To build an effective A.I. agent, getting its memory right is essential. In today's episode, our agent-memory guide is brilliant (and very funny!) machine-learning architect and engineer, Richmond Alake.
More on Richmond:
• Director of A.I. developer experience at Oracle.
• Previously roles include: staff developer advocate for AI/ML at MongoDB, ML architect at Slalom, writer for NVIDIA and computer-vision engineer at Loveshark.
• Holds a master's in ML and robotics from the University of Surrey.
In this episode, Richmond magnificently covers:
• How agent memory is the encapsulation of systems (embedding models, rerankers, databases, and LLMs) that allow AI agents to learn and adapt with new information over time, rather than starting from scratch every session.
• The four types of agent memory (all drawn from human cognition).
• Memory-first agent harnesses.
• Predictions for a flattening of AI engineering roles, where the future developer will need end-to-end understanding of the full agent stack.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Filtering by Category: Interview
Building AI Agents Where 99.9% Accuracy Isn't Good Enough, with Raju Malhotra
The headlines shout “SaaSpocalypse,” but I don’t buy it. Neither does my guest today, Raju Malhotra, who argues that, thanks to humans collaborating with agents on optimized workflows, the SaaS opportunity is now far bigger than ever before.
More on Raju:
Chief Product & Technology Officer (CPTO) at Certinia, an Austin, Texas-based company whose Professional Services Automation software is used by over 1400 organizations around the world.
Was previously CPTO at PAR Technology and Khoros.
Earlier, spent 12 years at Microsoft working on cornerstone products like Visual Studio .NET.
Holds an MBA from The Wharton School and an undergrad in computer engineering.
In this episode, we cover:
Traditional SaaS isn't dead… instead, it's evolving into a hybrid of SaaS plus agentic capabilities, where humans and agents work together in optimized workflows.
By removing the human-skills constraint from professional services delivery, the agentic revolution could expand the addressable market by 7-8X.
The Agentforce 360 platform (by combining probabilistic AI with deterministic logic and guardrails) empowers innovators to turn their ideas into scalable software businesses, allowing businesses like Certinia to bring AI agents securely and reliably to their customers, even in sensitive industries where 0.1% error rates are unacceptable.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
AI in the Classroom: How a Top Elementary School Is Doing It Right, with Principal Traci Walker Griffith
Long overdue episode today on how A.I. can support children's education. Hard to imagine a better guest than Traci Walker Griffith, principal of a K-8 school that has used innovations like A.I. to become Boston's #1 school.
In this episode, we discuss:
How Traci transformed The Eliot School from an underperforming school on the closure list into the highest-performing school in Boston.
How kids as young as four at the Elliott work with robots and coding tools like Kibo and Scratch Junior, learning that the quality of their input determines the quality of their output ("garbage in, garbage out").
How, for younger students in kindergarten through fourth grade, teachers use A.I. behind the scenes.
How students in grades five through eight interact with A.I. directly, enabling them to build metacognition and critical-thinking skills.
Her concrete guidance for schools (or parents!) considering incorporating A.I. into pedagogy.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
In Case You Missed It in March 2026
It just keeps getting better and better... ICYMI, my on-air conversations with guests in March were extraordinary. Today's episode highlights the best bits from last month, specifically:
Zack Kass (who was head of go-to-market at OpenAI when ChatGPT was launched and who recently wrote bestselling book "The Next RenAIssance") details why classrooms must change in the age of A.I.
Renowned New York University professor KyungHyun Cho explains why A.I. learning to explore the world like humans will unlock major progress in A.I. capability.
Three-time bestselling O'Reilly author Chris Fregly tells us why, if we're still writing code manually in 2026, we're behind the times.
Fireworks AI CEO Lin Qiao explains the difference between artificial general intelligence (AGI) and what she terms "autonomous intelligence".
Acceldata CEO Rohit Choudhary provides a clear vision for how job roles will be transformed by A.I.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
How Data Engineers Are “10x’ing” Themselves With Agents, feat. Matt Glickman
Something big happened in February that changed the world forever. My guest today, Matthew J. Glickman, says code-generating models crossed an event horizon... and there's no turning back. Listen in for the implications.
