How a Non-Technical Founder Is Building Software With AI

I know there’s been a lot of debate over whether AI is going to destroy humanity or, at the very least, render most jobs obsolete. I don’t know. I tend to take a more moderate stance: it’ll eliminate many jobs, the same way the personal computer did, but it’ll also open new opportunities because people who use it will be more leveraged.

And I think that because that’s been my experience.

At the beginning of summer, I dipped my toe into the AI “vibe-coding” world. Traditionally, coding requires manually typing text/code. Vibe coding is when you tell AI what to make, and it generates the text/code for you. You give it feedback, it makes updates, and you keep going.

As a non-technical founder of a software startup, vibe coding sounded familiar: I hired someone, described what I wanted with words and pictures, and then they made it. Once they built it, I gave feedback (verbally and by marking up screenshots), they made updates, and the loop continued.

After selling the company, I learned to code a little on my own, but only made simple websites (like furlo.com). So I’d put myself in the 80% non-technical camp.

Before this summer, I used ChatGPT to help me solve coding problems by asking it questions. It was like having an expert sitting next to me. I still typed in the code, but ChatGPT saved me hours of reading forums and API documents. It saved a lot of time, but it also eliminated any serendipitous learning. For example, oftentimes while reading API docs, I’d learn about something unrelated the API could do while looking for the piece of information I needed (“I didn’t know the API would do that!”). And every once in a while, that unrelated thing would inspire a new feature I’d want to make. But the time savings were so significant (and I’m not a professional developer) that it was worth the trade.

Vibe Coding a Simple Webpage

Then this summer, I downloaded Claude and had Claude Code make a simple HTML invoice-maker webpage. Previously, I had a Word document template that I’d update. It was fine, but cumbersome. It was a simple quality-of-life improvement that saved me ~3 minutes any time I needed to make an invoice (which is a couple of times a week as a property manager. It wasn’t life-changing, but I saw the possibilities.

Just like at my startup, I described what I wanted, even uploaded my Word document template as an example, and then hit enter. Claude Code made it, I gave one round of feedback, it updated it, and my new invoice-maker was ready to go. There were two differences: First, what would have taken my developer a day took less than 20 minutes. Second, the webpage was fragile: if I didn’t “use it right,” it would break. But that was fine because I was the only user, and there were only a couple of ways to break it—such as pushing “Generate” before adding at least one item.

As a former development team manager, it’s hard to describe how mind-blowing the speed of development was.

So, I asked Claude Code to build another webpage to help me quickly analyze rentals. People often ask me about a property’s potential rent. So, this time, I had it create a page that pulled data from a couple of APIs and then used AI to write a summary document. It was still a standalone HTML page, but now it cost me a couple of pennies every time I ran it.

I was ankle-deep.

A Failed Voice Experiment

While listening to the fantastic [Shell Game](https://www.shellgame.co) podcast, in season 1, Evan described how he set up a voice agent. I was intrigued because I wanted to hire someone to answer the phone at my company, but it wasn’t a full-time position (we only get 2-10 calls a day). Could I have a voice agent fill in the gaps for me, especially during off-hours? Evan mentioned using Vapi.ai to create his voice agent, so that’s what I did.

Basically, you choose a transcriber to turn spoken words into text, a model to interpret and write a response, and a voice to speak the answer back. Each choice has a different latency and cost.

And then you create a system prompt. These are the instructions you give the model to guide its response. For example, mine would greet the caller, determine what they need, gather key details (with different rules for maintenance requests vs. leasing vs. something else), and decide the next step. The next steps were mostly adding a message to our communication system, adding an item to our maintenance list, and potentially sending a Slack message to the team for urgent issues.

It’s a balance between speed and smarts. You can get the latency down to ~800ms, but it can’t handle complex conversations. Actually, the biggest issue I ran into was hitting the context window limits. Think of it as the agent’s short-term memory. The conversation would start out fine, but then after a few minutes, it would start forgetting things. It’s like it would “forget” the system prompt and just do its own thing. Importantly, you can connect the agent to other tools to do things like save a summary and action items from the call... but if the call was long enough, it wouldn’t do it! That’s not good.

And if you go for a smarter model, the latency is so long that callers become impatient. I ultimately couldn’t find the right balance for my needs and shelved the project. It’s technically still live, so if you want to try it, let me know, and I’ll share the number.

