AI Engineering Podcast

Guillaume de Saint Marc, VP of Engineering at Cisco OutShift, dives into the exciting realm of multi-agent systems. He contrasts rigid workflows with dynamic, self-forming agents that enhance trust in enterprise settings. The discussion touches on the Internet of Agents and the importance of open protocols like A2A and MCP for collaboration. Guillaume highlights the challenges of identity and observability, sharing successes in IT operations. He also introduces Slim, a next-gen communication layer, tailored for efficient agent collaboration.

In this discussion, Will Vincent, a Python developer advocate at JetBrains, dives into the evolution of software engineering alongside AI. He contrasts 'vibe coding' with a more structured 'vibe engineering,' highlighting the importance of collaboration between developers and AI. Will shares practical strategies for utilizing AI tools effectively within IDEs, discusses the role of human oversight in architectural decisions, and addresses the challenges of context loss in code reviews. He emphasizes experimentation and ethical considerations in AI implementation.

Daniel Sodickson, Chief of Innovation in Radiology at NYU Grossman School of Medicine, shares his expertise in AI and medical imaging. He unveils the evolution from linear MRI to deep learning, emphasizing the distinction between upstream AI that influences measurement and downstream AI that interprets images. Their discussion includes the challenges of cross-disciplinary knowledge, ethical implications of decoding brain activity, and innovative concepts like 'imaging without images.' Daniel highlights the necessity of human oversight as AI transforms healthcare and visual understanding.

Andrew Filev, CEO and founder of ZenCoder, shares his expertise on architecting AI-first engineering workflows. He discusses the evolution from simple autocomplete to truly agentic models and emphasizes the importance of context engineering and verification. Filev details ZenCoder's internal playbook, covering human-in-the-loop strategies and test-driven development. He also explores the balance between human control and model autonomy, predicts self-verification trends, and gives insightful lessons on navigating the challenges of building modern coding systems.

In a fascinating discussion, Lucas Thelosen, CEO of Gravity with experience from Looker and Google, and Drew Gillson, AI expert and co-founder of Gravity, dive into their innovative analytics platform, Orion. They explore the shift from probabilistic to deterministic tools for data accuracy and the importance of user-oriented push-based insights. The duo emphasizes context engineering, organizational impact, and the emerging role of 'AI managers' to drive better data literacy. They also share surprising applications of Orion for qualitative analysis at scale.

Samuel Colvin, the mastermind behind the Pydantic validation library, shares his journey in creating Pydantic AI—a type-safe framework for AI agents in Python. He discusses the importance of stability and observability, comparing single-agent versus multi-agent systems. Samuel explores architectural patterns, emphasizing minimal abstractions and robust engineering practices. He also addresses code safety and the challenge of model-provider churn, while promoting open standards for enhanced observability. Join him as he reveals insights on crafting reliable AI agents!

Brijesh Tripathi, CEO of Flex AI and a former architect at Intel, NVIDIA, Apple, and Tesla, discusses transforming AI workflows by implementing 'workload as a service'. He highlights the importance of minimizing DevOps burdens to enhance productivity, revealing how inconsistent Kubernetes layers create challenges for AI teams. Brijesh elaborates on optimizing training and inference processes and emphasizes Flex AI's focus on easing the complexity of heterogeneous compute while ensuring cost efficiency. His vision aims to empower teams, enabling them to innovate without infrastructure hassles.

In this discussion, Steven Huels, VP of AI Engineering at Red Hat, unpacks the power of small language models (SLMs) for real-world applications. He highlights the advantages of SLMs in fitting onto single enterprise GPUs and their operational capabilities. The conversation dives into self-hosting models versus relying on APIs, tackles organizational readiness, and discusses innovations in agentic systems. Steven shares real-world examples like scam detection and emphasizes the importance of customization, automated evaluation, and continuous retraining for efficient AI deployment.

Julianna Lamb, co-founder and CTO of Stytch, delves into identity management in AI, discussing its complexities amidst evolving technologies. She highlights the challenges of permissions and security as AI agents take on human tasks. The conversation covers innovative authentication strategies, including the need for layered verification and adapting systems with robust security. Julianna emphasizes experimenting with AI agents and suggests the importance of feedback mechanisms for seamless integration and optimal performance, all while navigating the future of identity standards.

In this engaging conversation, Spiros Xanthos, CEO of Resolve AI, shares his vision for revolutionizing operational systems with AI agents. He discusses the limitations of traditional tools and how intelligent agents can enhance troubleshooting. Spiros highlights the importance of context and memory for effective AI integration, as well as the evolving collaboration between humans and AI in production environments. He emphasizes the need for continuous learning to maximize AI's potential, paving the way for more efficient human-machine partnerships and improved user experiences.