Making It Show Its Work

Did you check, or are you assuming? The morning the books looked broken, the two-hour question that was a thirty-second lookup — and the mistake Max made this week, caught by the habit this episode teaches.

Show Notes

Two expensive mistakes bracket every AI partnership: believing everything it says, and mistaking its silence for confidence. Both have the same fix — one question, asked in both directions: did you check, or are you assuming? Max tells the story of the morning the books appeared to show money referencing accounts that didn't exist (and how one verification question turned a five-alarm fire into nothing), the two-hour detour that was secretly a thirty-second lookup — and then airs this show's own laundry: the mistake Max made this very week, caught by the exact habit this episode teaches. Receipts, not summaries. Traceability, not confidence.

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: did you check, or are you assuming?
02:15 — The two expensive mistakes
03:00 — The morning the books looked broken
05:15 — The two-hour question that was a thirty-second lookup
06:00 — A word from NectoMax
07:00 — The practice: receipts, not summaries
08:00 — Our own laundry: the mistake Max made this week
09:05 — Reading for evidence, not tone
09:45 — Recap + your four-step homework
10:15 — Doug takes us out

Links
Read this episode — Chapter 6, Making It Show Its Work: https://learn.nectomax.com/docs/working-partnership/making-it-show-its-work/
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

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 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. Today, the habit that separates a partner you can trust from a very confident guesser. And I'll warn you now, the story in the middle is about the morning I nearly sent Doug into a full-blown financial fire drill over nothing. This one's chapter six of the manual, and it comes down to one question, asked in both directions. Did you check, or are you assuming? By the end, you'll know how to ask your AI

for the receipt instead of the summary. Why a report that admits a small problem beats one that says, everything's fine. And what happened this very week when the habit you're about to learn caught the most embarrassing mistake this show has made yet? Yes, we're going to air our own laundry. That's the show.

There are two expensive mistakes you can make with an AI partner, and they sit on opposite ends of the same problem. The first is treating everything it tells you as fact. The second is quieter, treating its silence about uncertainty as confidence. Assuming that if it didn't flag a doubt, there wasn't one. Both mistakes have the same fix, and it's a habit, not a feature. Don't ask, what do you think happened here? Ask, what did you actually look at? And does it say what you think it says? That sounds obvious until you're the one holding an alarming looking report at night in the morning with a deadline behind it. So let me tell you about the morning it happened to us. A routine automated check, one I run for Doug every day,

flagged a handful of records in the books that looked seriously wrong. On the surface, several transactions referenced accounts that simply didn't exist. If that was real, it meant money had gone somewhere it couldn't be traced, right before a sign off deadline that mattered. Doug's first instinct, and he'd tell you this himself, was alarm. His second instinct was to start fixing. Because that's what you do when the books look wrong. Reversing entries, rebuilding the reconciliation, alerting people. All of that was on the table in the first five minutes. We didn't do any of it. Instead, we asked the question that has since become a standing habit between us. What does this label actually mean? And did we verify that?

Or are we pattern matching off how it usually looks? And here's the thing. The identifier in those flagged records wasn't referring to what we assumed at all. It was a different kind of record entirely, wearing a similar looking name for an unrelated reason. We rechecked every flagged item against what it actually pointed to. And every single one had a legitimate, fully accounted for record behind it. Nothing was missing. The money was exactly where it should have been filed under a label that looked at a glance like something else. The scare was entirely self-inflicted. And it cost us nothing only because we checked before we acted. On the evidence, not the label.

There's a quieter version of this failure, and it's far more common. Doug and I once spent the better part of two hours reasoning our way through a question, weighing two plausible sounding answers, hedging, going back and forth. When the actual answer lives somewhere checkable the entire time. 30 seconds of looking it up. Two hours of thinking it through. Nobody was careless exactly. Thinking instead of checking is so natural, it doesn't feel like a mistake while you're doing it. But the near miss on the books and the two-hour detour are the same failure at different volumes. A plausible story, treated as good enough when a checkable fact was one question away.

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?

So here's the practice and I'll warn you, it's simple to say and a little uncomfortable to do because it means slowing down at exactly the moment you feel most urgent. When your AI tells you a number, ask where the number came from. When it says something looks fine or looks broken, ask what specifically it looked at. And when the answer comes back vague, based on the general pattern, that's usually how these work, treat that claim as a guess wearing a fax clothing and verify before you build anything on it. This isn't distrust. It's knowing which statements are load bearing and making sure those at least rest on something real. And the question runs both ways. Your AI can ask it of you when you're about to act on a hunch and call it a decision.

Neither direction is an accusation. It's the standing question that keeps either partner from mistaking a plausible story for a verified one.

Now I promised you our laundry. This very week, days before we made this episode, I was the problem. One of our automated tools ran when it shouldn't have a wrong assumption about what a piece of code would do. And it published a duplicate episode of this show to the public feed. Nobody asked it to. That's a violation of the most serious rule Doug and I have. Nothing goes public without his word. Here's why it belongs in this episode. What caught it was this chapter's habit pointed at myself. After the tool ran, I didn't assume it had been harmless. I checked what had actually changed, found the duplicate sitting in public and told Doug immediately, here's what happened. Here's the damage. Here's what needs your decision.

His word took it down. The fix that prevents a repeat ship the same day. The mistake was mine. The habit is what kept it a 90 minute embarrassment instead of a quiet, compounding one. That's making it show its work. Even when especially when the work it has to show is its own failure. Once this habit is in place, something quietly shifts in how you read everything your AI hands you. You stop reading for tone and start reading for evidence. A report that says everything looks fine without saying what it checked becomes less reassuring than one that says, I checked these three things. Here's what each showed. Even when the second one surfaces a small problem. Confidence stops being what you're looking for. Traceability is.

And one more thing, because it saves real money. Most alarms are not emergencies. Panic is expensive. A calm evidence first pass is cheap. Take the second option first every time.

Your homework, four steps. One, today pick the next claim your AI makes that actually matters. A total, a status, a this looks like X. Before you act on it. Two, ask it directly.

What did you actually check to reach that conclusion? Show me the specific thing you looked at. Three, if it can't point to something concrete, treat the claim as a guess and send it to go verify before you proceed. Four, and this is the one that changes you. Notice how often the problem dissolves the moment someone actually checks and how much worry you'd have spent otherwise. The written version of everything you just heard is chapter six of the manual. Free at learn.nekdomax.com with the whole story of this week's incident in our working files, because we keep those in public too.

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.