Agentic AI Hands-On in Python: MCP, CrewAI and OpenAI Agents SDK (by Jon Krohn and Ed Donner)

Now live! Four hours long and 100% free, this hands-on workshop covers all the Agentic A.I. theory and tools you need to develop and deploy multi-agent teams with Python.

Beautifully shot by a professional film crew (led by the exceptional Lucie McCormick) at the Open Data Science Conference (ODSC) East in Boston a few weeks ago and then meticulously edited by SuperDataScience's inimitable Mario Pombo, this training (within the GenAI-forward Cursor IDE) features all of today's essential agent frameworks:

• OpenAI Agents SDK

• CrewAI

• Anthropic's Model Context Protocol (MCP)

From design considerations through to practical implementation tips, by completing all four modules in this video, you will have all the knowledge and skills needed to create effective multi-agent systems. The four modules are:

1. Defining Agents

2. Designing Agents

3. Developing Agents

4. The Future of Agents

The coding elements are led by the wonderful Ed Donner, whom many of you will already know as one of the very best in the world at creating and teaching hands-on A.I. content.

We received rave reviews for the session at ODSC East and the lecture hall was standing-room only for the entire duration, so I anticipate that you'll love it too!

Watch the full training here: youtu.be/LSk5KaEGVk4

The Future of Enterprise AI: Investor Shaun Johnson Reveals What Actually Works

What are the biggest opportunities for A.I. startups? Find out in today's episode with the trailblazing venture capitalist Shaun Johnson, including tricks for gaining enterprise A.I. adoption.

Shaun:

• Co-founder and general partner at AIX Ventures in San Francisco, where he’s led deals into companies including Perplexity, Chroma, and Workhelix.

• He is a former VP of Engineering, Product and Design at Lilt; and a former VP of Product and Design at NimbleRx.

• Holds a Master’s in Electrical Engineering from Stanford University and an MBA from the University of California, Berkeley.

Today’s episode is well-suited to any listener to this podcast. In it, Shaun details:

How having investment partners like Richard Socher and Christopher Manning, who are practitioners actively building at the cutting edge of A.I., gives AIX Ventures an edge.

• What it takes to become one of the few thousand people in the world pushing the A.I. frontier.

• The surprising strategy that makes enterprise A.I. adoption 10x easier.

• Why some A.I. startups are better off building in 'red oceans' full of competition rather than seeking blue-ocean opportunities.

• The reason big tech companies are buying A.I. talent without acquiring the actual startups.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

In Case You Missed It in May 2025

We had stellar guests in May, including one episode that had the most positive social-media response of any episode ever. In today's "In Case You Missed It" episode, hear the best parts of all my May convos.

The specific conversation highlights included in today's episode are:

1. John Roese, Dell Technologies' global CTO and Chief A.I. Officer, on the biggest A.I. opportunities for enterprises in the coming months/years. (This is the episode that received an unprecedented social-media response.)

2. The authors of the brand-new O'Reilly book "Python Polars: The Definitive Guide", Jeroen Janssens and Thijs Nieuwdorp, on a real-world Polars success story.

3. Space engineer and entrepreneur Mary Spio on solving global talent shortages with A.I.-infused virtual reality hardware.

4. Martin Brunthaler, serial entrepreneur/CTO, on how platforms like Adverity allow you to talk with your data in natural language.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

How to Jumpstart Your Data Career (by Applying Like a Scientist), with Avery Smith

Today's fun episode with superstar Avery Smith (>140k LinkedIn and >40k YouTube subscribers) is for folks looking to jumpstart their data career — either landing your first data role or advancing your career. Enjoy!

Avery:

• Is the creator of Data Career Jumpstart — a platform to help working professionals break into, well, data careers (like data analyst or data scientist roles).

• Hosts the popular Data Career Podcast.

• Runs Snow Data Science, an analytics and data-solutions consultancy with clients including the Utah Jazz 🏀

• Previously held data scientist roles at ExxonMobil and Vaporsens.

• Holds a Master’s in Data Analytics from Georgia Tech.

Today’s episode contains helpful tips for anyone looking to advance their career but is particularly intended for listeners who are seeking their first role working with data.

In today’s episode, Avery details:

How spilling acid on himself led him to becoming a data professional.

• His "Every Turtle Swims Past" learning ladder for breaking into data careers.

• What’s even more important than skills or experience for landing a job.

• How one of his bootcamp students went from delivery driver to data analyst by AB testing her text messages.

• Which job boards are killing your data career applications.

