
Practical AI
Making artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more).
The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!
Latest episodes

71 snips
Jun 18, 2025 • 42min
Behind-the-Scenes: VC Funding for AI Startups
Explore the thrilling world of AI startups, where enormous valuations clash with questionable practices. Discover the chaotic journey from bootstrapping to attracting venture capital, touching on critical funding terminology and the delicate balance between product and service-based models. Learn what it's like for founders to transition from tech wizards to CEO juggernauts, managing investor relationships and team dynamics. The discussion also dives into the ethical considerations facing the rapidly evolving AI landscape.

87 snips
Jun 12, 2025 • 43min
AI-Automated Film Making
In this discussion with Sami Arpa, CEO of Largo AI and innovator in AI for the film industry, listeners dive into the revolutionary use of AI in filmmaking. Sami explains how AI-driven script analysis and financial forecasting can empower filmmakers, leveling the playing field for smaller studios. The conversation also touches on the intriguing concept of 'genre recipes' to enhance machine learning in storytelling. As the industry evolves, Sami projects a future where AI reduces production costs and fosters creativity while preserving the essential human touch in filmmaking.

111 snips
Jun 4, 2025 • 45min
Federated learning in production (part 2)
Chong Shen, a research engineer at Flower Labs with a background in computational physics, shares insights on building production-ready federated learning systems. He discusses the user-friendly Flower framework, essential for handling sensitive data across industries. Topics include the design challenges for developers, the integration of diverse models, and how the generative AI boom is influencing future developments. The conversation sheds light on the balance between usability and production demands, especially in sectors like healthcare.

108 snips
May 30, 2025 • 45min
Federated learning in production (part 1)
Patrick Foley, Lead AI architect at Intel and a key player in OpenFL’s development, delves into the transformative potential of federated learning. He highlights how this approach ensures data privacy by training models where the data resides, particularly in sensitive areas like healthcare. The discussion covers real-world applications like brain tumor segmentation, the challenges of trust and verification, and the role of frameworks in enhancing collaboration. Foley also hints at the future of federated learning in breaking down data silos while maintaining security.

372 snips
May 20, 2025 • 47min
Emailing like a superhuman
Loïc Houssier, Head of Engineering at Superhuman, discusses the transformative role AI is playing in reshaping email interactions. He emphasizes the importance of user experience and real human workflows in developing tools that genuinely resonate with users. The conversation dives into the challenges of prompt optimization and infrastructures while revealing how AI can streamline email management. Loïc also highlights the shift in user expectations and how agile product development is crucial in navigating these disruptive innovations.

467 snips
May 8, 2025 • 42min
Model Context Protocol Deep Dive
Dive into the revolutionary Model Context Protocol (MCP), a game-changer enabling seamless AI interactions with external systems and APIs. Discover how it fosters interoperability and community contributions, shaping a vibrant AI ecosystem. Tune in for insights into enhancing AI capabilities with tools like FastAPI-MCP and overcoming compatibility challenges across different platforms. Plus, explore Candle, a minimalist ML framework for edge inference that opens up new creative avenues. This discussion is packed with practical advice for navigating the future of AI.

59 snips
Apr 30, 2025 • 43min
Seeing beyond the scan in neuroimaging
Gavin Winston, a Professor at Queen's University and an expert in neuroimaging and AI in healthcare, dives into the fascinating world of epilepsy diagnosis using machine learning. He reveals how MRI data can identify subtle brain abnormalities and discusses the cultural and ethical challenges of integrating AI in clinical settings. The conversation also covers the potential of AI to enhance diagnostic workflows and improve collaboration between radiologists and physicians, shaping a promising future for neuroimaging.

749 snips
Apr 17, 2025 • 42min
Open source AI to tackle your backlog
Join Robert Brennan, CEO of All Hands AI, and Graham Neubig, Co-Founder and Chief Scientist, as they dive into the evolving landscape of AI in software development. They explore how AI tools are reshaping coding workflows, from enhancing developer productivity to managing GitHub issues with open-source agents. The duo discusses trust in AI, coding on the go, and the creative shift in perception around programming. Discover how these innovations are not just about efficiency but transforming coding into a collaborative and accessible craft.

465 snips
Apr 14, 2025 • 43min
Orchestrating agents, APIs, and MCP servers
Pavel Veller, Chief Technologist at EPAM Systems, shares his extensive expertise in orchestrating AI agents and agentic architectures. He dives into the complexities of connecting disparate systems and highlights the challenges of making AI assistants truly useful despite the ease of API connections. Pavel also discusses the vital role of MCP servers in bridging traditional software and language models, and the innovative Dial platform that enhances team collaboration and efficiency in AI applications. Prepare for insights that finely balance innovation with real-world application!

117 snips
Apr 2, 2025 • 43min
Software and hardware acceleration with Groq
Dhananjay Singh, a Staff Machine Learning Engineer at Groq, discusses the cutting-edge advancements in AI acceleration. He reveals how Groq optimizes AI inference by focusing on software-first design, setting a new standard against traditional GPU architectures. The conversation dives into the integration of hardware and software for superior performance, showcasing practical applications like a snowboarding navigation system. Lastly, Singh touches on the importance of edge computing and the evolving landscape of physical AI, highlighting the challenges and innovations within the field.