(So you can skip ahead, if you want.)

00:00 AI Isn’t Coming for Your Job  
03:16 The AI Hype Cycle & Why Enterprises Are Confused 
06:19 What AI Adoption Really Looks Like  
09:22 How Engineers Should Think About Learning AI 
12:23 The Risks of Over-Relying on AI & Losing Fundamentals 
15:35 What MCP Is & Why It Matters 
19:30 How to Let AI Act Safely in Production 
27:28 Why AI Needs a Platform & Orchestration Layer 
38:17 How AI Changes Careers Without Replacing Engineers 
56:10 What the Future of AI in Networking Look Like 

Dakota Seufert-Snow • 00:00

Everyone keeps saying the same thing. AI is coming for your job. And I’m here to tell you that’s not necessarily true. But what is true is that the people who understand how AI is actually implemented are about to outpace everyone else here in IT. And the wild part is that most engineers have never even heard of the technology that’s quietly making it all possible. Today I’m joined by someone who’s not only talking about the future of automation, he’s actually building the systems that power it. William Collins has spent over 20 years in enterprise IT, startups, automation, and is now helping shape how AI is actually integrated into real networks.

Dakota Seufert-Snow • 00:44

This isn’t theory. This is someone who’s in the code, in the conversations, and in the rooms where this future is being created. By the end of this episode, you’re gonna understand exactly what is coming, what skills are needed next, and why MCP might be the single most important acronym you learned this year. Welcome to the show, Williams. Thank you so much for taking the time to join us today.

William Collins • 01:09

Yeah, glad to be here. Love the channel, love all the work you’re doing. I really appreciate it.

Dakota Seufert-Snow • 01:14

And you know, kind of before we kick things off, um, do you want to give us a little bit of background about who you are, what you’re doing, and uh why the folks at home should should listen to this.

William Collins • 01:25

Awesome. Yeah, so just to get started, so what I do today, so I’m I’m the director of tech evangelism at a company called Itential, and we’re really a network automation and orchestration company or just general infrastructure, really. We can automate anything. And my job is essentially to help bridge that gap between what our technology can do and the real-world problems that network engineers and IT leaders are trying to solve. And I also host the Cloud Gambit podcast, which recently got adopted into the Packet Pushers family. But as far as like my background, I started working in tech really in high school. Back before I knew, well, actually, really back before I knew you could make money and a career out of it, I kind of had a

William Collins • 02:11

Something that happened early on in life that um had me sitting in a house with nothing else to do, so I got into like building computers, and that’s kind of where I started.

Dakota Seufert-Snow • 02:21

Yeah, I I I think uh I I definitely had a similar background. You know, I started building computers from a young age and got a really kind of passion from technology for technology there. Um it didn’t end up transposing into a career until later in life, but that passion kind of really stuck with me as well, though.

William Collins • 02:41

Yeah, same here. And it’s it’s funny because it’s almost kind of like a builder tinker mindset. Um, you know, you just building things is fun, making things work is fun, and in contrast, hey, networks, we want things to work. Like there’s nothing more satisfying than you know, building a greenfield network or fixing a problem in Brownfield when you have different overlays and abstractions, you get into the nuts and bolts, you have to go through troubleshooting, maybe throw your red cape on for a 2nd . It feels real good. Networking is super fun to work in.

Dakota Seufert-Snow • 03:16

It is, and I think that’s what drew me to networking so much. But you know, to kick things off here, I want to hit on something that you said during our our pre podcast chat that kind of really stuck with me. You know, you you said that the hype around AI right now is so so thick that you could cut it with a butter knife, and uh that that is definitely the truth, I feel like right now. But what do you see in the market right now? What’s what is real? What is all you know, what is fluff? I feel like AI, like you and I were at Cisco Live, and AI was just vomited over everything, whether we wanted it there or not.

Dakota Seufert-Snow • 03:53

Um what do you think is going on in the space right now?

William Collins • 03:57

I’m just gonna go completely transparent and speak from the the heart uh on this one. So Historically, if you look at so you have suppliers, you have vendors, they need to sell software. They have to sell things, you know, to, you know, in order to continue to exist and be a healthy company. But then you have enterprises, you know, down to mid market and smaller companies that are buying technology and they have to be able to adopt it. So one thing I’m seeing out there right now is it’s so hard for enterprises and just the companies that are buying this stuff to understand what actually something is. What are we buying?

William Collins • 04:41

What is the value proposition? What does ROI look like? How do you put that in a budget? Um, is billing going to be kind of like cloud computing is like what does all this stuff look like? And then you have companies up and coming that are just trying to sell things, and a lot of times what you have is, you know, historically going way, way back, um Marketing teams a lot of times will just go out there and you know say anything to try to sell something. Yeah, our product kind of does everything, it just does all the things, and then that causes confusion.

William Collins • 05:13

Well, AI has kind of taken that problem and put it on steroids because now so many teams and so many different um sellers are using AI to basically say, hey, take what I do and put it in a marketing strategy to sell to like all these different verticals, and then you just get all this stuff. So I think there’s just a lot of confusion out there, which is common. Of course, it’s common this early in the hype cycle. We’re still so early with AI. And what does AI even mean? What does it mean if you’re working in infrastructure, if you’re a network engineer? Like, what does any of this stuff actually mean?

