Michael Carducci

An Engineer's Guide to the Semantic Layer (Critical Infrastructure)

9:00 AM MDT

Gartner just named the semantic layer a non-negotiable foundation for AI. Almost nobody in the industry knows what that means yet, or why it should worry them.

Every LLM response is a guess, not a fact. Most of the time it's close enough that nobody notices. Then it's wrong, and there was no way to see it coming, because the model doesn't know what your data means—the model doesn't know anything. It's always guessing, based on patterns, every time. The guess is right often enough to feel like magic. It will never be right 100% of the time, and can't change that. It's not a bug waiting on a fix. It's a hole in your architecture.

As one recent paper on the semantic gap puts it:

> “When AI systems enter the picture, descriptive documentation is insufficient. LLM-based interfaces operate directly over data representation. If meaning is not encoded structurally, the model infers it probabilistically.”

Your systems are full of structured data (JSON, databases, APIs) that means something to the code that built it and nothing to anything else, including the AI you just pointed at it. A field called status: 3 means nothing outside your system. Multiply that by every field, every service, every team, and you get an enterprise fluent in nothing but itself. That's the wall every serious AI initiative eventually hits, and it's why so many AI initiatives are underdelivering.

The fix isn't a bigger model or a new platform. It's a set of open standards that have quietly run major parts of the web for decades, built for making data mean something on its own, without a person or a program standing by to translate it. Once your data can say what it is, your AI stops guessing about it. Data-driven interactions become deterministic-first, your entire enterprise data landscape becomes more powerful, and whole classes of problems in AI disappear. That's the semantic layer.

This workshop is a hands-on introduction to building one, starting from data you already have, with tools you already know. You'll leave with a working model of what a semantic layer actually is, why it's about to become as fundamental as the database, and why the people who understand it now will be the most valuable engineers in their organization for the next decade, while everyone else is still tweaking prompts.

When Code is Cheap, Architecture is Everything

Architecture in the Age of AI

8:30 AM MDT

As code generation becomes increasingly automated, our role as developers and architects is evolving. The challenge ahead isn’t how to get AI to write more code, it’s how to guide it toward coherent, maintainable, and purposeful systems.

In this session, Michael Carducci reframes software architecture for the era of intelligent agents. You’ll learn how architectural constraints, composition, and trade-offs provide the compass for orchestrating AI tools effectively. Using principles from the Tailor-Made Architecture Model, Carducci introduces practical mental models to help you think architecturally, communicate intent clearly to your agents, and prevent automation from accelerating entropy. This talk reveals how the enduring discipline of architecture becomes the key to harnessing AI—not by replacing human creativity, but by amplifying it.

The Art of Being an Architect

10:30 AM MDT

The hardest part of software architecture isn’t the technology, it’s the people. Every architecture lives or dies by its ability to influence behavior, build consensus, and turn vision into change. In this session, Michael Carducci explores the real work of being an architect: communicating clearly, guiding decisions, and driving meaningful change in complex organizations. Drawing from decades of experience and the principles behind the Tailor-Made Architecture Model, Carducci shows how to identify where change is needed, package ideas for adoption, and lead with both clarity and empathy.

And while AI may soon help us design systems, it still can’t align humans around them. The enduring art of architecture lies in shaping not just the code, but the culture that makes progress possible. You’ll leave with practical tools to navigate the human side of architecture and a renewed appreciation for why that art still matters.

3rd Generation Agentic AI

Solving Integration, Intelligently

1:00 PM MDT

Every generation of system integration has made the same mistake: a standard protocol with bespoke incantations on top. Telnet. CORBA. SOAP. even REST APIs. And now? MCP and tool schemas (the JSON WSDL). We can do better.

This session argues that the challenges of agentic AI are not a model problem or a tooling problem. They're an interoperability problem. And we already know how to solve it, we've been doing it for decades on the world wide web. The problem is tractable.

Through live demos and a real production system, you'll see what anarchic interoperability looks like for AI agents: a single way to talk to any system, without constraining what any system can do.

Why AI Acceleration Keeps Slowing You Down

The Paradox of Speed vs Delivery

3:00 PM MDT

AI is accelerating software development at an unprecedented pace, but many teams are discovering a frustrating reality: faster coding isn’t translating into faster delivery.

