Systems | Development | Analytics | API | Testing

Stop the AI Iceberg | Secure AI Using Ontologies and Semantic Layers

Don’t let the "AI iceberg" sink your IP Most leaders only focus on the flashy models at the surface, but the real value—and the risk—is what’s underneath. Tony Seale and Jessica Talisman reveal why turning AI back onto your own data infrastructure to build connected ontologies is the key to security. This semantic foundation is the core of Agentic Analytics, ensuring your insights are grounded in your specific business logic rather than generic LLM guesses.

Ontology: The Secret to Semantic Layers | The Data & AI Chief Podcast

Is your AI-driven "autonomous enterprise" a reality or a peak-of-inflated-expectations dream? Most organizations rush toward the end state of AI agents without doing the foundational work of defining how their data actually relates through a robust ontology. In this episode of The Data & AI Chief, we sit down with Tony Seale, Founder of The Knowledge Graph Guys, and Jessica Talisman, CEO and Founder of The Ontology Pipeline. We break down why the "lost art" of data modeling and the development of semantic layers are the secret weapons for scaling Agentic Analytics.

How Semantic Layers and Ontologies Create Trusted AI

Learn why an organization’s ontology, a structured framework for how a business defines, connects, and makes sense of its data and knowledge, is the most valuable and most overlooked asset in any AI strategy. Jessica Talisman, CEO and Founder of The Ontology Pipeline, and Tony Seale, Founder of The Knowledge Graph Guys, break down what it actually takes to build trusted AI, covering everything from semantic layers and knowledge graphs to why provenance is non-negotiable.

Why Enterprise AI Can Get the Query Right and the Answer Wrong

Most teams deploying AI agents on their data are watching the wrong things. They check whether the query ran and whether the number looks plausible. When both checks pass, the agent gets credit for a correct answer, and the output flows into dashboards, decisions, and the next agent in the chain. There's a gap between those two checks and actual correctness, and it's where the expensive mistakes live. Getting to a correct answer requires more than a formally valid calculation.

AI-Ready APIs for Legacy Systems

80% of enterprise apps still use decades-old systems, but accessing their data for AI is tough. The challenge? Security risks, outdated interfaces, and slow performance. Here's the solution: API abstraction. This method creates a secure, no-code layer between AI and legacy systems. It keeps your old code intact while enabling AI to access data safely and efficiently.

RAG Pipeline Testing: How to Validate Retrieval, Context Use & Answer Accuracy

Large Language Models (LLMs) are impressive, but they are not without significant flaws. Their biggest hurdles are "knowledge cut-offs" where they cannot access information created after their training, and a tendency to "hallucinate" or confidently state false information. These models often struggle with the specific or real-time data that modern businesses rely on daily.