Before shelving it, I figured out how to connect my voice agent to my knowledge base. And by “figured it out,” I mean I asked ChatGPT how to do it. The “best” solution turned out to be to replicate my knowledge base (furlo.com/help) and vectorize it. I have no idea how it works, but it made response times significantly faster. It walked me through setting up a Cloudflare Worker and wrote all the code. It would also have been possible to connect it to my contact list and vectorize previous emails/texts/calls to give the agent more context, but I had already decided to shelve it.

In my previous projects, I knew how to do everything, but this was the first time AI built something for me that I couldn’t have done on my own.

Am I Eliminating Jobs?

This feels like the right time to answer this question.

Let’s pretend my voice agent worked.

There are two types of expenses: capital and operating.

The capital expense is the actual cost to create the thing. For my startup, I personally contributed over $50,000, plus my time. For this project, I spent ~$100 on testing, plus ~40 hours off and on trying to make it work. Could I have hired someone (via Upwork) to make it? Probably. But I would’ve spent more time vetting and managing the project. And it definitely would have been more than $100. If I had invested, say, $2,000 into the project, would they have made a usable voice agent? It’s hard to say. I tried a whole bunch of combinations.

Honestly, the hassle and expense of hiring a developer for an experimental “what if” project would have been high enough that I simply wouldn’t have done it. So, in this case, I don’t think I eliminated a job.

The operating expense is more interesting. We get 2-10 calls a day, or about 60 to 300 calls a month. According to our stats, our call talk time is just over 5 minutes. That’s 300 to 1,500 minutes a month. At $0.13 per minute for the agent, that’s $39 to $195 per month.

Contrast that with hiring someone at $25 per hour. My total cost would be about 25% higher after employment expenses—or roughly $31.25 per hour and $2,500 per month for part-time work. It’s a real human, which is a huge bonus, but I still have a general context problem. They probably won’t forget to take notes, but the summary may not be as good; searching the knowledge base during a call is harder, and they have limited context (especially part-time). The context piece is huge; otherwise, they’re just a fancier (and more expensive) message taker. Oh, and it still doesn’t solve my after-hours problem. Not to mention the amount of initial and ongoing training.

For my call volume, it’s not worth hiring someone. Instead, I rely heavily on my answering machine. So, right now it’s not eliminating a job. As my company grows, using an agent like this would probably eliminate a job. Most likely, the agent would do the initial triage, and if it couldn’t handle it, then it would transfer them to a human receptionist. And that person would wear a couple of hats to help justify the expense.

Property Management Supplemental Software

My property management software is great! I looked at a bunch of them and genuinely believe I’m using the best (I do not get the love affair other PMs have with AppFolio). However, like all of them, it’s not perfect. But, and this is critical, it has a decently robust API.

So I went all in on vibe coding.

I used ChatGPT to help me think through a maintenance tracking app. I told it about my current system (it was good, not great). It asked questions and shared ideas. We finished by creating a product design document. I probably spent an hour.

Voice-to-Text

When I say “I told it about my current system,” I mean I spoke to it using WisprFlow. I know there are other voice-to-text options, but theirs is really good. I find AI works best when you give a lot of details in the prompt. And I tend to talk and talk and talk, which makes it that much better. Here’s a raw example:

Okay, this is me using WisprFlow because I want to give an example in this blog post. What I do is I hit the little world button and the spacebar at the same time, and then it just kind of stays on at the bottom of my screen, which is pretty cool. When I'm done, I'll just hit the world button or function button (I guess that's what it's called). I'll hit that again, and then it'll stop, do some magic processing, and then it will paste this text that you are reading now.

Pretty cool, right? It’s not as tidy as typing, but it’s significantly faster. And the AI systems handle it just fine. If you haven’t tried talking to an AI chatbot yet, I recommend it.

Back to My Development Workflow

So, I start with ChatGPT for brainstorming because I find it’s more creative than Claude. The output is a product design document.

Then I opened Claude Design, shared the document, and mocked up how it would look. I probably spent 5 hours tweaking and refining it. I like starting by asking it for 3-4 wireframes and then combining ideas into a semi-working mockup. The output is a standalone HTML file and a handoff file explaining the thoughts behind it.

Then I open Claude Code Opus and share the files (stored in a docs folder in the project folder). It creates the engineering plan and asks any clarifying questions. The output is yet another document. You’ll notice that I don’t rely on the AI’s internal memory. Instead, I ask it to document everything separately.

