An AI Workshop Should Still Work When the Demo Fails

If the AI assistant won’t load during a workshop, the participants should still have something useful to do. That means preparing an exercise they can finish without the assistant, with the sources and materials available outside the service that just stopped cooperating. Start with what the participants are supposed to learn. Reviewing a draft against […]

Read article: An AI Workshop Should Still Work When the Demo Fails

How Watergate Led to Disney+

Watergate happened in 1972. Disney+ launched in 2019. I’m going to start somewhere in the middle, with the publication of Marvel Super Hero Contest of Champions in 1982. (I had reached that series in a read-through of some of the comic book collected editions I started acquiring during the pandemic shutdown.) Follow along! Contest of […]

Read article: How Watergate Led to Disney+

Cleaning a Nearly Full Server Without Guessing What’s Disposable

When a server is nearly full, a directory called “old” starts to look helpful. It might contain something removable. Or it might contain the only copy of something we still need; the person who named it has left us an adjective, not a retention policy. In a shared-server cleanup last month, I set the preservation […]

Read article: Cleaning a Nearly Full Server Without Guessing What’s Disposable

Design the Review Handoff Before You Design the Prompt

“Please review” can mean anything from “check the spelling” to “find the assumption that will leave twelve volunteers standing outside a locked building”. If we expect someone to approve AI-assisted work, we need to tell them what requires a decision and give them enough information to make it. That starts before the prompt. Who will […]

Read article: Design the Review Handoff Before You Design the Prompt

Zero, Unknown, and Not Applicable Deserve Different Answers

An empty attendance list can mean that nobody came or that nobody entered the attendance. A report that displays zero has chosen one of those explanations; it needs a reason. That distinction comes up in the reporting work for the Dayton Hash website. The pilot’s test cases distinguish confirmed empty attendance from unknown rosters and […]

Read article: Zero, Unknown, and Not Applicable Deserve Different Answers

Turn an AI Friction Log into Reusable Procedures

In Give Your AI Agent a Friction Log, I described recording unexpected failures and what actually resolved them. I’ve since added maintained procedures, helper scripts, and focused skills to that workflow. The next question is whether another task finds and uses them. A growing collection of instructions can also become a growing collection of instructions […]

Read article: Turn an AI Friction Log into Reusable Procedures