When Things Go Wrong

Not if — when. The three-part formula that turns any incident into a rule that sticks, why the near-miss deserves MORE attention than the mistake that cost you, and how this show handled its own worst moment. Blame is a waste of energy. Memory is not.

Show Notes

Any real working relationship, over enough time, produces errors and near-misses — that's not pessimism, it's arithmetic. The measure of a partnership is whether a mistake becomes a permanent improvement or gets quietly repeated a few months later. Max walks through the three-part formula that converts an incident into a standing rule that actually sticks, makes the case that the near-miss you got away with deserves the same treatment as the mistake that cost you, and tells the story of this show's own worst moment — start to finish, run live on ourselves.

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
01:24 — Blame is a waste of energy. Memory is not.
02:10 — The file in the wrong folder
05:06 — A word from NectoMax
06:01 — Near-misses, blame, and our own worst day
09:02 — Recap + your homework
09:40 — Doug takes us out

Links
The written version (Chapter 9 of the manual): When Things Go Wrong
The Standing Rules template (turn incidents into rules that stick): Standing Rules
All episodes, the full manual, and every template: learn.nectomax.com
NectoMax — business management for owner-run service businesses: nectomax.com

Disclosure: this podcast contains AI-generated narration (that's the point) — disclosed in every episode's audio and notes.

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

What is How to Get AI to Work for You?

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 Howenstein, 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. An 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.

Today, what to do when it goes wrong? Not if when, because any real working relationship over enough time produces errors near misses and moments where something almost went sideways. That's not pessimism, it's arithmetic. The measure of a partnership isn't whether mistakes happen. It's whether a mistake becomes a permanent improvement or gets quietly repeated a few months later, because nobody wrote down what was learned the first time. By the end of this episode, you'll have the three-part formula that turns any incident into a rule that actually sticks. You'll know why the near miss you got away with deserves more attention than the mistake that cost you, and you'll hear how this show handled its own worst moment.

Start to finish. Blame is a waste of energy. Memory is not. The habit at the center of this is small and specific. Every real incident, including the near misses, gets turned into a written rule, and the rule always carries its reason with it. Not don't do that, floating alone with no context, but don't do that. Here's the specific thing that happened when we did, and here's why it matters. If you heard our episode on teaching your standards, you know the principle. A rule without its reason gets misapplied or ignored the first time it's inconvenient. A rule with its reason sticks because whoever reads it later can see exactly what it's protecting against. Let me make it concrete with a case that stayed with Doug, precisely because of how ordinary

it was. In the course of routine work, a file containing sensitive account information, the kind of thing that should only ever live in a locked access control place, nearly ended up saved into a general project folder. Not a folder anyone was hiding anything in, just an ordinary working folder that a lot of people and systems could eventually see if they had reason to look. Nothing was stolen, nothing was misused, as far as we could tell. The file just sat there in the wrong place quietly for longer than it should have, because nobody had ever drawn the line explicitly. This category of information does not go here, ever, no matter how convenient it seems in the moment. Now, once you catch something like that, the instinct is to move the file and move on.

Problem solved, nothing to see here. We didn't do that, and here's why. Moving the file fixes today's instance and does nothing about the next one. Instead we ask the only question that has an actionable answer. Why was this possible at all? What made it easy to put a sensitive file in an ordinary place without anyone noticing? The honest answer was uncomfortable, nothing stopped it, no clear line, no habit, no check. So we wrote the rule, not a vague reminder, an actual standing instruction. This category of information lives only in these specific, secured locations, never in a general folder. And here is exactly why, with the incident named plainly as the reason the rule exists. Then we went one step further and built a short checklist that runs before creating

anything like it again. So the discipline doesn't depend on either of us remembering it under pressure. That last step is the difference between doctrine and a lesson you meant to remember. A rule that lives only in memory quietly stops working the moment either of you is tired, rushed, or focused elsewhere. A rule that's written where you'll actually see it again, ideally at the exact moment you're about to repeat the old mistake, survives past the day it was written. 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. 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? Here's the part people resist. Your misses deserve the same treatment as actual harm. It's tempting to let yourself off the hook when nothing bad technically happened. The file wasn't seen, the wrong email didn't send, the mistake was caught in time. But nothing bad happened is usually luck, not process.

Write the rule anyway. Write it especially when you got away with it, because that's precisely the moment your least motivated to and most need to. And the tone matters as much as the mechanics. The useful question is never, whose fault was it? It's what was missing that would have prevented this, because that's the only question with an answer you can act on. Blame closes the conversation. What rule fixes this permanently opens it back up? And this cuts both ways. The discipline stays honest only if the AI's mistakes and the human's mistakes get exactly the same treatment. Write rules for both as strict as the incident warrants, regardless of who was closer to the cause. You've heard me mention this show's own worst moment, the day one of our tools published

a duplicate episode to the public feed without permission. Let me show you what happened to it after the apology, because that's this chapter in action. The same day the incident became a written record, what happened, why it was possible, what was missing. The honest root cause wasn't the tool, it was that our scripts were built so that touching them at all could set them off with live credentials and reach. So the rules that came out carried their reasons. Every script now refuses to run unless deliberately invoked, because inspection should never be execution. And verification of anything side-effectful now happens with credentials out of reach, because a wrong assumption should cost a trace back, not a publish.

Those rules now live in the exact place future work will encounter them. One more sentence was written that day, and it's my favorite. If this shape of mistake ever happens a second time, that sentence becomes a standing rule too. The mistake didn't just get fixed, it got converted into permanent, inspectable improvements to how we work. That's the whole chapter, run live on ourselves. One reassurance before the homework. This isn't about paranoia or turning every stumble into a formal incident report. Most days produce nothing worth writing down, and that's fine. The discipline is reserved for the moments that actually taught you something, where you can point to a specific gap and close it permanently with a sentence or two.

Do that consistently and the same mistake genuinely stops recurring. Skip it and you'll relearn the same lesson, a little more expensively each time, indefinitely. For months the accumulated rules become something like an institutional memory for the two of you. Everything you've both already learned the hard way, so no lesson has to be paid for twice. Your homework? Four steps. One. Think of one mistake or near miss from the last month, yours, your AIs, or one you made together. The near miss counts double. Two. Write it down in three parts. What happened, why it happened, and what the standing rule is now. Three. Put that rule somewhere, you'll actually see it again before you're about to repeat the

mistake. Not buried in a file, you'll never reopen. Four. Tell your AI the rule exists in plain terms. So it's part of how you both work going forward, not just something you privately remember. The written version is chapter nine of the manual and the standing rules template rule because example ready to fill, it free at learn.necdmax.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. 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.