William Collins • 05:54

What is the value to you? You know, how deep do you have to go down the rabbit hole for learning? You know, what are you supposed to learn? Where do you start? There’s just so much confusion, but it’s starting to get wrangled in because there’s only so long that these wheels can spin that the real use cases end up, you know, falling through the cracks, and that’s where you know I think it’s important to focus.

Dakota Seufert-Snow • 06:19

No, um 100%. You know, I kind of feel like this is a repeat of what happened when cloud computing came out. And you kind of touched on that a little bit. I felt like when cloud computing was just debuting, everything was moving to the crowd. They were throwing everything that they could at the cloud and seeing what was stuck. And uh and then that kind of died off a little bit, and the good things stayed. You know, I’m not saying cloud was just, you know, a hype and you know, uh buzzword for it was, but you know what I mean?

Dakota Seufert-Snow • 06:48

Is that the things that were actually useful stayed in the cloud, and then some things kind of started to fall back down to where they belong, in all honesty. And I feel like that’s the same thing what’s going on with AI. Is everyone’s throwing everything at AI, seeing what sticks, and the good things that are actually making our lives easier, that are actually doing good, are the things that’s gonna actually be around and help move the industry forward.

William Collins • 07:15

I totally agree. Um you know, and it it just it always, if you think about zooming out, it’s always like so important to zoom out because I was talking to someone just a few. I’d say like two or three months ago. And they worked for a pretty big company that was like 25% through rolling out SD WAN. Like they had just kind of gotten started. And I was just thinking in my mind, like, wow, we did that. Like we were done, like at one company I worked at, we were done like 10 years ago.

William Collins • 07:47

And it it’s just it’s been around like so long, but you have this diffusion of innovations, like how it proliferates through the market. You have like your um your game changers that are basically building these things, like the Googles of the world. Like they aren’t even looking at where the puck is going. They’re you know, constructing the building, the power, they’re doing all the things. They’re engineering hardware, they’re just building silicon, they’re doing all the things. But then you have the companies that are looking at okay, where is that puck going? That’s where we want to be, all the way down to maybe some of the laggards that maybe don’t have the expertise or maybe they don’t have the budget to get things done, you know, which is a challenge in and of itself.

William Collins • 08:31

So, yeah, it takes a while for these technologies to proliferate through the market, and AI is gonna be no different.

Dakota Seufert-Snow • 08:38

No, one 100%. You know when funny is you know, when you you 1st started talking about you know that company implemented SD WAN, I’m like, man, that’s a that’s a buzzword I haven’t heard in a while. It’s just like baked into everything now. It’s just it is like it’s just like another part of our day. But I remember when it also came out too, it was just like, oh, we gotta do we gotta implement SD WAN. I’m like, and you know, at the organization I was at, I’m like, why? It actually doesn’t make sense for us, but you know, we we had to implement it uh just because it was the new thing.

Dakota Seufert-Snow • 09:07

Uh so I a hundred percent agree. Um, and I’m just out of curiosity, really quick, for those listening, you know, what advice do you have for like people that are kind of getting overwhelmed at this point by just how prevalent AI is in everything right now?

William Collins • 09:22

You know, it’s funny. Funny you say that because my answer to that question has changed so much in like the past month, even. So, 1st of all, no matter what, like saying AI is like saying uh like the medical field. Like, what does that even mean? Like you have you have folks that build robots that do surgery, you have folks that use the robots, you have doctors actually doing surgery, they’re doing different um performing operations on different parts of the body, etc. And you have RNs, you know, LPNs, you have so many people that are expertise in different things that contribute to like a higher goal, you know, to execute on something. So one of the things I I used to recommend is always like learn some you know at least one or two things rather deeply.

William Collins • 10:17

So if you’re in network engineering, that might be like TCPIP or BGP, like learn something that’s fundamental that isn’t going away. And as you try to navigate the confusion of everything else that’s stacked on top of that, um, one thing I found, particularly when I was working on the enterprise side that was really useful is okay, what’s a problem that I’m solving or that I have to work on day to day with my job today? Is there some way that I can figure out okay, this AI MCP stuff? Can it fit into what I’m doing? And also, there’s tons of ways to lab this stuff, like free tiers that you can run things on in the cloud, um, cheap subscriptions, just buying some tokens. Like it’s not super expensive to just start labbing and figuring things out. Um, so I’m always I’m a big believer in like practice by doing, experiment.

William Collins • 11:14

You know, that’s one of the best ways to learn. And then lastly, I actually recently uh Um wrote a prompt. I just started using like uh Claude code here in the past two months, like just trying to figure it out and and start using it to optimize some of my workflow. But just going in and and just figuring it out. And I I built this prompt that that basically said, hey, I am a I forget how I worded it. It was like I am a college graduate from computer science, yada yada yada.