More on Matt:
Co-founder and CEO of Genesis Computing, a New York-based company building enterprise-ready data agents that automate everything from raw data to production applications, compressing projects that took months into hours while recovering massive hiring costs.
Previously spent over two decades at Goldman Sachs leading analytics and data platform teams, then joined Snowflake as employee 81, where he led Product Management, launched the Snowflake Marketplace, and grew Financial Services into Snowflake’s largest industry vertical.
Holds a degree in Computer Science and Math.
In this episode, which will be fascinating to anyone but especially to hands-on A.I. and data practitioners, we discuss:
How February 2026 marked the moment the latest frontier models crossed a threshold where they could handle complex, multi-step data engineering workflows that previously required human expertise... and there's no going back.
How finance and healthcare were late to adopt the cloud but are among the earliest and most aggressive adopters of A.I.
How Genesis deploys its agentic platform directly inside a client's environment (more like onboarding a new employee than adopting a SaaS product) so that all accumulated knowledge remains the company's asset.
How, rather than acting as a copilot that waits for human instructions step by step, Genesis inverts the model: Agents work autonomously on complex data engineering tasks and only escalate to humans when their confidence is low, memorializing every answer so they never ask the same question twice.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Attention, World Models and the Future of AI, with Prof. Kyunghyun Cho
What's going to be the next big step function in A.I.? To find out, I saw down with Prof. KyungHyun Cho, who's 200,000 citations put him among the most influential A.I. researchers in the world... and he's a delight to listen to!
In case you aren't already aware of KyungHyun:
Iconic New York University professor of computer science and data science.
Co-directs the Global A.I. Frontier Lab alongside Yann LeCun.
Regularly keynotes at the most prestigious academic A.I. conferences (including being a keynote at NeurIPS 2025).
Was a postdoc under Yoshua Bengio at the Université de Montréal, where they coauthored a paper introducing attention for neural networks, a technique that is ubiquitous within the transformer-based LLMs that enable most A.I. capabilities today.
Lots of other hugely influential papers on deep recurrent neural networks, neural machine translation, visual attention, speech recognition and multivariate time-series modeling.
In today's episode, which will be of particular interest to hands-on A.I. practitioners, KyungHyun eloquently discusses:
The human story behind the invention of attention.
World models.
Why today’s models have already captured most correlations in passive data, making the real challenge about actively choosing which data to collect.
Whether A.I. needs high-fidelity, step-by-step imagination or whether a high-level latent representation that lets it skip ahead is sufficient.
How he's adapting computer-science and A.I. education at the university level now that such capable code-generating agents exist.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Unmetered Intelligence is Heralding the Next Renaissance, with Zack Kass
Today's episode is one of my fave convos ever. Based on his new bestseller, Zack Kass makes a clear case for why cheap abundant intelligence is heralding the next Renaissance — the greatest period for humans yet.
More on Zack:
Was head of go-to-market at OpenAI from 2021 to 2023, including during the initial public launch of ChatGPT.
Advises Fortune 1000 board rooms, including Coca-Cola, Morgan Stanley and Amgen.
His book, "The Next Renaissance: A.I. and the Expansion of Human Potential", went on sale recently and is already a national bestseller. In it, he argues that A.I. will provide the greatest leap in human history.
Today's episode should be of great interest to any listener. In it, we discuss:
How to actively counter tech pessimism.
Ways AI can transform education for the better.
The "intellectual K-curve" that empowers motivated learners.
His four principles for thriving in the age of A.I.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
AI Systems Performance Engineering, with Chris Fregly
Chris Fregly spent $6000 at Starbucks writing a 1000-page book Nvidia's own docs couldn't provide. In today's episode, the three-time bestselling author reveals all, updating everything you know about engineering A.I. systems.
More on Chris if you don't know him already:
Long-time A.I. systems performance specialist at Amazon Web Services (AWS), where he, for example, pioneered the design and launch of SageMaker and Bedrock.
Was Chief Product Officer at PipelineAI (acquired by AWS).
Previously held Principal Engineer roles at Databricks and Netflix (earning him an Emmy)!
Was an investor/advisor in xAI (acquired by SpaceX) and Groq (acquired by NVIDIA).
Three-time author of O'Reilly books.
