# From Data Models to Mind Models: Designing AI Memory at Scale

Page: https://stenobird.com/podcast/data-engineering-podcast/from-data-models-to-mind-models-designing-ai-memory-at-scale
Text version: https://stenobird.com/podcast/data-engineering-podcast/from-data-models-to-mind-models-designing-ai-memory-at-scale.md
Podcast: [Data Engineering Podcast](https://stenobird.com/podcast/data-engineering-podcast)
Published: 2026-02-22T23:12:36+00:00
Episode link: https://www.dataengineeringpodcast.com/agentic-memory-design-and-application-episode-502
Audio file: https://op3.dev/e/dts.podtrac.com/redirect.mp3/serve.podhome.fm/episode/f6ff0caa-931b-4c08-bfdd-08dc7f5cd336/639073981323893202146bcc19-cf93-4fa2-9e96-70bb5d041afc.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/data-engineering-podcast/episodes/from-data-models-to-mind-models-designing-ai-memory-at-scale
Duration seconds: 3467

## Resource

Designing AI memory requires moving beyond simple vector stores to a multi-layered architecture of graph and vector layers. This discussion explores how to implement agentic memory that distinguishes between session and long-term state while maintaining multi-tenant isolation.

## Highlights
- Main idea: Agentic memory must differentiate between short-term session state and long-term persistent knowledge
- Practical takeaway: Use a hybrid graph and vector approach to enable complex relationship retrieval and temporal searching
- Failure mode: Avoid naive summarization or uncontrolled fine-tuning as substitutes for structured memory systems
- Security insight: Implement physical isolation and multi-tenancy to prevent agents from accessing unauthorized data silos
- Future trend: The emergence of 'pseudo-languages' or structured SQL-like commands for more efficient multi-agent communication

## Topics

Agentic Memory, Vector Databases, Graph Databases, Multi-tenancy, Cognitive Science, AI Infrastructure, Knowledge Engineering, LLM Orchestration

## Chapters
- 1:00 — Introduction to Knowledge Engineering: Vasilije Markovic discusses his transition from data engineering to cognitive science and the inspiration for building memory engines.
- 5:30 — Defining Agentic State: The necessity of providing agents with a state representation to allow for continuity and data exchange across sessions.
- 10:00 — Long-term vs. Session Memory: Exploring use cases for persistent memory, such as maintaining user profiles and breaking down data silos.
- 18:30 — Optimizing Embedding Retrieval: Technical considerations for optimizing embeddings and managing large-scale retrieval for agentic workloads.
- 23:10 — Temporal Relevance and Decay: How to model the temporal aspect of memory and handle information that becomes outdated over time.
- 27:20 — Advanced Search Architectures: Implementing multi-modal search across graph and vector stores to find temporal and relational data.
- 31:30 — Multi-tenancy and Security: Architecting isolated memory stores to ensure agents cannot cross-contaminate or access sensitive company data.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/data-engineering-podcast/episodes/from-data-models-to-mind-models-designing-ai-memory-at-scale/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/data-engineering-podcast/from-data-models-to-mind-models-designing-ai-memory-at-scale.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.