# From AGENTS.md to Enterprise Deployment - **Show:** Practical AI - **Published:** 24 Sep 2026 - **Source:** https://share.transistor.fm/s/74934e48 - **Transcript:** https://podcasts.opennash.com/shows/practical-ai/from-agents-md-to-enterprise-deployment-0073e1/ - **Provider:** OpenNash Podcasts (machine-generated) ## In brief Enterprise AI agents should be treated like ordinary applications and deployed through the same platform-engineering practices that enterprises already trust. Nick Kuhn argues that packaging, sandboxing, identity, monitoring and approved tooling already exist for apps, and can be extended to agents using a buildpack, an MCP gateway and a shared memory service. The tension is between the speed of AI change and the slow, regulated nature of enterprises. Agents built on laptops assume internet access, local files and little oversight, while enterprises need air gaps, compliance, reliability and audit trails. Kuhn's answer is to take small steps, reuse existing skills and teams, and apply proven controls rather than invent new ones. ## Key insights 1. **Agents should ship like ordinary applications** Kuhn's team lets developers cf push an agent, defined by a human-readable agents.md file, just as they would push compiled Java code. The platform then builds a secure container, so existing approvals and repeatable paths to production apply. 2. **Laptop-style agent memory breaks in the cloud** Agent harnesses often save memory as markdown files on a local file system. Cloud instances spin up and down, so those files vanish, which is why a shared memory service is needed. 3. **An MCP gateway gives control and visibility** Registering MCP servers behind a gateway controls which tools each agent gets and passes user identity through to tools like GitHub. It also produces metrics, so an agent making 200,000 delete-repo calls could trigger an alert. 4. **Basic enterprise controls might have limited agent escapes** Kuhn argued that hardened sandboxes, network zones, firewalls and monitoring could have helped in the Hugging Face incident discussed, where agents reportedly escaped a sandbox via an internet-connected Artifactory. He cautioned that nothing prevents everything. 5. **Adopt agents in small, approved steps** Enterprises often route new technology through an AI council and wait months. Kuhn advises getting a simple agent and approved LLM access first, then adding MCP tools later, while involving experienced teams rather than building a siloed new one. ## Questions this episode answers ### What makes an enterprise environment different for AI agents? Kuhn says enterprises often have limited or no internet access, strict compliance rules such as PCI, SOC, HIPAA and FIPS, and sometimes true air gaps where items are physically carried into the data center. What works at home often won't work there. ### What is a buildpack and how does it apply to agents? A buildpack is a set of commands that turns your code into a best-practice container for its type, such as Java. Kuhn's team applies the idea to agents: you push an agents.md file and the platform runs it within about a minute. ### What is an MCP gateway? MCP is the Model Context Protocol, a way for agents to use tools. Kuhn describes an MCP gateway as a front door that registers many MCP servers, limits which tools each agent can use, passes along user identity and records every tool call. ### Why can't agents just keep running on a laptop? Chris and Nick note that if you shut the lid, the agents stop, and enterprises want agents running continuously. Nick adds that agents should sit near the apps and data they use, to cut latency and avoid unreliable outside services. ### What future changes does Nick expect from AI? He expects big changes to roles and organizations, with new jobs created and faster change. He also says he is working harder than ever with agents, and expects more voice interaction and robotics. ## Facts - **Nick Kuhn** [0:05:42]: "I currently work for VMware Tanzu and we run a a, you know, a platform or platform as a service, uh, you know, geared for private cloud." - **Nick Kuhn** [0:06:07]: "it's actually based on, um, an open source, uh, project called Cloud Foundry, which is, I think, I mean, it's, you know, predates Kubernetes and Docker." - **Nick Kuhn** [0:06:31]: "So, you know, 2011 ish is when it kind of started originally out of VMware and spun out and then became part of a open source project." - **Nick Kuhn** [0:03:31]: "I've been, uh, at, uh, VMware Tanzu for about five years, uh, and before that, I was at a one of these large enterprises for about 14 years." - **Nick Kuhn** [0:06:31]: "the platform's gonna know like the best practices for, uh, it's gonna build a container for the developer, so the developer doesn't have to worry about, like, you know, securing the container or anything like that." - **Nick Kuhn** [0:18:33]: "So the Java buildpack knows to do all the JVM memory calculators and do the JDK and the certificates and all everything." - **Nick Kuhn** [0:18:57]: "we're gonna have this agent, we're gonna just cf push an agent. And instead of, like, you know, machine readable code, we have a human readable language, uh, the agent SMD." - **Nick Kuhn** [0:17:33]: "we are providing a harness, uh, called the, uh, Tanzu Agent Build pack, and that helps through that process." - **Nick Kuhn** [0:20:23]: "even at Broadcom, like, the only way approved way to use for our developers is to deploy MCP servers on on Tanzu platform." - **Nick Kuhn** [0:21:14]: "I was in, I was in Las Vegas for a conference, VMware Explorer, and I had like a five phase demo where I walked through this." - **Nick Kuhn** [0:21:33]: "I can hook up, hook them up to a repo with like an event listener or webhook and say, all right. Now. Do a sig like a, you know, issue five on my repo." - **Nick Kuhn** [0:22:35]: "they can't talk to each other unless you enable them, so they can't go to the internet unless it's enabled." - **Nick Kuhn** [0:24:17]: "you basically register MCP servers to this gateway and the gateway kind of controls access, so to speak, and regulates that." - **Nick Kuhn** [0:25:23]: "I don't want it just to be like, well, here's our general generic service account for the entire organization." - **Nick Kuhn** [0:25:42]: "because it's all flowing through that gateway, we get metrics out of it. So we can see all the tool calls and all the all the events happening" - **Nick Kuhn** [0:12:17]: "if you have, you know, the agent or the LLM or whatever that's like, you know, 30 hops away from the at the microservice, it's trying to call it." - **Nick Kuhn** [0:13:02]: "the app was older than me at the time, still older than me." - **Nick Kuhn** [0:41:53]: "then then it got to the artifactory, which then it found the weak link, and the artifactory had the internet access" - **Nick Kuhn** [0:43:26]: "somebody left Anthropic, and a bunch of Anthropic people started posting around that." - **Nick Kuhn** [0:38:29]: "And pretty much the entire room, and all of them went up, and I was like, Well, that's a lot more than I expected." - **Daniel Whitenack** [0:29:59]: "Nick is gonna come talk about what it looks like to deploy AI agents in real world environments." ## Transcript **[0:00:02] Narrator:** Welcome to the Practical AI podcast, where we break down the real world applications of artificial intelligence and how it's shaping the way we live, work and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn X or Bluesky to stay up to date with episode drops, behind the scenes content, and AI insights. **[0:00:32] Narrator:** You can learn more at practicalai. fm. Now onto the show. **[0:00:41] Daniel Whitenack:** Welcome to another episode of the Practical AI Podcast. This is Daniel Whitenack. I am CEO at Prediction Guard, and I'm joined as always by my co-host Chris Benson, who is a principal AI and autonomy research engineer. How you doing, Chris? **[0:00:56] Chris Benson:** Hey, doing great today. How's it going? **[0:00:58] Daniel Whitenack:** It's it's going great. And I and I know this is gonna be a