Your turn

Try it. Go back to the question you wrote down at the start. Ask any AI chat tool you use the same question, and compare its answer with this chapter’s on three points. Does it give dates? Does it say what was counted, or which court decided? Does it say who disagrees? Then look up one fact it gives in the source it names. On paper: Take any news story about AI and underline every number or ruling. Beside each, write what it counts or decides, who said so, and as of when. Where the story doesn’t say, write a question mark.

Think about it. Which of these questions matters most in your work or home? It could be your team’s AI energy use, fairness in a decision about people, who owns a report drafted with AI, or a call asking for money in a hurry. What would you need to know before you trusted one number about it?

Good questions for any AI tool

This book began with a lawyer who thought he was using a search engine. Everything since has been a way of seeing which part is doing what, and Chapter 9 put the parts together in one picture. Those four parts are also a way to question any AI tool you meet, including ones that don’t exist yet.

Ask of the model: What did it learn from, and what can’t it know? Ask of the prompt: What instructions am I not seeing, and what did I give it to work with? Ask of the harness: What does it remember, what does it ask before it acts, and where do my words go? Ask of the tools: What can it reach and do, and did it actually use them? And of any number or ruling about AI, ask what was counted, who says so, and as of when.

So the honest answers to the questions people ask are short, sourced, and dated, and most of them begin with “it depends which part.” The products named in this book are examples, each tied to its date. The questions are yours to keep, and to ask of whatever you use next.

That is the real point of learning the parts. These tools work best when they multiply what you can do, not when they replace it. Knowing the parts shows you the different kinds of help on offer, how each one can extend your work and save you time. It also shows you the limits, as the lawyer learned: A model on its own isn’t a search engine. Used well, the model, the prompt, the harness, and the tools work together to move your task forward, while the thinking and the judgment stay yours.

If you are wondering whether you really need to learn this, that question is exactly why this book exists. The parts may be hard to follow at first, so go through the book and experiment with the AI tools you already have access to. Most of the big search engines and AI companies offer a free version, so try a few and pick the one you like. Then think about paying a little each month for fuller access, so you can use it for the things you care about. As of October 2026, free versions included Duck.ai from DuckDuckGo, Microsoft Copilot, Google Gemini, and Claude.¹²³⁴ And remember the one thing that makes this safe to learn, which is that you are the judge of whether an answer is right and whether to use it.

I have spent much of my career helping people learn new tools. Years before AI, I built a five-day bootcamp for developers learning a new way to build software. At that bootcamp I met three kinds of learners. There were the ones who weren’t interested, the ones so eager to help that they ran ahead, and the ones who wanted to skip the training and just start. Each of them got the same things from the bootcamp: the tools, the words for them, a repeatable way to work, and a chance to practice. Those same things are what this book has tried to give you. I am still learning too, and as the tools keep changing, I expect to keep learning alongside you.