Videos

Lightly edited for clarity.

The quality of what AI gives you is only as good as the context you provide, and organizations differ wildly in how well they manage context.

Again, AI doesn’t think. It generates tokens based on the context you give it. And if that context is weak, scattered, conflicting, incomplete, AI will fill in the gaps coherently, but not necessarily correctly.

So let’s say you’ve got two marketing teams. They both use AI to create website content, email campaigns, social media posts. One has rich, clean customer data and detailed campaign history, the other’s missing half of it, and it’s clear who wins in that scenario.

It’s not about the tools, it’s about organizing and managing that context effectively.

Garbage in, garbage out has been a core concept in software since there has been software. AI doesn’t change that.

The competitive edge isn’t just who has AI, it’s who builds better context systems, better memory, better retrieval, better data quality.

Lightly edited for clarity.

AI is changing work faster than most people can process, in every industry, not just tech.

I'm the CTO of a digital agency that builds large custom websites, enterprise-grade software, and increasingly, AI solutions for mostly Fortune 1000 clients. I've been building software for 30 years, and I'm watching this shift happen in real time.

It's not subtle. It's not theoretical. It's reshaping how work actually gets done. Developers, analysts, PMS, designers, everyone, everyone's job is changing, in ways that most people haven't caught up to yet.

In this series I'm gonna show you how I use AI, how my team uses AI how enterprises are adopting it, and what that means for your career going forward. If that interests you follow along. I'll be posting videos a few times a week.

Lightly edited for clarity.

AI makes you smarter, not in theory, but in the way you actually work.

And when I say that, I don't mean it improves your IQ, but it improves the quality of your decisions, your clarity, your options, and how deeply you think through a problem.

There's a quick example.

Let's say you're a front end developer. You know HTML, CSS, and React. You get put on a new project to build a public website based on Optimizely. Since you don't know Optimizely, traditionally you'd spend some time on Google. You'd read some blogs, maybe watch a few videos, read through the documentation, generally figure out what you need to do and how to approach it, and get started coding.

With AI, you have different options. You can use it to plan what you're actually gonna do. So you can ask it questions like: what's the best architecture for this? What are the new React features I should be using? What pitfalls do people usually run into, enough to optimize the implementation?

And even more critically, what can I automate? What can I use AI to do? How can I do this faster than I did in the past?

And it walks you through the things that you would think about, and fills in the details and answers questions, but it also points out things that you wouldn't think about.

You still have to bring your own judgment, but AI expands the surface area of your thinking.

So that's what I mean when I say AI makes you smarter. It doesn't replace you, but it does extend you.

Lightly edited for clarity.

The biggest reason I see people not using AI is privacy concerns. And honestly, that's very reasonable.

By default, most AI tools log your conversations. They store what you type. Many of them are using your conversations to train future versions of those models. That's how the defaults work.

The good news, though, is that you have options. You can turn on no training or zero retention modes. You can use enterprise accounts that don't train on your data. Or, if it's very private, you can run a local LLM, and none of the information ever leaves your device.

I'll be covering all this in follow-up videos. So I'll go through which tools truly honor zero retention, the settings that most people don't change and should, how enterprise versus consumer privacy differs, and when you should be using local models. And I'll go through that provider by provider and cover OpenAI, Microsoft, Google, etcetera.

Here's the key, though: you need to decide for yourself what you're comfortable sharing.

And I'd recommend you start with low risk tasks. So use AI for planning, for brainstorming, for cleaning up your documentation. And then as you see the value that provides, and your comfort level increases, and your knowledge of privacy increases, then you can use it more and more.

Once you understand privacy and how it affects what you do, what you type, which types of models you use, it really unlocks the capabilities of AI and allows you to use it confidently instead of cautiously.

Lightly edited for clarity.

What are your goals in life? What do you wanna do? What do you wanna achieve?

Do you want a promotion? Well, do you have a well structured, detailed, step by step plan for doing that? If the answer is no, let's fix that. We can do it right now.

Explain what you know about the job you want, which is not everything, cause you don't have that job yet. Explain the social dynamics involved, the team members, any financial considerations, any context you have that would affect this outcome.

Give a model that context and then use it to help you define a detailed, step by step plan for achieving that goal.

And the amazing thing here is that it's not just for promotions. It's for literally any feasible goal that anyone has.

You wanna retire early? Give them all the context. How much money you have. Tell it how it's invested. What assets do you have? What debts do you have? How much do you earn? How long are you gonna continue working?

You wanna start a business. You wanna move to Costa Rica. Wanna become a cowboy. It doesn't matter what your goal is or your goals are.