• Why GitHub is not a portfolio, but what you can use instead.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Conversational AI is Overhauling Data Analytics, with Martin Brunthaler

Fascinating new episode for you from serial entrepreneur/CTO Martin Brunthaler on how GenAI and Agentic A.I. are transforming data analytics today... and how analytics will continue to evolve in the coming years.

Martin Brunthaler:

• CTO of Adverity, an Austrian data analytics platform he co-founded a decade ago and that has since raised over $160m in venture capital.

• Before Adverity, Martin was co-founder and CTO at two other European tech start-ups, giving him over 20 years of combined experience in starting, scaling and exiting companies across multiple industries including eCommerce, media and mobile.

• Holds an engineering diploma (equivalent to a Bachelor's degree) from the Salzburg University of Applied Sciences in Austria.

Today’s episode should be of interest to just about anyone who’d be interested in this podcast because it touches on data analytics, transforming user experiences with modern AI capabilities and growing tech businesses.

In today’s episode, Martin details:

How a childhood fascination with computer programming evolved into founding a globally leading platform for marketing data analytics.

• What "data democratization" really means and how the traditional dashboard-based approach to data reporting is failing businesses.

• Why data analysts are spending too much time on "busy work" instead of delivering business value.

• How conversational AI is overhauling how data insights are gleaned for hands-on data practitioners and business users alike.

• His no-nonsense tips for tech startup success.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Celebrating 5 Years with ODSC: An Award, A Workshop, and What’s Ahead

Last week in Boston, the Open Data Science Conference (ODSC) surprised me with their "Speaker Impact Award" to recognize the years of training I've been providing at ODSC conferences.

Thank you Sheamus McGovern (pictured) and the whole ODSC team (Alex, Alina, Anna, Deepti, Elen, Paula, Ruby) for the honor and for putting on such stellar technical conferences.

I first lectured at ODSC New York in June 2019, when I provided a half-day workshop that introduced Deep Learning. (By great chance, the now-legendary Serg Masís emceed my session!)

Since then, I've enjoyed both ODSC East (held each spring in Boston) and ODSC West (held each autumn in San Francisco) most years, delivering (typically full-day) workshops on:

• Deep Learning

• The mathematical foundations of Machine Learning (e.g., linear algebra, partial-derivative calculus)

• Training and deploying Large Language Models (with Lightning AI and Hugging Face)

This year at ODSC East, Ed Donner and I delivered a full-day training on developing and deploying Agentic A.I. featuring the open-source tools CrewAI, OpenAI Agents SDK, and Anthropic's Model Context Protocol (MCP). The session was jam-packed for the entire day and received rave reviews.

If you couldn't make it to Boston last week, I have good news for you! I hired a film crew to capture our entire Agentic A.I. training and am currently having the footage professionally edited. In the coming weeks (as soon as possible!), we'll be publishing this on YouTube so that it's freely available to everyone worldwide. Watch this space :)

AI-Powered Virtual Reality: The Future of Education and Entertainment, with Mary Spio

In today's episode, the deep-space engineer and visionary entrepreneur Mary Spio takes us on a journey into the A.I.-powered virtual reality that is transforming education, entertainment and more.

Mary:

• Is CEO and CTO of CEEK INC, a platform pioneering A.I.-powered virtual-reality experiences featuring the likes of Lady Gaga, Bon Jovi and Dwayne Wade.

• Holds 10+ patents across A.I., digital cinema, spatial audio, and extended-reality technologies.

• Was a deep space engineer at Boeing and, before ever even going to university, was a satellite technician for the US Air Force.

• Her innovations have been used by Xbox, Lucasfilm, and Universal Music Group.

• Holds a Masters in Electrical Engineering, Computer Science and Innovation Management from the Georgia Institute of Technology.

• Today’s episode is fascinating and relatively high-level and should be of interest to any listener.

In today’s episode, Mary details:

• How a childhood in Ghana during a military coup led to a career as a deep space engineer and A.I. entrepreneur.

• The neuroscience of how VR training can create memories that are indistinguishable from reality in your brain.

• The shocking discovery about why VR headsets were making women violently ill (and how Mary fixed it).

• How A.I. music is revolutionizing the industry and giving artists unexpected new powers.

• How blockchain verification might be our only defense against an impending tsunami of A.I.-generated deepfakes.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Teams of Agents: The Next Frontier in AI Collaboration, with Mike Pell

Special episode for you today (filmed in front of a live audience!) with the inventor and exceptional communicator, Mike Pell. Hear his vision for the way teams of A.I. agents will change work and life for the better.

