Sponsored Keynote: Scaling Platform Ops with AI Agents: Troubleshootin... Jorge Palma & Natan Yellin

This talk explores the integration of AI tools within software development and operations using specific technologies. The speaker highlights the use of Headlamp, a Kubernetes UI, and Home GPT, an AI-powered operations agent, to streamline troubleshooting in cloud environments. A scenario is presented where a pet store's checkout process encounters a service-related issue, demonstrating how the on-call engineer utilizes AI to diagnose and resolve the problem quickly. The discussion includes the advantages of GitOps practices with Flux for managing deployments, as well as the introduction of Home GPT's operator mode, which proactively monitors production environments. The session concludes with a look at future developments, including self-mutating agents for enhanced connectivity.

So, we've all seen how AI's becoming pervasive and we've all been told that we probably should be using it to become more productive. But, that can become a bit cumbersome when we're find ourselves between our day-to-day tools, different chat windows, asking them questions, copy-pasting from our tools to different context windows, then going back and doing something with those tools again. Wouldn't it be great if that were

actually well, fluid and integrated? George, you work with a ton of Acast customers. How do they do that on a day-to-day basis? Well, we have a lot of different customers with different tool sets, but there's a few tools that stand out that are very, very common. One of them is Headlamp, the Kubernetes UI that is part of the SIG UI as a subproject, and it's an extensible

and simple UI that allows you to manage clusters and applications. We also see them use things like Home GPT, which is an agent for operations as well as SREs. And we've seen them as we've seen today on stage that they're using GitOps flows with things like Flux. So, let's see how we can put all together and troubleshoot an issue that one of our users is having. So,

we're Contoso, we're a pet store, and one of our users is making a purchase for things like catnip and some cat toys. And so, they're going to add to their cart, and they're going to try and check out, typical flow, but there's an issue. So, they're going to open a ticket and it's going to go to one of our on-call engineers who luckily has no idea what's

going on and is going to go into Headlamp and ask the AI assistant, which is powered by Home GPT, to about what's going on. And he's hoping it's not the NS once again cuz it's been apparently typical. So, here Home GPT's actually going to leverage a myriad of tools such as Cube CTL, of course, but also things like the Inspector Gadget tool set. So, it's going to

run a EBPF gadget from Inspector Gadget to do a TCP dump, figure out that it's actually calling a order. -service that doesn't exist. What exists is orders, plural, -service, and it actually found that as well when listing the services. So, it's telling me, "Hey, there's a typo here. You're pointing to the wrong service that doesn't exist." And it analyzed that looking at the TCP dump and where

the application was calling. So, now I'm telling it, "All right, go right ahead. Please submit the PR. Give me a good description cuz I need to hotfix this, so I need to give this to my incident management." And we're going to go straight up and merge it cuz we're in hotfix mode. But, this is our production cluster, so we can't just apply it now. We're going to

go ahead and go to Flux. And we see this from the Headlamp Flux plugin. And as we access our application, we're going to sync it from source, and we're going to get this new PR that resolved the typo issue with our service. So, typically, what you found here is in 2 minutes, we were able to diagnose, mitigate, and root cause what the issue actually was. So, now

we're probably going to have to do some explaining to our team, so we're going to ask the AI to write the root cause analysis for us so we can explain to our users and explain to our stakeholders what happened here. And what happened here was, of course, a developer submitted a PR that wasn't that had a typo because their environment might have order-service, but in production, that

didn't match. So, this was pretty good. In 2 minutes, we did all of this, but could we do any better, Natan? Well, AI's fantastic at troubleshooting and fixing problems. We all know that, we all do that. But, it still needs a human to notice that something went wrong and to trigger an investigation. Not anymore. As you all know, Home GPT is the CNCF SRE agent, and we

recently launched [clears throat] operator mode. In operator mode, Home GPT monitors your entire cloud environment and any other data sources you've connected. On-premise virtual machines, network devices. We have customers that use Homes with the entire stack running in their environment. And in operator mode, Homes monitors the deploys from those developers on your teams using coding agents, shipping multiple PRs to production every day. It catches the problems

in production as soon as they're rolled out and something goes wrong and before your customers know this. With operator mode, you can ship at the speed of AI and also catch problems and fix them at the speed of AI. That's a good tagline. That looks pretty cool. What else you got in your road map? We have a busy road map for Home GPT, but I want to

focus on just one item, self-mutating agents. Homes today can connect to any MCP server, any raw HTTP API, even if it doesn't have an MCP, any database with our generic database connectors. And still, people come to me all the time and they say, "Natan, can you connect Home GPT to Uber?" And I say, "Why would you want to connect an SRE agent to Uber?" And they say,

"Well, so we can send a taxi to pick up our on-call engineers." Now, I don't know if that's a good idea, but we've noticed that when that happens, I say to my dev team, "Create an Uber integration." They do what all of you would do. They open to their cloud code or co-pilot. They spin up their coding agent. They develop it, and we ship it to customers.