The reason is counterintuitive. When you accelerate one part of a system, you don’t improve the system… you stress it. More code becomes more review, more coordination, more cognitive load, and ultimately, less flow.

This talk connects that modern failure mode to a foundational systems insight from The Goal: local optimization usually degrades overall performance. From there, Michael Carducci shows how to apply the Theory of Constraints to modern software delivery.

Using concrete examples, you’ll see how practices like XP, DevOps, Domain-Driven Design, and Team Topologies act as targeted interventions on specific bottlenecks—and how misapplying them can make things worse.

You’ll leave with a practical mental model for identifying constraints in your system, reasoning about trade-offs, and designing for flow in an AI-accelerated world.

Six Secrets to Succeeding with Microservices

5:00 PM MDT

Microservices architecture has become a buzzword in the tech industry, promising unparalleled agility, scalability, and resilience. Yet, according to Gartner, more than 90% of organizations attempting to adopt microservices will fail. How can you ensure you're part of the successful 10%?

Success begins with looking beyond the superficial topology and understanding the unique demands this architectural style places on the teams, the organization, and the environment. These demands must be balanced against the current business needs and organizational realities while maintaining a clear and pragmatic path for incremental evolution.

In this session, Michael will share some real-world examples, practical insights, and proven techniques to balance both the power and complexities of microservices. Whether you're considering adopting microservices or already on the journey and facing challenges, this session will equip you with the knowledge and tools to succeed.

Art of the Impossible

8:00 PM MDT

We all have an innate sense of what's possible. Not only is this how magicians fool you, but it might also be what's holding you back.

In this session Michael Carducci shares how he applied lessons learned in his career as a professional magician to his “day-job” as a technologist.

Magicians have a simple process for creating new material; think of the most impossible thing you can imagine, the engineer a way to make it possible. Michael has been engineering solutions to “impossible” problems for nearly 20 years and this has given him a unique perspective on dealing with challenges in all aspects of his life.

This talk combines illusion, anecdotes and real-world examples to help identify and overcome your mental obstacles.

An Engineer's Guide to the Semantic Layer (Critical Infrastructure)

9:00 AM MDT

Gartner just named the semantic layer a non-negotiable foundation for AI. Almost nobody in the industry knows what that means yet, or why it should worry them.

Every LLM response is a guess, not a fact. Most of the time it's close enough that nobody notices. Then it's wrong, and there was no way to see it coming, because the model doesn't know what your data means—the model doesn't know anything. It's always guessing, based on patterns, every time. The guess is right often enough to feel like magic. It will never be right 100% of the time, and can't change that. It's not a bug waiting on a fix. It's a hole in your architecture.

As one recent paper on the semantic gap puts it:

> “When AI systems enter the picture, descriptive documentation is insufficient. LLM-based interfaces operate directly over data representation. If meaning is not encoded structurally, the model infers it probabilistically.”

Your systems are full of structured data (JSON, databases, APIs) that means something to the code that built it and nothing to anything else, including the AI you just pointed at it. A field called status: 3 means nothing outside your system. Multiply that by every field, every service, every team, and you get an enterprise fluent in nothing but itself. That's the wall every serious AI initiative eventually hits, and it's why so many AI initiatives are underdelivering.

The fix isn't a bigger model or a new platform. It's a set of open standards that have quietly run major parts of the web for decades, built for making data mean something on its own, without a person or a program standing by to translate it. Once your data can say what it is, your AI stops guessing about it. Data-driven interactions become deterministic-first, your entire enterprise data landscape becomes more powerful, and whole classes of problems in AI disappear. That's the semantic layer.

This workshop is a hands-on introduction to building one, starting from data you already have, with tools you already know. You'll leave with a working model of what a semantic layer actually is, why it's about to become as fundamental as the database, and why the people who understand it now will be the most valuable engineers in their organization for the next decade, while everyone else is still tweaking prompts.

An Engineer's Guide to the Semantic Layer (Critical Infrastructure)

11:00 AM MDT

Gartner just named the semantic layer a non-negotiable foundation for AI. Almost nobody in the industry knows what that means yet, or why it should worry them.

