AI Catalyst: Agentic AI
Published by Pearson
From Reactive to Proactive: Exploring AI Agents that Plan, Reason, and Act
- Agentic AI and multi-agent systems address the most significant emerging trends in AI—the shift from passive to proactive AI systems that can plan and collaborate.
- From technical implementation to business strategy, this special event offers value for both technical practitioners (e.g., data scientists, ML engineers) and business decision-makers.
- This event features hands-on sessions led by industry experts demonstrating how to build a real multi-agent system using popular open-source tools (Hugging Face, Gradio, Chroma) to solve actual business problems.
Agentic AI represents a paradigm shift in artificial intelligence, moving beyond passive information processing to active, goal-oriented behavior. This special event delves into the cutting-edge world of AI agents capable of autonomous decision-making, long-term planning, and complex problem-solving. Leading experts will explore the latest advancements in agentic AI architectures, discuss real-world applications across industries, and address the ethical implications of increasingly autonomous AI systems. Attendees will gain insights into how agentic AI is revolutionizing fields such as robotics, virtual assistants, and automated decision-making, while also learning about the challenges and opportunities in developing and deploying these sophisticated AI agents. Whether you're a researcher, developer, or business leader, this event will equip you with the knowledge to navigate and leverage the transformative potential of agentic AI in your work and ventures.
AI Catalyst
The AI Catalyst event from Pearson brings together fresh voices in AI to make complex topics understandable and actionable. Host Jon Krohn guides the conversation and explains how to bring state-of-the-art methods into practice. Gain new information or a different perspective to make an impact in your job and in the world.
What you’ll learn and how you can apply it
- Evaluate where and how to implement agentic AI in your organization's products and services, with insights into both the technical requirements and business considerations.
- Design AI agent architectures that collaborate effectively to solve complex business problems, moving beyond single-purpose AI to more sophisticated solutions.
- Build and deploy practical multi-agent systems using popular open-source tools like HuggingFace and Chroma, with a concrete example you can adapt for your own needs.
This live event is for you because...
- You are a data scientist, software developer, ML engineer or other technical professional who would like to incorporate profitable state-of-the-art LLMs into real-world applications.
- You’re an entrepreneur, intrapreneur or business professional who’s keen to accelerate commercial innovation and profitability at your firm.
Prerequisites
- All you need is an interest in how AI can impact you and your organization.
- Feel free to bring questions for the experts.
Recommended Follow-up
- Attend: Choosing the Right LLM by Ed Donner (live course)
- Attend: From Software Engineer to AI Data Scientist by Ed Donner (live course)
- Read: Hands-On Large Language Models by Jay Alammar and Maarten Grootendorst (book)
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Jon Krohn: Welcome (10 minutes)
Shingai Manjengwa: From Specialized AI Agents to Multi-Agent Systems: Highlights, Epic Fails, and the Future of Agentic AI (30 minutes) AI systems are evolving from single-purpose specialized agents to complex multi-agent ecosystems capable of tackling more sophisticated tasks through collaboration. This session by Shingai Manjengwa will explore successes, pitfalls, and the ongoing challenges in building these interconnected agent systems. Join us to uncover the world of de-siloing high-performing agents and creating high-performing teams. Shingai Manjengwa is the Head of AI Education and Solutions Engineering at ChainML Labs, where she drives adoption of Theoriq’s decentralized AI agent governance protocol. A seasoned data scientist, Shingai previously led Technical Education at the Vector Institute, transforming complex AI research into high-impact programs for industry. She’s also the founder of Fireside Analytics and has taught over 500,000 learners through her online courses. An advocate for AI literacy and fairness, Shingai is an award-winning industry leader and she is the author of The Computer and the Cancelled Music Lessons.