Once that’s done, I switch to Claude Code Sonnet to do the actual coding (technically, Claude switches for me). I do that simply to save tokens and expense.

Once it’s built, I try it and provide feedback. I have my own notes file and sometimes hand it 12 updates, ranging from tiny tweaks to “let’s rethink how this part works.” Opus comes up with a plan, and Sonnet builds it. The first build can take an hour, and then I’ll spend a few hours using it and providing feedback.

Once I like it, I go back to ChatGPT to review the entire code (vs. the documentation). All it does is... You guessed it... document any bugs, concerns, or efficiency improvement ideas. I share the review doc with Opus, which decides what to implement (and if there’s a question, it’ll ask), creates the plan, and Sonnet implements.

And naturally, I have an AI_WORKFLOW doc that spells this out so each system knows how it fits in the development process.

It’s a lot.

I know.

But AI is weird. In some ways, it’s crazy advanced. But in other ways, it’s a dumb toddler. So these checks and balances help surface times when it’s acting like a dumb toddler.

I didn’t write any code, and I honestly don’t understand how the backend works. Yet I can take an idea to v1 in a day or two, which is crazy! In my startup days, the maintenance-tracking app would have taken one to two weeks of focused effort. That’s $4,000–$8,000! I did it with $20 subscriptions to ChatGPT and Claude! The capital-cost savings are huge.

And when I find an issue, I fire off a quick message, and it’s fixed within 5 minutes. I love my PM software, but when I submit a ticket, it takes much longer to resolve. A new feature idea? I don’t know when I’ll ever see that.

Oh yeah! On the operational costs side, the software I used to track maintenance issues internally cost me $70 per month — and it didn’t connect to my PM software. The new one I built costs $5 per month as a Cloudflare Worker and syncs to my PM software via API.

More Internal Apps

So naturally, I rebuilt my invoice-maker... errr... had my invoice-maker rebuilt into my new software. I can now create an invoice with one click from a maintenance item, transferring the details and pictures. Plus, one more click creates a bill in my PM software with the invoice attached.

I didn’t stop.

We used to track all of our lock combos in an Airtable spreadsheet. It worked, but was clunky. Now that has a spot in the app.

I now create monthly owner reports that pull in financial data from my PM software, maintenance items, and communications to create a narrative that goes with the financial software. The summaries are good, but the really valuable part is what I call my “analyst.” For anything mentioned in the summary, it explains the technical details and where it came from. It was so good that I created... umm... had created... a plugin for our communication software that looks at the thread, pulls all the data, and organizes it to help answer a question. That has been a massive time-saver.

The one I’m most excited about is a new inspection app. I used to pay $117 per month for inspection software. It was fine, but once again it was siloed. Plus, it was a general inspection app, which meant it did some things I didn’t care about and was missing some features I really wanted. No more compromises!

Since I was taking photos and it needed to work offline, I decided to make it an iPhone app. I had never done it, but with some guidance from Claude, it was easy to set up. Now I have an inspection app tailored to my business, with proper syncing. It’s fantastic. That said, setting up a developer account and getting it downloadable (even for an internal app) is a lot more complicated than publishing on the web. Without guidance from Claude and ChatGPT, I wouldn’t have made the time to figure it out.

I have more ideas and now need to prioritize what to build next. The constraint now is giving my team time to incorporate the new tools into our operations. It’s genuinely exciting. I did have to upgrade my Cloudflare account, but I’m still way ahead on both my capital and operational (subscription) expenses.

An interesting aside. I asked Claude and ChatGPT for icon ideas, but I never 100% liked what they made, so I made each of these by hand in Pixelmator.

What About Ongoing Support?

It’s fun to make new things, but all software requires ongoing support. Bugs get found, underlying technology needs upgrading, and components get deprecated. What happens if something happens to me? What I’m doing carries a lot of key-person risk.

My honest answer is that I don’t know.

Right now, my entire business depends on me (I’m the licensee, owner, and operator), so it’s hard to add on more key-person risk. I suppose I’m technically decreasing my enterprise value because I’m making it more dependent on me. But the cost savings and better service seem worth it at this stage. And there’s a question about the value of my time. Is building software the best use? Will ongoing support be the best use? So far, the answer is yes, but what happens if my little internal software grows to be three times the size? I have a hunch that AI tools are particularly good at maintaining and refactoring code, but I’m not sure.