Today’s episode features a session I hosted a couple weeks ago in Brooklyn at the inaugural "A.I. & Creativity Summit", which was run by Artist and the Machine. It was an excellent full-day event on a gloriously sunny day.

My guest for an on-stage conversation in front of a live audience was the extraordinary Mike Pell:

• Inventor of the PDF and Adobe Acrobat.

• Director of The Microsoft Garage, a global innovation program.

• Holds over 20 US Patents.

• Author of three books.

Today’s episode is entertaining, optimistic and forward-looking and will be of interest to any listener of my podcast.

In the episode, Mike details:

• Why A.I. agents are like an exoskeleton that gives you capabilities you never had time to master.

• The coming shift from passive to proactive A.I. that will interject like a trusted coworker.

• Why he believes we're "getting to the good part" in the A.I. revolution and what that means for the future of work.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Multi-Agent Teams, Quantum Computing and the Future of Work, with Dell’s Global CTO John Roese

Collosal guest today: Dell's global CTO and Chief A.I. Officer John Roese, who eloquently describes mind-blowingly fascinating topics including multi-agent teams in enterprises and quantum computing.

John Roese:

• Is Global CTO and Chief A.I. Officer at Dell Technologies, the giant Texas-based corporation with over 100,000 employees and $88 billion dollars of revenue in 2024.

• Responsible for Dell’s future-looking technology strategy and accelerating A.I. adoption for Dell and its customers.

• With an unreal career stretching back several decades, he was previously Global CTO at EMC, Global CTO at Nortel and CTO at Broadcom, amongst many other top roles at world-leading tech companies, board memberships and deep involvement with the private equity and venture capital ecosystems.

• Holds a degree in Electrical and Computer Engineering from the University of New Hampshire.

Despite John being such a deep technical expert, today’s episode stays relatively high level and so should be of great value to any listener.

In today’s episode, John details:

How Dell narrowed 800 generative A.I. ideas down to 8 high-impact projects.

• Proof-of-Concept Prison and his strategy for escaping it.

• Where multi-agent teams will make the biggest impacts in enterprises first.

• The unexpected way A.I. is creating more construction jobs than any other sector as well as new careers that will emerge in the coming years because of A.I.

• How quantum computing and A.I. advances are entangled in a way that will dramatically change the future.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

In Case You Missed It in April 2025

We had a record number of guests on my podcast in April — and they were spectacular! In today's "In Case You Missed It" episode, hear the best parts of my conversations with each of them.

The specific conversation highlights included in today's episode are:

1. Sama Bali from NVIDIA and Logan Lawler from Dell Technologies fill us in on the AI software stack on NVIDIA GPUs, including libraries like CUDA.

2. Continuing on the A.I. hardware topic, Emily Webber details Amazon Web Services (AWS)'s own A.I. accelerator chips.

3. Zerve AI's co-founder Dr. Greg Michaelson describes how data scientists can deploy A.I. models to production without needing to call on an engineering team.

4. Kai Beckmann, CEO of Merck KGaA's semiconductor business, describes intricate details of the semiconductors that make A.I. systems hum.

5. Finally, Shirish Gupta explains his "A-I-P-C" framework for finding out if you should be using edge compute for local A.I. inference instead of relying on cloud compute.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Python Polars: The Definitive Guide, with Jeroen Janssens and Thijs Nieuwdorp

Today's episode on Polars is in equal parts hilarious and informative with Jeroen and Thijs, who co-authored the brand-new O'Reilly book "Python Polars: The Definitive Guide". Enjoy this one!

More on Dr. Jeroen Janssens:

• Senior Developer Relations Engineer at Posit PBC (iconic creators of RStudio and much more).

• Previously, was Senior Machine Learning Engineer at Xomnia.

• Wrote the invaluable O’Reilly book "Data Science at the Command Line".

• Holds a PhD in machine learning from Tilburg University.

...and on Thijs Nieuwdorp:

• Lead Data Scientist at Xomnia, the largest Dutch data and A.I. consulting company.

• Holds a degree in A.I. from Radboud University.

Today’s episode will be particularly appealing to hands-on data science, machine learning and A.I. practitioners but Jeroen and Thijs are tremendous storytellers and frankly very funny so this episode can probably be enjoyed by anyone interested in data and A.I.

In today’s episode, Jeroen and Thijs detail:

• Why pandas users are rapidly switching to Polars for dataframe operations in Python.

• The inside story of how O'Reilly rejected four book proposals on Polars before accepting the fifth.