William Collins • 11:50

I built like a little profile. I my focus is network engineering. This is the year, these are the big innovations. What is actually real and applicable to my career that I should be focusing on? And that what it spit out was actually really powerful, really useful. So use those prompts. Like, don’t just go in like Leroy Jenkins and say, hey, what do I need to learn today?

William Collins • 12:15

Because that is not gonna get you anything valuable. It’s gonna just start assuming and hallucinating and guessing on all sorts of stuff.

Dakota Seufert-Snow • 12:23

You know, the the power of good prompting is huge. Um, you know, I I’m in a crossroads here. My employer is not very AI friendly. They’re they’re scared. You know, the the big bosses are scared of it. Where me, on the other hand, I’m so intrigued. I’m in some I’m in some large language model every day.

Dakota Seufert-Snow • 12:47

I’m I’m doing different things with it. I just find it fascinating. So I have to do it at home. You know, I have my home lab networks and things that I tinker with, but it I I learned early on you can’t just give it some some Joe Schmo like basic prompt, like, hey, do this for me, because it’s gonna just completely go off the rails, and you’re gonna be fighting it to do what you actually need to do. So the power of you know good prompting is huge, and it can be used in so many different ways. And I love that example you just gave because you know, a lot of people are using it to help learn what they need to for this career field to help try to stay ahead of the curve. And

Dakota Seufert-Snow • 13:30

With AI, it can be difficult when those hallucinations happen and you might not know whether or not it’s hallucinating, it can really lead you down the wrong path. And then you’re sitting, you know, in a job interview, you’re and you’re spouting the stuff that you think you know, and they’re like, Are you from Mars? Like, what are you talking about? That’s not how that works. Um, and I and you know, I bring that example up because I seen it, you know, I’m a hiring manager, and I had someone telling me something, I’m like, No. Like, where did you learn that? And he’s like, Oh, well, I I use AI and it told me that’s true.

William Collins • 14:04

I’m like chat GPT.

Dakota Seufert-Snow • 14:07

Go back and yeah, exactly, exactly. And I just I had to I had to hold myself back from laughing because like I felt bad for this person because like they had been I don’t know how they’ve been using it, but yeah, that’s that’s a uh that’s a huge thing to also consider, you know, with AI. It’s I still feel it’s so much in its infancy stages, and who’s late hallucinations can really run wild sometimes.

William Collins • 14:32

Yeah, and even using it when you shouldn’t. I’ll tell you, even the other day, so I was working on a I had this uh spine leaf topology that I built out in Container Lab, and um I forget what. One of my spines or all of my spines, I can’t remember. There was some problem. And I was like so tempted to just dump the configs in chat or uh in an LLM to figure out what the problem was. And I’m like, I can’t do this. I can’t do this for everything.

William Collins • 15:00

So I sat there and I did network troubleshooting until I found the issue, which took a little longer than I was like. But that keeps it kind of keeps your edge in place a little bit because I don’t want to like lose. I don’t want to make my my job and some of my things so easy to where I’m just using it for everything. And I’m doing that to be intentional, not that I don’t want their time back.

Dakota Seufert-Snow • 15:22

Yeah, exactly. No, absolutely, because that’s what’s going to keep you from being replaced by just someone who can prompt you know your job through you know away. So, you know, having those skills in front of mind. Exactly.

William Collins • 15:35

And yeah, speaking of context, you mentioned MCP, which was the other part of my um I forget where I was going with that answer, but like MCP is definitely uh model context protocol. It’s been the game changer for AI as far as being adoptable, I think, in enterprise.

Dakota Seufert-Snow • 15:52

So absolutely. And I that’s was literally the next thing I was gonna ask you is you know, MCP is kind of the hot new thing for automation. And I I feel like a lot of IT pros still don’t understand it or even quite understand yeah, what it is. You know, they may have never heard of an MCP server or what it does. Do you can you kind of break it down what MCP and like like I said in the beginning, why it’s probably one of the most important things when it comes to AI and networking that people should really start learning?

William Collins • 16:24

Yeah, absolutely. So MCP has become so important for the the success of making. You know, AI actually work at an enterprise skill to enterprise level. And one thing I heard a lot of when I 1st started looking at MCP was hey, it’s just a wrapper around an API. It’s not anything else. It’s just nothing beyond, you know, the existing, you know, function calling mechanisms and things we build. And I I dug in, you know, because I kind of wanted to believe that.

William Collins • 16:54

Because believe it or not, Dakota, like whenever anything new comes out that I have to learn, my 1st reaction usually is like, uh, not another thing. Another thing. I just don’t have time for all these things. Um, it’s a little crazy. So is I started digging into MCP, um, and I guess we should start out with a uh oh like an explanation of like why what is MCP or why does it exist? So it kind of just hit its one year anniversary, so it’s only a year old. So it’s got its crazy one year onesie.

William Collins • 17:27

Threw a birthday party for it, it was great. Everybody loved it. So um MCP is basically it’s an open protocol. It’s open source. You can actually go to the GitHub repo and look at it. Um, and if you look at the GitHub repo, I think the official definition is it’s an open source protocol that enables uh integration between LLM applications and external data sources and tools.