Jon and Shingai Discussion + Q&A (15 min)
Break (10 min)
Ed Donner: Engineering AI Agents Hands-On (30 minutes)
In this session, Ed demonstrates how the open-source Python libraries HuggingFace, Gradio, and Chroma can be called upon to build a framework with multiple autonomous agents collaborating to tackle complex problems. More specifically, we'll build a framework with five agents collaborating to hunt for online deals and text us when a bargain is found. To pull this off, one of our agents will be a fine-tuned open-source LLM, deployed to Modal, that predicts product prices more accurately than GPT-4o and Claude. Another Agent will use a RAG pipeline drawing on 400,000 products vectorized in a Chroma datastore. And yet another agent will feature a frontier model parsing RSS feed to find deals. There’s a lot to build in a short period, but the results will be satisfying and extensible to an infinite universe of real-world problems. Ed Donner is a technology leader and repeat founder of AI startups. He’s the co-founder and CTO of Nebula.io, the platform to source, understand, engage and manage talent, using Generative AI and other forms of machine learning. Previously, Ed was the founder and CEO of AI startup untapt, an Accenture Fintech Innovation Lab company, acquired in 2020. Before that, he was a Managing Director at JPMorgan Chase, leading a team of 300 software engineers in Risk Technology across 3 continents, after a 15-year technology career on Wall Street. Ed holds a patent for a Deep Learning matching engine issued in 2023, and an MA in Physics from Oxford.
Jon and Ed Discussion + Q&A (15 min)
Break (10 min)
John Alexander: Agentic AI Product Development: From Vision to Reality (30 minutes) There's been a lot of interest in developing autonomous agents and multi-agent systems capable of performing complex tasks and collaborating in various environments. From concept to market, learn about the entire AI product development lifecycle, positioning you to innovate and lead in the AI-driven marketplace. Understand what's needed to tackle the challenges and opportunities of the AI-driven future, so you can build, test, and launch your own AI products and services. John Alexander is the Microsoft Learn content lead for Azure AI App Development. He also is a Tutor at the University of Oxford, where he develops and lectures on pivotal AI topics. John has over 25 years of experience in applying technology to real world situations and loves to share his knowledge and passion for AI through teaching, writing, and speaking.
Jon and John Discussion + Q&A (15 min)
Jon Krohn: Closing Remarks (20 minutes)
Your Hosts and Guests
Jon Krohn
Jon Krohn is Co-Founder and Chief Data Scientist at the machine learning company Nebula. He authored the book Deep Learning Illustrated, an instant #1 bestseller that was translated into seven languages. He is also the host of SuperDataScience, the data science industry’s most listened-to podcast. Jon is renowned for his compelling lectures, which he offers at leading universities and conferences, as well as via his award-winning YouTube channel. He holds a PhD from Oxford and has been publishing on machine learning in prominent academic journals since 2010.
Ed Donner
Ed Donner is a technology leader and repeat founder of AI startups. He’s the co-founder and CTO of Nebula.io, the platform to source, understand, engage and manage talent, using Generative AI and other forms of machine learning. Nebula matches people and roles with greater accuracy and speed than previously imaginable — no keywords required. Nebula’s long-term goal is to help people discover their potential and pursue their reason for being. Previously, Ed was the founder and CEO of AI startup untapt, an Accenture Fintech Innovation Lab company, acquired in 2020. Before that, Ed was a Managing Director at JPMorgan Chase, leading a team of 300 software engineers in Risk Technology across 3 continents, after a 15-year technology career on Wall Street. Ed holds a patent for a Deep Learning matching engine issued in 2023, and an MA in Physics from Oxford.
Shingai Manjengwa
Shingai Manjengwa is the head of AI education at ChainML, a tech startup that has developed an open source platform for the rapid and responsible development of generative AI tools. ChainML works with clients on AI education, adoption, and implementation from an AI product idea to an affordable and scalable deployment. A data scientist by profession, she led technical education at the Vector Institute for Artificial Intelligence in Toronto, where she translated advanced AI research into educational programming to drive AI adoption and innovation in industry and government. She also founded Fireside Analytics Inc., a data science education company that develops customized programs to teach digital and AI literacy, data science, bias and fairness in machine learning, and computer programming. Shingai’s book, The Computer and the Cancelled Music Lessons, teaches data science to kids ages 5 to 12. She also sits on the Service Advisory Committee for Employment and Social Development Canada and she’s a board member at the Institute on Governance. You can find Shingai on LinkedIn and X (Twitter) as @Tjido.
John Alexander
John Alexander is the Microsoft Learn content lead for Azure AI App Development. He also is a Tutor at the University of Oxford, where he develops and lectures on pivotal AI topics. John has over 25 years of experience in applying technology to real world situations and loves to share his knowledge and passion for AI through teaching, writing, and speaking.