Jessi asked me what I’d do if AI prices started to increase. I don’t foresee that happening, but if they did, I don’t know if it’ll be a huge problem because my AI costs are capital expenses. The tools I’m making aren’t AI-dependent (except perhaps the first draft of my owner reports). So I could just stop developing the software and use what I have. Given current trends, I don’t see a need to hedge.

Coding for Non-Technical Folks

As a non-technical person, all of this is amazing because I can finally build what I want! I used to dream about someday “making it” and funding cool software startup ideas. Now I can just do it. I’m not pushing the development world forward, but I never would have. Of course, even if I “make it,” I probably won’t fund a software startup now. Multiply that by thousands of business owners, and that will definitely impact an industry.

I wasn’t paying attention during the PC boom (because I was a child). Were presentations better before PowerPoint? I know good presentations are still given, but there are a lot of really bad ones because PowerPoint makes it too easy to give bad presentations. Will AI-coded software do the same thing? I can easily see the quantity of apps increasing, but the average quality decreasing because it’s easier to make bad apps. But maybe that’s OK because it will give people who had zero chance to finally have a chance.

For now, I’m having a blast creating apps that are useful quality-of-life improvements. They have the features I want, none of the features I don’t want, and they operate at a fraction of the capital and operational costs.

Why We Made Our Kids Help Paint the House

Our house has been in terrible need of repainting. It needed it when we bought it 10 years ago, and well… other things just kept coming up.

This was 3 years ago. Look at the back wall!

That, and we could never agree on a color. I remember two years ago, hiking in India and Jessi pointing out house colors she liked (we had been talking about it for the last year). I dutifully took photos of them, but… I don’t know… they just didn’t resonate with me.

Jessi liked the bottom part. I'd call that brown?

But this summer would be different. The house needed it, we had the time and budget for it, so we had to reach an agreement.

We did the classic things: drove around neighborhoods, looked at houses on Pinterest, and spent way too long staring at color swatches in Home Depot.

Jessi wanted a burnt-orange-ish (almost copper) color; I wanted something blue; Elinor wanted pink or yellow; and Samson wanted a modern white (with black trim).

Oh boy.

At one point, I half-jokingly suggested that each of us could choose a side. The kids loved the idea. Jessi… not so much.

With the clock ticking, we all gave in to Jessi’s choice. But even within that color family, there are an almost unlimited number of shades and hues. It was difficult to imagine those colors on our house, and it felt like we were going to stall out again.

And then we had a breakthrough. We uploaded a picture of our house and the color we wanted to ChatGPT. It was great because we could finally see what it would actually look like.

And Jessi HATED burnt orange because it made our house look like a cabin.

Uh-oh.

But with ChatGPT’s help, we quickly tried a bunch of colors. And it turned out that we all liked green — a color not on anybody’s initial list. I think there’s also something magical about deadlines that forces decisions.

We went to Home Depot, and everyone got to choose a green sample color. We put them on the house and narrowed it down to two. We then put those into ChatGPT, and the final selection became clear.

Step one done. And it only took 3 years.

Now the real work had to begin: preparing the house by scraping off old paint, sanding rough edges, and applying new caulk.

Initially, Jessi wanted to ask a bunch of folks from our church’s youth group to come and help. It probably would have been done in a day, but I had a different idea in mind.

Instead, I thought it would be great for the kids to experience a long, difficult project. I mean, they do projects in school, but this was different. And Jessi let us do it! We got the kids the tools, showed them how to use them, and had them work on the house for at least 30 minutes each day.

It was awesome. Really slow progress. But awesome. The kids scraped, sanded, caulked, and primed raw wood. Jessi helped a lot as well, especially getting the caulk off in higher-up places. I helped scrape caulk one morning and bought an oscillating multi-tool in the afternoon.

It was everything I dreamed of. They spent a month working on it and really experienced a long, tedious, drawn-out project. I had to keep reminding Jessi that it was OK. And to stop working — teach the kids how to do it and let them do it.

Step two done.

The weekend finally came for painting. We taped everything off and prepared ourselves for a full day’s effort.

I set up the paint sprayer and let the kids practice spraying our fence with water. Once they [mostly] mastered the technique, I brought out scrap boards and let them practice with paint. The big lesson: don’t stop moving or change direction while pulling the trigger.