I challenge you, go do it right now. Go give a model context to achieve whatever your goal is. Put together a plan and then start executing that plan.

And by the way, if you get stuck on any step of that plan, you have AI, which is an expert coach in literally everything people do, that can teach you and show you how to do those things, how to accomplish your goals.

This is amazing. This is a game changer. I can't believe more people don't use AI in this way.

So whatever it is your goals in life are, go put a plan together and then let's get started.

Lightly edited for clarity.

AI isn't wiping out white collar work. It's compressing it. And the shift's already underway in real businesses that we work with.

AI is not replacing entire professions, but it is replacing the slow parts: the drafts, summaries, research, Q&A, scaffolding, documentation, prep work.

When you remove all that, you don't need 5 people for a project anymore. Maybe you need two.

You have PMS that previously needed a BA to create requirements. They can use AI to take a first pass of that. Is it final? No. Is it enough to get started? Yes.

A dev that needed QA support, you can use AI to build their own test scaffolding. Now a strategist who needed a writer can spin up multiple outlines in minutes.

And again, this doesn't remove the need for people doing any of those jobs, but it does make it dramatically faster, easier, removes the busy work, and improves the quality.

So this is the real transformation. White collar work is not disappearing, but it is condensing. It's fewer people needed to build more output, and there's higher expectations on everyone.

And then you've got AI kind of quietly filling in all the details around the edges.

So to thrive, you need to learn to orchestrate AI across your entire workflow, and not just use it for one off tasks.

Lightly edited for clarity.

The biggest impact of AI right now isn't about replacing people. It's about reducing the number of hours it takes to get work done.

If you look at most workdays, a lot of the time we spend is not the actual job. It's the friction around the job. You're waiting on replies, searching for context, drafting something that needs to get rewritten five times, sitting in meetings where the first 20 minutes are spent figuring out what's going on.

AI removes a lot of that friction.

And when you remove friction, the amount of time required to produce the same output naturally shrinks. Not the role, but the time attached to the role.

And this creates quiet structural changes inside organizations. Workflows tighten up. People get more done with fewer hours. Hiring slows. Backfilling slows. And the shape of work shifts, even if the org chart doesn't.

This is what happens when a technology that accelerates clarity, writing, coordination, and decision-making is implemented.

The part that matters is seeing where your own friction is, and how quickly you can offload it.

AI doesn't eliminate people first. It eliminates wasted hours.

And recognizing that early gives you a real advantage.

Lightly edited for clarity.

If you feel behind on AI, there's nothing wrong with you. Your habits came from a different world.

Most of us built our work habits in a pre AI environment. So especially if you're my age, you remember when home computers were new. You remember when the internet was new, then when mobile was new, then when remote work was new. And each one took years for people to fully adjust to.

But AI didn't give us years. It arrived very quickly, and it changed expectations even faster.

It's a lot like the shift to working from home during COVID. The technology was already there—Zoom, cloud files, messaging tools—but our habits were built around offices, commutes, and in person everything.

So the technology changed overnight, and the habits took time to catch up.

AI is the same dynamic, but it's on a much faster timeline. The tools moved ahead instantly, and our habits are still catching up. And that's okay.

Once you build a couple of simple habits—clarifying what you want, asking clean questions, iterating instead of judging the first answer—everything gets easier.

You're not behind. Your habits are from a world that didn't have AI built-in, and habits can change quickly.

Lightly edited for clarity.

AI can generate a lot of things, but the thing it can't generate is good judgment.

Judgment is the ability to choose between options, to understand what matters, to see context, nuance, timing, and people.

AI can help you brainstorm, summarize, draft, rewrite, but it can't decide what's right for this situation, this team, or this moment.

It can give you material, but you're the one that gives it meaning.

This becomes even more important as AI accelerates the easy parts of work. When everyone can generate content instantly, the value shifts to the people who make sound, thoughtful decisions.

And by the way, judgment isn't fixed. It's a skill you can develop. We'll talk more about how to do that in a future video.

So AI can produce the work, but only you can decide what the right work is. That's judgment, and it gets more valuable as AI gets better.

Lightly edited for clarity.

Many companies aren't ready for AI yet, but that doesn't have to slow you down.

Organizations move slowly, and for good reasons. They need policies, they need approvals, they need alignment, training, security reviews, and budget cycles. And all of that takes time.

Meanwhile, this technology is moving very quickly, much faster than the social and adoption curves inside most companies.

So you end up with this gap where the tools evolve weekly, but the organization adapts yearly. So that's not a failure, but it is how large systems work.

