Key Topics

  • Knowledge Graphs in RAG architectures: How to integrate graph-based knowledge structures into multi-agent retrieval-augmented generation systems using Python, LangChain, and OpenAI.

  • Ontologies for context governance: Using OWL and RDF ontologies to structure, version, and ensure traceability of contextual information in AI systems operating in regulated environments.

  • Semantic web standards: Practical application of RDF, OWL, and SHACL for knowledge representation, validation, and reasoning in agentic pipelines.

  • Graph databases: Design and query patterns in GraphDB and Neo4j as knowledge backends for LLM-based agents.

  • RAG design patterns: Retrieval strategies, chunking approaches, and tokenization considerations when combining vector search with structured graph retrieval.

  • Agent context auditing: Leveraging ontologies as a mechanism for versioning and auditing the context provided to AI agents.

  • Tree-of-Thought reasoning: Practical agent design using ToT prompting strategies, including a "judge"-style evaluation component for output validation.

  • Applied domains: Case studies and examples drawn from medical data management and legal tech, where traceability and explainability are non-negotiable.

@Nothofagus
FAVORITES EXPERIENCE MASTERCLASS CONNECT