And then we started on the house. I did the upper half and the trickier sections. The kids painted around a quarter of the house. It took 8 hours, and the kids hung with us all day. At mid-morning, Samson asked if he could take a break to play with his friends. I told him, “No. We’re painting today. This is what we’re doing. You can play with them once we’re done.” And to his credit, he kept a great attitude and genuinely helped all day — including helping to remove all the plastic and tape from the gutters (he was more than happy to get on the roof).

And now we have a green house! It’s a fun color, and the white trim really pops. It’s not perfect, but the kids feel a sense of ownership over it, and that’s more important to me than perfection.

At bedtime, Samson asked Jessi when the house had been painted last. Upon hearing it had been more than 10 years, he did some quick math and said, “Oh, good. I’ll be out of the house by then.”

That kid.

What Will Life Look Like in 2276? My Predictions for America’s 500th Birthday

To celebrate the US’s 250th birthday, I traveled to Boston with my brother. It was a fantastic place to celebrate the 4th of July given all the historical events leading up to the Declaration.

Given all of the looking back, I’ve also found myself thinking about what life will be like 250 years from now (in the year 2276). The difficult part is that we have things today that folks in 1776 couldn’t even imagine. I mean, we’re not even talking about AI, smartphones, the internet, or computers! They didn’t have electricity, the telegraph, cars, or an awareness of germs. So they couldn’t even imagine things like TV or the radio. Having 50 states wasn’t even on the horizon.

But hey, it’s fun to guess. So, here are my wild guesses.

Health

We’ll be beyond the tricorder featured in Star Trek. Not only will we be able to diagnose illness, but we’ll also create medicine uniquely tailored to each individual. There’s also a good chance that there will be new illnesses as people live longer because we understand and overcome today’s leading diseases. It’ll be a game of whack-a-mole with life expectancies slowly creeping up.

I personally want a passive way to do my strength and cardio workouts. Alas... RIP vibrating belt machine. In 250 years, I think we’ll have something that comes close to that goal.

Energy

This seems like a more urgent problem to solve. I can easily see small nuclear reactors inside each home — similar to solar panels today. Those will generate enough electricity to power everything that leaves the house. We’re still new at understanding nuclear power (mostly because of apprehension about building them), so over time our understanding will increase exponentially (similar to the CPU development trend). Is there something beyond nuclear? Probably, but just making it smaller, safer, or portable will be huge.

There will absolutely be battery breakthroughs that make our current storage solutions seem primative. I’m not talking about a 100X improvement, but a totally different way of storing & transmitting energy. This will allow devices and vehicles to either do crazy amounts more, or take totally radical form factors.

Communication

In 1776, information traveled at the speed of horse. When the telegraph was invented, information traveled ~500 miles in a single day. Today, we can instantly video call anyone around the world. Where do you go from there? I don’t think virtual reality (like in The Matrix) is it. Perhaps it’ll be calls where we feel like we’re actually there? Perhaps we’ll inhabit a robot — a cybernetic android? — with all 5 senses connected to us (like in Avatar)?

There are obvious downsides to that, and if social media is any indication, we’ll embrace it, and it’ll cause massive social problems.

Transporation

Flying cars seem inevitable, but it’s felt that way for a little over 100 years (the Wright brothers took flight in 1903, and the Model T was made in 1908). So... as inevitable as it still feels, it’ll have to wait for the energy improvements.

More interesting is long-distance travel. Traveling from Oregon to India takes 24 hours. In 1776, it would be at least a year, assuming you survived the journey... If I assume a straight line of improvement (a bad assumption since improvements were step changes). In 250 years, that same trip could only take 4 minutes! That seems impossible, but I bet 24 hours seemed impossible 250 years ago.

It’ll probably be less about humans traveling, given the improvements in communication, and more about shipping items. So constraints like g-force will be less of an issue. Would I want to live in a world where I ship my android across the globe in 4 minutes so I can “hike” Mt Everest? Something about that doesn’t feel right, but I bet it happens.

Call me a naysayer, but I don’t think we’ll have a meaningful presence on any other planets. It seems like such a huge effort with relatively small benefits. It sounds cool, but I think we’ll still be in the exploratory phase in 250 years.


Work & Wealth

I do NOT see a future like the Jetsons where work is as simple as pressing a button for a partial day. I also don’t see a post-scarcity future like Star Trek where people do their jobs out of noble virtue because material goods are essentially free and energy is abundant.