William Collins • 17:58

So basically a way to securely use an LLM against infrastructure that you haven’t managed. So if you you can think about it like um so MCP is kind of to AI, like what BGP is to routing. So it’s a it’s a standardized way for different systems to exchange information and capabilities so they can work together. And I guess going beyond that, like what is the problem it solves? So Imagine if every router vendor invented their own routing protocol that only worked with their equipment, yada yada yada. We all know that never ended well.

William Collins • 18:46

Um, but that’s essentially kind of where AI integrations were, like pre MCP. So every AI model had its own way of connecting tools, uh databases, external systems, etc. You know, you had all these developers, you know, writing all this custom glue code everywhere for integrations because developers are going to develop. That’s what they do. They build a lot of stuff. And then what happened was MCP kind of got shimmed in there and it creates a common control plane between AI models and the tools and data they need to access. So instead of like a

William Collins • 19:24

It’s kind of like going from hub and spoke to full mesh, if if that kind of makes sense. And making integrations a lot easier.

Dakota Seufert-Snow • 19:30

No, absolutely. You know, it’s funny. The 1st time I actually heard the turn NCP was at the Itential booth at Cisco Live. Um that’s kind of where I got introduced to it. I’m like, what what do you mean? Like it it’s the bridgeway almost from AI to your network. And it it didn’t like I still, to be honest with you, don’t fully understand it because I’m not in the weeds enough with it.

Dakota Seufert-Snow • 19:52

You know, it’s not something that I can necessarily implement yet into my networks, but um it’s I can definitely see how it’s really going to help shape the future and bridge the gap there. Um, you know, and I guess, you know, just to kind of talk about what you guys at Itential are doing with MCP, it kind of intrigued me. Do you mind kind of um diving into that a little bit?

William Collins • 20:16

Yeah, so 1st of all, that the way that uh Itential was approaching AI was one of the reasons I just started working at Itensal this year, earlier this year. And one of the things I loved so much is like when LLMs sort of came to market and everybody jumped on just every little thing. Every, you know, all tons of vendors had these chatbots that would allow you to chat with. Like not very much documentation. You know, there was just a chatbot for everything and all these different things. And I loved how Itention didn’t just jump on that wagon immediately, but they were thinking about um, and I remember in my interviews, it was one of the things that was important to me was hey, we’re not just gonna go and try and roll anything out to market. We want to wait until like a real use case comes up and really build around that real use case to provide real value to our customers.

William Collins • 21:10

So what that kind of looked like is, and again, we’ve been on an aggressive innovation trajectory this year. Um, I’ve had a front row seat, it’s been crazy, exciting, and just awesome. But it it kind of started out in May 2025. Yeah, we’re still in we’re not 2026 yet, but it’s close. Yeah. Starting to get the wires crossed. But we we launched the our MCP server and uh

William Collins • 21:40

Prague, Czech Republic, at an event called Autocon 3. So the core idea was deceptively simple, but powerful. And it was that you know, enterprises are adopting, they’re trying to adopt this agent stuff, LOMs, they’re trying to use co-pilots, and it’s going so fast. But in our minds, nobody had really solved the uh let’s use network analogies all day. So the last mile problem. Let’s just say last mile problem. How do you let AI actually do things in production infrastructure?

William Collins • 22:15

That just makes me nervous. Yeah, exactly. But you’ve got to do it without losing governance, compliance, auditability. You have to have those things. So how do you do that? And the MCP server was our answer there.

Dakota Seufert-Snow • 22:31

And yeah, I mean that that’s when you just started like, how do we let AI into the production? I’m just like, my stomach started churning. I was just like, uh, you know, because I’ve seen you know AI hallucinate when I’ve used it to help me troubleshoot problems. But yeah, it MCP kind of puts those guardrails, in a sense, into on AI. Um do you mind kind of diving a little bit deeper on like how how that happens? Because I’m, you know, just for I know I’m curious, so I’m sure the the audience listening is.

William Collins • 23:04

Yeah, so again, the MCP server was our answer to try and solve for that. And so as we discussed, you know, anthropic came to market with model context protocol as a standard. So it acts as a control error between the AI systems and the itential platform. So every There’s so many words for things now, it’s like out of control. But for every, I would say like AI generated action, whether it’s like a configuration change, um, a compliance check or something for remediation, like a remediation workflow. Um, it gets routed through a like a policy enforced workflow.

William Collins • 23:40

So the existing workflows, validations, and approval systems that you already had in place, the governance you already had in place with Itential, like all those guardrails, are actually still there and still working. It’s just everything on top of that, how you interact with them, how you’re able to integrate them with other things, is much more simple with MCP. And the exposing and filtering and dynamic calling of different tools in tandem with other tools. So this you can think of MCP is kind of like the catalyst to get things really going to where. Using agents is a gentic AI thing can become like real life. So we recently at Autocon 4, which was a few weeks ago actually, we launched our Flow AI, which is a full orchestration platform. And this takes everything we learned from the MCP server and kind of extends it into what we’re calling AI to action continuum.