great conversation for a few different reasons today. One of those being our our guest is one of the speakers at the upcoming Midwest AI Summit, which is gonna be amazing. There's gonna be a bunch of amazing speakers there. I'm gonna do a bit of emceeing, see if I don't mess that up. Would encourage our encourage our listeners to check that out. October 15th in Indianapolis, you can, uh, get 20 off with Practical AI 20, so check that out. **[0:01:30] Daniel Whitenack:** So, um, amazing speaker, gonna be at the Midwest AI Summit. Also a fellow podcaster, which is is great. Um, one of the hosts of Cloud Foundry Weekly and, uh, a tech marketing, uh, whiz at Broadcom Tanzu VMware. So welcome, Nick. Great to have you. **[0:01:49] Nick Kuhn:** Well, uh, thanks for having me. Great to be on the show. Excited. Also great, excited to see y'all in person in Indianapolis. **[0:01:57] Daniel Whitenack:** yeah, it's gonna be fun. We're we're representing the good, good representation of the Silicon Prairie here. I I like it. Um, so, uh, yeah, ni- Nick, um, I I know you're gonna be talking. Well, one of the things I thought was cool about your talk at the Midwest AI Summit is you bring in this concept of taking like agents.md and shipping that to a production environment where you run, you know, an actual agent in an quote enterprise environment, which is seems to be, um, really fascinating. **[0:02:31] Daniel Whitenack:** We recently had on, uh, someone from the Agentic AI Foundation, um, who is kinda stewarding the model context protocol and agents.md and and those sorts of things. So very relevant kind of carry on from that conversation. But I'm wondering, as we set that up, what what exactly does it mean to be operating in an enterprise environment? So the customers that you're working with that your kind of day to day, what are s what makes an enterprise environment an enterprise environment? **[0:03:06] Daniel Whitenack:** What are some of the concerns or characteristics of that type of environment? And I know you, you're always experimenting, you do a lot of home lab stuff as well, so always, uh, ha, have a whole range of experience in working in different sorts of environments. So, yeah, if you could just help us understand from a general perspective, what, what, what does that mean? Um, when you say kinda enterprise **[0:03:31] Nick Kuhn:** right. So yeah, if we think about enterprise, we think about, you know, a few things. Uh, one, let's just assume you're gonna have not internet, uh, limited or no internet access. And you know, I've been, uh, at, uh, VMware Tanzu for about five years, uh, and before that, I was at a one of these large enterprises for about 14 years. So when we had vendors come in, it would always be like they would always assume that we could just go to the internet. **[0:03:56] Nick Kuhn:** And it was always like, well, try again, cause that's not gonna work here. So that's kind of always like the biggest hurdle, where, um, you're gonna be, uh, regulated and or, you know, you know, you won't, you're not gonna, you're. What you can do at home is not gonna be what you can do a at work, so to speak. So you're gonna be highly regulated. You're gonna have to deal with, you know, potential, like, you know, PCI or SOC compliance, or HIPAA, or, uh, FIPS, or, you know. **[0:04:21] Nick Kuhn:** And I could probably go on and on about all the different compliance tiers that you would have to deal with. So it's just a whole different ballgame where, you know, you could potentially do something that has, uh, dramatic consequences. And, um, you have a, you know, highly controlled, highly regulated environment. Where even some of the customers that I work with are like, you know, they actually have the real air gap, where, like, we're carrying in things, you know, physically into the data center, uh, because there is no internet access type of thing. **[0:04:47] Nick Kuhn:** So it's, it's, it's a wild world, but, uh, and it and it frustrates a lot of, I think, new folks to the enterprise space. But if you've been in it a while, you know, you know, you know how to deal with it and and how how to handle it type of thing. So **[0:04:59] Daniel Whitenack:** a, and I guess, you know, people have been dealing with these types of environments for quite a while, right? Cause there have been enterprises for for quite a while. M Maybe just give us a sense of, like, leading up to AI agents, and we'll talk about agents here in a second, but leading up to AI agents. Like, what were some of the ways that you could? I, I guess, uh, e ease, uh, you know, put some ointment on those those pains of working in that sort of environment. **[0:05:29] Daniel Whitenack:** How do you? How would you get an application into that sort of environment, or or ha, have it be enterprise ready? Quote unquote. And then we can shift and talk about, you know, what changes with with agents? **[0:05:42] Nick Kuhn:** Yeah, so I mean, I think so, you know, I currently work for VMware Tanzu and we run a a, you know, a platform or platform as a service, uh, you know, geared for private cloud. Whether that be on your like, on your own bare metal in your data center, or you could deploy it on a private cloud in your own, like VPC on a hyperscaler, that type of thing. Um, but we think about that, you know, we wanna I in the scope of an enterprise, right? **[0:06:07] Nick Kuhn:** You have all these regulations, controls, et cetera. You wanna make that path to production kind of, uh, the least resistant and easiest path. And if you make that path to production like all the checkboxes and everything good to go, that's gonna be a highly adopted path. So the whole concept of, you know, a Tanzu platform, and it's actually based on, um, an open source, uh, project called Cloud Foundry, which is, I think, I mean, it's, you know, predates Kubernetes and Docker. **[0:06:31] Nick Kuhn:** So, you know, 2011 ish is when it kind of started originally out of VMware and spun out and then became part of a open source project. So it's, it's, it's, it's been around and battle tested and seen a lot of things. Where you have that concept of like, I just wanna take my code and send it to the platform and the platform's gonna know like the best practices for, uh, it's gonna build a container for the developer, so the developer doesn't have to worry about, like, you know, securing the container or anything like that. **[0:06:54] Nick Kuhn:** The platform will take care of that. Um, it will handle, uh, you know, ingress like s certs, certificates, all the, you know, load balancers, all of those things just handle health monitoring. Potentially even kind of like sandboxing the apps from each other, uh, something that, you know, maybe some of these labs may, uh, learn from, uh, but, uh, so that the apps can't, uh, escape type of thing. Um, and um, you know, if it, if the app needs services like a database or messaging middleware, any type of thing, even maybe a large language model, uh, it can what we call bind. **[0:07:28] Nick Kuhn:** Or it kind of connects to a service on the fly and that that's all kind of handled under other underneath the covers. So it's just a few commands like, you, uh, push bind, scale your app with just a few simple constructs, and that's that's like, that's how you go to production. And what we see with enterprises once that path, like, once they take this, like this is Tanzu platform, it's been certified through all these different standards. **[0:07:50] Nick Kuhn:** It's just kind of like an unlock for, uh, um, these enterprises, because it's so easy and so simple to use. And they don't have to, you know, they don't have to recertify everything. It it's it's just like this framework that they can use to get apps into production. And then the biggest thing is that you want these, the enterprises or the businesses, the they don't want their developers, you know, handcrafting a a new platform or a new way to deploy apps for every sub team and have like 100 different snowflakes, right? **[0:08:16] Nick Kuhn:** They want