Why intelligence breaks when meaning is implicit, and how linked data, ontologies, and knowledge graphs repair it.
The Semantic Lounge
Make meaning explicit.
Hands-on training in the semantic layer: the open W3C standards that let applications and agents read what your data means instead of guessing at it. Small public cohorts, and private workshops built around your own systems.
Next Denver · October 8–9 · 35 seatsOne hour on why AI guesses.
If you have an hour before deciding anything, spend it here. This is the argument the workshops are built on, recorded at the Great International Developer Summit.
Open seats, small rooms.
Small enough that everyone builds. You meet the problem first, in something you can touch; the name arrives when it has something to attach to.
Two days · in person · No Fluff Just Stuff
Architecting the Semantic Layer
Why AI can’t tell truth from probability in your data, and how to build the layer that fixes it: the standards stack, context carried in the data itself, and semantics added to the systems you already run. You leave with the model you built and the thinking that produced it.
16 hours · online, instructor-led · Iasa
Designing a Semantic Layer
A working session, not a survey. You’ll leave able to judge whether your own systems are agent-ready, argue the case to your team, and start adding a semantic layer to the systems you already run, the same week.
Where the idea is next.
Workshops, plus the talks I’m giving on the semantic layer. The full calendar lives on michaelcarducci.com.
- LLMs Without the Guesswork: A Blueprint for Deterministic AITalk · Calgary Software CraftersOnline
- Architecting the Semantic LayerTwo-day workshop · No Fluff Just StuffWestminster, CO
- Enterprise AI Needs a Semantic LayerTalk · SALT: Software Aficionados Learning TogetherSouth Jordan, UT
- Designing a Semantic LayerOnline workshop · IasaOnline
- The Semantic Layer in Plain EnglishTalk · Louisiana IT Symposium (EFM)New Orleans, LA
- Designing a Semantic LayerOnline workshop · IasaOnline
Your people, your data, your problem.
Private workshops
Built for the room that’s actually there.
Everything on this page runs privately too, on-site or online. The difference: your team works on your own schemas, APIs, and data, so the exercises become the first draft of the real system. Two deliverables, always: the work, and the thinking that produced it.
When it’s time to build
Some teams want a guide as well.
A workshop often turns into the first week of an engagement: harvesting the ontology already implicit in your systems, validating it, and putting it behind APIs that describe themselves. That work is consulting, and it starts the same way, with a conversation about the problem.
Read the first chapter now.
Packt · 2027 · in progress
The Semantic BlueprintBuilding an AI-Ready Semantic Layer with W3C Open StandardsWorking title
The book the workshops grew into: why AI can’t use data whose meaning is implicit, and how to build the layer that fixes it, one system at a time, with standards that have been quietly solving this for thirty years.
Chapter 1 · free to read
The Semantic Ceiling
“There is no mechanism in the architecture for truth, only probability.” Why an LLM can’t know anything, why RAG is weak justification, and what it takes to break through. About 12 minutes; set on paper.
Read Chapter 1