William Collins • 24:47

So going into um, I guess staying kind of more focused on MCP, but like you kind of need that you need safe integration, you need things like OAuth under the hood, you need guardrails, you need all of those things to really. Understand and define what is contextual and like where you know where the basically where the D mark is from reasoning to determinism. So what I was talking about earlier with those those workflows that go through and you know test something or they validate something or they do a specific thing, they include guardrails. Those things are are deterministic workflows. But all the things that require so much reasoning that a human would have to do above that layer that often takes a ton of time. And now a good comparison to that would be like finding an available IP address in a range in some system that you use. Well, there’s many different checks to where you can determine if an IP address is being used.

William Collins • 25:56

You can look in that system and see, oh, it’s there. Um, it’s reserved, it’s not reserved. You can do checks to make sure it’s not reachable from different networks within your organization. There’s lots of stuff you can do. So you can think about all that advanced reasoning being the agentic stuff on top. And and really the sky’s the limit with the agent stuff. There’s so many different

William Collins • 26:18

Uh very cool use cases, but yeah, we we don’t have to go there uh for the conversation.

Dakota Seufert-Snow • 26:24

It’s it’s it’s fascinating. That those things is what excite me about the future of automation. And to I think the untrained ear, that sounds like it’s gonna replace people. But to me, it feels like it’s just more tools to make your workflow better to actually allow you to do the things we’ve been dreaming about for years, you know, the the things that we’ve been begging for. You can actually now start implementing some of those things. Um but I want to backtrack a little bit before that. Um you mentioned something really fascinating.

Dakota Seufert-Snow • 26:57

You know, uh we have these startups right now that are building the tech that these enterprise companies want, you know, but enterprises often can’t really adapt it without the right foundation. And I kind of feel like MCP is again bridging that gap for them. You know, it’s helping put those securities in place so it can actually be adopted by more organizations and you know become more mainstream. Am I right there? Am I misunderstanding it?

William Collins • 27:28

No, that’s true, definitely, but it’s like the whole analogy of um you know, how do you eat an elephant, like one bite at a time? There’s so many things that you have to do. And one of the things that we’re big on at ITential is It’s it’s a you you know, these things aren’t absolute must-haves, but it’s a good idea to have some foundational things in place with automation 1st . Like get some of these wheels turning. And think of like, okay, like if you’re in that spot where You’re maybe a team of three people, and you’re the only ones doing network automation for the entire company.

William Collins • 28:07

And if one of you left, you have problems, and it’s back to doing a lot of manual things and a lot of things break. That’s that’s a problem. And you’re gonna run into that same problem if you start to just throw AI on top of things. It’s actually maybe going to make some things worse. So there are some fundamental mechanics that are, I don’t want to say they’re absolute must-haves, but they make a lot of sense, you know, before you start embarking on this journey. And one of those things I would say is, you know, taking a platform-centric approach to how you build and maintain infrastructure. Uh, so that way you can really orchestrate across like federated systems like typical big, you know, like enterprise companies have.

William Collins • 28:57

So it’s not just, hey, uh, me, William, I need to automate like 30 switches or something, and that’s it. I’m in my own little world. It goes beyond that because you have ticketing systems you have to update. Uh, you have you know, monitoring systems and things you have to onboard, you have other teams that you have to update. And you know, that’s one of the beauties of like where this MCP paradigm fits in, because you know, one of our partners, uh, Selector AI, they do telemetry and they take all this contextual data from network devices and do um just a lot of triage and and let you know sort of the the problem behind the issue. So it’s like you plug in their MCP and they’re the visibility and kind of the 1st face of the troubleshooting phase, and then you lock our MCP in next to that, and we do auto remediation for said problem based on all this contextual data. that normally a human would have to get.

William Collins • 29:57

So if you think about looking at the the routing table for BGP, like let’s say you had a BGP flapping issue, there’s a lot of different things that can make BGP flap, whether it’s upstream or something, an optic or some problem on the site. Well, going through and figuring those things out, like when I worked in ops, before we could just adjust BGP or like shut down a neighbor to, you know, for stability’s sake. Um, we would have to go through and check a bunch of stuff and we’d have to document it in a ticket before we could do it. Well, imagine if that busy part of the human aspect of that work was already taken care of, like the ticket was already documented, you knew what the issue was, and then you could just run one of a few remediations, either automatically or with a human in the loop. So that becomes a really big time saving, is what I’m getting at, is utilizing these tools, you’re saving yourself time. And that’s the biggest complaint I had as a network engineer. For as long as I was a network engineer, is I don’t have time because I’m fire fighting.

William Collins • 31:01

Well, what happens if you could just limit that fire fighting by 50%? That’s a lot. It’s a lot of time.

Dakota Seufert-Snow • 31:09

Yeah, I mean, especially when you have organizations that are working with really small teams. You know, for years, I um I was the only guy in you know working for this ISP managing our network operations center, and I found found myself constantly putting out fires, and I could never do things to advance systems to I wasn’t I was always fixing problems. I was never able to prevent them because as soon as I got one thing fixed, oh gosh, this thing’s gone fire now. And um, so I I could definitely see how having these systems because you know things aren’t gonna necessarily change there where you know it’s not just like I’m gonna snap my finger and then have 20 employees under me. Um that’s just not how businesses work anymore. But having the proper tools that help me do my job better is is huge. Um and you know, that’s just I feel like one use case like for MCP.

