
90-Second Teaser for 4-Hour "Agentic AI Engineering" Workshop
Super Data Science Podcast with Jon Krohn16 June 2026Watch on YouTube
Part of series
Ep. 10 · Agentic AI Essentials
Toegankelijke introducties en workshops over agentic AI en autonome AI-systemen.
View the seriesDescription
This is a short teaser for the four-hour "Agentic AI Engineering" workshop that Ed Donner and I have published in its entirety on YouTube. The full video is here: https://youtu.be/LSk5KaEGVk4 ...and more info on the full workshop is below: In this comprehensive hands-on workshop, Jon Krohn and Ed Donner introduce AI agents, including multi-agent systems. All the essential theory of agentic AI is provided alongside hands-on code demos in Python that feature the critical agent frameworks: MCP, CrewAI and the OpenAI Agents SDK. 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 develop and deploy your own multi-agent teams. The four modules are: 1. Defining Agents (with OpenAI Agents SDK) 2. Designing Agents (with CrewAI) 3. Deploying Agents (with MCP) 4. The Future of Agents The accompanying slides and code are available in GitHub: github.com/ed-donner/action Jon Krohn is co-founder and CEO of Y Carrot, a software firm that specializes in designing and implementing agentic AI systems for enterprises. He also serves as ML Practice Fellow at Lightning AI and is the host of SuperDataScience, the data science industry’s most listened-to podcast. He wrote the book Deep Learning Illustrated, an instant #1 bestseller that was translated into seven languages. He lectures at leading universities (Columbia, NYU), keynotes at top global conferences (Web Summit, Collision) and presents content on Bloomberg TV that’s viewed by millions. Jon holds a PhD from Oxford and has been publishing on machine learning in prominent academic journals since 2010. Ed Donner is renowned for his teaching on LLMs and agentic AI via O'Reilly and Udemy. He’s the co-founder and CTO of Nebula.io, the platform that uses generative AI and other forms of machine learning to source, understand, engage and manage talent. Previously, Ed was the founder and CEO of AI startup untapt, an Accenture Fintech Innovation Lab company that was acquired in 2020. Before that, Ed was a Managing Director at JPMorgan Chase, leading a team of 300 software engineers in Risk Technology across three continents, the culmination of a 15-year technology career on Wall Street. Ed holds a patent for a deep learning matching engine issued in 2023 and a master's in physics from Oxford. This high-quality footage was shot live during a packed house at the Open Data Science Conference (ODSC) East in Boston on May 14th, 2025. The director of photography was Lucie McCormick and media editor was Mario Pombo.
What you'll learn
- You learn the theory and practice of AI agents, including multi-agent systems with frameworks like OpenAI Agents SDK, CrewAI and MCP.
- The workshop covers four modules: defining agents, designing agents, deploying agents and the future of agents.
- You get practical Python code examples and design principles to build and deploy your own multi-agent systems.
Frequently asked questions
Which frameworks are covered in this workshop?
What are the four modules of this workshop?
Are practical code examples provided in Python?
Topics
In this video
Related reads
OpenAI aangeklaagd in zelfdodingszaak ChatGPT-gebruiker
OpenAI en ceo Sam Altman zijn in de VS aangeklaagd door een Canadese moeder die stelt dat haar dochter door ChatGPT is aangezet tot zelfdoding.
OpenAI mikt op lang draaiende agents met overname van Ona
OpenAI neemt Ona over, voorheen bekend als Gitpod, een startup die AI-agents laat draaien in cloud sandboxes. De overname versterkt Codex en stelt OpenAI in staat agents taken te laten uitvoeren die uren of dagen in beslag nemen.
OpenAI boekte bijna 39 miljard dollar verlies in 2025
Volgens uitgelekte documenten liep OpenAI's verlies vorig jaar fors op tot 38,53 miljard dollar bij een omzet van 13,07 miljard dollar.
OpenAI patcht beveiligingslekken in opensourcesoftware
OpenAI en Trail of Bits starten Patch the Planet om beveiligingsproblemen in opensourceprojecten op te sporen en te repareren.
OpenAI onthult eigen AI-chip Jalapeño
OpenAI kondigt Jalapeño aan, zijn eerste eigen AI-chip ontwikkeld met Broadcom, bedoeld voor LLM-inferentie met betere prestaties per watt dan bestaande chips.
OpenAI en Broadcom presenteren Jalapeño-chip
OpenAI en Broadcom onthullen Jalapeño, een AI-inferentiechip ontworpen voor LLM's, als eerste stap in een meerjarig hardwareplatform.
