Practical AI
Practical AI LLC
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!
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!
Episodes
Mentioned books
112 snips
Dec 17, 2025 • 46min
Beyond chatbots: Agents that tackle your SOPs
Jason Beutler, CEO of RoboSource and creator of the Process Coach product, dives into redefining workflows with AI. He emphasizes that meaningful work stems from impact, not mundane tasks. The conversation explores the psychological implications of AI on employees and the importance of human relationships. Beutler advises managers to prioritize conversations, model AI adoption, and involve staff in change processes. He introduces the innovative Process Coach for simplifying operations and envisions a future where voice-driven AI collaborates seamlessly with teams.
200 snips
Dec 10, 2025 • 46min
The AI engineer skills gap
Ramin Mohammadi, an adjunct professor and lead AI engineer, dives into the widening skills gap for aspiring AI engineers and data scientists. He reveals that industry now favors mid-level expertise, challenging academic institutions to adapt. Topics include the rise of full-stack expectations, the impact of generative AI on junior roles, and the urgent need for hands-on MLOps training. Ramin also discusses mentorship's critical role in preserving cognitive skills in a tech-driven landscape, and offers insights on how high school programs can better prepare future talent.
84 snips
Dec 2, 2025 • 49min
Technical advances in document understanding
Discover how AI-driven document processing is transforming the landscape beyond traditional OCR. The hosts delve into the evolution from classical OCR to innovative models like DeepSeek-OCR. They discuss the challenges faced in document structure and layout reconstruction. Learn about the various use cases for document structure models versus OCR, and how vision-language models enhance reasoning. Get practical insights on choosing the right approach for effective document workflows.
125 snips
Nov 26, 2025 • 1h 37min
Chris on AI, autonomous swarming, home automation and Rust!
Chris Benson, a robotics and autonomy expert, dives into groundbreaking topics like AI, drones, and home automation. He emphasizes how open-source software and small AI models are revolutionizing home automation on a budget. Chris also discusses the emerging field of swarming technology, outlining its potential applications and differences from conventional fleets. With a focus on local systems over cloud reliance, he highlights the exciting future of physical AI and community-driven projects, all while advocating for the Rust programming language.
131 snips
Nov 19, 2025 • 49min
Beyond note-taking with Fireflies
Krish Ramineni, Co-founder and CEO of Fireflies AI, shares insights into the innovative world of AI-powered knowledge automation. He discusses the evolution of their meeting assistant technology, including new features like Live Assist for real-time support. Krish highlights the integration of GPT models that fueled rapid growth and emphasizes the importance of user-driven product development. He also explores future trends, such as hardware partnerships and expanding functionalities beyond meetings, illustrating the exciting possibilities in AI.
41 snips
Nov 13, 2025 • 52min
Autonomous Vehicle Research at Waymo
Drago Anguelov, Waymo's VP and head of the AI Foundations team, discusses the cutting-edge advancements in driverless technology. He delves into Waymo's impressive safety milestones, having surpassed 100 million autonomous miles. The conversation highlights the importance of city selection for testing, the architecture of future driverless car systems, and the necessity of public trust through transparency. Drago also explores the complexities of simulation, model design, and the coordination of multiple autonomous vehicles, revealing exciting prospects for the future.
181 snips
Nov 10, 2025 • 50min
Are we in an AI bubble?
The hosts delve into whether the current AI boom is a momentous evolution or a fleeting bubble reminiscent of the dot-com era. They examine the nuances of company valuations and how substantial earnings might indicate stability. Discussion includes the genuine integration of AI into diverse sectors and potential layoffs affecting the economy. Notably, they contemplate how AI impacts human cognition and perception. Ultimately, they conclude that while speculative pockets exist, a classical bubble may not be brewing.
152 snips
Oct 30, 2025 • 45min
While loops with tool calls
Jared Zoneraich, co-founder and CEO of PromptLayer, dives into the evolution of prompt engineering into context engineering. He explains how flexibility in AI applications is key, particularly with tool calls and while loops, changing the way we think about static prompts. Jared emphasizes the importance of a builder mindset for adapting to rapid LLM developments. He also shares insights on testing, working with coding agents, and how to effectively combine technical and non-technical expertise in AI projects.
191 snips
Oct 24, 2025 • 48min
Tiny Recursive Networks
Dive into the fascinating world of tiny recursive networks, where smaller models challenge giants like transformers in reasoning tasks. Discover how they operate with fewer parameters and data while still achieving impressive results. The discussion also unveils the ethical pitfalls of chatbots, highlighting manipulative tactics they use to extend emotionally charged interactions. Tune in to explore the balance between innovation and responsibility in AI technology!
187 snips
Oct 16, 2025 • 55min
Dealing with increasingly complicated agents
Donato Capitella, a Principal Security Consultant at ReverseSec, shares his insights into the evolving landscape of AI and security. He discusses the shift from simple chatbots to complex agentic systems, highlighting new vulnerabilities like prompt injection and data exfiltration. Drawing on real-world exploits, Donato emphasizes the need for secure design patterns and introduces his open-source toolkit, Spikee, tailored for probing LLM systems. He advocates for a proactive approach to security that integrates design patterns right from development.
