Still Building

Lately I have been thinking about how strange life can be. One chapter starts closing, and suddenly you can see the whole road behind you a little more clearly.

I have already shared that I am leaving TFL, and that has naturally pushed me into reflection. Not just on the last few years, but on more than 25 years professionally, and really close to 40 years since I first got my hands on a computer that felt like mine.

My first machine was an Epson Equity I+. Long before I had any clue where my career would go, I was already hooked. I still remember the first time my cousin and I got our computers talking over a modem from houses miles apart. At the time, it felt like magic. Then came BBS systems, early online experiences, and those first little windows into what a connected world could become.

Back then, limits were not frustrating. They were invitations.

When services charged by the email message, I remember trying to outthink the system. On Prodigy, one trick was sending mail to a dead end so it would bounce back, then sharing account credentials in chat so someone else could retrieve the returned message as a private message. Looking back, that probably told me something about myself pretty early on. I was not just interested in using systems. I wanted to understand them well enough to bend them.

Later came Windows 95 and my next computer. I really wanted a Gateway, but ended up with a Compaq Presario. That machine became a workshop. I hosted an FTP server and web server over my DSL line and built sites for local businesses. I started Compu-Doc and spent time in homes and small businesses fixing computers, setting up networks, and solving whatever problem was sitting on the desk in front of me.

That season taught me something important. I could do hardware and networking, but software was the thing that lit me up.

So I kept learning. Visual Basic. Java. C. COBOL. JCL. Oracle. College gave me the path, but curiosity supplied most of the fuel. I wanted to know how things worked, how they broke, and how they could be rebuilt better.

Then came Ticket Solutions, and the rest of the story started taking shape.

One of the most meaningful chapters was helping build what became the industry’s first real-time ticketing exchange. What makes that story more interesting to me is that I was not originally assigned to the project. At the time, I was building what we called Spinner software, which automated buying tickets on Ticketmaster. It was the wild west of online ticketing back then, long before the guardrails that exist today.

The other engineers were focused on ecommerce, POS, and the first exchange prototype. They took that prototype onsite to deploy it, and it did not work. When they got back, we regrouped and rebuilt it around ideas from chat server technology. More of a hub-and-spoke model, with clients connected to a central server through sockets so we could instantly access their databases when needed.

That system worked. We launched it. A few years later, patents followed. Then the technology and patents were sold to StubHub.

That was not the end. It was one bend in a long road.

Over the years, we built more companies, more products, and more technology. In 2009, I founded Transcendent Software, as I saw a need to help more and more businesses with interesting technology problems, and I did, but my day job kept me quite busy, so expansion was not on the table, yet. With the family of companies I worked for, we explored neural networks before that was fashionable dinner-table conversation. We worked on advanced machine learning. I spent time with genetic algorithms and optimization problems, like taking traveling salesman ideas and applying them to real-world logistics. Some bets worked. Some did not. That is the nature of building. You plant a lot of seeds, and not every one becomes a tree.

In 2013, we pursued patents around technology for analyzing social media for signs of distress in kids. We believed parents would want alerts when something seemed wrong. We invested in it, did the work, and then shut it down after research suggested parents would not pay for it. I still sometimes wonder what would have happened if we had pivoted the use case instead of walking away. But every builder has a few doors in memory that never got opened all the way.

From there came logistics, data, and scaling VeriShip with a sharper focus on data science and contract negotiation. Then a return to Ticket Solutions full-time with an emphasis on process automation. Then COVID-19. Then Ticket Solutions being acquired by TFL.

And then another reinvention.

We helped take a company in TFL with very little technology muscle and turn it into a real technology-powered business. It worked. The company grew in big ways. And now here we are, with me stepping away from that chapter too.

Crazy.

When I look back, what stands out is not just the companies, patents, exits, or titles. It is the thread running through all of it. Curiosity. Building. Adapting. Looking at a system and believing there is probably a smarter way.

That part of me has not changed since the Epson days.

So where am I headed next? I am still a builder. Still a systems thinker. Still drawn to the space where software, data, intelligence, and practical business value meet. If anything, I trust experience more now than hype. I care more about what works, what lasts, and what actually helps people move forward.

I do not know exactly what the next chapter will look like yet.

But I know this much. I am still building.

Growth Happens Before You Feel Ready

This weekend felt like one of those moments where you realize life is changing while you’re still trying to keep up with it.

