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

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.

About Michael Carducci

Michael Carducci spent years learning to see things as they actually are; first as a magician, then as a software architect, now as both simultaneously. And somehow that’s not even the whole story.

He’s the author of Mastering Software Architecture (Apress, 2025) and is currently writing The Semantic Layer. He has spent over 25 years following interesting problems; through roles from individual contributor to CTO and back again, across industries and continents.

As a speaker, he applies the same toolkit he uses in close-up magic: attention, misdirection, timing, storytelling, and the instinct to take the long way around when that’s where the truth lives. Audiences at hundreds of conferences across four continents have described his talks as the kind that change how you think about a problem rather than just what you know about it.

He also makes YouTube videos about technology and curiosity with his wife Kate, because some ideas are too important (or too interesting!) to leave only in conference rooms.

More About Michael »