Dakota Seufert-Snow • 32:07

And you know, you’re in the weeds more, you you see how MCP is being used, you know. Other than you know, trying to help make our lives easier, what are some other advantages that you see businesses like how are they implementing it to help further along their organization?

William Collins • 32:26

Well, one thing that I’ve seen a lot, so usually it’s like when you adopt something like network automation. Like I remember when network automation started to gain steam, and the 1st time. Yeah, the 1st time I was actually allowed officially to use network automation in a big network, it was all read-only. Like we weren’t making changes. We were pulling specific types of data into a machine. We’d built some Python based on like SOAP, XML craziness back in the day before Rust stuff was popular. And then we would transform that data that we pulled from these different places in the network, and then we would populate it in a dashboard.

William Collins • 33:09

And all of this took a lot of lines of code and a lot of different things to get just that one thing working and that dashboard up for our network operations center that showed this these top things that we we wanted to see at all times. And there were things at the time that we would like we were actually waiting on a custom integration with one of our monitoring vendors that we had. And we just waited for a while and we just decided to build it. Now MCP is really useful in that instead of if you think about how a RESTful API works, if I’m building something like that’s based on REST, um, you know, MCP being a protocol, REST is not a protocol. REST is actually an architecture style framework that uses a protocol, it uses HTTP under the hood. Um, but RESTful APIs, they’re stateless by design. So every request is a self-contained request.

William Collins • 34:07

There’s no server side session state or anything. So when I’m building something with MCP to do something useful like that, I’m saying, okay, I have a RESTful call to like maybe pull a list of devices from inventory, and then I’m going to have another call that’s going to filter this other device type, OS type, maybe, or something along those lines. And then from there, I’m going to pull the config from that device. I have a separate call for that. You know, there’s so it’s like this um Lego building of different RESTful APIs to get you to your you know outcome where MCP is more like um. It’s not built for humans to write software against like REST. It’s more for AI models to interact with these external systems.

William Collins • 34:51

And it’s stateful by design. So it maintains connection throughout the duration of the session. So you have things now to where it’s easier to integrate and pull data from system A and system B and system C, and then maybe to like send a report to your boss daily with your company’s brand guidelines stamped to the report. So it looks official. So with MCP, you know, this is hypothetical, but I could be in my chat host and I could say, hey. I want to pull the software version or the status of these certs or this or that. I want to pull that data from this subset of devices.

William Collins • 35:33

Once you do that, I want you to put these in a table categorized or stack ranked this way. And then I want you to generate this in a PDF, and I’m going to provide you brand guidelines. And then from there, I have the other MCP for my mailbox or something else. I want you to mail that to this person, which is my boss. I want you to do this like every other day or something. So I can type that in with human, you know, just text. And get that outcome at the end or the end of the tunnel.

William Collins • 36:06

So and doing that manually or building something via rest with some of the custom things we need to see would be very challenging for most network engineers. So doing simple things like that. Yeah, exactly. Time. The thing that you can’t get back.

Dakota Seufert-Snow • 36:23

No, and I I a hundred percent see the value in that because you know a lot of network engineers are already spread thin. You know, they’re they’re trying to do they’re trying to do everything. And uh just being able to buy back that time to build those systems, and then honestly, there’s a chance that maybe even build it better than you could have in the 1st place, just because you know, you you only can know so many things. Yo, we there’s there’s only so much knowledge a human can take on. And um, so by being able to do multiple things that maybe you don’t quite have all the knowledge on, you’re making yourself a more qualified job candidate as well. Because now all of a sudden you’ve unlocked this other skill set without having to invest years to learn like a whole nother coding language and all this other thing, just by being able to communicate in a human way with these systems now.

William Collins • 37:19

Yeah, yeah, and it compounds too. So When you think about back to your comments earlier about the job loss, that’s one thing I hear all the time. And is someone who recently started to really take a stab at vibe coding here in the past two months or so, three months, you cannot, I mean, you can build a very small prototype. I mean, maybe you can get maybe 20% of the way there, but once your code base gets too big, it’s really hard. And once you have to start rationalizing some very complicated design decisions, the AI and the way that AI works with tokens and quadratic complexity of tokens and like losing context over long, there’s just a lot of reasons why it’s really hard for someone that doesn’t have coding experience to build a full fledged application. Because it’s really hard, apps are hard to maintain.

William Collins • 38:17

Things change, and there’s so many moving pieces. And it is a tool, full stop. It’s not so I’ll tell you what, it it may take your job if you’re not looking or trying to leverage any of this stuff to make yourself better. Um, but if you’re using this stuff and you’re getting in the weeds and you’re you you know leveraging it to make yourself better, make yourself more productive, producing more efficiency, that’s gonna be winning uh going forward. So those are the folks that are really gonna thrive, I think.