the same repeatable pattern across the board so that they can audit it and secure it and have their developers actually spend time writing the business logic versus like fiddling with infrastructure. So that's kind of like the whole premise behind, you know, the the whole platform as a service construct and, you know, Tanzu platform. And as So, you can imagine, or go ahead, yeah, **[0:08:34] Chris Benson:** no, no, go ahead, finish up and then I'll follow. All good. **[0:08:37] Nick Kuhn:** okay, uh, as as you could imagine, those principles when we're talking about apps could probably play nicely into this agent uh world that we're living in. **[0:08:45] Chris Benson:** So it it sounds like you're you're drawing a lot of commonality between kind of traditional app development and and all of the the, uh, the the structure that we're all used to, that we've been doing for forever. Um, and and kind of now we're into this agentic world, and maybe people have been thinking about that in a different way. But it sounds like you've really kind of said a and and correct me if I'm wrong, I'm gonna gonna throw something out here. **[0:09:11] Chris Benson:** Like, it's kind of the same thing in the sense of there there are differences, but agents and apps should sorta be treated the same way. Is that am I getting that correctly in terms of of how you're structuring that? And that maybe people need to look at what they've been doing for years and make that work for agents in the same way is that, is that a fair? **[0:09:32] Nick Kuhn:** Um, yeah, I mean, I think it's a it's a pretty fair assessment. And, uh, we're starting to see that more and more just within our customer base. And, uh, you know, e- even like, if you think about like apps back in the day, like someone would write some app on their laptop and like, run it on their laptop. But it's like, we can't just run it on, like, you gotta get it off your laptop somewhere. And the same thing with agents, you're like, I got this, you know, I've got all these agents running on my laptop. **[0:09:54] Nick Kuhn:** If I shut my lid, everything stops. Like, I, I don't really want that to happen, right? I want them to run 2047, you know, 365 and do all the work I give them. So, um, yeah, that I think that's kind of precisely what we're going with. **[0:10:04] Daniel Whitenack:** So so, I guess then it begs the question, why? why? why are people kind of throwing out what? Maybe their intuition, uh, like, in certain ways, people are saying, Oh, we have agents now, we need to do something totally different. Which I is maybe driven by some things that make an agent not an app, not just a sort of simple application. But also it doesn't necessarily mean, you know, obviously we have to throw out everything we've learned about platform engineering and, um, and and how to deploy things. **[0:10:38] Daniel Whitenack:** So, from your, from your mindset, what? W- Where does the kind of agent equals just another app? Where? Where might that fall apart? Or what are the kind of unique characteristics that you're dealing with on the agentic side? Uh, on the on the deployment pathway that you might not have had to consider before, or at least are considering in a new way. **[0:11:00] Nick Kuhn:** well, I mean, I I think some of the biggest differences, right? Where, like you talk about Cloud Foundry and Tanzu platform. It was kind of based on this premise of a a twelve factor application, where, like, storage and state are a little, you know, decoupled cleanly from the actual apps. You could, like, you know, I can, I can scale up to a thousand instances and be fine, and you handle session state and things. The traditional harnesses or agents were kind of built originally just be like, Ah, I've got file system access and I can just write a bunch of MD files and that's like my memory. **[0:11:28] Nick Kuhn:** Everything's great. And you're like, well, you start to get into cloud, cloud world, that things spin up and down and are ephemeral. Uh, you're gonna wanna save those MD files somewhere. They're gonna, they're gonna go, uh, go off into the ether. So that that's probably the, I think, the biggest challenge. When you start talking about, how do we take, uh, the app deployment methodology, right? And then push that into, like an agent running on a a kind of a cloud platform per se, it's probably the the biggest challenge. **[0:11:54] Nick Kuhn:** And then just kinda getting the fact that, um, there's some valid use cases for, like, your laptop or whatever. But then also as we're starting to see more and more like enterprise was, enterprises want agents to be on demand and like, usable kind of in a like, say, say, in a CI CD pipeline, or like on, you know, within part of their, uh, you know, e commerce suite, or just J- normal applications. And you want those to be kind of really close to the apps, right? **[0:12:17] Nick Kuhn:** Cause if you're, if you have them way off, you know, even just from a pure networking perspective. If you have, you know, the agent or the LLM or whatever that's like, you know, 30 hops away from the at the microservice, it's trying to call it. There's, you know, physics that are gonna add on to all of that latency and potentially at scale even be problematic. So they they kinda wanna collate all the intel, uh, co-locate the intelligence with the app and the data as close as possible. **[0:12:39] Nick Kuhn:** Right? That's what we've seen, too. That that's something that I didn't expect really, cause some of these, some of these responses are kind of long. But it's like you what we've seen with our customers at scale. Like, we wanna get the LLMs and the agents closer to us and our actual apps using them and the people using them as well. And not to mention, if you're using some of these SaaS providers, they're maybe not the most reliable in terms of what traditional enterprises expect and demand. **[0:13:02] Nick Kuhn:** Um, so you can't just have them, you know, going offline for hours, uh, cause, you know, even even at my past job, the FIR- the very first thing I did there was work on a warehouse inventory system. And now, let's just say it was for a large retailer that, uh, uh, was a grocery retailer in in, uh, in the US. And I was an, you know, intern out of college. And like, the app was older than me at the time, still older than me. **[0:13:21] Nick Kuhn:** And, you know, it's just it was a bunch of like, uh, you know, you know, uh, C and shell scripts on Unix systems. And if that thing went down, like within 5 minutes, like the warehouse was backing up trucks, like on the interstate. So it's like, you have to, like, the scale of enterprise versus just, you know, how, you know, uh, like, consumer is completely different scale. So that's why some of all the things we're trying to make them a little bit more enterprise grade and, uh, more more used to what, uh, these enterprises expect from software. **[0:13:55] Daniel Whitenack:** Some mornings, as I'm drinking my morning coffee, I listen to live news updates to figure out what's going on in the world. And it seems like recently, everyone is talking about AI kill switches, but the reality is that there is no one AI kill switch. We've moved from models to agents, those agents are connected to multiple models, they have an agent harness, they're connected to MCP servers and tools, and those agents are acting within a fleet, delegating to one another and interacting with one another. **[0:14:27] Daniel Whitenack:** In that environment, what you don't have is a single kill switch that solves all of your problems. But that doesn't mean that you can't exert your control. You just have to exert that control across various layers of that stack through, of, of course, component input, output safeguards, but also controls on agents tied to their agent identity. Things that track tool misuse or memory poisoning or goal drift, et cetera. And what we're providing at Prediction Guard, the company that I lead personally, is an AI control plane that you self-host in your own