-
Complexity Signals the Unresolved
I had fourteen AI agents, and I couldn’t decide which ones to cut. I’d built each one for a reason. Research, writing, editing, coaching, Obsidian vault management, code, distribution, travel. Every agent had a brief and a defined role. The system still felt oversized. Two more AI models had joined the workflow. Several roles overlapped.…
-
GPT-5.6 Sol Got Its Own Release Wrong. That Was the Useful Part.
I asked GPT-5.6 Sol to suggest three AI-learning activities I could finish in under five minutes. It ran a web search to ground the suggestions and came back with a warning: GPT-5.6 was still in preview and unavailable in ChatGPT. There was one problem. I was already using it. The model had found an official…
-
What 30 Days of AI Use Actually Changed
The experiment started badly. On Day 1, I built an Obsidian plugin for the AI Learning Path. The plugin worked. The logging habit didn’t. I missed the first entry and had to recover it the next day through a structured interview. That was the first useful signal. The failure wasn’t model quality. It was system…
-
The Website Started in the Vault
Claude didn’t start my website redesign by asking what color I liked. It started from the vault. That matters because most AI-assisted design work begins in the wrong place. You give the model a vague brief, and it gives you something that looks like every other portfolio site: gradient background, soft cards, oversized hero claim,…
-
The Demo Worked. Mine Didn’t.
The first agent that broke wasn’t Vera. It was Giulia. I’d sent her into the background to file some vault notes while I worked on something else. She reported back fine. Searched the right folders, identified the right structure, confirmed the file paths. Then nothing. No new files appeared. I ran the session again. Same…
-
How to Use AI as Your Accountability Partner for Habit Formation
I’ve tried a few habit trackers over the years. The arc is always the same: a strong first two weeks, a broken streak somewhere around week three, and then the app sits unopened until I delete it. The tracker wasn’t the problem. The accountability system built around it was. Most of them are generic by…
-
How to Build a Multi-Agent Team
When I wrote the original version of this post, I used a fictional content team to illustrate what a good orchestrator prompt looks like. I called the team lead Marco. He managed a researcher, a writer, and an editor. He received briefs, broke them into tasks, assigned them to the right person, and made sure…
