From Data Models to Mind Models: Designing AI Memory at Scale
About this episode
Vasilije Markovich discusses the design and implications of agentic memory in AI systems.
Summary In this episode of the Data Engineering Podcast, Vasilije "Vas" Markovich, founder of Cognee, discusses building agentic memory, a crucial aspect of artificial intelligence that enables systems to learn, adapt, and retain knowledge over time. He explains the concept of agentic memory, highlighting the importance of distinguishing between permanent and session memory, graph+vector layers, latency trade-offs, and multi-tenant isolation to ensure safe knowledge sharing or protection. The conversation covers practical considerations such as storage choices (Redis, Qdrant, LanceDB, Neo4j), metadata design, temporal relevance and decay, and emerging research areas like trace-based scoring and reinforcement learning for improving retrieval. Vas shares real-world examples of agentic memory in action, including applications in pharma hypothesis discovery, logistics control towers, and cybersecurity feeds, as well as scenarios where simpler approaches may suffice. He also offers guidance on when to add memory, pitfalls to avoid (naive summarization, uncontrolled fine-tuning), human-in-the-loop realities, and Cognee's future plans: revamped session/long-term stores…
More episodes of Data Engineering Podcast
- The AI-First Data Engineer: 10–50x Productivity and What Changes Next
- Treat Metering Like Finance: Building Data Platforms for Consumption Economics
- Beyond the PDF: Rowan Cockett on Reproducible, Composable Science
- Beyond Prompts: Practical Paths to Self‑Improving AI
- Orion at Gravity: Trustworthy AI Analysts for the Enterprise
- From Models to Momentum: Uniting Architects and Engineers with ER/Studio
Explore listener stats, chart rankings, contacts and more on the Data Engineering Podcast podcast page.