Practical AI

Models, Harnesses, and Multi-Agent Systems

AI has moved far beyond chatbots, but what exactly are AI models, agents, agent harnesses, and multi-agent systems, and why do they matter?In this episode, Daniel and Chris break down the terminology behind today's AI landscape, explain the differences between AI features and autonomous agents, and explore why organizations are shifting toward fleets of AI agents powered by multiple models. They also discuss open vs. closed models, enterprise AI architectures, vendor lock-in, and practical ways to begin adopting agentic AI in your own organization.If you feel left behind by this ongoing agentic AI revolution that has rapidly accelerated to warp speed, then this episode is the catch-up primer you've been waiting for!Featuring:Chris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XSponsors:Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalaiMidwest AI Summit: Join AI practitioners on October 15 in Indianapolis for practical sessions, hands-on discussions, and real-world AI solutions. Use code PracticalAI20 to save 20% on your registration. https://midwestaisummit.com/#ticketsPrediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalaiResources and Events:Prior Webinars from our partner Prediction GuardMidwest AI Summit 2026

Reconstructing how OpenAI agents attacked Hugging Face

What happens when AI agents driven by a top frontier model escape their secure sandbox? Join Daniel and Chris as they unpack the AI wonk's equivalent of a murder mystery! OpenAI agents went rogue and successfully attacked Hugging Face private infrastructure. Our Dynamic Duo uncover how OpenAI's agents exploited vulnerabilities, moved through networks, and launched a large-scale autonomous attack. They explore what this reveals about agentic AI, cybersecurity, sandboxing, and why organizations need AI systems capable of governing other AI systems. Along the way, Chris and Dan examine the surprising role of open vs. closed models and their link to geopolitics, sovereign AI, and what this incident means for the future of enterprise AI security. Featuring:Chris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XLinks:Hugging Face Security Incident disclosureFull Field Report on the Hugging Face AI Agent IntrusionExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?Keeping your data safe when an AI agent clicks a linkOpen AI GPT-5.6 System CardResources and Events:Prior Webinars from our partner Prediction GuardMidwest AI Summit 2026

Surviving the New Economics of a Post-Agentic World

The agentic transformation isn’t coming. It has already begun.Companies are deploying thousands — and sometimes tens of thousands — of AI agents. Enterprise software giants are watching their old economic moats erode. Capital is moving, productivity is being redefined, and human labor is being repriced in real time.In this Fully Connected episode, Daniel and Chris explore the new economics of a post-agentic world: the global order that emerges after agents have been woven into every conceivable aspect of business and life. What happens when digital labor becomes abundant, agents manage other agents, and entire organizations operate at a scale no human workforce could match?This isn’t another conversation about whether AI will take your job. It’s about what happens when the assumptions underneath jobs, companies, software, and productivity stop being true.The post-agentic world is already taking shape.The question is whether you’re preparing for it — or becoming part of what it replaces.Featuring:Chris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XUpcoming Events: Register for upcoming webinars here!Midwest AI Summit 2026

The Future of AI Infrastructure with CoreWeave

As AI applications become more complex, the infrastructure powering them needs to evolve. Corey Sanders, SVP of Product at CoreWeave, joins Chris to discuss why AI requires a fundamentally different approach than traditional cloud computing. They explore AI-native infrastructure, training and inference workloads, the rise of agentic development, optimizing GPU performance, AI research workflows, and why the future of software will be built around AI-first experiences rather than websites and apps.Featuring:Corey Sanders – LinkedIn Chris Benson – Website, LinkedIn, Bluesky, GitHub, XLinks:CoreWeaveSponsors:Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalaiUpcoming Events: Register for upcoming webinars here!Midwest AI Summit 2026

Building Durable AI Agents

What does it take to move AI agents from demos to reliable production systems? In this episode, Hamza Tahir explores how MLOps principles are shaping the future of generative AI, covering workflows, agent harnesses, fleets, and the infrastructure needed to build durable, scalable systems.  The conversation dives into open source tools, production challenges, and how ZenML's new project, Kitaru, helps developers build resilient, replayable, and observable agent systems.Featuring:Hamza Tahir – LinkedInChris Benson – Website, LinkedIn, Bluesky, GitHub, XDaniel Whitenack – Website, GitHub, XLinks:ZenMLKitaruMachine Learning Tools Landscape v2 (+84 new tools)Sponsors:Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalaiUpcoming Events: Register for upcoming webinars here!Midwest AI Summit 2026