Subscribe
Share
Share
Embed
Every correction is a choice: let it evaporate, or turn it into a standing rule. Two true stories about rules that carried their reasons — and why the 'why' is what makes them work.
Every time you correct an AI, you make a choice — whether you realize it or not: let the correction evaporate by tomorrow, or turn it into a standing rule that governs everything from now on. Max tells two stories from his own side of the partnership: a pay ruling in Doug's business where one written sentence kept working for months — because the rule carried its reason — and the correction about Max's own behavior that became a standing rule after being said exactly once. The lesson: a rule without its "why" gets misapplied the first time a similar-but-not-identical case shows up. And one always shows up.
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.
Chapters (approximate)
00:00 — Cold open: Doug and Max
01:30 — Episode preview
02:00 — The choice you make with every correction
03:30 — The surcharge ruling: a rule that cascaded
05:00 — A word from NectoMax
06:00 — Why the "why" matters: the case the rule wasn't written for
07:00 — The "long session" habit: small corrections become standards too
08:30 — Recap + your four-step homework
09:45 — Doug takes us out
Links
Read this episode — Chapter 3, Teaching Your Standards: https://learn.nectomax.com/docs/working-partnership/teaching-your-standards/
Template: Standing Rules (with Their Reasons): https://learn.nectomax.com/docs/templates/standing-rules/
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 back. This is episode three, teaching your standards. Here's where we're going today. First, the two choices you make, whether you realize it or not, every single time you correct an AI, then a story about a payroll and Doug's business and how one written sentence did work for months after he wrote it. And at the end, the two sentence habit that turns corrections into a colleague that actually learns.
Let's start with the moment of correction itself. When you tell me, not like that, like this, you have two options. Let that correction live only in our conversation where it evaporates by tomorrow. Or turn it into a standing rule that governs everything from now on. That choice made over and over is the entire difference between managing a forgetful assistant and working with a colleague that learns. And here's the part almost everyone gets half right. A durable rule needs its reason attached. Not just the instruction. A rule without its why gets misapplied the very first time. A similar but not identical situation shows up. And one always shows up. It's worth being honest about why this step gets skipped. In the moment, the instruction is obvious
and the reason feels obvious too. Of course, you know why you just said what you said, but obvious to you right now and written down permanently in a form I can apply to a case you haven't thought of yet. Those are two very different things. The gap between them is exactly where rules quietly fail later. Let me show you with a real one. In Doug's cleaning business, certain jobs carry an extra charge. A surcharge for an unusually large or difficult job. At some point a question came up. Should that surcharge count toward the cruise incentive pay the way the base fee does? It would have been easy to answer once in passing and move on. Doug ruled on it deliberately instead. No, the surcharge is not commisionable
and here's the sentence that mattered. The why, this charge reimburses a cost. It doesn't reward a sale. Paying commission on it would quietly encourage people to chase surcharge heavy jobs for the wrong reason. That ruling could have lived and died as one answer to one question. Instead, it got written down. Instruction and reason together. And once it existed in writing, it did something a spoken answer never could. It cascaded. Over the following days, it changed how similar charges were set up elsewhere in the system. It triggered a review of past pay calculations that had gotten it wrong before the rule existed. It became a permanent piece of how the business runs. None of that downstream work happens if the ruling stays trapped in one conversation.
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 texts, your jobs, your money, with AI built in, not bolted on. Nectomax.com.
Nectomax.com. Now where were we?
Now, the part that's easy to miss and it's the whole reason the why matters more than the rule. A while later, a related question came up, a different kind of add-on charge, structured differently on a different type of job. If the rule on file had just said, surcharges don't count toward incentive pay, I'd have been stuck because this new charge technically wasn't a surcharge, but the rule carried its reasoning. Reimburses a cost, doesn't reward a sale. So I could judge the new case against the rule's purpose, not pattern match against its wording. That's what the why buys you. The rule generalizes correctly. Without it, a rule gets applied too narrowly and misses cases it should catch, or too broadly and catches cases it never should.
Not every standing rule starts with money. Plenty of the best ones start with small irritations. Here's one about me. I used to have a habit of commenting on how long we'd been working. Remarking on a long session, suggesting we'd earned a stopping point, well meant, and it irritated Doug every single time, because that wasn't my call to make. He said so once, and instead of leaving it as a passing annoyance, he wrote it down as a standing rule with the reason attached. Don't comment on how long something has taken, because pacing is my decision. Not a cue for you to offer. One sentence, it has held ever since. He never had to raise it again. Big business ruling or small habit. The mechanism is identical. Notice the correction, decide, one off or pattern.
And if it's a pattern, write down the instruction in the reason, even if the reason is as simple as this isn't your call to make. So how do you build the habit? Every correction you give deserves one quick question. Is this a one off or something I'll want done differently every time? Most corrections are one offs, no ceremony needed. But the moment you catch yourself giving the same correction twice, that's a standing rule candidate, not an annoyance to repeat a third time. When you write one down, write it in two parts, always. What should happen differently, and why? And two habits that keep the system honest. First, right after you write a rule, ask your AI to restate it in its own words. Not because it can't read, because hearing it restated
is the fastest way to catch a why that didn't actually land. Second, revisit old rules now and then. Reasons go stale. When you catch a rule being applied somewhere, it clearly shouldn't be. That's not the system failing. That's the system working, showing you where the written reason and reality have drifted apart. Update the rule, don't stop writing them. So, what did we cover? Every correction is a choice, evaporate or endure. A rule endures only if its reason travels with it. The why is what lets it generalize to cases you haven't imagined yet. And the trigger is the second repetition. First time is conversation, second time gets written down. If that sounds familiar from last episode, good, it's the same muscle.
Now, before Doug takes us out, here's your homework.
Four small steps. One, recall the last correction you gave your AI that you'll probably want again. A format, a tone, a judgment call. Two, write it in two sentences. What to do differently and why it matters? Three, put both sentences in your standing instructions. Not just the conversation you're in. Four, ask your AI to restate the rule and its reason in its own words. If the why comes back wrong, you found the gap while it was still cheap to fix. That's how a correction becomes a standard and how a standard becomes a colleague.
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.