In October of this year, Enterprise Knowledge held our annual Semantic Layer Symposium (SLS) in Copenhagen, Denmark, bringing together industry thought leaders, data experts, and practitioners to explore the transformative potential, and reflect on the successful implementation, of semantic layers. With a focus on practical applications, real-world use cases, actionable strategies, and proven paths to delivering measurable value, the symposium provided attendees with tangible insights they can apply within their organizations.

We’re excited to release these discussions for viewing, starting with Ben Clinch of Ortecha (who we also got the chance to speak with ahead of the event on Knowledge Cast).

Using Semantics to Reduce Hallucinations and Overcome Agentic Limits – Neuro-Symbolic AI and the Promise of Agentic AI

Speaker: Ben Clinch (Ortecha)

With the pace of change of AI being experienced across the industry and the constant bombardment of contradictory advice it is easy to become overwhelmed and not know where to start. The promise of LLMs have been undermined by vendor and journalistic hype and an inability to rely on quantitative answers being accurate. After all, what good would a colleague be (artificial or not) if you already need to know the answer to validate any question that you ask of them? This is further compounded by the exciting promise of Agentic AI but the relative immaturity of frameworks such as MCP. The promise of neuro-symbolic AI that combines two well established technologies (semantic knowledge graphs with machine learning) enable you to get more accurate LLM powered analytics and most importantly faster time to greater data value and when leveraged alongside solid data management foundations can mitigate and empower AI Agents while limiting the inherent risks in using them.

In this practical, engaging, and fun talk, Ben equips participants with the principles and fundamentals that never change but often go under-utilized to help you lay a solid foundation for the new age of agentic AI.