Volume 39: AI Got the Keys to Your Refills but Not Your Denials
A daily ChatGPT user of two years spent one week inside Claude's free version. Long documents fit whole, the usage limits hit faster than expected, and the real lesson was which tool fits which task, not which one wins.
Volume 38: Why Your Best AI Idea Is Stuck in Someone's Inbox
When an AI tool misbehaves, "train it more" is usually the wrong instinct. Prompting handles one-off tasks, retrieval handles changing information, and fine-tuning earns its cost only at high volume, so here is how to choose the right lever.
Volume 37: Better AI Is Discipline, Not a Larger Budget
Every commercial AI you use was trained to be helpful through a process most professionals have never heard of. It is why these tools feel useful instead of bizarre, and also why they sometimes tell you what you want to hear. Here is how that training works.
Volume 36: A Maine Mill Town Wrote the Better Playbook
Most professionals believe fine-tuning an AI model on company data teaches it the business. It does not. Fine-tuning shapes how a model behaves, not what it knows, and confusing the two is why so many internal AI pilots quietly fail.
Volume 35: Build the System Before You Need It
Frontier AI models now ship with million-token context windows as the floor, not the ceiling. Independent testing shows the number on the spec sheet is rarely the number you can rely on. Here is how context actually works in 2026 and what to use instead of raw size.
Volume 34: The Question You Have Not Asked Yet
Most AI pilots track time saved and call it a win. The real question is what separates the 34% of companies reimagining their business from the 37% changing nothing.
Volume 33: Build Smaller Than the Hype
Every morning, an AI agent I built scans 13 sources and emails me what matters. Less than $10/month to run. Inside: how to build the small version of an agent that actually gives you time back, how Copilot's agentic layer works, and a 10-minute audit to rewrite your LinkedIn profile.
Volume 32: Data Is the Work
ServiceNow lost 18% of its value in one trading session. The deeper story is a moat reset, and what hit software is coming for everything else. Inside: the one question to ask before any AI workflow, what Copilot really does in Word, Excel, and PowerPoint, and a vision-AI workflow for dinner.