Individuals, on the other hand, can move immediately. You don't need a policy to rewrite an email, or to summarize a meeting, or clarify a thought, offload a tedious task, or explore a new workflow.

Companies wait for structure. People can start with habits.

And that creates a meaningful advantage for anyone who's willing to move a little faster than the environment around them.

Your company will catch up, but you don't have to wait for that. You can become more capable today.

Lightly edited for clarity.

If you only build one AI habit, this is the one. It makes every prompt, every workflow, every output instantly better.

Most people jump straight into asking AI for something, and then wonder why the response is vague or off target.

The fix is simple. Take the time before you ask to clarify your intent. It doesn't necessarily need to be a long explanation, but at least a sentence of what am I actually trying to do here.

What is my goal?

Am I trying to summarize, rewrite, brainstorm, explain, compare options, make a decision, create a plan?

Once you name the intent, everything gets easier. Your prompts get clearer, your answers get better, you spend less time fixing things and more time applying them.

AI doesn't need complexity. It needs clarity. And clarity starts with that pause.

Most people don't struggle with AI. Most people struggle with AI because they skip this step. Clarity in, clarity out.

Lightly edited for clarity.

AI doesn't think, but it is really good at guessing the next thing to say.

When people talk about AI, usually what they're talking about is large language models, or LLMs.

Now, LLMs operate on tokens. Tokens and words are not the same thing, but it is really helpful to think of them as the same thing to understand the concept.

So in language, words have relationships to each other. When I say, “uh oh, sounds like somebody has a case of the Mondays,” every word connects. “Uh oh” relates to what follows. It signals that something bad is coming. “Case” relates to “Mondays.” And together they form a phrase.

And even if you've never heard that phrase, you can tell from context it's not good.

LLMs are mathematical models that learn those relationships, not as rules, but as probabilities. When we train a model, we give it a bunch of examples of language. Training teaches it to map which words are likely to come next, based on all the words that came before.

So in that example, “uh oh, sounds like somebody's got a case of the blank,” it might predict Mondays, or it might predict flu. And it really depends on if you were talking about Office Space, or you were talking about the fever that you have.

When AI is responding to you, what it's really doing is predicting the next word, one at a time, based on all the words that came before it in the conversation. And then it predicts the next one, and the next one, and so on.

And that's why it can sound so confident while being completely wrong. It doesn't know. It just guesses well, based on context.

This is the fundamental concept for using AI. Once you understand this, all the weird behaviors start to make a lot more sense.

Lightly edited for clarity.

Some people seem to learn AI very quickly, and it's not necessarily because they're smarter. It's because they're comfortable with one specific thing.

The people who pick up AI fastest aren't always the ones with technical backgrounds. They're the ones who are comfortable with iteration.

So most of us were trained to get things right on the first try. School rewards the correct answer. Work rewards polish. AI rewards the opposite.

AI works best when you try something, see what happens, adjust, refine, and repeat. It's a collaboration. It's not a test.

The people who struggle with AI usually expect perfect output immediately. When they don't get it, they assume, well, AI is not good at this.

The people who thrive treat the first output as a starting point, and they shape it. They ask follow ups. They give context. They clarify the goal. They correct misunderstandings. They iterate.

AI isn't about knowing. It's about exploring.

So if you can build the habit of iteration, you'll learn AI faster than almost anyone, because you're working with the tool instead of judging it.

Lightly edited for clarity.

If you're trying to figure out use cases for AI, you're going the wrong direction.

Most people approach AI by asking, what can AI do here? How can I use AI? Can AI help me? Executives do it, managers do it, teams do it. It's logical, but it's the wrong lens.

The better question is, where is the bottleneck? Where are you waiting? Where are people confused? Where does work slow down? Where do things get lost? Where is clarity missing? Where is rework high? Where do people spend time on things that don't actually matter?

AI is not about sprinkling capabilities across your workload. It's about removing friction from the places that slow everything else down.

When you find a bottleneck, you'll find leverage. And when you apply AI to leverage, the impact is disproportionate.

So stop searching for use cases. Start identifying bottlenecks, and the AI fits naturally once you understand where the friction is.

Lightly edited for clarity.

There's one AI mistake that instantly makes people feel like they don't get it, and it is avoidable.

Most people treat AI like a search engine. That makes sense. We've all been using search engines for a long time. They ask once, and if the answer isn't great, they stop.

They think, I must be doing this wrong. Maybe AI isn't for me, or this tool isn't good.

But AI is not a database. It's a collaborator. And the first answer is almost never the best answer. It's the starting point.

The real power comes from the next question. Refine this. Push this further. Explain the trade offs. Rewrite it at a higher level. What am I missing? Give me three alternatives. Simplify this.