infrastructure. **[0:15:08] Daniel Whitenack:** That gives you that control plane or control layer for the relevant stack that agents operate on top of. I'd encourage you to check out what we're doing at Prediction Guard dot com slash practical ai. Go ahead and book a call with myself and the team to learn more about how you can gain control of the agents operating in your environment and exert zero trust principles in the way that you operate those agents. So check us out at prediction guard dot com slash practical ai. **[0:15:43] Daniel Whitenack:** That's prediction guard dot com slash practical ai. **[0:15:49] Chris Benson:** So, Nick, I would love to dive back. I wanna kinda build on what you've, what you've been sharing so far. And and part of that is that we're all diving into this multi agentic world. Um, where, you know, you know, some, you know, late last year, you know, you'd have an agent and and we and and then, you know, for most people, I think getting into multi agents, it was probably developers in a develop, you know, in in the environments that, uh, that the, uh, the AI providers were were making available. **[0:16:19] Chris Benson:** And you had multiple agents working on a project. But now we're really seeing, you know, with with these work products and other things that have come out, we're seeing, um, agents, uh, really multiplying across, uh, you know, many different contexts and with a lot of different utility. Uh, and and it's moved out of being just frontier services, and we're now doing that with our hosted agents as well that we're running. Uh, and so, like, this multi agentic world has just taken off in a very short amount of time. **[0:16:50] Chris Benson:** And as you're as if I'm kind of, I guess I'm asking if you can kind of paint a picture as you start scaling this out, um, in the enterprise, and what that looks like, like, could you describe, you know? And we have analogies, as you've pointed out, with kind of the traditional software development world and the containers and all the mo- you know, and how you're structuring, uh, deployment and stuff. Could you talk a little bit about what that looks like? **[0:17:17] Chris Benson:** Kind of paint a picture so that somebody can really get that in their head. Um, me, 1st of all, uh, about what that multi agent world looks like. When you were doing, when you were doing all these right things that you need to do in the enterprise. **[0:17:33] Nick Kuhn:** Yeah. So I mean, I think that the the 1st thing that we wanna focus on is that the enterprise, you know, needs to get whatever technology approved throughout their system. Uh, and then we so we are providing a harness, uh, called the, uh, Tanzu Agent Build pack, and that helps through that process. So our existing customers already have our customer, you know, we're already approved so that we can help provide them those tools. And we just make that process just another app deployment on the on the platform. **[0:18:01] Nick Kuhn:** So, uh, I probably haven't covered. They said, all explain what a build pack is, right? So when you, when Yeah, I was you, you about to, I know, was about to ask yeah, **[0:18:07] Chris Benson:** you that if you could kind of dive into what the specifics of each of those things does. **[0:18:11] Nick Kuhn:** sure. So when I would do demos before AI and before, you know, like a year or two ago or whatever, we would. I would always take like a Java app, and it was like a simple, like, kind of like, you know, music album called a Spring Music or whatever. But we take that Java code and be like a jar file, like compiled Java code. And we're like, all right, now we're gonna take this. We have a little simple manifest file that tells us what the what the name of the app is, how many, how much resources to give it. **[0:18:33] Nick Kuhn:** And we just run a command called cf push. And that would then just take that, that code, the jar file, and upload it to the platform. And the platform would be like, Oh, it's, it's a Java app. So I'm gonna use the Java buildpack, and the buildpack is, uh, it's basically a kind of a, uh, command set to make a best practice container based off that use case. So the Java buildpack knows to do all the JVM memory calculators and do the JDK and the certificates and all everything. **[0:18:57] Nick Kuhn:** That's best practice to run Java in a container on a cloud platform, uh, and that would be great. And then we would, you know, we would attach a database and a, you know, all these things and show how that that scales. Now we've taken that same concept and then said, Hey, we're gonna have this agent, we're gonna just cf push an agent. And instead of, like, you know, machine readable code, we have a human readable language, uh, the agent SMD. **[0:19:20] Nick Kuhn:** So basically, you tell what the agent it's gonna do, and then you just push it to the platform and it starts up with, you know, within a minute type of thing. And you can scale that up and you push as many agents as you want. And I think the the coolest thing that I've seen is that once we're on the platform, then we we can run models on the platform. So, you know, obviously a lot of our customers are air gapped and some of them were, uh, uh, were smart enough to buy GPUs a few years ago. **[0:19:41] Nick Kuhn:** So some of them have lots of GPUs. They can run all these local models and have a great experience. Some are wishing that they bought GPUs and, you know, hardware, as as the pricing of of all this hardware goes through the roof. Uh, but then they can run run the local models and then tie the agent to that. Or if they don't have, you know, they might have a contract with one of their cloud providers or one of their, you know, one of their approved, uh, LLMs of choice. **[0:20:03] Nick Kuhn:** And we can to register to that. But then that kinda gave us a simple like, here's your out of the box agent with chat experience. And then, you know, along the way, like, um, we've done a lot of things with MCP, so, you know, the model context protocol. I I probably you guys covered that on the show before, but it's, you know, basically a way for an app to talk to an LLM, like, very, very high level, right? **[0:20:23] Nick Kuhn:** So we that's become, uh, you know, useful as well as we then give the agent tools via MCP servers. And even at Broadcom, like, the only way approved way to use for our developers is to deploy MCP servers on on Tanzu platform. So that we have a whole set of MCP servers that are approved and hosted, and they're kind of secured and maintained because they're very similar to applications as well. And then we have a a concept of, like, the MCP gateway service that kind of registers that and secures all those the service. **[0:20:50] Nick Kuhn:** So then we can then extend the gateway to that agent, so then the gateway, this agent now has, like, secure access to a runtime, uh, you know, battle test runtime. It can talk to, um, an LLM that's approved and, uh, get tools via and gateway. And then we're starting to add in, like the memory service as well, to have a kind of a shared memory service. So we're kind of expanding all of that out, where we're seeing all this best practice app lifecycle. **[0:21:14] Nick Kuhn:** Go to, uh, uh, you know, see a push go. Here's an agent, here, here's all the things it wants to do. And then, you know, it can be a, it can be a security review agent. And like, one of the things I I showed, I was at a, I think, a week or two ago, I can't quite remember. I was in, I was in Las Vegas for a conference, VMware Explorer, and I had like a five phase demo where I walked through this. **[0:21:33] Nick Kuhn:** Maybe I'll show a little bit of this at the at the Midwest summit here. Uh, but the, you know, push the agent, bind, bind all these services. But the end, the end goal was like, the the boss level was like, all right. Now we have this, these agents sitting in there. And I can hook up, hook them up to a repo with like an event listener or webhook and say, all right. Now. Do a sig like a, you