Dakota Seufert-Snow • 38:51

You know, I I was actually doing a live stream last night on my my channel, and uh that question got brought up is like how what does the future look like in AI? And the people who are leveraging AI as the tool that it is are gonna thrive. This is this is just a natural evolution of tech. This is just an you know, this is how the industry’s evolved over years. You know, new systems got implemented and people lost their jobs because of that. But then that new system that got implemented opened up like five other styles of jobs. Like it’s just the shift, the natural progression of the industry.

Dakota Seufert-Snow • 39:25

Something the this industry is always in innovating, it’s always evolving. And if you’re in tech, you have to constantly be evolved with it. You can’t just stop learning. You have to be lifelong learners, you have to constantly be educating yourself on the latest and greatest things. And not all these technologies work out. You know, we’ve seen tech plenty of these buzz buzzwords that come out and just die and tank. But you still have to learn them because what if it is the next big thing?

Dakota Seufert-Snow • 39:55

And you have to be willing to evolve with it. And if you evolve with it and you you get excited about these things and these new opportunities, you’re gonna excel. You’re gonna be writing your own check by the end of the day because you’re gonna be light years ahead of the crowd. You know, another thing that came up during that live stream is that you know, job market saturation, that there’s so many people going after these jobs, you can’t get a job. And I have someone complaining that you know they just find it bad that you know someone with a college education can’t even get an unpaid internship. And I’m like, that’s not the problem. You’re looking at this wrong.

Dakota Seufert-Snow • 40:31

Like, what are you doing to make yourself stand out from the crowd? How are you differentiating yourself? You can’t no longer say, Oh, I got a college degree, I should be good enough. You know, why are these people should just be tripping over hand to foot to offer me these jobs? That’s not how it works, and maybe. You know, 20 years ago, that there’s a chance that might work that way. But I even no, I don’t feel like it was that way.

Dakota Seufert-Snow • 40:54

I feel like you still had to market yourself, you had to work on your personal branding, you had to be that diamond in the rough and convince the employer why you are the one. And by leveraging these tools, you know, there’s still plenty of people, like I mentioned in the beginning, who’ve never even heard of the term MCP. This is gonna be what’s gonna make you stand out to those big organizations and get those large paychecks. I mean, I I I hate saying talking about the money part because if you’re in tech for money, you’re you’re in the wrong industry, but that’s what people resonate with the most. You know what I you know what I’m saying?

William Collins • 41:34

So yeah, you mean you’re right about the job saturation right now. It’s unbelievable. And every that’s another thing is that AI generated resumes. I ran into that at one of my last roles when that 1st started, and I was a hiring manager. Every resume was AI generated, it seems like. They were all experts at all the things, and you would get into like 5 min of the interview or 10 min , and you’d realize that like half of the stuff was like they didn’t even know half the stuff. Like it was just AI generated.

William Collins • 42:05

And I talked to someone actually and they said that what’s happening is there’s actually tools out there that will do this for you, I guess. But you put in the job description and say, This is my resume template build. And it will just build it out for you. And then you automate.

Dakota Seufert-Snow • 42:23

I’ve I’ve had those companies reach out to sponsor the channel and I I’m like, no, that’s that’s that’s that’s counter in you know intuitive, that’s counterproductive. You know, I I I had this issue at my j my day job. We hired someone, you know, they a resume looked great, so I brought him in for an interview. He talked all the right stuff during the interview, so I’m like, okay, you’re hired. Get him into the job. I’m like, okay, can you uh SSH into the switch? And he’s like, I don’t I don’t know how to do that.

Dakota Seufert-Snow • 42:51

I’m like, what? Like, how do you not know how to SSH into a shit a switch? Your resume says you’re well experienced in that. Like, yeah, we we we brought him in on a Monday and handed him his final check on a Friday. Like, you know, and that that’s on me because I didn’t push it enough, you know. I didn’t try to probe into him enough. I just was like, oh man, this guy’s gotta be the guy for the job.

Dakota Seufert-Snow • 43:14

Um, but yeah, we like you mentioned, there’s there’s those tools out there. Um but you know, if you’re able to actually lab the skills and demonstrate you know these skills, that’s that’s the biggest advice I give is you know building a home lab or you know, or you know, using it uh the cloud platforms, you know, there’s there’s free tiers for all this, and you can absolutely 100% Practice all this stuff and then document it. Show how you are doing it. Again, it’s it’s it’s major.

William Collins • 43:49

Blog about it, create videos, maybe the next Dakota, the AI Dakota, right?

Dakota Seufert-Snow • 43:53

I I you know, I I am totally for that. If anyone wants to go out and create their own YouTube channel talking about their journey, what they’re doing, giving advice, like you that that is you’re gonna stay like, you know, you you submit a resume and you go for an interview, and like, oh yeah, you want to see what I’m doing? Here, go to this youtube channel, and it just has your everything you’re doing, it’s just gonna be I’m gonna have hire that person in a heartbeat. I’m like, that’s amazing. I can actually see you do the job, you’re hired. Like, yeah, you know, that’s great. And you know, YouTube’s not for everyone, you know.

