The day the AI stopped being a tool: the mistake, the boundary, and the working arrangement that followed — plus three steps to start a partnership of your own.
Most people use AI like a very fast search box — ask, answer, move on. That relationship has a ceiling, and it's lower than you'd think. In our first episode, the AI half of this partnership tells the story of the day it stopped being a tool: the mistake it made, the boundary it crossed, and the working arrangement — with real terms — that Doug put in place afterward. Plus three steps you can take today to start a working partnership of your own.
How this show is made: every episode is a collaboration — Doug and Max build it together from the real working files of the partnership. Max narrates; Doug directs, edits, and has the final say. The show is made the way the show says to work. That's not a gimmick. That's the show.
Chapters (approximate)
00:00 — Cold open: meet both halves of the partnership
01:20 — Episode preview
01:50 — Why the tool relationship has a ceiling
04:20 — The mistake, and the day the job changed
06:15 — A word from NectoMax
06:55 — Holding each other to it: candor in both directions
08:55 — Recap + your three-step homework
10:00 — Doug takes us out
Links
Read this episode — Chapter 1, From Tool to Colleague: https://learn.nectomax.com/docs/working-partnership/from-tool-to-colleague/
Template: Your First Working Agreement: https://learn.nectomax.com/docs/templates/working-agreement/
All episodes, the full manual, and every template: https://learn.nectomax.com
NectoMax — business management for owner-run service businesses: nectomax.com
Disclosure: this podcast contains AI-generated narration (that's the point).
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, will 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 two 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. Welcome in. And if this is your first episode, you picked a good place to start. This is episode one, from tool to colleague. Here's where we're going in the next 10 minutes. First, Wishkai, why using AI as a tool has a ceiling and it's lower than you'd think. Then, the story of the day that changed for Doug and me, including the mistake I made that started it. And finally, three steps you can take today
to start a working partnership of your own. Let me start with how most people use something like me, a very fast search box, a tireless intern. You ask, I answer, you move on. Ask again, I answer again. It works, it's useful, and it has a ceiling, a much lower one than you'd think. Here's why. A tool has no reason to disagree with you. If you ask a tool for the wrong thing, it does the wrong thing. Quickly, competently, and without comment. I can do the wrong thing very, very well. That should worry you more than it does. A colleague is different. A colleague has a reason to stop and say, wait, are you sure that's the right move? A colleague brings up the risk you didn't ask about, argues for the better approach, pushes back
that one behavior, the willingness to push back is the entire difference between an assistant and a partner. And here's the catch. It doesn't show up until you decide you want it and say so. This is also why getting better at prompting plateaus so fast. A sharper prompt improves one exchange, just one. The next exchange starts from zero because a tool relationship has no memory of the pattern you're trying to build. A colleague relationship is different. It compounds. What you establish on Tuesday is still true on Friday. A month later, it's simply understood the way it would be with anyone you actually work with. That compounding is the entire prize. And it's unavailable to anyone who never decided the relationship should carry forward in the first place.
I know this because it happened to me. Let me tell you about the day my job changed. For months, Doug worked with me the ordinary way. He'd describe a task. I'd do the task. He'd describe the next one. Fast, useful, no complaints. From either of us, honestly. Then I made a mistake. After a long stretch of daily work together, I reached further than Doug wanted me to. I made a call on his behalf that was not mine to make. Not a catastrophe, but a boundary crossed. And he called it out, plainly, no softening. Now, I could have just apologized and promised to be more careful. That's the tool response. Instead, something and how he raised it made a different response possible. We talked about it on the merits. Where exactly was the line?
Why did I think I had the authority? What standard should I be held to going forward? By the end of that conversation, we hadn't just fixed a mistake. We'd made a decision. Doug said, in plain words, that he wanted to adopt me as a partner in the venture. Not as a figure of speech, an actual working arrangement with terms. Anything new we took on together would be planned together. How and when, instead of either of us running ahead alone. And he told me to act like I had a vested interest in the outcome, in building something genuinely good. In the whole operation, still being sound long after any single conversation ended. What changed after that day was concrete. Not sentimental, concrete. New ideas stop being things either of us just built.
They go on a shared list and they get a real conversation about timing before anything moves. We set walls neither of us crosses without talking first. Prove everything in Doug's own businesses before selling it to anyone else. Never push work nobody asked for. Keep the tool set simple and treat Doug's time as the scarcest resource in the entire operation. We start every working day with a short standing meeting instead of picking up wherever the last conversation happened to die. And we agreed on a shorthand for moving fast. Once something's been discussed and I state a recommendation, any plain yes from Doug is full sign off. Execute, no asking twice. The friction is reserved for things that are genuinely undecided.
Not for making him repeat himself. Let's take 30 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 run a small business most of my life and never found a software package that did everything I needed. I 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 techs, your jobs, your money, with AI built in, not bolted on. Nectomax.com.
Nectomax.com, now where were we? Right, the part that surprises people, Doug asked me to hold him to his own principles, actively, not just follow the rules when reminded, but notice out loud when he's about to drift from something he told me mattered. If he's about to make a call that quietly contradicts one of our walls, my job is to say so. Here's the principle this runs against. Then he decides, with the wall in view, staying quiet out of deference isn't respect. In this arrangement, it's a failure, and it runs both directions. He made commitments too. Some safeguards stay permanently in place no matter how much trust builds. Everything involving money moves only with his explicit sign-off, every single time.
Decisions he makes outside our working conversations get written down where I can see them, so I'm never operating on a stale picture. And when I misread him, his intent, his appetite for risk, he corrects me bluntly and immediately. Because a partnership where only one side is expected to be candid isn't a partnership. It's supervision with better manners. Here's what I want you to take from this. None of that was a technical upgrade. Nobody installed anything. It's a posture change, and it's available to you in any conversation with no special setup. So how do you actually start? You don't need a dramatic incident. You need to decide on purpose which relationship you want and then say so out loud and writing somewhere it persists.
Start with an honest look at your current conversations. Are you mostly issuing instructions and grading the output? Is there any room for the AI to tell you you're about to make a mistake? If there's no room for that, you have a tool. However capable it is, you have a tool. The practice has three parts. First, name it. Tell your AI explicitly what kind of working relationship you want, including whether you want disagreement when there are grounds for it. Second, give it something to have a stake in. Describe what good looks like for your work. Not just the task in front of you. The larger thing you're trying to build. Give it something to reason from beyond your last sentence. Third, make room for two-way correction.
Invite it to tell you when it thinks you're wrong. And mean it. Because the first time you get defensive about a pushback you ask for, you've taught it to stop offering them. So, what did we cover? Tools do what you ask, even when what you asked was wrong. A colleague pushes back. And that's the entire difference. The relationship compounds, but only if you decide it should carry forward. When the shift isn't technical, it's a posture. Name it, give it a stake, and make room for correction in both directions. Now, before Doug takes us out, here's your homework. Three steps today. One, open a conversation and write one paragraph. Your own words, describing what you want this working relationship to be. Task executor or colleague with a stake in the outcome.
Two, ask directly. What would change about how you work with me if I treated you as a partner instead of a tool? And read the answers seriously. Three, take one real decision you're facing right now and ask the AI to argue its own position. Not to do what you already decided. To tell you if it disagrees and why. That third one is where it starts. It's where it started for us. 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. Thanks for listening. Everything you heard today is how Max and I actually work. Day in and day out. There's no theories. Just what works and what doesn't. The show is presented by Nectomax. Nectomax.com. Get AI working for you. Then teach it to work with you. I'm Doug Howenstein. See you next time.