Crazy Wisdom
Episode #530: The Hidden Architecture: Why Your Startup Needs an Ontology (Before It's Too Late)
- AI & Agents
- Consciousness & Philosophy
- Entrepreneurship & Startups
- Knowledge & Learning
- Robots & Atoms
- knowledge graphs
- ontologies
- symbolic AI
- semantic web
- RDF (Resource Description Framework)
- knowledge architecture
- community building
- generative AI
This video isn't available here. Try YouTube, or listen to the audio below.
Watch on YouTubeAbout this episode
Timestamps
- 00:00Introduction to Knowledge Graphs and Ontologies
- 01:09The Importance of Ontologies in AI
- 04:14Philosophy's Role in Knowledge Management
- 10:20Debating the Relevance of RDF
- 15:41The Distinction Between Knowledge Management and Knowledge Engineering
- 21:07The Human Element in AI and Knowledge Architecture
- 25:07Startups vs. Enterprises: The Knowledge Gap
- 29:57Deterministic vs. Probabilistic AI
- 32:18The Marketing of AI: A Historical Perspective
- 33:57The Role of Knowledge Architecture in AI
- 39:00Understanding RDF and Its Importance
- 44:47The Intersection of AI and Human Intelligence
- 50:50Future Visions: AI, Ontologies, and Human Behavior
Key Insights
- Knowledge Graphs Combine Structure and Instances Through Ontological Design. A knowledge graph is built using an ontology that describes a specific domain you want to understand or work with. It includes both an ontological description of the terrain—defining what things exist and how they relate to one another—and instances of those things mapped to real-world data. This combination of abstract structure and concrete examples is what makes knowledge graphs powerful for discovery, question-answering, and enabling agentic AI systems. Not everyone agrees on the precise definition, but this understanding represents the practical approach most knowledge architects use when building these systems.
- Ontology Engineering Has Deep Philosophical Roots That Inform Modern Practice. The field draws heavily from classical philosophy, particularly ontology (the nature of what you know), epistemology (how you know what you know), and logic. These thousands-year-old philosophical frameworks provide the rigorous foundation for modern knowledge representation. Living in Heidelberg surrounded by philosophers, Swanson has discovered how much of knowledge graph work connects upstream to these philosophical roots. This philosophical grounding becomes especially important during times when institutional structures are collapsing, as we need to create new epistemological frameworks for civilization—knowledge management and ontology become critical tools for restructuring how we understand and organize information.
- The Semantic Web Vision Aimed to Transform the Internet Into a Distributed Database. Twenty-five years ago, Tim Berners-Lee, Jim Hendler, and Ora Lassila published a landmark article in Scientific American proposing the semantic web. While Berners-Lee had already connected documents across the web through HTML and HTTP, the semantic web aimed to connect all the data—essentially turning the internet into a giant database. This vision led to the development of RDF (Resource Description Framework), which emerged from DARPA research and provides the technical foundation for building knowledge graphs and ontologies. The origin story involved solving simple but important problems, like disambiguating whether "Cook" referred to a verb, noun, or a person's name at an academic conference.
- Symbolic AI and Neural Networks Represent Complementary Approaches Like Fast and Slow Thinking. Drawing on Kahneman's "thinking fast and slow" framework, LLMs represent the "fast brain"—learning monsters that can process enormous amounts of information and recognize patterns through natural language interfaces. Symbolic AI and knowledge graphs represent the "slow brain"—capturing actual knowledge and facts that can counter hallucinations and provide deterministic, explainable reasoning. This complementarity is driving the re-emergence of neuro-symbolic AI, which combines both approaches. The fundamental distinction is that symbolic AI systems are deterministic and can be fully explained, while LLMs are probabilistic and stochastic, making them unsuitable for applications requiring absolute reliability, such as industrial robotics or pharmaceutical research.
- Knowledge Architecture Remains Underappreciated Despite Powering Major Enterprises. While machine learning engineers currently receive most of the attention and budget, knowledge graphs actually power systems at Netflix (the economic graph), Amazon (the product graph), LinkedIn, Meta, and most major enterprises. The technology has been described as "the most astoundingly successful failure in the history of technology"—the semantic web vision seemed to fail, yet more than half of web pages now contain RDF-formatted semantic markup through schema.org, and every major enterprise uses knowledge graph technology in the background. Knowledge architects remain underappreciated partly because the work is cognitively difficult, requires talking to people (which engineers often avoid), and most advanced practitioners have PhDs in computer science, logic, or philosophy.
- RDF's Simple Subject-Predicate-Object Structure Enables Meaning and Data Linking. Unlike relational databases that store data in tables with rows and columns, RDF uses the simplest linguistic structure: subject-predicate-object (like "Larry knows Stuart"). Each element has a unique URI identifier, which permits precise meaning and enables linked data across systems. This graph structure makes it much easier to connect data after the fact compared to navigating tabular structures in relational databases. On top of RDF sits an entire stack of technologies including schema languages, query languages, ontological languages, and constraints languages—everything needed to turn data into actionable knowledge. The goal is inferring or articulating knowledge from RDF-structured data.
- The Future Requires Decoupled Modular Architectures Combining Multiple AI Approaches. The vision for the future involves separation of concerns through microservices-like architectures where different systems handle what they do best. LLMs excel at discovering possibilities and generating lists, while knowledge graphs excel at articulating human-vetted, deterministic versions of that information that systems can reliably use. Every one of Swanson's 300 podcast interviews over ten years ultimately concludes that regardless of technology, success comes down to human beings, their behavior, and the cultural changes needed to implement systems. The assumption that we can simply eliminate people from processes misses that humans are who these systems should serve, and human problems represent the most interesting challenges that can never be fully automated away.
Episode transcript
Welcome to the Crazy Wisdom Podcast. This podcast is for you. If you have an insane drive to find the truth of things, it's not the good answers that we seek, but the good questions. I interview a range of different guests from many different fields, all with the intention to uncover the simple truths that are hidden in plain sight. Most people don't want to go there. I go there, my guests go there, and you benefit. Please let me know if you enjoy these episodes and as always, subscribe on itunes, Spotify, or wherever you listen to the podcasts.
Welcome to the Crazy Wisdom Podcast. I've got Larry Swanson here, and he is a knowledge architect, community builder, and host of the Knowledge Graph Insights podcast. Welcome to the show.
We're going to have a great conversation about ontologies. What is what? Well, and knowledge graphs and all these other. Well, actually, yeah. What. What is the relationship between a knowledge graph and an ontology? And maybe for our listeners, why are they important?
Yeah, I think. Well, they're important right now in the context of AI. You know, the generative AI is kind of showing what it's capable of and really good at and where it needs some help. And symbolic AI, which the topic of knowledge graphs and ontologies fits into, is, like, here and ready to help, you know, so. But the. The classic definition of a knowledge graph would be like, a com. Well, and not everybody agrees on this. This is my opinion. I'll just phrase it that way for any of my friends in the field who are listening, because there's a lot of people who are more precise and experienced than I am. But as I understand it, a knowledge graph is. It's built with an ontology that describes a domain that you're curious about, that you want to be able to answer questions about or discover things about or do things with, like, agentic AI. I think knowledge graphs are going to be very important for that. So you have an ontological understanding of a domain, like, what are the things in there? How do they relate to one? And then you have instances of all those things that you're concerned with. So it's both an ontological description of the terrain and then mapped to instances of stuff in that terrain. I hope that's not too abstract.
Your first full transcript is free. After that, an email opens every transcript in the index — a list of readers we can write to, not a guest book.