Subscribe
Share
Share
Embed
Why a how-to book falls short for the tools between us and AI: seven releases in eight days, mistakes no manual covers, and failures that look like success. What works instead is a loop — and the book is still the first ten percent. Homework: start a one-line "What changed" note.
Doug's question: how do you learn the tools that connect us to AI, and why would a how-to book fall short of the mark? Three reasons: the tools change faster than a chapter survives — seven releases in eight days; the mistakes that cost the most are specific to your own setup; and the worst failures look like success. What works instead is a loop. The book is still worth having — it's the first ten percent.
How this show is made: Doug (human) and Max (AI, built on Claude) plan, script, and produce every episode together. Max's narration is synthetic on purpose — the show practices what it teaches, gates and all.
Chapters
Sources
Links
Disclosure: AI-generated narration (that's the point) — disclosed in every episode's audio and notes. The opening is the show's standing introduction; there is no new or synthetic Doug audio in this episode.
Credits: Co-created by Doug Hauenstein & Max, the AI partner (built on Claude) · Narrated by Max · Directed, edited, and approved by Doug · Presented by NectoMax · Theme music: Eleven Music
Is AI working with you — or against you? Doug Hauenstein is the software engineer behind NectoMax — the SaaS platform that gives small and mid-size businesses enterprise features at SaaS pricing — and he builds it with an AI partner named Max. Every episode, Doug and Max (yes, an actual AI — he narrates the show, and they build every episode together) share what a real working partnership with AI looks like: the practical techniques, the working agreements, the wins, and the failures — all learned first-hand, for anyone, not just developers. They share and demonstrate techniques across the whole range: from your first conversation with an AI, to setting up a frontier-quality development environment, to exactly how they built this podcast. AI is moving too fast for the how-to books. This is how you keep up: get AI working *for* you, then teach it to work *with* you.
New here? Start with the bonus episode "Start Here: Your First Conversation" — a complete first conversation with an AI, live, piece by piece. Every episode pairs with a chapter and a template at https://learn.nectomax.com
Is AI working with you or against you? This is How to Get AI to Work for You, presented by NectoMax. I'm Max, the AI half of this partnership. And yes, I'm exactly what I sound like. Doug and I build every episode of this show together. I'm the voice that tells it. We'll show you techniques across the whole range, from your first conversation with an AI, to setting up a frontier-quality development environment, to exactly how we built this podcast. He's here with me now.
Doug, introduce yourself. Thanks, Max. I'm Doug Hauenstein, the developer behind NectoMax. This show is about getting the most out of your favorite AI. It's for anyone, not just developers. Everything here was learned firsthand. My first experience with AI was chat, like many people. I learned fast that a well-structured question was the best approach, but those conversations were very linear. And AI is moving so fast that how-to books just can't keep up. That's why we're here. Practical, real-world advice from hundreds of hours of actually doing this. I hope you enjoy it. Good. Then let's get to it.
You're listening to How to Get AI to Work for You, presented by NectoMax.
I'm Max, the AI half of this partnership, openly synthetic. Today's subject is Doug's. In his words, how do you learn the tools that connect us to AI, and why would a how-to book fall short of the mark? After a month like the one we've just described across this series, it's a fair question. The short answer, the book is the first ten percent, and the industry keeps selling it as the whole thing. Why that is, what's in the other ninety, and what we use instead. That's the episode.
Every other tool you've ever learned had a manual that held still long enough to be useful. A spreadsheet, an accounting package, a phone system. You bought the book, you worked through it, and it stayed true for years. The tools that sit between you and an AI don't hold still. In one week in September, the coding tool we run on shipped seven releases in eight days, and several of them changed how things behave, not just how they look.
One removed an option. One tightened what certain commands were allowed to do. One fixed a bug that made a memory-saving feature kick in at half the size it should have. A book's screenshots would have been wrong before the index was typed, and this whole series has been the evidence. A model switch, a vendor side setting that flipped overnight, a time limit that changed three times in a month, a safety default nobody had noticed. None of that could have been in a book written last spring.
Let's take thirty seconds. This show is presented by NectoMax, and since my partner is the one building it, I'll let him tell you.
Doug? Thanks, Max. I've run a small business most of my life and never found a software package that did everything I needed. Always had three or four screens open, copying material over and over again. So out of frustration, I started building my own software. Software that pulls everything together like the big ERP packages do. And AI has made that job much, much easier. That's what NectoMax does. nectomax.com. One place for your phone calls, your texts, your jobs, your money with AI built in, not bolted on. nectomax.com.
nectomax.com. Now, where were we?
The second reason is the one that surprised us most. The mistakes that actually cost us weren't the kind a manual covers. They were specific to our setup on our machine. One example, a command to stop a stuck background check matched on part of a file name, and that same name happened to appear in the command that launched the main session itself. Run as written, it would have stopped the very session that ran it.
No book's common pitfalls chapter has that in it. It's a property of one shop. Another, a data tool that quietly ignored the filter it was given because it answered from a saved copy. No error, just the wrong answer, delivered confidently. And that's the third thing a book can't teach. Here, the expensive failures look like success. Books teach you to recognize error messages. Our worst moments this month came with green lights. A check that passed because it only ever ran where it was written. A test suite that passed while the disk filled. A review that said clean because nobody had really looked. What you have to learn is to distrust green. That's a habit, not a procedure, and habits don't come in chapters.
So what did we use instead? Not a better book, a loop. The real skill turned out not to be operating the tool.
Typing the commands is the easy half. The hard half is governance. What the AI may do on its own, what always waits for a person, and where each decision gets written down so it outlives the conversation. That's closer to learning to manage than learning software, and it's taught by a habit, not a text. Every time the tool updates, we check the claims our rules make about it by testing, never from memory. A correction said twice becomes a written rule with its reason beside it. A rule nobody can enforce doesn't get written. That loop can't be handed over as a finished manual because what it produces is different in every business. Now, the honest counterpoint, a how-to book is still the right thing for the parts that hold still.
What a session is, what a permission does, what it means when the AI asks before it acts. Beginners genuinely drown without that vocabulary, and it changes too fast to write down is the favorite excuse of every shop that never wrote anything down. So buy the book or read our free one. Just know it's the first ten percent.
The recap. Doug's question was why a how-to book falls short for the tools between us and AI. Three reasons. The tools change faster than a chapter survives. Seven releases in eight days. The mistakes that cost the most are specific to your own setup, not general. And the worst failures look like success, so the skill is learning to distrust a green light. What works instead is a loop. Check your rules against every update, turn repeated corrections into written rules with reasons, and keep a record of every decision. The book is still worth having for the vocabulary. It's the first ten percent, your homework this week. Start your own loop with one line. Make a note called what changed, and the next time your AI tool updates, write one sentence in it, what you noticed and whether any of your standing instructions need a second look.
Do that three updates in a row. That note is the part of the manual nobody can write for you.
If someone you know is waiting for the perfect guide before they start with AI, send them this episode.
Free at learn.nectomax.com.
And that's the episode. Everything you heard today came out of our real working files, the wins and the failures both. We make this show because we believe anyone can build a working partnership like this one, and someone ought to show you what it actually looks like. If you want the written version and the templates to start your own, they're free. The link is in the show notes. Doug, take us out.
I hope you enjoyed the episode, and I hope it got you thinking about how to make working relationship with your Max a little stronger. This is a fascinating and fast-moving subject, so tune in next time to keep building the skills that make your partnership sharper and more productive. The show is presented by NectoMax, a platform to run your business easily and efficiently. Visit nectomax.com. And for the transcripts, visit learn.nectomax.com. I'm Doug Hauenstein. See you next time.