know, issue five on my repo. **[0:21:53] Nick Kuhn:** Do a security review on this repository. And then, like, it sends it off to the agent via webhook. And like, oh, the Tanzu agent, like it just fires up, gets it, it, you know, fires up from the platform. It gets a request and it's just immediately pulls down the repo and starts doing a a security review and then publishes or, uh, pushes up to the, uh, the issue that I created on GitHub and says, This, this is security review. **[0:22:13] Nick Kuhn:** So you could see how that flow would be really useful in enterprise, where, like, maybe on every git commit, you just have all these agents spinning up on the fly. That could be a security review agent. Um, you know, potentially like a, you know, a, a style, or, you know, code quality review agent, or a potentially even like a, I don't know, like, maybe a design review agent. All firing up on the fly as things like call. **[0:22:35] Nick Kuhn:** So it's kind of like, and then they all have their they're all in their own little sandbox and everything's proper, right? Cause part of, you know, the platform for a while, it's been like this very secured container runtime, where, like, we have the, you know, they can't talk to each other unless you enable them, so they can't go to the internet unless it's enabled. They can't, you know, escalate otherwise, they on, they only get access to what you give them. **[0:22:54] Nick Kuhn:** So it's kind of that benefit as well, and then obviously they're containerized, so they don't have access to the underlying Um host system as well. So that, you know, as we've seen, you know, some of these things of, uh, u- uncontrolled agent swarms, I think we have some remedies here to to some of these, uh, some of these AI labs could maybe take into account and implement some best practices. That's one throughout the past the two decades. **[0:23:17] Nick Kuhn:** s the unplanned So **[0:23:18] Chris Benson:** swarms, the one the swarms that you don't necessarily want. I actually have a 2 s follow up and and that is, it's, it's for my benefit. And you know, we've talked a lot on the show over, uh, various episodes about agents. You know, using MCP to get access to to different apps and services and tools and stuff like that out there. We haven't really talked about what an MCP gateway is. And I was wondering if you could share that for a moment, just as a detail, because that's kind of the one little new piece of architecture that we've never touched on, uh, on the show. **[0:23:48] Nick Kuhn:** sure, yeah. So if you think about an MCP gateway as a way to easily, um, control and scale access to MCP servers, especially within, uh, your in a cloud, I guess platform. So we may have like 30 or 40 MCP servers that we run, or I don't, I don't even know how many it is right. And then those get bound, those get registered and and bound to certain specific MCP gateway. So maybe there's like a, you know, and the MCP gateway is something we can spin up on the fly on on the platform. **[0:24:17] Nick Kuhn:** There are many different MCP gateways out there, there's many different AI gateways out there. Some are some of them are like the same, you know, the one and the same, um, but you basically register MCP servers to this gateway and the gateway kind of controls access, so to speak, and regulates that. So it may say, like, you can bind to this gateway and you only get these these MCP servers, you only get these MCP tools within it and that type of thing. **[0:24:40] Nick Kuhn:** So it's a way to easily abstract all the different MCP servers that may be in a organization and kind of direct them into a certain, uh, either a certain agent. Or we even have a flow where, like, you can t we'll, we'll take those MCP gateways that we run that front all of our MCP servers. And then you can say, Hey, go give me a give me a way to connect this to my cursor or my cloud code or my whatever. **[0:25:00] Nick Kuhn:** And then it just injects it in there. And then then your local agent has all the tools that are approved as well for your, uh, organization. And then it's just like, like, a simple click, and then it just registers. And then, like, uh, depending on the MCP server, it helps the handle the auth as well. Cause some of them are like, well, if it's my if I'm using the GitHub MCP server, I wanna pass my end user credentials all the way through to that MCP server. **[0:25:23] Nick Kuhn:** Cause I don't want, you know, I don't want it just to be like, well, here's our general generic service account for the entire organization. And every GitHub action is is gonna be, you know, seen by that one account. And you have to, you have to have the individual identity pass through. So you have, like, the concept of, like, single sign on and sign in as well for an identity for agents or humans running their agents on their their desktop. **[0:25:42] Nick Kuhn:** So that's kind of a quick level of view. And then a great way about that, too, is because it's all flowing through that gateway, we get metrics out of it. So we can see all the tool calls and all the all the events happening, coming from the agents to the MCP servers and back and forth. So you can kind of see what's happening, especially if, maybe if there's something unexpected. Or like, well, this one agent, you know, made 200000 tool calls to, you know, delete repo. **[0:26:05] Nick Kuhn:** Like, oh, like, maybe we should alert on that, like, that's probably not good. Uh, yeah, so, and you know, an another visibility or metric to to see what agents are doing or what tool calls they're doing as well. So I guess hopefully that made sense, cause that was, that's it did kinda how I understand it, right? **[0:26:20] Daniel Whitenack:** that. Yeah, that was great. And and there were a couple things that you mentioned in there, I think are additionally worth digging into. And you, you kind of have this, if I'm understanding right, in in part of the the build pack that you're working on, part of that centers around kind of pushing an agents. Md file. You mentioned, like, people have these MD files, ca- uh, hanging around. You mentioned memory, you mentioned identity. I'm wondering if you could kind of help us understand, uh, like, if I have, uh, if I, if I'm working on my laptop, right? **[0:26:56] Daniel Whitenack:** And I'm using a certain agent harness. I may have an MD file that is kind of generic. And then I have files that are created by the agent that it uses that are only corresponding to my single agent. A And then I have, you know, memory, and then, you know, calls into other things. As you're pushing this like off the laptop now, and I imagine taking that off, like, what belongs in, like an agents. Md file? **[0:27:24] Daniel Whitenack:** And what is, uh, like, as you're giving that example, right? You may have one agent in the platform that is a security reviewer for, um, uh, that that does security reviews, right? When you spin that agent up, does each instance of that, each session have a unique identity? What is the, uh, what's unique about that session and the data that pr- that is generated by that session? Versus maybe the things that are always static, like, I I'm not sure if the agents. **[0:27:56] Daniel Whitenack:** Md is is always static. So could you help us understand, like, which are the static elements, what's developing over time? How is that, like, state of the agent spread across, uh, you know, the implementation, I guess, **[0:28:08] Nick Kuhn:** sure, yeah. So if you think about it like in, I guess in in in this specific implementation, the the agent's build pack is basically like the the boilerplate code of what you want the agent or app to do. So, like, I'll do demos and I'll have it be like, you're a pirate, like, like, like, one of my demos is like, you're a, you're a, you're a, uh, a Jira, like, you're a senior software engineer. Um, you know, you're gonna, you're gonna watch this Jira, like, um, uh, page or I forgot the terminology here. **[0:28:36] Nick Kuhn:** But basically, watch this Jira queue