Show Notes
Bret and Nirmal explore AI agents in Kubernetes with Eitan Yarmush, Senior Architect at Solo.io. Eitan explains how AI agents work through three simple components (system prompts, LLMs, and tools), and demonstrates the kagent project, which provides a Kubernetes-native way to deploy and manage AI workflows.
😇 My new GitHub Security workshop has launched! A free 2-hour workshop with hands-on labs to harden your repos and your workflows from common supply chain attacks. I'll cover how attackers are getting in, and then we'll lock down a sample repo so you know what needs to be done to protect your code. You'll leave with a deep understanding of risks and mitigations as well as a list of helpful tools to keep your repos safe, including my new "gasa" tool for scanning your repos and orgs.
Also in this episode, we cover the Model Context Protocol (MCP), which standardizes how agents communicate with external tools, along with practical use cases like incident response, debugging workflows, and CI/CD integration. Eitan shows how to create an agent through a web interface.We also address the challenges including security concerns (MCP lacks built-in security standards), cost considerations, and technical limitations like context window constraints. Check out the video podcast version here: https://youtu.be/JTTqG5SOpWY Creators & Guests
Bret Fisher - Host
Beth Fisher - Producer
Cristi Cotovan - Editor
Nirmal Mehta - Host
Eitan Yarmush - Guest
(00:00) - Intro
(04:36) - Hype vs Reality
(06:28) - Incident Response and Debugging
(09:46) - Defining Agents and MCP
(15:33) - Where Do You Run Agents?
(18:37) - What Problem does kagent Solve?
(29:05) - Authentication and Tool Limitations
You can also support this podcast by subscribing to my YouTube channel and my weekly newsletter at bret.news! Grab the best coupons for my Docker and Kubernetes courses on Udemy. Join my cloud native DevOps community on Discord. Grab some merch at Bret's Loot Box Homepage bretfisher.com
★ Support this podcast on Patreon ★
More from Agentic DevOps : AI Engineering for Infrastructure
The OpenAI Hugging Face hack. The Anthropic testing failures. Listen to the security and ops experts, not lab researchers. I walk you through the production failures that allowed OpenAI’s models to access the internet, and what we can learn from the last few months on how to protect our systems and data. Let’s stop debating imaginary outcomes and start working through that security backlog in our infrastructure. I agree with the labs needing to slow down, but not because I believe AI will do uncontrollable harm on humans, but because the labs clearly need better production security and ops teams and more advanced lab infrastructure that’s been properly hardened. They also need to become a production ops security innovator and share that knowledge far and wide. Watch the video of this episode.
Luke Hinds, co-founder of nolabs Inc. and the nono project, joins me to dig into AI agent sandboxing with the nono CLI. It's been my go-to sandboxing tool for local agent use, but I know there are more features I should be using, like secure secrets injection and egress URL path control. Watch the video of this episode.
My friend Mike Rollins joins me for a chat about what it’s like leading a software engineering team that doesn’t read code anymore. Click here to watch a video of this episode.
A deep dive into GitHub’s Agentic Workflows feature, with Don Syme of GitHub Next & Peli de Halleux of Microsoft Research. Check out the video podcast version here: https://youtu.be/zmM8VISTOwo
Bret’s joined by the Anyshift.io co-founders, Roxane Fischer and Stephane Jourdan to discuss how an always-on SRE agent can help you proactively find risks and avoid incidents.