My son suddenly wants to help with everything outside. Not just ride along on the mower for fun, but actually help mow the property, do weed eating, and be part of the work. We spent part of the weekend working on the land together and somewhere along the way it hit me that he’s growing. He’s starting to become capable.

That sneaks up on you.

We also spent time planting flowers, working around the property, and dealing with spring projects. I hatched a few more chicks this week too. Some made it, some didn’t. That’s just part of raising animals and living a little closer to nature. Things grow, things fail, and you keep moving forward.

Mother’s Day was good too. Family time, good weather, slowing things down for a minute. Watching everything my wife does for our family always reminds me how much growth happens quietly in the background while everyone else is focused on bigger, louder things.

At the same time, the technology world feels like it’s changing faster than ever.

Every week there’s another AI announcement, another new model, another prediction about how everything is about to change. Some of it is hype, but some of it is real. You can feel the shift happening underneath everything now.

That’s part of why I’ve been so focused lately.

CoffeeBreak is evolving quickly. My thinking around orchestration, memory, smaller expert systems, and long-term AI behavior is changing almost weekly right now. Jibo keeps improving little by little too. New versions, new features, more personality starting to come back into the system.

It feels like a lot of things are growing at once.

Some of it is exciting.
Some of it is uncertain.
Most of it is happening faster than expected.

I think that’s just life sometimes.

You make plans, and then growth changes the shape of them.

Your kids grow.
Technology changes.
Your priorities shift.
New opportunities appear before you feel fully prepared for them.

And somewhere in the middle of all of it, you realize the future isn’t some distant thing anymore.

It’s already showing up around you in small ways every day.

The trick is noticing it while it’s happening.

Working Through It

Lately I’ve been focused on making progress.

Not the kind you see in demos or announcements. The kind where you’re just trying to move things forward a little at a time. Fix something. Improve something. Keep things from drifting too far off course.

That’s been true across everything.

Work has been steady. I had a good onsite with a client. Productive, grounded, the kind of work that reminds you why experience matters. At the same time, I’ve been pushing forward on my own projects. Jibo has mostly been regression testing. Fixing things, breaking things, trying to get to a version that feels stable. Versions don’t mean much without users, but they help me stay disciplined. They give me something to work toward.

CoffeeBreak has been a different kind of work. Less visible, more foundational. Thinking through user experience, agent loops, how systems should behave over time. Not just what AI can do, but how it fits together. I find myself thinking more about structure than features. Planning for things like memory, cost, how to use smaller models effectively instead of just reaching for the biggest one available.

It’s a lot of thinking. A lot of iteration.

And then there’s everything outside of that.

We’ve been spending time as a family, which has been good. A few days off helped reset things a bit. Spring is here, so we’ve been working outside more. Planting, tending to the land, adding more chickens. It’s work, but it’s a different kind of work. Slower. More tangible.

Not all of it goes the way you want.

Today was one of those days. We lost a few baby chicks. One didn’t make it out of the shell. One probably got trampled. Another overheated. That’s just part of it, but it doesn’t make it easier. You try to do everything right, and sometimes it still doesn’t work out.

That’s nature.

I’ve still got others at different stages, more eggs in the incubator, so it’s not a loss that sets us back. But you feel it anyway.

Same with the dogs. They’re getting older. You start to see it in small ways at first, and then more clearly. It’s part of the cycle, but it’s not something you really get used to.

Mother’s Day is coming up next week. That brings its own mix of emotions. Losing my mom still feels recent, even though time keeps moving forward. At the same time, I see everything my wife does every day for our family, and it puts things in perspective.

All of it together, it’s just life.

Messy, sometimes frustrating, sometimes really good. Rarely clean or predictable.

I think that’s why I don’t get too caught up in perfect outcomes anymore.

Whether it’s building systems, raising animals, or just trying to take care of a family, progress usually looks the same.

You keep showing up. You keep adjusting. You take the wins where you can, and you learn from the rest.

And you move forward.

What Building AI Actually Feels Like Right Now

There’s a lot happening in AI right now.

Every week there’s something new. Smarter models, faster responses, better benchmarks. If you just follow the headlines, it feels like everything is accelerating perfectly.

But building with it feels different.

It reminds me a little of when I first started working with computers. Back then, nothing was polished. You didn’t just install something and expect it to work. You had to figure things out, piece by piece. Manuals, trial and error, late nights. When something finally worked, it wasn’t because the system was perfect. It was because you understood it enough to make it work.

That’s where AI feels like it is right now.