His latest book, "A.I. Systems Performance Engineering" is a thousand-page tome that was published in December and has received rave reviews so far.
Today's episode will appeal primarily to hands-on A.I. practitioners like A.I. engineers, data scientists and software developers. You'll learn a ton about GPUs and getting the best performance from them!
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
The Laws of Thought: The Math of Minds and Machines, with Prof. Tom Griffiths
Based on his latest bestseller "The Laws of Thought," today's fascinating episode with Princeton professor Tom Griffiths digs into mathematical models of both biological and artificial intelligence.
More on extraordinary Tom:
• Professor at Princeton University in both the Departments of Computer Science and Psychology.
• Directs Princeton's Computational Cognitive Science Lab (research group focused on understanding the mathematical foundations of human cognition) as well as the Princeton Laboratory for Artificial Intelligence (a new effort that supports innovative research efforts in A.I. and related fields).
• Co-author of the megabestselling book "Algorithms to Live By" (2016) and author of the sensational new book "The Laws of Thought."
• His award-winning research has been published in venues that include the prestigious journals Science and Nature.
In this episode, which will appeal to anyone interested in human intelligence or A.I., Professor Griffiths details how the mathematical principles governing the external world can also be used to explore cognitive science, or “the internal world.”
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
AI for the Physical World, with Samsara's Praveen Murugesan
Samsara processes 20 trillion (!!) data points for physical applications (e.g., construction, transport, manufacturing). Today, their VP Engineering Praveen Murugesan details how they make A.I. impactful on this vast scale.
More on Praveen:
As Vice President of Engineering at Samsara, leads the development and strategy for products that transform IoT data into automations and insights.
Previously worked at Uber, Salesforce, VMware, Cisco and more.
Active angel investor.
Holds an MS from Carnegie Mellon University.
More on Samsara:
Publicly-listed on the New York Stock Exchange.
Recently named one of Fast Company’s Most Innovative Companies.
Ranked #7 on the Fortune "Future 50".
Today's episode will particularly appeal to folks who build A.I. systems hands-on, but will be interesting to anyone keen to understand how A.I. can be developed and deployed to make a huge impact at scale in real-world, physical applications, including on edge devices.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
From PhD Side Project to $500M ARR: Will Falcon’s PyTorch Lightning Story
How did William Falcon grow a PhD side project into an open-source phenomenon with nearly 400 million downloads and a startup with over $500m (🤯) in ARR? Find out in today's episode!
In case you're not already familiar with Will, he's:
Creator of PyTorch Lightning (open-source framework for rapidly training and deploying A.I. models that has been downloaded nearly 400 million times).
Founder and CEO of Lightning AI.
Pursued PhD at New York University under Yann LeCun and KyungHyun Cho focused on biologically inspired deep learning and reinforcement learning techniques, involving pre-training models on 4,000+ GPUs.
Former U.S. Navy officer in SEAL training pipeline.
More on Lightning AI:
The only fullstack A.I. neocloud for enterprises and frontier labs.
$500m in ARR in under two years (hence the head-exploding emoji above!)
3rd largest neocloud by GPUs (35,000+).
Serves 400,000+ developers and companies (e.g., Cursor, Cisco, Reflection AI).
This episode will especially appeal to hands-on practitioners like software engineers and data scientists but Will's fascinating story will be of interest to anyone involved in A.I.
And note that I hold a fellowship at Lightning AI so I am not an unbiased interviewer in this episode :)
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
In Case You Missed It in January 2026
January flew by for me... how 'bout you? ICYMI, today's episode of my podcast features the best parts of my conversations with my January guests:
1. Wharton professor and bestselling author of "Co-Intelligence" Ethan Mollick addresses how both individuals and companies can benefit from workers being upfront about their use of A.I.
2. Sadie St Lawrence — renowned data-science instructor, author and CEO of HMCI.AI — details why enterprise agents were her biggest disappointment of 2025.
3. Vijoy Pandey, the head of Cisco's incubation engine Outshift, introduces "distributed artificial superintelligence".
4. Famed O'Reilly instructor, many-time bestselling author and A.I. entrepreneur Sinan Ozdemir explains that finding a common language for A.I. evaluative frameworks will be crucial to their success.