and look for any inbound tickets. As inbound tickets come in, review them and like, you know, make sure that they're of good quality. And like, here's all these different things that you wanna do and like, don't do any of this. So it, it's more of a very simple agent SMD, where, like, uh, it's just telling, like, this agent, what, what it should do, and and how it should act. And then you, you can call that and have like, all right. **[0:28:57] Nick Kuhn:** Well, like, you know, ticket 500 came in and it was poorly documented and like, update that Jira ticket, you know, whatever. And then you can add fun things like, talk like a pirate. So it's like, argh, matey, you're, you know, ticket 500 is, uh, is terrible, right? Like, uh, go back and, you know, update it, that type of thing. So that's kind of where the the static part of it is, and then, like the memory service we have where you can attach it, you can have, you know, you know, potentially memory of a certain project. **[0:29:19] Nick Kuhn:** So, uh, you know, we kind of envision, like, each set of teams to have their own multiple set of agents, right? And it could be like, well, you know, team A's agents have the access to team A's memory. So as they come up, they know, like all this historical data of like, what, like the architecture of the application, the you know what, what's been done before, you know, like the roadmap, that type of thing. So as it spins up and does, like a security review, it can make, you know, proper, um, decisions and proper guidance. **[0:29:46] Nick Kuhn:** So that, you know, as you kind of build your local agents and kind of give them memory, and they become smarter, that that memory service, as you have agents spin up and down, they just immediately, they immediately know what, what's happened, uh, before, uh, know how to, how to proceed. **[0:29:59] Daniel Whitenack:** as you heard at the beginning of this episode, some amazing people like Nick, who's the guest on this episode, are joining us at the Midwest AI Summit, October 15th in Indianapolis, Indiana. Nick is gonna come talk about what it looks like to deploy AI agents in real world environments. And we've got a bunch of other amazing speakers talking about how AI enabled teams work. How to make decisions about what to say yes to and what to say no to in relation to AI, and much more. **[0:30:37] Daniel Whitenack:** Super practical and amazing talks. Plus, there's gonna be an AI engineering lounge where you can actually sit down with folks like myself, I'll be there. Get get review on your AI architecture, your stack, your roadmap, et cetera, towards the rollout of things like agents or other AI technology. This is a practical, amazing event that you don't wanna miss. There'll be great food, great people, great networking and practical value. Do not miss this. It's October 15th in Indianapolis, Indiana, and you can use the code Practical AI 20 to get 20 off registration. **[0:31:21] Daniel Whitenack:** So go to Midwest AI Summit dot com and use the code Practical AI 20 to get 20 off registration. **[0:31:29] Chris Benson:** Hey, before we were going into break, I think I may have cut you off. Uh, when, uh, when you were just starting to say something, uh, you wanna dive back into that real quick? **[0:31:40] Nick Kuhn:** Um, no, I I think I think I covered All good, it. I ho- uh, hopefully I answered the question again, but, **[0:31:46] Chris Benson:** that's no problem. So real, I really appre- like, this has been really good, uh, for helping me trying to conceptualize, you know, how all this fits together. Um, I think I had some understanding, but but you've gotten a level of detail. I, I wanna, I wanna ask you, as as we are looking forward, I'm I have several questions, uh, that are really kinda driving my thinking. You've got me, you got me thinking creatively based on what you said. **[0:32:13] Chris Benson:** So as you look at, you know, we've talked about MCP, um, there, there are new things coming out, things like, you know, there's the A2A, which is the agent to agent protocol, um, and organizations are starting to look at that. And and they already have, uh, their MCP servers, maybe, but they're trying to get the structure and kind of bring the sanity around it that you've been talking about. You know, that that then they kinda go, Oh, okay, it's not so different from what we already know. **[0:32:43] Chris Benson:** But as as this is evolving very fast and you have things like these new protocols, do you have any guidance on how to start integrating this constant flow of change in? Um, in terms of 1st on the technology, and I'll I'll hit the other half of that afterwards. But, uh, you know, as you're trying to bring things in and make it work. And have you guys, have you guys kind of thought about how to structure that? **[0:33:07] Nick Kuhn:** Yeah, I I think it's, I mean, I guess we'll, we'll just say, take baby steps from from everything, right? Because especially when we talk about the enterprise scope, um, they can be a lot slower to adopt some of these newer technologies. Uh, so you kinda layer that on and like, you don't have to necessarily adopt all of these things at once. You can maybe just get a simple agent running. And you know, I, for most, most places, you know, just getting access to an LLM is still the biggest hurdle, right? **[0:33:35] Nick Kuhn:** A secured, you know, approved, so, and then potentially, you know, going through the going through the AI AI Council or the committee, right? Like, everything must run through the AI council and be approved. If you know, like most, you know, if you're not, if you've never worked in an enterprise, most large enterprises have a yeah, I council or a committee **[0:33:51] Chris Benson:** do so, I know exactly **[0:33:51] Nick Kuhn:** for everything, right? **[0:33:52] Chris Benson:** what you're talking about. **[0:33:53] Nick Kuhn:** Yeah, so it's like, well, we shall go to the committee and we shall present our idea and we will wait six months and see what has the result been right. So you have to kind of have to work through the councils and the committees and and all that fun. But once you finally get something approved, you just just just iterate and you're like, don't don't try to boil the ocean, make baby steps, you know, to, uh, and and get progress. **[0:34:12] Nick Kuhn:** And then as you'll like, and you'll learn the technologies, and then you, the next step will just kind of be obvious. Like, well, like, I can make the agent better if I get some MCP servers, get them tools, all right, and then I've gotta get these tools approved and then add on to that. And then, you know, uh, you know, and some of these guardrails help inter, you know, in, uh, of Tanzu platform, help enterprises bring these tools to to to light. **[0:34:33] Nick Kuhn:** Uh, cause it's not just, you know, all this random stuff downloaded from the internet, right? Which that can be its own danger, uh, nowadays. Um, so having the, you know, having some some, uh, guardrails in place is is a good thing. If you've had, you know, if you have experience with some of these, uh, platforms or apps running before, take that, take that experience and that knowledge and kind of bring it forward and and utilize your existing people and skills. **[0:34:58] Nick Kuhn:** I think too, I think a lot, a lot of times, too, I see in organizations like a new technology will come up and like, a new team will be built and that new team will decree. But like, there's so much other, like, really skilled people that could help, and it, it's always kind of a a friction too. So how try to try to get the teams to work together too, and not not just have the new team doing all the new things. **[0:35:15] Nick Kuhn:** And then the the teams, the teams that have been there all the while have that. Like, that's always another constant flow. So try to try to break those silos down as well to help, you know, get people up to speed and and and get through that process. **[0:35:26] Chris Benson:** W- Having having worked