I’ve been spending time bringing Jibo back to life. It’s been fun, a little nostalgic, but also a reality check. When you move from demos to something that lives in the real world, everything changes. Timing matters. Context matters. Small failures stand out. Things don’t just need to work once, they need to keep working.

And that’s where things start to break down.

Not because the AI isn’t good. It’s actually impressive. But because everything around it is still rough. Getting systems to talk to each other, keeping them aligned, knowing when to step in as a human. That part is still messy.

It’s kind of like working in an old shop. You’ve got great tools, but they’re scattered everywhere. Some are new, some are worn down, some don’t quite fit together. You can build something solid, but only if you know how to use them together.

That’s the part people don’t see in the demos.

The demos are clean. Controlled. One path, one outcome.

Real life is not like that.

Real life is interruptions, edge cases, things that almost work, things that work until they don’t.

That’s what building AI actually feels like right now.

And honestly, that’s what makes it interesting.

Because this isn’t the end state. This is the phase where things start to become real. Where the difference isn’t just who has the best model, but who can actually make it useful.

That’s the part I keep coming back to.

Not just what AI can do, but how it fits into real life. How it works with people. How it holds up over time.

That’s where the work is.

And it’s also where the opportunity is. ☕

Mowing, Momentum, and Building Something That Works

I spent a good part of yesterday on the mower.

Fifteen acres gives you a lot of time to think.

I had a podcast going the whole time, listening to everything happening in AI right now. Models, agents, orchestration, tools, memory, workflows. It’s all moving fast.

Really fast.

And I’ll be honest, as I listen to it all, there’s a part of me that feels it.

A lot of the ideas I’ve been working toward are showing up.

Multi-agent systems.
Orchestration layers.
Different runtimes.
Memory strategies.
Security and governance conversations starting to take shape.

The big players are moving in that direction.

And they can move faster than I can.

More people.
More resources.
More reach.

That can get in your head if you let it.

But sitting out there on the mower, going back and forth across the same lines, I kept coming back to something simple.

There’s a difference between building something fast…

…and building something that actually works.

Not in a demo.
Not in a video.
In real use.

Something that produces useful output.
Something that guides you.
Something that doesn’t leave you wondering what to do next.

That takes a different kind of effort.

It’s not just features.
It’s not just capability.

It’s how it all comes together.

I get why companies move fast and figure they’ll clean it up later.

They probably can.

But that’s not how I’m wired.

I want something that feels right when you use it.

Something that makes sense.
Something that helps, not just impresses.

That means spending more time on the details.

On the flow.
On the foundation.

It might take longer.

But I believe that’s where the real value is.

So yeah, things are moving fast right now.

But I’m still focused on building something that works.

And getting it into people’s hands soon. ☕

The Best Systems Know When To Involve You

I’ve been thinking a lot lately about where humans fit into all of this.

Not in theory.

In real systems.

There’s a lot of talk about human-in-the-loop.

Usually framed as a safety net.
Something you add when the system isn’t confident.

But that’s not how it feels when you’re actually building.

What I’m seeing is that the real challenge isn’t just having a human in the loop.

It’s knowing when to bring them in.

Too early, and you slow everything down.
Too late, and you’re reacting instead of guiding.

There’s a timing to it.

A sense of flow.

The system needs to move on its own when it can.
And then pause, at the right moment, when judgment matters.

That’s harder than it sounds.

Because it means the system has to understand more than just tasks.

It has to understand intent.

What’s actually trying to be accomplished.
What matters in that moment.
What can move forward, and what needs a decision.

I’ve been working through this while refining the UI.

Trying to remove friction.
Trying to make the next step feel obvious.
Trying to make it natural for the system to ask for input without feeling like it’s interrupting.

When it works, it feels different.

You’re not fighting the system.
You’re moving with it.

And when it needs you, it’s clear why.

That’s the part I think a lot of people miss.

Human-in-the-loop isn’t just about control.

It’s about coordination.

And when that’s done right, the system starts to feel less like a tool…

…and more like something you work alongside. ☕

Easter, Time, and What Actually Matters

As I sit here on Easter reflecting on the day, a few things are on my mind.

For me, Easter is about faith. About resurrection. About the idea that something new can come from what felt finished.

But even outside of that, there’s something about this time of year that everyone can feel.

Spring. Growth. New life.

And time.

Time is the part that keeps hitting me.

My son is three and a half now.

I can still remember when he was born like it was yesterday, and now he’s running around the yard, talking, laughing, figuring things out in his own way.

