Heavybit Podcasts Ep. #20, Exploring AI Memory with Vasilije Markovic of Cognee
Aug 21, 2025
In this fascinating discussion, Vasilije Markovic, a data engineering and cognitive science expert from Cognee, delves into the world of AI memory. He tackles challenges like 'context rot' and emphasizes the need for effective data organization to enhance AI’s decision-making capabilities. Markovic shares insights on AI's practical applications across industries like construction and education, while humorously illustrating the complexities of context and relational data. The conversation also touches on the intricate relationship between creativity and technology in today's landscape.
AI Snips
Chapters
Books
Transcript
Episode notes
Ground LLMs With Ontologies
- Combine LLM-extracted entities with ground-truth RDF ontologies to avoid hallucinated facts.
- Use explicit ontologies to mark reliable facts versus LLM-generated context.
Education Client Mapped Learner Networks
- A German education client used memory to map learners and transfer knowledge from strong to weak students.
- Cognee profiled users and connected those in the same class to route helpful content automatically.
Construction Firm Unified Supply Names
- A Singapore construction firm used memory to unify supplier names across projects and track materials end-to-end.
- That reduced delays and enabled just-in-time ordering by exposing the true supply chain flow.
