A book, and three free pieces from it
How to get real work out of AI — and keep getting it when the models change.
If you've read anything about prompting, you've been told three things: give the model an expert persona, be polite to it, and tell it to think step by step.
All three have been tested.
162 role assignments across 2,410 questions and four model families. No consistent improvement; the average effect was slightly negative. Low-knowledge personas often reduced accuracy outright.
Some effect on older, weaker models. Little on modern ones. Keep the habit for your own sake if you like — just not because it buys better work.
Excellent, well-evidenced advice in 2022. OpenAI's own guidance now says it's unnecessary for reasoning models and notes it can make one model's output worse.
Nothing went wrong here. The last one was genuinely good advice — a real finding, a real effect. It didn't fail. It got absorbed: what was once an external trick became a behavior trained into the model itself.
That's the pattern worth having. The trick expired; the principle didn't. Anyone who memorized the words has to relearn. Anyone who understood why it worked changed nothing at all.
Now consider what that implies about a book selling you three hundred prompts.
In a randomized trial, sixteen experienced developers using AI took 19% longer on real tasks in code they knew well. That part has caveats — sixteen people, expert users, familiar ground — and I wouldn't generalize it.
What they believed is the part worth sitting with. Beforehand they expected to be about 24% faster. Afterward, having just done the work, they still estimated they'd been 20% faster.
Their perception didn't merely miss. It had the wrong sign, and direct experience did not correct it.
Sixteen people can't carry a general claim, and the book doesn't ask them to — that job belongs to several decades of automation-bias research finding the same under-monitoring in experts and novices alike, in cockpits, control rooms and clinics. This trial is the vivid version, not the evidence.
The hard part isn't getting AI to produce something. It's knowing when what it produced is worth having — and you cannot rely on your own sense of how well it's going.
That's not a prompting problem. No phrasing solves it.
The context pack template from the book's appendix — the single change that improves most people's output today. Plus the three posts as they publish, and a note when the book is out. No other email.
It assumes you already use AI. No tour of what a language model is, no convincing you it's useful, no prompt library that expires next quarter.
It's a map of where AI genuinely helps and where it makes you measurably worse, six systems you install once, a verification method fast enough that you'll actually keep it, and an argument about what you should never hand over.
Every system is demonstrated end to end, including where the demonstrations failed. You'll watch a model invent a launch date it was never given, promote a passing remark into a tracked commitment, and quietly resolve a question that was deliberately left open.
You'll also watch one chapter's central failure refuse to reproduce under testing — and the chapter report that, rather than quietly keeping the better story.
Written with AI, disclosed up front. The research, drafting, and revision were done by a language model working from direction. Every technique in the book was demonstrated rather than described — including the demonstrations that failed, which are reproduced as they occurred. Factual claims are sourced per chapter, and where the evidence is weak the book says so rather than rounding up. A book about getting real work out of AI seemed like the wrong place to be coy about how it was made.