985: The Four Types of Memory Every AI Agent Needs, with Richmond Alake

985: The Four Types of Memory Every AI Agent Needs, with Richmond Alake

Author: Jon Krohn April 21, 2026 Duration: 1:04:29
Oracle’s Director of AI Developer Experience Richmond Alake returns to the show to talk to Jon Krohn about agent memory; the network of systems, models, databases and LLMs that enable AI agents to learn and adapt over time. Listen to the episode to hear about Richmond’s “100 Days of Agent Memory” initiative, retrieval-augmented generation’s (RAG) limitations with AI agents, the layers of the AI agent stack, and what makes the Oracle AI database so useful to developers. Additional materials: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠www.superdatascience.com/985⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information. In this episode you will learn: (03:15) What agent memory is and why it’s important (28:28) RAG’s limitations for AI agents  (35:19) What matters in the AI agent stack beyond memory (41:34) Why memory was undervalued in the AI agent stack

Hosted by Dr. Jon Krohn, Super Data Science: ML & AI Podcast with Jon Krohn is a deep and accessible exploration of how artificial intelligence and machine learning are reshaping our world. Each episode features conversations with leading researchers, engineers, and entrepreneurs from both academia and industry, breaking down complex ideas into something tangible and relevant. You'll hear firsthand about emerging techniques, practical applications, and the evolving landscape of data-driven careers. The sheer volume of data in our world is growing at a staggering rate, and this podcast serves as a guide to understanding that expansion and finding your place within it. Rather than offering abstract theory, these discussions focus on real-world impact, from cutting-edge algorithms to the human stories behind major breakthroughs. Tune in for a thoughtful, nuanced look at the tools and trends that are defining the future, all through the lens of experts who are building that future every day. Whether you're actively working in the field or simply curious about the forces driving technological change, this podcast provides a consistent source of insight and inspiration, demystifying the science that is quietly transforming every aspect of our lives.
Author: Language: English Episodes: 100

Super Data Science: ML & AI Podcast with Jon Krohn
Podcast Episodes
924: 95% of Enterprise AI Projects Fail (Per MIT Research) [not-audio_url] [/not-audio_url]

Duration: 5:27
MIT lab NANDA (“Networked AI Agents in Decentralized Architecture”) reveals less than promising results for the future of AI adoption in businesses. According to “The GenAI Divide: State of AI in Business 2025”, a whoppi…
922: AI for Manufacturing and Industry, with Hugo Dozois-Caouette [not-audio_url] [/not-audio_url]

Duration: 28:29
Hugo Dozois-Caouette speaks to Jon Krohn about his startup MaintainX and how he secured $254 million in venture capital, reaching a $2.5 billion valuation. MaintainX builds computerized maintenance management systems (CM…
920: In Case You Missed It in August 2025 [not-audio_url] [/not-audio_url]

Duration: 21:57
This month’s episode of In Case You Missed It gives us reasons to be cautiously optimistic about the future of large language models (LLMs), with guests discussing what to do about recent reports that found AI agents bla…
918: Multi-Agent Systems with CrewAI [not-audio_url] [/not-audio_url]

Duration: 9:16
In this Five-Minute Friday, Jon Krohn introduces listeners to CrewAI, an open-source Python framework that can create and manage multi-agent teams. The clue is in the title: CrewAI assembles specialized agents into singl…
917: 8 Steps to Becoming an AI Engineer, with Kirill Eremenko [not-audio_url] [/not-audio_url]

Duration: 1:15:33
Founder of SuperDataScience, Kirill Eremenko, talks to Jon Krohn about how he found the best tools and approaches to help launch his 8-week AI engineering bootcamp. He breaks down the topics participants cover each week,…
916: The 5 Key GPT-5 Takeaways [not-audio_url] [/not-audio_url]

Duration: 9:40
GPT-5 has just been released, but with not very much fanfare. In this Five-Minute Friday, Jon Krohn asks if GPT-5 deserves the community’s underwhelmed response to its release. He outlines five features of the model and…