Instead, I think we’ll continue to experience scarcity and a widening wealth gap. Think about it: relative to 1776, our lives are unimaginably rich. We have indoor plumbing, washing machines, refrigerators, and penicillin — all of which we take for granted! Now I complain when I go somewhere, and my internet upload speed is “only” 5 GB. 20 years ago, nobody had a smartphone, but now we all pay for data plans (along with city water and electricity). Last year, I didn’t pay $20 a month for Claude, and now I do (and likely for the rest of my life to some AI provider).

So yes, we’re wealthier, but in addition to being bad at comparing to the previous generations, we spread our wealth across an ever-growing number of things. Our appetite for more (and better) never ceases. So, it feels like resources are still scarce.

That feeling won’t go away in 250 years.

But at the same time, we’ll make life easier for people who don’t want to work. It’s mostly the right thing to do, but I have a hunch we’ll take it too far. I’m also almost 100% certain we’ll have some sort of universal basic income, housing, and healthcare. That will enable this group to simply hang out (and entertain themselves). Will they take fancy trips and get the latest medical advancements? Probably not, but they’ll be OK with that. Unfortunately, it’ll disincentivize people who could contribute to society. But I already feel that way about social media.

Another group will want to continue competing and striving for more (while claiming a righteous high ground...). They’ll continue working long hours, increasing their productivity through automation and technology. You’ll see more and more small business owners with zero to 5 employees, with a few amassing unimaginable wealth, because they’ll be the ones driving the changes mentioned above.

This seems like a human nature trap that we won’t escape in 250 years.

Government

I still think the US will be around in 250 years. I know this current political climate feels contentious, but that started during Washington’s second term. You could almost replace any reference to Jackson with Trump, and it would be hard to tell the difference. We’ve always been a country with intense differing political beliefs.

Part of what made the Civil War happen was that fundamentally differing beliefs on slavery were clustered in two regions (the North and South). So, it was physically possible to separate. As far as I know, there aren’t any differing political beliefs (worth splitting away from) that are regional.

Having said that, I think our founding fathers would be SHOCKED by how much power is with the executive branch vs. Congress. And I think we’ll be similarly shocked looking ahead 250 years with how much it’s changed. It’s a kind of death-by-a-thousand-cuts, slowly-boiling-pot situation. Increasingly, we’ll see Living Constitutionalism winning out over Originalism.

Final Predictions

I feel like I painted a rosy picture, but that’s because life today is SO much better than it was 250 years ago. I mean, virtually unlimited clean drinking water is pretty hard to beat! I'm reading about the Wright Brothers at the moment, and their dad is constantly harping on them to watch out for contaminated water.

I'll finish with a favorite quote from George Box: "All models are wrong but some are useful." I know I'm wrong on my guess, but hopefully some of these ideas are actually being pursued.

The Fastest Sports Fan Conversion I've Ever Seen

Our house has World Cup fever. Well... Samson and I have it, which has been a blast!

When the tournament kicked off (pun intended), we printed off a schedule of the group stage and the knockout rounds. Samson has been dutifully recording match scores.

He also decided to root for whichever country is closest to us. I thought that was a fantastically objective way to choose. He asks our echo device which team is closer — pretty smart (though, not always the most accurate...).

In game 1, Mexico beat South Africa, and he was elated. In game 2, his team, Czechia, went up 1-0. But late in the game, South Korea tied it at 1-1, and then scored another goal to win it 2-1. Samson went to bed SOBBING over the loss... for a team he didn’t know existed a couple of days ago!

Talk about passion!

It reminded me of two Super Bowls ago when the Chiefs played the Eagles. Samson was all-in for the Chiefs. He wore his red gear and cheered for them. The Chiefs struggled early, and Samson became despondent. I was rooting for the Eagles, but tried to play it cool when I saw how upset he was.

At halftime, he went to his room, changed into a green outfit, and declared he was now rooting for the Eagles. He changed his attitude instantly and genuinely celebrated the Eagles' victory. It was borderline: "The Chiefs are dead to me because they let me down."

It’s whiplashing at how fast and intensely he changes.

Back to soccer. Jessi asked me what we should do about our sobbing son after the game. I voted for exposure therapy: watch as many of the 104 games as possible to show him that life goes on.

It seems to be working. He hasn't been upset about a single outcome since. Though now he also looks up the winning probabilities along with their distance. But his attitude is closer to “let’s see if the stats are correct” instead of rooting for a specific team.

Except for Argentina.