Every LLM response is a guess, not a fact. Most of the time it's close enough that nobody notices. Then it's wrong, and there was no way to see it coming, because the model doesn't know what your data means—the model doesn't know anything. It's always guessing, based on patterns, every time. The guess is right often enough to feel like magic. It will never be right 100% of the time, and can't change that. It's not a bug waiting on a fix. It's a hole in your architecture.

As one recent paper on the semantic gap puts it:

> “When AI systems enter the picture, descriptive documentation is insufficient. LLM-based interfaces operate directly over data representation. If meaning is not encoded structurally, the model infers it probabilistically.”

Your systems are full of structured data (JSON, databases, APIs) that means something to the code that built it and nothing to anything else, including the AI you just pointed at it. A field called status: 3 means nothing outside your system. Multiply that by every field, every service, every team, and you get an enterprise fluent in nothing but itself. That's the wall every serious AI initiative eventually hits, and it's why so many AI initiatives are underdelivering.

The fix isn't a bigger model or a new platform. It's a set of open standards that have quietly run major parts of the web for decades, built for making data mean something on its own, without a person or a program standing by to translate it. Once your data can say what it is, your AI stops guessing about it. Data-driven interactions become deterministic-first, your entire enterprise data landscape becomes more powerful, and whole classes of problems in AI disappear. That's the semantic layer.

This workshop is a hands-on introduction to building one, starting from data you already have, with tools you already know. You'll leave with a working model of what a semantic layer actually is, why it's about to become as fundamental as the database, and why the people who understand it now will be the most valuable engineers in their organization for the next decade, while everyone else is still tweaking prompts.

The Innovation Playbook

A Blueprint for Tech Leaders

5:00 PM MDT

Statistically speaking, you are most probably an innovator. Innovators actively seek out new ideas, technologies, and mental models by reading books, interacting with a broader social circle, and attending conferences. While you may leave this conference with the seed of an idea that has the potential to transform your teams, products, and organization; the battle has only begun. While, as a potential changeagent, you are ideally positioned to conceive of the powerful new ideas, you may be powerless to drive the change that leads to adoption. Your success requires the innovation to diffuse outward and become adopted. This is the art of Innovation.

Fortunately there has been over a century of study on the topic of how innovations go from novel idea to mainstream adoption. The art of innovation is difficult, but tractable and this session illuminates the path. You will get to the heart of why some innovations succeed while others fail as well as how to tip the scales in your favor. You'll leave armed with the tools to become a powerful change agent in your career and life and, ultimately, become a more powerful and influential person.

Refactoring REST APIs for the Last Time: Strategies for a Future-Proof Design

8:30 AM MDT

REST APIs often fall into a cycle of constant refactoring and rewrites, leading to wasted time, technical debt, and endless rework. This is especially difficult when you don't control the API clients.

But what if this could be your last major API refactor? In this session, we’ll dive into strategies for designing and refactoring REST APIs with long-term sustainability in mind—ensuring that your next refactor sets you up for the future.

You’ll learn how to design APIs that can adapt to changing business requirements and scale effectively without requiring constant rewrites. We’ll explore principles like extensibility, versioning, and decoupling, all aimed at future-proofing your API while keeping backward compatibility intact. Along the way, we’ll examine real-world examples of incremental API refactoring, where breaking the cycle of endless rewrites is possible.

This session is perfect for API developers, architects, and tech leads who are ready to stop chasing their tails and want to invest in designing APIs that will stand the test of time—so they can focus on building great features instead of constantly rewriting code.

Innovation: Why the Majority Is Always Wrong

12:30 PM MDT

If everyone agrees with you, you’re probably not innovating, you’re just conforming faster. History’s breakthroughs rarely came from consensus; they came from heretics, hackers, and the hopelessly curious. In this talk, Michael Carducci takes aim at the myth of collective wisdom and explores why the crowd is almost always optimized for the past. Through stories of misfits who changed the world—from computing pioneers to magicians who reinvented wonder; Carducci reveals the hidden patterns of real innovation: discomfort, doubt, and persistence in the face of polite disbelief.

You’ll learn how to recognize the subtle forces that suppress new ideas, how to trust your intuition when it runs counter to consensus, and how to cultivate the curiosity and courage that real innovation demands. This is a talk for the misfits, the tinkerers, and the quietly visionary… because progress has always started at the edges.