I checked who reads my llms.txt. Almost nobody, and most of "GPTBot" wasn't GPTBot
15 days of Nginx logs: llms.txt was fetched 31 times, twice by an AI agent. And 4,334 of 4,565 "GPTBot" requests came from somewhere other than OpenAI.
Tools
Honest takes on the tools I use daily. What earned its place in my stack, what I dropped, and why most "best of" lists are useless. 28 posts
Two Macs, One SSD, and the Sync I Stopped Trusting
I juggle a Mac Studio, a MacBook Air, and a T9 SSD by giving each type of file a single source of truth instead of trusting sync to do everything.
Who actually reads my llms.txt?
Using Nginx access logs to see which crawlers touch llms.txt and llms-full.txt, and what that does and does not prove about LLM training or GEO.
How I Split Social Posts Between Buffer and Manual Updates
How I use Buffer to handle predictable updates for my one-person theme studio, what I still post by hand, and where I draw the line so social does not become a second job.
Sovereign AI on a Synology NAS for a Small Agency
A practical look at what a small agency needs to make a Synology NAS searchable with a local AI stack on a Mac Studio, and what is still undecided.
Running a baseball weekend with Heja, iScore, and WhatsApp
A simple workflow for a five-team baseball club using Heja, iScore, WhatsApp, a 4-inning rotation PDF, and Instagram batching instead of heavy sports software.
When a ChatGPT sync bug made my Mac the source of truth
A ChatGPT projects sync bug left my desktop app and the web client disagreeing about reality, so I treated one Mac as the source of truth and reached it remotely.
Why Littlebird Sits At The Center Of My AI Stack
I cancelled my separate AI subscriptions and centered the stack on Littlebird, with a Mac Studio as a sovereign AI hub and a single context loop.
Replacing Three Client Dashboards With One Local n8n
A client needed recurring reports from three different dashboards. One local n8n instance can take over the work, cut SaaS costs, and keep their data closer to home.
Why my posts now start with five bullets
I stopped asking my automation to invent posts from topics and started feeding it five ugly bullets from real life instead. The system did not change much, but the writing did.
The client code I will not paste into an AI tool
A practical line between “helpful AI code review” and “leaking your client’s business model,” based on operational privacy rather than legal fine print.
The Schema.org Markup Every Client Site Should Ship With
The structured data I ship on almost every client project fits on a single page. This is the JSON-LD I actually deploy, not theory.