When you treat AI as iterative, you stop feeling inadequate and you start feeling capable.

The mistake isn't getting a mediocre first answer. The mistake is stopping there.

Lightly edited for clarity.

When people argue about whether or not AI thinks, they're collapsing several different abilities into a single word, and that creates confusion.

Human thinking is not one process. It's a layered system. And language models overlap with parts of it, but they skip the foundation.

And the foundation is how we build mental models of reality.

Humans don't just store facts. We build working models of how the world behaves. We form concepts like pressure, balance, or risk from direct experience, from physics of the world and emotions that we feel, and consequences of our actions.

And these mental models are grounded in the sensory experience of life. They let us reason across completely different domains, using the same internal structures.

And that's what grounding means, connecting abstract ideas back to the systems of cause and effect that built them.

When something breaks that structure, it feels wrong, and long before we can explain why, that signal keeps our reasoning tethered to reality.

Language models don't have those grounded models of reality. They don't touch, or sense, or experience.

They map how words relate to each other. Their internal representations live in language space, statistical relationships among tokens in text.

And a concept like pressure isn't a force or a feeling. It's a pattern in word usage.

And that's why they can sound perfectly correct, and still be disconnected.

They generate local coherence without global understanding.

Now, multimodal systems are starting to link language to images, or sound, or video. But even those links remain shallow. They're correlations, not lived experience.

Humans reason from grounded models outward, from perception to language. LLMs reason from language inward, from patterns to probability.

And one builds meaning from contact with reality. The other rearranges symbols that point to it.

Grounding is not a detail. It is the difference between modeling the world and echoing its descriptions.

So when someone says AI does think, look at the layer it performs. The surface behavior of thought.

But without a model of reality underneath, humans think because we live inside the systems we're modeling. AI predicts what thinking sounds like.

Lightly edited for clarity.

You hear a lot of predictions right now that AI will make programming obsolete, that developers will disappear, that college majors like computer science are already outdated.

They're not.

But the field is shifting. Not in what we learn, but in what that knowledge gets used for.

Computer science has always had two layers. One is technical: languages, frameworks, tools. And the other is structural: how humans coordinate to turn logic into value.

And the technical layer is changing fast. Every few months there's a new model, or a new API, or a new tool that reshapes what coding means.

In three years, students won't be writing as much raw code. They'll be describing behavior, verifying results, and orchestrating agents.

But the structural layer, how humans define problems, communicate intent, and decide what should be built, that part barely changes at all.

Teams still need people who can reason about systems, manage trade offs, and translate messy human goals into precise machine actions.

AI accelerates execution, but judgment, clarity, and deep thinking remain human.

So if you're studying computer science today, don't panic. But don’t stay static either.

Keep learning the fundamentals: logic, systems, data structures, architecture. And then also build the new muscle: prompt clarity, workflow design, AI integration.

The best developers in three years won't just know how to write code. They'll also know how to shape systems, human and machine, that produce better outcomes faster, with less friction.

AI is not the end of computer science. It's just the next layer of abstraction.

Learn to work with it, and you'll still be at the center of how technology gets built.

Lightly edited for clarity.

The adoption percentage in this transcript is Mike’s directional estimate, not a universal benchmark.

Most companies today are not AI driven, AI native, AI first.

They're a handful of people using AI tools in a few corners of the business. And that's the first stage of a long maturity curve.

Adoption moves through layers. It starts with individuals, and they use AI to summarize notes and draft an email, or experiment with built-in vendor tools.

And 2025 is really where we've seen the beginning of that. The point where people are just starting to get AI enabled tools in their day to day stack.

And these early steps are about proof of concept, small MVPs, quick experiments, and just getting something working.

And then once multiple people start using AI, consistency becomes more important.

And so we see teams standardizing on how they use tools, shared prompts, templates, and workflow integration.

So they start coordinating their use of AI across projects.

And then the next level of structure is a full department. And that's often IT or marketing, which are moving the fastest right now.

Different teams within those departments start to align around broader systems and shared data.

And then it goes to enterprise wide integration. It's full end to end automation across business processes.

And that's kind of the current technical end state for AI adoption today, before we start talking about any future AGI territory, which at the moment remains science fiction.

And right now, maybe 15 to 20% of organizations even have the foundational infrastructure for that upper tier.

Everyone's either experimenting with fragmented projects, or actively working to build that foundation.

And AI maturity is not just about tools. It's about repeatability, reliability, and integration.

It's not a switch. It's a staircase.

So figure out where your organization stands, and focus on the next step, not the entire climb.