He wants Messi to win it all. He is, of course, excited for the US, but it’s not the same. If they get a chance to play each other, I imagine his emotions will run hot again. It's wild!

For now, I’m enjoying watching lots of soccer with Samson, talking about amazing goals, and swapping stats.

Some Days I Feel Like a Phony

A few days ago, I was working on the listing for our new vacation rental. The photos look great, the descriptions are written, and the unit is ready. And yet, running a short-term rental is new for me. I know there will be bumps in the road, and I find myself worrying that people will realize I don't fully know what I'm doing.

I’m not certain this is the correct term for how I feel, but I sometimes (often?) struggle with what’s called Imposter Syndrome. It’s when you feel unqualified to be doing something (a “phony”), and you fear that people are going to figure out you’re not qualified to be doing that thing.

Apparently, there are several forms of imposter syndrome (I just learned this while double-checking my definition was correct):

1. The Perfectionist: Sets crazy high goals and feels like a failure even if they meet 99% of them.

2. The Natural Genius: Feels like a fraud if they have to work to master a skill. It should come... naturally, right?

3. The Solist: Feels that asking for help is a sign of weakness. So, they must do everything themselves to prove their own worth.

4. The Expert: Constantly seeks more certifications/training, feeling they’ll never know “enough” to be truly qualified.

5. The Superhero: Pushes themselves to excel in every role (worker, parent, spouse) to cover up perceived insecurities.

Jessi (my wife) and I often fall into the first type: perfectionists. Actually, one of the things I appreciate about Jessi is that she sees the flaws. Not because she's negative, but because she genuinely wants things to be better. When I ask her for feedback, I know I’ll get her brutally honest thoughts and a clear map of where to improve. There’s a time and place for cheerleaders, but I’m finding them less helpful. Don't get me wrong, encouragement is nice, but I often want accurate feedback.

I appreciate the harsh truth from others, but it’s potentially destructive when done to myself because I see all the imperfections. Even if something turns out well, I can nitpick the process and my mindset. Yikes!

As a small business owner, I find myself regularly wading into the unknown and fighting perfectionist thoughts (and the natural genius... discounting years of practice to get to where I am today). For example, as my property management business grows, I keep wondering when people will realize I’ve never scaled a business before. It regularly feels like we’re just staying ahead… which is a classic imposter syndrome feeling! Of course it feels that way — growth, by definition, puts you into inexperienced territory.

Another example: I can no longer keep every unit and tenant in my head. Things fall through the cracks, and we’re building new processes (and ways to store/access info) while still maintaining daily operations. I keep thinking, “We just have to stay ahead for a bit longer… then it’ll be OK.” But, according to owners I respect, it’ll still be hard; it’ll be a different hard, but still hard.

The more experienced I get, the more I suspect most adults are just making it up as they go. Parents are raising kids they've never raised before. Managers are leading teams they've never led before. And business owners are solving problems they've never encountered before. The people I admire most aren't the ones who always know what to do, but the ones willing to move forward despite not knowing.

I suppose this is more of a note to myself to remember that, even though I sometimes feel like a phony. I still have things falling through the cracks, I still disappoint people occasionally, and I still find myself thinking that if I can just stay ahead a little longer, I'll eventually feel qualified. But perhaps that's how this works. Maybe competence isn't the absence of uncertainty (and mistakes). Perhaps a large component of competence is continuing to move forward despite the errors.

So, on the days I feel like a phony, I'm trying to remember: I may not be perfect, but I'm not starting from zero either.

The Baker Tower Penthouse Vacation Rental

Last year, we bought the Baker Tower and have been waiting for the top-floor tenants to move out so we could turn it into a vacation rental. Well... they moved out, and this last month we furnished the place — and it looks awesome!

I’m... shall we say... designed challenged. I care about functionality and have virtually no eye for what “looks good.” So, I hired an interior decorator to help. I gave her a video of the place, a budget, and let her loose on the IKEA website.


She picked out everything, and we had it delivered right before we showed up to assemble it. It was her and one of my investors (who gets credit for introducing me to her) who put it all together over a weekend. Then the following weekend, I returned with another friend (and real estate photographer) to do some finishing touches and get the photos below.

The Airbnb listing isn’t live yet because we still need to do a test run and identify missing items. But I’m too excited about it not to share it.

The view is amazing! It’s the tallest building in Oregon east of the Cascades. And on the 9th floor — the penthouse — the nearby Elkhorn Mountains look incredible. And now we have an interior to match.