5. Ashwin Rajeeva, co-founder and CTO of Acceldata (a Bay Area A.I. startup that has raised over $100m in venture capital), talked to me about how to find and keep the best developers and data scientists in their jobs.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Reinforcement Learning for Agents, with Amazon AGI Labs’ Antje Barth
In today's excellent episode, renowned technical author Antje Barth reveals how Amazon's prestigious "AGI Labs" are using Reinforcement Learning to make A.I. agents vastly more reliable.
In case you don't already know brilliant Antje:
Member of Technical Staff at Amazon AGI Labs, where she is responsible for bridging cutting-edge AI research with the global developer community.
Over 400,000 students have taken her "Generative A.I. with LLMs" course via DeepLearning.AI.
Multi-time bestselling author of O'Reilly books ("Generative A.I. on AWS" and "Data Science on AWS").
Holds a Diploma (equivalent to an undergraduate degree) in Computer Science from the University of Tübingen in Germany.
In this episode, which will be particularly appealing to hands-on practitioners but can be enjoyed by any interested listener, Antje covers:
"Nova Act", Amazon's new service for building reliable A.I. agents (available free to prototype with now).
How Nova Act achieves over 90% reliability by training on reinforcement learning "web gyms".
The future of agents, including multi-agent collaboration with humans.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Wharton Prof Ethan Mollick on Why Your AI Strategy Is Already Obsolete
Ethan Mollick is (no hyperbole!) one of the world's most sought-after A.I. experts. Don't miss this: In today's episode, the Wharton prof provides his most impactful A.I. strategies for enterprises.
In case you don't already know Ethan:
Distinguished Faculty Scholar and Associate Professor at The Wharton School of the University of Pennsylvania.
Co-Director of the Generative AI Labs at Wharton.
Studies the effects of A.I. on work, entrepreneurship and education.
Recent book, "Co-Intelligence", was a New York Times bestseller.
One of TIME’s Most Influential People in Artificial Intelligence.
Holds a PhD and an MBA from the MIT Sloan School of Management of Management and his bachelor’s degree from Harvard University.
Today's episode is so information-dense, you very well may need to slow down your player’s playback speed to make the most of it! It can be enjoyed by anyone looking to get ahead of the game on impactful A.I. deployments.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
In Case You Missed It in December 2025
Wow, the guests we had on my podcast last month! I laughed a lot and learned even more from these luminaries. ICYMI, today's episode features the best parts of my conversations with them:
Dell Technologies' global CTO and Chief A.I. Officer John Roese returned to the show to explain how to get a 10x return on your investment in an enterprise A.I. project.
Software engineer and Modern CTO host Joel Beasley describes how he uses A.I. to dramatically accelerate his stand-up comedy career.
"The Fit Data Scientist" Penelope Lafeuille details how she used A.I. to help her recover from work fatigue and put her on the path to a much more rewarding career.
Netflix senior data scientist Jeffrey Li explains the application and interview process behind his success winning roles at tech giants like Netflix, Spotify and DoorDash.
Stanford University professor Alex 'Sandy' Pentland on why the Soviet Union fell apart because of A.I... and how we're repeating some of their mistakes today.
Dropbox VP of Engineering Josh Clemm talks us through a sure way to ensure we get A.I. slop everywhere in our organization :)
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Building Agents 101: Design Patterns, Evals and Optimization (with Sinan Ozdemir)
Want to be building and deploying agentic A.I., but don’t know where to start? Distilling the best bits of Sinan Ozdemir's latest book, today’s episode is an intro “101” course on everything you need to know!
Sinan’s latest book is his TENTH book and it’s called “Building Agentic AI”. It’s a hands-on book (in Python) and one of the first books in Pearson's "Jon Krohn A.I. Signature Series". It covers everything you need to know to design, fine-tune, optimize and deploy agentic systems effectively… and today’s episode distills all of the most valuable tips and tricks from the book into a fun, hour-long conversation, including:
What exactly is an A.I. agent?
Should you use an agent or a workflow to automate a given task?
What LLM should you select for your agentic task?
How can you evaluate your agent's performance?
In case you don't already know Sinan:
As mentioned above, a TEN-TIME author of bestselling technical books.
