someone who steers by it.
My Actual AI Stack
I maintain a directory of 139 AI tools in my knowledge base. The AI stack I actually use every day is six tools deep. Here's what survived contact with real work - and the simple rule that decides what gets in.