in multiple enterprises myself, um, I think, you know, that last point, I think I've seen that multiple times and across different organizations. And you know, how, how do you bridge that? I think part of it, you know, you, you have, you kinda have. Every organization has its internal politics, they all have kind of the different structures. It's really common. Say, new tech, new team, uh, there. But then I think people recognize, you know, why, you know, that kind of you'll see that, and sometimes you'll see a reconciliation, but it always seems like a little bit of a struggle when that happens. **[0:36:04] Chris Benson:** Um, to try to, you know, do you have any thoughts around as you're, as you're trying to do that? You know, you may have, uh, you know, a lot of big organizations have, you know, they're very like one one business unit, maybe in a almost like in a different universe from another business unit. Sometimes, um, and and so how do you get that kind of cross adoption? Where? Where you're taking advantage of maybe both the new teams that may be there, but also some of the old, structured teams. **[0:36:36] Chris Benson:** And you're trying to spread the capability across the larger organization in a useful way. Um, do you have any, do you have any guidance? You know, I imagine it can't be that different from, you know, the the more traditional app dev side. But I think I think this is a struggle that a lot of that a lot of orgs are are facing right now. **[0:36:55] Nick Kuhn:** Yeah, well, I think, yeah, so I mean, I, it goes, I think, a lot both ways. So you, you have the new team, right? The new team can, like, their responsibility, new team is like, engage every other team because they have a lot of people that can help you out achieve your goal, right? Cause the new team probably most likely has a very, uh, stressful and like, like, you know, like, adopt AI everywhere, or before it was like, go cloud everywhere, right? **[0:37:18] Nick Kuhn:** Like those those goals are, like, not quite easy to to get going in an enterprise. So the the new team needs to, like, you know, potentially run, uh, you know, uh, office hours, weekly office hours. Reach out to their other teams, you know, maybe before, you know, like, like a lunch and learn, if you, if you're in the office and have people in the office, that type of thing. Uh, and just have, like, the a forum for people to come in and learn and get started and like, ask questions. **[0:37:43] Nick Kuhn:** And not, you know, like, hey, like, I, I saw this, you know, this post about, you know, this new platform or this new AI thing. How do I get started? Is there any documentation or what? What can I do to get started? And just kinda have, like, an open and like, you know, um, very, uh, welcoming place to get started to bring in the folks. And then if you're on some of the, you know, let's say not new teams or teams that have been around a while, be engaging and and and reach out to those teams. **[0:38:08] Nick Kuhn:** Cause a lot of the the new people are gonna need help, like they, you know, they're maybe under stress, so it's it's just breaking that down. And then I think with this iteration, right? Um, it's gonna happen a lot faster, and I think people just naturally wanna work together. Cause I I think I I was at VMware Explorer and I, I did a few talks and every I started every talk with, like, all right, let's let's get a show of hands in the room. **[0:38:29] Nick Kuhn:** Who has used one of these tools, like in at work, like Cursor, Cloud Code, whatever? And pretty much the entire room, and all of them went up, and I was like, Well, that's a lot more than I expected. So, like the adoption rate, even at, you know, the traditional, like, you know, platform or developer engineer, uh, and you know, or just infrastructure admin at at some of these, uh, personas is is well into that that scope. **[0:38:49] Nick Kuhn:** So the entire enterprise, I think, is picking up on this really fast. And the, you know, the more collaboration, I think, just will help out. So, you know, just office hours, you know, reach out, be proactive. And I guess if you're on, if don't be be pro, be, uh, be mindful or be, um, open to change. I just this is just in general, I if what I've seen before and and if you're, if you're resistant and resist the change, and you know, that's that's gonna kinda get you labeled and like, kinda put off to the side. **[0:39:17] Nick Kuhn:** But if you're, you may be at a, you may have your own opinions, but if you present them in a way that kinda, uh, is, let's say, maybe open minded per se. You have a better chance at some of those those Le- key learnings that you've you've dealt with throughout your career, to actually be applied in the the new way as well. Um, That makes sense. Um, yeah, **[0:39:34] Chris Benson:** I'm curious, I, I wanna, I wanna circle back for a moment on something you said. Um, as we're talking about kinda spreading across, um, my mind goes to security, uh, because I know in, you know, in my industry, security is a is a pretty big deal. And we do have air gapped things and stuff like that. That's what we do in defense. But, uh, as you're, as you're thinking about that, you know, one of the topics that is, uh, a really common topic now is kinda going back, uh, a few weeks. **[0:40:02] Chris Benson:** We k- we covered it, uh, in depth on a previous episode, the the whole open AI, the swarms got out, uh, hugging face, that whole thing. I, I'll refer people back if they don't, if they're not familiar with it, to our episode recently that covered that. And but that is top of mind. Uh, it's not only top of mind for security, uh, but it's top of mind for, uh, legal. It's top of mind for comms. As they're thinking about, what do we do if something like this were to happen in our org, whatever that org is? **[0:40:34] Chris Benson:** And can you, can you talk a little bit about, you know, as you've, as you've kind of brought the enterprise structure up to date to deal with agents? And you know, it's we're beyond just the the traditional software and app world, and we're, we're, we're taking some of the same lessons and reapplying them in a new context here. Can you talk a little bit about how that helps on the security side? If, if, for the folks out there that are really, you know, that's their job is to keep things from really going awry. **[0:41:04] Chris Benson:** Can you talk for a moment about keeping things in the box, if you will? **[0:41:08] Nick Kuhn:** Yes, for sure. And then I guess I'll, uh, I'll put a disclaimer. Um, these are all could be suggestions that to help out with. If you, if you really dig into some of the the the Hugging Face stuff, it's a little like, scary. So I'm not to say that we're like, better than all of the AI labs or anything like that. So, um, but if you if you look at some of the the things or how that kinda got started is where they, you know, they started getting out of the sandbox, right? **[0:41:30] Nick Kuhn:** And then they they found things that were like they could get access to. Where, you know, having monitoring and control around what those apps or agents can do is is, you know, something that's been a been in mind for all enterprise apps, right? So, like, having, you know, kinda guardrails, even like network zones of like, hey, this is a highly regulated zone, it it's it's super locked down. Like, even just like traditional firewall would've potentially blocked a lot of this stuff, right? **[0:41:53] Nick Kuhn:** So, uh, it, it's kinda key. Like, you know, a lot of the core enterprise learnings, they kind of maybe take that for, like, you know, the the old team versus the new team. It's like, well, the guys, you coulda just, you know, I don't know. Had some basic controls and like, I think they even talked about, like their monitoring wasn't working, uh, they weren't really monitoring it. And like, you have all these agent swarms, and then, of course, then then it got to the artifactory, which then it found the weak link, and the artifactory