Thanks to everyone who helped make this happen. Check it out:

I Built An AI Agent. It was Both Amazing And Underwhelming

Good news, kind of. I think it’ll be a while before AI starts taking over swaths of jobs and displacing people, or at least I think it’s true at the small-business level.

I've been playing around with different AI tools recently, trying to figure out ways to incorporate them into my business, and it's been an interesting adventure. On the one hand, there are things AI can do that are helpful, and I think most of us have experience with: drafting messages, summarizing large documents, and creating cool images (like above). It's genuinely useful but not transformational.

So I've started experimenting with more agentic types of processes, specifically using lindy.ai, and the experience has been interesting. The basic idea is that you can create a workflow that's based on a trigger. It could be off a timer, an incoming message, a webhook, or whatever. If you’ve ever used Apple Shortcuts, it’s the same idea. Here’s a simple example:

Every morning, my team discusses ongoing maintenance and tenant issues, and then we create a plan for the day. We record those meetings, transcribe them, and save them in a Google Drive folder.

Now, every Monday morning at 9am, it grabs all the new transcripts from the past week (that’s the purple loop) and compares them against our existing knowledge base (KB) articles. In the final blue-circled-magical-AI step, it looks for gaps and missing information and sends me an email with suggested article topics.

At this step, it's not fully written-out articles; it's just internal and external topic ideas. Eventually, Lindy will write full articles on approved topics, let me edit them, and save them to our KB. The KB, by the way, is what we use to automate message replies (therefore, in the long-run, saving time while keeping a consistent communication style).

But here’s the deal: this “simple” flow took me an hour to build. And really, it started with a prompt to Lindy’s Agent Builder, which took a first (second, third, fourth,...) pass. I had to enter some manual data (like my KB’s API Token), but most of the time I copied/pasted errors from a test run and the Agent Builder to try to fix them.

At one point, the Agent Builder told me:

“I need to stop and be honest with you. We've been going in circles for a while, and the core issue is clear... [reasons why it’s not working] .... The real fix is a different architecture. Instead of a separate LLM node, the analysis should happen inside an AI State node — which DOES have context accrual and can see all upstream data naturally.”

You see, that magical blue box used to be four separate steps that didn’t work. Which, for the record, the Agent Builder created! This current version works, but it was a process to get there, and it’s still not what I fully want...

AI Agents Are Both Amazing And Underwhelming

On the one hand, creating this was amazing because I just typed in a prompt for what I wanted, and it made it (eventually). Without the Agent Builder, I would have struggled to even get started.

On the other hand, it's a strange combination of doing something fairly simple, but in an overly complex way. It reminds me of Adobe’s Dreamweaver in the early 2000’s. Sure, it was a drag-and-drop website builder (easier to make vs coding), but in an effort to match your design exactly, it fixed everything in place with a ridiculous number of nested elements. It easily doubled or tripled the file size of a “human-made” version while being less responsive (yikes!).

I get it — there’s a balance. Dreamweaver enabled more people to build websites, but those websites were fragile. Lindy feels the same way (and Make, and n8n). It enables normal people — like me — to automate workflows, but it’s not as robust or flexible as writing code in my own server environment.

And to be clear: this is just an automation; I wouldn’t call this an “AI agent” (I mean... I will, because it sounds cooler, but strictly speaking, I don’t think it is). There’s no feedback, learning, or figuring out its own path. It’s funny, the Agent Builder feels like AI, but this output doesn’t.

I’m fairly certain it’s worth my time to create these automations, but it’s not an obvious win. It’ll partly depend on the maintenance requirements, but it’ll mostly depend on how close it gets to my quality requirements. Is it worth the eventual productivity gains if it’s only 80% as good? What about 95%? It probably depends on the process.

That’s Why AI Isn’t Taking Your Job Anytime Soon

For these reasons — it’s hard to implement/upkeep and fragile — I don’t see AI taking thousands of jobs this year. Instead, I think it’ll continue to be a solid multiplier on existing efforts. And let’s be honest, no healthy company is going to say, “let’s just do the same with less.” Instead, they’ll use the efficiencies to tackle new opportunities (because if they don’t, their competitors will). That’s what happened with calculators, personal computers, and smartphones.

Over time, automation tools will get easier and more robust, just as Squarespace does today with drag-and-drop responsive websites. But it’ll take a while to get there, and chances are good that healthy companies will adapt along the way.