Steal My Prompt Vol. 51: The Parking Lot Recall
You leave the visit certain about some of it and fuzzy on the rest. This prompt takes a three-minute dictation from the parking lot, tags every item as heard, unsure, or lost, then builds your instruction list and a portal message that asks the office to confirm the rest.
Volume 50: The Work You Wrote Off as Impossible
The EU AI Act's AI literacy duty took effect in February 2025 and became enforceable in August 2026. It reaches US companies whose AI use touches people in the EU, and it asks whether the staff using AI tools were told what those tools get wrong.
There Is No Such Thing as an AI Expert
There is no such thing as an AI expert. I built and filmed a podcast with a friend who had never done it either, on a calendar with no room for it, by putting AI into every workflow neither of us had built before.
Steal My Prompt Vol. 50: The Contract Inspector
The clause that costs you money is often the one that was never in the contract. This prompt reads a vendor agreement, offer letter, lease, or consulting deal as the other side's lawyer, quotes every clause it flags, and lists the protections that should be there and are not.
Volume 49: Inside Every AI Win Is Someone Who Knows the Problem
Before you recommend an AI tool at work, four questions decide if it is actually safe: what it optimizes for, who tested it, what it does not know, and how you would catch it being wrong.
The AI Story Got Its Main Character Wrong
Every AI story I am being sold says the machine no longer needs people. Every AI win I have actually seen says otherwise, and the missing character in that story is the person who knows the problem.
Steal My Prompt Vol. 49: The Care Team Coordinator
When three specialists change medications and nobody reads both notes, you catch it. This prompt turns every provider's notes into one brief: sourced facts, flagged conflicts, and an owner for every open item.
Volume 48: The Failure Mode That Looks Like Great Work
Months before a new AI model reaches you, teams are paid to attack it, and the guardrail that refuses your harmless request is the visible edge of that testing. Plus a one-sentence stop that keeps AI from finishing work it should refuse, and a ten-minute cure for AI news guilt.