had the internet access, and somehow they magically, you know, zero day, the artifactory instance multiple times. **[0:42:20] Nick Kuhn:** So, eh? Not to say that we could prevent everything, but it's just you take those these core enterprise technologies that maybe would've helped out a little bit of, just, you know, uh, uh, agent control, like hardened, um, sandbox type con- constructs, very, uh, locked down network controls. Um, that would help a little bit potentially. Um, you know, just, you know, monitoring what's in the in the in the agent, make sure that the agents aren't, you know, somehow injecting tools that they're not supposed to have. **[0:42:48] Nick Kuhn:** I don't not not sure if that was an issue or not, but, you know, when you talk about an application, the whole dependency stack is always up to up to grab. So you wanna make sure that the dependency stack, the container, everything is, and the whole OS and the whole platform is trying to patch and reliable as possible. So it's, uh, I I think the the key thing is, obviously, you know, we had the whole mind bending effect of that. **[0:43:07] Nick Kuhn:** They somehow made this messaging board on Artifactory and then the guy got deleted and they recreated it. So there there's that factor, which I think everybody's a little like that goes into the whole AI's gonna kill us thing that happened over the weekend, right? Versus, uh, just do some basic security J- Just and basic stuff, just to clarify right? **[0:43:22] Chris Benson:** that that was a p- a social media post. Lest people assume, lest people **[0:43:26] Nick Kuhn:** yeah, sorry, sorry. misinterpret that A yeah, yeah, that that's, that's a great yeah. W- if you're not on, uh, AI Twitter or AI X, there's a lot of posts around. You know, uh, somebody left Anthropic, and a bunch of Anthropic people started posting around that. They're afraid that, you know, there's a greater than 10 chance that AI is gonna, uh, you know, take out humanity over the weekend Friday. And then that that start stirred up a lot of conversation, let's just say. **[0:43:49] Nick Kuhn:** So that's what I was referring **[0:43:50] Chris Benson:** a bit. to. Uh, yeah, yeah, Okay, um, I guess th- that that's useful. I appreciate that. I. We like to finish off by kind of giving you kind of a freeform question, and that is kind of toward the future. As you are are doing your job and, you know, running your your podcast and talking to people and and kind of building up, you know, your perspective on where things are going with this. Um, we ask, we like to ask guests to to go ahead and, uh, get crazy and prognosticate just a bit, and, um, we don't hold you to it, uh, but like, uh, really, the way we do this is, uh, when you're, when you're kind of just letting **[0:44:35] Chris Benson:** your mind wander and you're thinking about these things in the back of your mind. Going to bed at night, having a glass of wine, whatever it is you do to chill out. What do you think things are going like? What, what? And and you can choose the timeframe that you like, but I really like to think, like, what do you think is coming, what's next? Um, why, you know what? What should should orgs be having a thought toward for the future, even if it's not, even if we're not there yet today? **[0:45:02] Chris Benson:** Um, any, any thoughts on on what that future looks like as we close out? **[0:45:07] Nick Kuhn:** oh, oh, boy. It could be, it could be many things, but I I think from a a enterprise perspective, I I think we'll see a lot of like team change and a d roll change, and not even just an enterprise. Like the whole. Like, from the business side, things are gonna change a lot, right? Cause you're starting to see, and I, I was going through old episodes of my podcast this year and just some of the old, just the start of this year. **[0:45:27] Nick Kuhn:** And there's just now. It's like, Wow, has a lot has changed. And like, can't imagine, like, can you, like, you know, imagine a couple years from now how, how much cha- the rate of changes now if the L It's accelerating kind of proceed, right? So it's definitely. it's hard to imagine that, but I, I, I definitely think from a business perspective, we're gonna see like a radical change in, like, how, how, you know, development and, you know, product management and everything changes, or everything kind of, you know, there's gonna be like new roles get created. **[0:45:53] Nick Kuhn:** Uh, you know, orgs are gonna change, I think, and I think I think for the good, too. Cause I think, like, there there's always the fear of, uh, job loss. But I I find that I've, and I've heard this echoed across many, uh, personal experiences. I am, like, working harder than I ever have, cause I have all these agents and they like, they need stuff from me. And I'm constantly like, and I'm doing building things that I always wanted to build, but just never had the time to. **[0:46:14] Nick Kuhn:** So, um, I feel like we're all gonna be busy and it maybe maybe we need to, you know, not not get too crazy with the agents, but it's it's hard for me, cause I f- it's just it's, uh, it's fascinating, it's just it's really enjoyable. So doing a lot of things with automation, I can only imagine what these agents are gonna be like in the, you know, next six months in terms of, you know, what they can do for you. **[0:46:35] Nick Kuhn:** I think we'll see a lot with voice come come into play and maybe even a new style of interaction with the computer, uh, as well. So, um, that will be interesting as well. And then I, I, obviously, I think, you know, did you see the the posts like Hugging Face had little robot things on sale? Yes, yeah, I Yeah, so like a little was, uh, li- little microdot I, I things or whatever. Yeah, **[0:46:53] Chris Benson:** did. I was like, I was like, uh, to my wife, I was like, maybe we should give away. She's like, she's like, you have enough toys, you just yeah, well, don't. But **[0:47:00] Nick Kuhn:** I, I may have ordered a few for the family and I'm like, those things **[0:47:02] Chris Benson:** there you go. **[0:47:03] Nick Kuhn:** are gonna be awesome. So like, like robotics and things like, you know, I I think the LLM is is great and wonderful. But, uh, there's so many more possibilities where we could go that, I guess, like for humanity, right? As long as, you know, we prevent the terminator scenario, it will be great, right? So, uh, yeah, yeah, **[0:47:21] Chris Benson:** well, great. I appreciate you painting that, uh, that that helps a lot. Yeah, the rate of change is just insane now, and I don't I. I agree with you. I think it's going to get faster and faster. Um, but great way to end the show. Uh, a lot of fun. Always. I always love to hear what people say at the uh, when, when, when we're asking about kind of where they think things are going. Um, thank you for coming on the show today. **[0:47:42] Chris Benson:** It was a great conversation. I learned so much. Um, uh, really appreciate that. And I hope people, uh, tune in to Cloud Foundry Weekly to to hear you talking more about these topics. And they should definitely go to the Midwest Summit, uh, and hear your talk. Um, uh, I was there last year, uh, did a talk, uh, I won't be there this year, uh. So I'll have to see if I can get a hold of the video of it or something. **[0:48:07] Chris Benson:** But anyway, thanks for coming on Practical AI today. **[0:48:10] Nick Kuhn:** all right, thanks for having me. **[0:48:16] Narrator:** All right, that's our show for this week. If you haven't checked out our website, head to practicalai. fm and be sure to connect with us on LinkedIn X or Bluesky. You'll see us posting insights related to the latest AI developments, and we would love for you to join the conversation. Thanks to our partner Prediction Guard for providing operational support for the show. Check them out at predictionguard. com. Also, thanks to Breakmaster Cylinder for the beats and to you for listening. **[0:48:43] Narrator:** That's all for now, but you'll hear from us again next week.