A top A.I. educator and content creator with Pearson (often within the O'Reilly platform), transforming the way people learn about and engage with LLMs.
Provides advisory services on A.I. to VCs, publicly-traded companies and startups alike.
Holds Master's in Pure Mathematics from The Johns Hopkins University where he also lectured on A.I.
Founded one of the first Generative A.I. startups to go through Y Combinator, patenting the concept of tool use with agents in 2018.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
How AI Agents Are Automating Enterprise Data Operations, with Ashwin Rajeeva
Acceldata has raised over $100m to bring you self-healing data pipelines. Today, brilliant co-founder/CTO Ashwin Rajeeva explains how they detect errors, rewrite code and redeploy... all fully automatically!
Ashwin’s outstanding communication on this meaty technical topic, involving autonomous ("agentic") scouring over petabytes of enterprise data, makes for a tremendous episode that will probably appeal most to hands-on practitioners like software engineers and data scientists.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
From Agent Demo to Enterprise Product (with Ease!) feat. Salesforce’s Tyler Carlson
Building AI agents is easy... but only for demos. Getting agents from prototype to enterprise-grade production, that's tricky. Or, it was! ...Until today's guest, Tyler Carlson, helped open up Salesforce's new Agentforce 360 platform for entrepreneurs to build upon, customize and monetize. hashtag#ad
Tyler:
• SVP, Head of Product for AppExchange & Ecosystem at Salesforce, where he's been for nearly a decade.
• Focused on delivering a modern AI marketplace that allows folks to discover and install apps, integrations, agents and agent components from Salesforce’s open ecosystem.
• Holds a degree in math from UC Santa Barbara.
We partnered with Salesforce on this episode to announce the launch of the Agentforce 360 platform for businesses, which provides an easy way to white-label commercial AI agents and applications.
This episode will be of interest to hands-on AI practitioners (e.g., data scientists, software developers, AI engineers) as well as anyone who'd like to understand the challenges of deploying enterprise-grade agents and solutions.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Nested Learning, Spatial Intelligence and the AI Trends of 2026, with Sadie St. Lawrence
The same level of A.I. capability that cost you $100 a year ago now costs ONE dollar. Such radically cheap intelligence changes everything about work and society; today, Sadie St Lawrence explains how!
For the fifth year in a row, we’re kicking the year off by welcoming the inimitable Sadie to the show to:
Predict the five biggest trends in A.I. for 2026, including nested learning, spatial intelligence and AiOps.
Recap how she did on her predictions for 2025.
Bestow four awards for 2025 (biggest “wow” moment, comeback of the year, disappointment of the year, and overall winner).
Get a glimpse at the year ahead, in which intelligence will be vastly cheaper than ever before... transforming work and play for all of us.
📚 Her brand-new book, "Becoming an AI Orchestrator", guides readers to work creatively and confidently alongside intelligent machines. It is part "Jon Krohn's A.I. Signature Series" published by Pearson.
More on Sadie:
Founder and CEO of HMCI.AI, optimizing human-A.I. collaboration in the knowledge economy (amplified by an ecosystem partnership with NVIDIA).
Founded Women In Data™️, a global non-profit spanning 55 countries and empowering 70,000+ data professionals; it earned Top 50 Non-Profit status and was named the premier Women in A.I. & Tech community in 2021.
Named among DataIQ’s Top 100 Most Influential People in Data & A.I. and Dataleum’s Top 30 Women in A.I.
Has educated over 700,000 learners through courses with University of California, Davis, Coursera, and LinkedIn Learning.
This episode can be enjoyed by technical and non-technical folks alike.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.
Beyond “Agent Washing”: AI Systems That Actually Deliver ROI, with Dell’s Global CTO John Roese
Today's blockbuster episode (on MCP, agent-to-agent protocols, getting an ROI on A.I. investment, and more) stars a blockbuster guest: Dell's global CTO and Chief A.I. Officer John Roese.
Last year, John helped Dell Technologies' revenue grow by $10 billion dollars while A.I. helped costs go DOWN. That decoupling of revenue and cost had not happened in Dell's 41-year history but now, thanks to A.I., it has and John tells us exactly how they did it... so you can too!
This is an exceptional episode that can be enjoyed by technical and non-technical folks alike.
The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.