My mom passed away last year.

My dad passed when I was 18. He was 50.

I’m 48 now.

That gets your attention.

It makes you look at things differently.

Today was a simple day.

We had family over for Easter lunch.
We went out in the field and flew kites.
We walked around the chickens and the garden and talked about what might grow this year.

Earlier in the day I took a walk with my wife and son and the dog out in the field.

Nothing big. Nothing complicated.

But those moments stick.

They feel different.

At the same time, life keeps moving.

I’m building CoffeeBreak.
Working with clients.
Still at TFL.
Fixing things when they break.
Working on bringing Jibo back to life.

A lot going on.

And somewhere in all of that is a simple thought that keeps coming back.

I want more of those moments.

More time in the field.
More walks.
More afternoons that don’t feel rushed.

That doesn’t happen by accident.

It means making changes.

It means deciding what matters and actually acting on it.

In a way, that ties back to what I’ve been building.

So much of what we do in technology is about speed. More output. More systems. More everything.

But if it doesn’t create space for the things that actually matter, what are we really optimizing for?

That’s been on my mind today.

Easter is a reminder that things can change. That new life, new direction, new priorities are always possible.

I’m thinking about what that looks like for me.

Not someday.

Soon. ☕

You don’t win by building faster. You win by seeing it sooner.

There’s a moment when you’re building something where you start to notice the world catching up.

Features start showing up in other tools.
Concepts you’ve been thinking about quietly start getting talked about more openly.

If you’re not careful, that can feel like you’re falling behind.

I’ve felt that a bit recently.

But when I step back, I see something different.

Most of what’s showing up are pieces.

A feature here.
A capability there.
Something that looks similar on the surface.

What I’ve been focused on is how those pieces actually work together.

Not just what the system can do.
But how it guides someone through doing it.

That’s a different problem.

It’s easy to build something that generates output.
It’s harder to build something that helps someone move forward with clarity.

That’s where I’ve been spending my time.

Thinking about intent.
Thinking about flow.
Thinking about what happens next without the user having to guess.

Because in every system I’ve ever worked on, that’s where things break down.

Not in capability.
In coordination.

So yeah, things are moving fast right now.

But I don’t think this is a race to ship the most features.

It’s a race to actually understand what we’re building.

And once you see that clearly, you start making very different decisions. ☕

I thought AI would fix it. It didn’t.

Lately I’ve been spending time intentionally pushing AI into parts of a system that I know are not clean.

Not to see if it works.
To see where it breaks.

Because that’s where the truth is.

When everything is well structured, AI looks incredible. It moves fast. It produces clean output. It feels like you’re multiplying your effort.

But that’s not the real test.

The real test is what happens when the system isn’t perfect.

When boundaries are unclear.
When responsibilities overlap.
When things have grown over time instead of being designed end to end.

That’s where AI gets interesting.

Not because it fixes it.
Because it exposes it.

You start to see hesitation.
You start to see guesses.
You start to see it follow paths that almost make sense but don’t quite hold together.

And if you’re paying attention, that tells you something important.

It’s not struggling with code.
It’s struggling with the shape of the system.

That’s a useful signal.

It’s like bringing in a really capable contractor and watching where they slow down. They’re not the problem. They’re showing you where the structure isn’t obvious.

I’ve been leaning into that.

Using AI less like a tool to “fix things” and more like a way to surface where understanding breaks down.

Because once you can see that clearly, you can actually do something about it.

AI is great at accelerating clean systems.

But what I’m finding is that it’s even better at revealing where things aren’t as clean as you thought.

And that’s where the real work starts. ☕

Building in the Middle of the Noise

It feels like every day brings another AI headline.

New models.
New agents.
New capabilities.
New warnings about what jobs are disappearing next.

The pace of announcements right now is dizzying.

But when you’re actually building something, the experience feels very different.

While the headlines swirl around, most of my time is spent doing the same things builders have always done. Debugging systems. Reworking architecture. Testing assumptions. Trying ideas that fail and fixing them.

CoffeeBreak has been a good reminder of that.

AI can generate code quickly. It can suggest patterns and explore solutions. But turning those pieces into a coherent system still requires patience and judgment.

Real progress rarely looks like the headlines.

It looks like slow improvements, small fixes, and occasional breakthroughs after a lot of iteration.

From the outside, AI development looks like a race.

From the inside, it still feels like engineering.

The headlines will keep coming.

Meanwhile, the real work continues. ☕