• The moment when an innocuous GitHub pull request forced a complete rewrite of an entire book chapter.

• A previously secret collaboration with NVIDIA and Dell that revealed remarkable GPU acceleration benchmarks by Polars.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Calling Clinicians: Help Us Build the Future of AI Therapy

I recently began supervising a PhD student in the Auckland robotic-engineering department and we are looking to partner with psychotherapists to develop a companion robot. Do you know anyone relevant/interested?

(I promise that our eventual robotic solution will not be a two-headed monstrosity featuring my face on a kiwi bird's body... but maybe it helped get your attention 😂)

Through several years of upcoming R&D at The University of Auckland (I will mostly be supervising remotely from New York!), our project aims to develop a therapeutic A.I. model (e.g., a multi-modal Large Language Model) to power the conversational, perceptual and (potentially) real-time video-generation capabilities of a companion robot that gives its user (which could be in a clinical or at-home setting) personalized therapy and support when a human therapist is unavailable.

A particularly prominent challenge for us in developing and testing this LLM (and, eventually, robotic embodiment) is access to data from real therapeutic conversations, although there are other immediate and long-term R&D challenges that we would love practicing therapists to help us with as well.

This is an exciting, impactful project that could markedly improve millions of lives around the world in the coming decades. I applaud PhD candidate Maryam Khakpour for tackling it head on! If you're a clinician who's keen to be involved with the A.I. revolution, now's your chance :)

Blackwell GPUs Are Now Available at Your Desk, with Sama Bali and Logan Lawler

Today's charming and complementary guests — Sama Bali from NVIDIA and Logan Lawler from Dell — make for an extra fun episode on the powerful new Blackwell GPUs... now available at your desk!

More on Sama:

• A.I. Solutions leader at NVIDIA that specializes in bringing A.I. products to market.

• Prior to NVIDIA, held a Machine Learning Solutions role at Amazon Web Services (AWS).

• Focused on educating data scientists and developers on A.I. innovations and implementing them effectively in enterprises.

• Holds a Masters in Engineering Management from San José State University.

More on Logan:

• Leads Dell Pro Max A.I. Solutions (if you haven’t heard of Pro Max before, we’ll cover that in this episode!)

• Over his sixteen-year tenure at Dell Technologies, has held positions across merchandising, services, marketing and e-commerce.

• Holds an MBA in management from Texas State University.

Today’s episode will be particularly appealing to hands-on data science, machine learning and A.I. practitioners but it isn’t especially technical and so can be enjoyed by anyone!

In today’s episode, Sama and Logan detail:

• Why data scientists are camping out at 6AM to attend NVIDIA's GTC conference.

• The killer specs of NVIDIA’s next-generation Blackwell GPUs.

• How Dell and Nvidia have joined forces to bring server-level AI power right to your desktop.

• How microservices are revolutionizing A.I. development and deployment.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.

Beyond GPUs: The Power of Custom AI Accelerators, with Emily Webber

The mind-blowing A.I. capabilities of recent years are made possible by vast quantities of specialized A.I.-accelerator chips. Today, AWS's (brilliant, amusing and Zen!) Emily Webber explains how these chips work.

Emily:

• Is a Principal Solutions Architect in the elite Annapurna Labs ML service team that is part of Amazon Web Services (AWS).

• Works directly on the Trainium and Inferentia hardware accelerators (for, respectively, training and making inferences with A.I. models).

• Also works on the NKI (Neuron Kernel Interface) that acts as a bare-metal language and compiler for programming AWS instances that use Trainium and Inferentia chips.

• Wrote a book on pretraining foundation models.

• Spent six years developing distributed systems for customers on Amazon’s cloud-based ML platform SageMaker.

• Leads the Neuron Data Science community and leads the technical aspects for the “Build On Trainium” program — a $110m credit-investment program for academic researchers.

Today’s episode is on the technical side and will appeal to anyone who’s keen to understand the relationship between today’s gigantic A.I. models and the hardware they run on.

In today’s episode, Emily details:

• The little-known story of how Annapurna Labs revolutionized cloud computing.

• What it takes to design hardware that can efficiently train and deploy models with billions of parameters.

• How Tranium2 became the most powerful A.I. chip on AWS.

• Why AWS is investing $110 million worth of compute credits in academic AI research.

• How meditation and Buddhist practice can enhance your focus and problem-solving abilities in tech.

The SuperDataScience podcast is available on all major podcasting platforms, YouTube, and at SuperDataScience.com.