Networked information as the foundation for Agentic AI - a practical example from the industry

How does technical documentation become an intelligent, agent-based AI system?

In episode 45 of the “Knowledge Graph Insights” podcast, Max Gärber, Technical Consultant at PANTOPIX, talks to Larry Swanson about successfully building a system architecture that combines Agentic AI with a structured knowledge graph.

Using the ZEISS Service Copilot project as a practical example, Max Gärber explains how modern Large Language Models (LLMs), semantic technologies and professional knowledge management work together to create real added value for service, engineering and sales.

Because this does not work with artificial intelligence alone. It requires a stable knowledge graph, clean metadata structures, a well thought-out ontology and taxonomy architecture and established knowledge management processes.

This episode therefore also deals with the question of why many AI projects fail. In the discussion, it becomes clear that successful AI strategies do not start with large language models, but that clean information architecture, semantic modeling, structured content and sustainable knowledge management play an essential role.

Listen in if you want to use AI in technical documentation, in service or in an industrial environment. The podcast with Max Gärber provides valuable insights from the field – from strategic conception to concrete system architecture.

The podcast is in English.