Can we trust AI agents in the enterprise? ft. Derek Carr | Technically Speaking
From Red Hat · · 23 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.
If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.
Description
What happens when your AI agent writes and executes code live in production without human intervention? In this episode of Technically Speaking, Red Hat CTO Chris Wright sits down with Red Hat Senior Distinguished Engineer Derek Carr to demystify AI agents and examine what it takes to deploy them securely beyond the developer’s laptop.
The conversation covers the development of OpenShell, an open source agent execution environment created in collaboration with NVIDIA, designed to isolate untrusted agent loops from enterprise secrets through granular, deny-by-default execution policies that can evolve safely at runtime. Chris and Derek also examine the evolution of OpenClaw and the newly introduced OpenClaw Enterprise architecture, illustrating how open source collaboration is transforming viral desktop experiments into hardened, auditable, and multi-tenant platforms.
Tune in to discover how runtime sandboxing, dynamic policy enforcement, and defense-in-depth isolation are establishing the trust required to run autonomous AI agents responsibly across the enterprise.
00:00 The speed of AI agent adoption and the trust we put in them 01:24 Derek Carr's path to agentic AI expertise 03:26 What is an agent? 05:36 How do agents work? 08:30 How are we running agents? 11:33 Building trust in increasingly capable agents 14:38 Reevaluating enterprise readiness of OpenClaw and OpenShell 18:12 Communities coming together to solve emergent problems 20:57 The year of the agent 21:56 Wrapping up
Learn More: 🔒 Red Hat AI and OpenShell: https://www.redhat.com/en/blog/red-hat-ai-and-openshell-driving-security-enhanced-agent-execution-for-enterprise-ai 🏖️ Bring Claude self-hosted sandboxes to OpenShell on Red Hat AI: https://www.redhat.com/en/blog/bringing-claude-self-hosted-sandboxes-to-openshell-on-red-hat-ai 🚀 Explore the Technically Speaking series hub: https://www.redhat.com/en/technically-speaking
Follow us: Chris Wright LinkedIn: https://www.linkedin.com/in/chris-wright-b733851/ Chris Wright Twitter: https://twitter.com/kernelcdub Derek Carr LinkedIn: https://www.linkedin.com/in/derek-carr-7738638/
What is Technically Speaking?
Technically Speaking taps into emerging technology trends with insights from leading experts across the globe and Red Hat CTO Chris Wright. The series blends deep-dive discussions, tech updates, and creative short-form content, solidifying Red Hat’s role as a pioneer in technology innovation and open source thought leadership.
Want to participate? Leave us a comment if there's a topic or a guest you'd like to see featured.
Watch More Technically Speaking: YouTube Playlist: https://www.youtube.com/playlist?list=PLbMP1JcGBmSGMPKkLoq6CGwwKDxl9VvBE Show Page: https://www.redhat.com/en/technically-speaking
Subscribe to Red Hat's YouTube channel: https://www.youtube.com/redhat/?sub_confirmation=1