Open models and the future of Physical AI with NVIDIA
Oct 1, 2026
Practical AI
Building Durable AI Agents
Machine Learning, Artificial Intelligence and Software podcast with Hamza Tahir
Practical AI, Hosted by Daniel Whitenack
About
Hamza Tahir discusses how experience with MLOps can inform more reliable agent systems. The conversation covers workflow execution, replayability and observability, including the design of agent harnesses and how ZenML's Kitaru approaches the practical work of running agents in production.
Topics
More from this series
- Building the Foundation for the Agentic AI EraAug 28, 2026 · 45 min
- Models, Harnesses, and Multi-Agent SystemsAug 6, 2026 · 50 min
- From AGENTS.md to Enterprise DeploymentSep 24, 2026 · 49 min
- Computer-Use Agents and the Future of the Agentic InternetSep 10, 2026 · 56 min
- Less about Models; More about ArchitectureSep 3, 2026 · 46 min
More from Practical AI
All episodesReconstructing how OpenAI agents attacked Hugging Face
Jul 30, 2026Practical AIImage Generation and Visual Intelligence with Black Forest Labs
Jul 2, 2026Practical AI
New episodes in Machine Learning
All episodesWhy AI Agents Break the GenAI Security Model with Devvret Rishi
Jun 16, 2026The TWIML AI PodcastAI Agents and The Golden Age of Asking Questions with Dimitris Papailiopoulos (MSR/UW-Madison)
Jul 9, 2026The Information Bottleneck
Upcoming talks in Machine Learning
All seminarsTrust, Sensing, and Learning for Provable Multi-Robot Performance
Nov 5, 2026Stephanie Gil