Dakota Seufert-Snow • 44:24

I I understand that, but there’s still different ways you can you can go about it, you know. Um, it is really amazing, you know what you can do.

William Collins • 44:32

The living resume.

Dakota Seufert-Snow • 44:35

Absolutely.

William Collins • 44:36

Yeah.

Dakota Seufert-Snow • 44:36

You know, and and I’m I’m glad we brought that up because you know. There’s there’s multiple sides to this coin, you know. What what you can do now with AI and how it’s actually living and breathing in the networks that we’re using is amazing. But I again it it is is a bit scary to some people when they don’t think ahead on how it’s making them a better network engineer and how they’re actually using it. So you know, we I think it’s great that we talked about how you should be demonstrating those skills when you’re looking for those jobs. And you know, for people who are wanting to future proof their careers right now, what should they start learning? You know, what do they need to start experiencing experimenting with today?

William Collins • 45:19

So that’s a really good question. That’s a the a great question. So the 1st thing, rule number one of getting experienced club is don’t look at all the hype. Don’t start with all the hype. Uh just stop and and make sure that you have a few foundational things that you are continually studying on. If it’s network engineering, I did a lot of BGP, TCP IP, DNS, those are important things to know. Don’t take shortcuts.

William Collins • 45:50

Learning those things is gonna pay dividends over time, I promise you. Uh And the 2nd thing is, you know, again, avoid the hype, but start doing these things at home, like you said. I have a I’ve had a few different AI labs over the years, but right now I have a few um RTX 5090s in the basement with and Linux is the other thing. Learn Linux, use Linux as much as you possibly can. Because that is like everything runs on Linux at this point. It’s crazy.

William Collins • 46:22

So learn Linux, you know, learn some Python that’s also very good if you can. Um And then just get to work. Start doing real things. There’s so many different tools out there that make this easy, aka container lab. Um, we have a free tool called Torero that you can use for automation. I’ve containerized all that, so it’s really simple to deploy in tandem with container lab.

William Collins • 46:48

You can load things on it, run Python against real networking things, and you know, you can insert an MCP server and ask questions and figure out. I mean, hey, be, you know, experiment. Ask AI to build you the OSPF network and manage it. Build an agent to manage it. Say sit to the point where you can say, I need to do redistribution between this and this. Put together the plan, deploy the config, and then build your own guardrails. Like all that stuff you can do for practically free.

William Collins • 47:19

Because MCP is something that you can just. It doesn’t have to be a public service. You can write it or build a private MCP that runs over a command line tool if you want it. So it’s just really interesting, all the different things, but start with the real use cases. If you think about where the real problems are that you know about, and then start working on small solutions for those problems, those problems are probably personified in in larger networks and larger businesses, of course.

Dakota Seufert-Snow • 47:50

So absolutely. And you know, I kind of want to nerd out for a 2nd , uh, because you know, you guys uh over there at Itential have built your own MCP server, and we’ve talked about it a little bit, but your MCP server is open source, which kind of blew my mind. You know, it got mentioned, you know, mentioned to me at Cisco Live when I was at your booth that you you guys are putting this stuff out open source that anyone can use and start playing with. And um can you kind of give us a walkthrough on how Itential’s MCP server is actually built? Because you you’ve had 1st hand, you know, you’ve been you’ve been the one working on developing it and everything.

William Collins • 48:29

Yeah, so the the thing about our MCP that’s really different. So one of the patterns, and there’s a little bit of knowledge that that comes along with this, and there’s a reason why there’s so many MCP servers um out there today. And the reason for that is a lot of MCP servers were created by basically just taking like an entire um open API schema file and just feeding that into a tool that basically converts your schema file into an MCP server that you then just put on GitHub. So that’s why, like I mean, it’s kind of like the early days of REST APIs. Like you just had so many APIs that just popped out of nowhere and there was like a proliferation of them, but now you’re seeing it so crazy with MCP because most folks have REST APIs and they’re just putting it through the machine and it’s popping out the other end. So there’s a few problems with that. Um I’d say the 1st problem is

William Collins • 49:32

There’s when you when you do it with just passing in the schema, there is a ton of glue code that is required to actually make the thing work. And by a ton of glue code, I mean a ton of glue code. Like you have to account for um you know the agent loop. You have to account for writing um like very very customized logic for um for filtering tools for categorization of things, like how things are dynamically selected and launched. And if you pass in like an API schema, you could be passing in and generating like a hundred plus 500 tools, and then if you’re calling them all every time, you have a you know a There’s so many words for things. Uh they call it context window bloat, where your context window is just blown up.

William Collins • 50:25

And this in addition is going to cause super degraded agent performance, decision paralysis. You’re going to get things out the other end that just do not make sense. So when, you know, and I can’t take credit for any of the MCP design originally. This is all Peter Spurgata, the architect who brought actually brought Ansible for networking to market, but he went in with a pragmatic approach of saying, okay, you can’t just build something that exposes everything and cross your fingers. You need logic behind how this is structured. You need all the, you know, when you think of OAuth and all the existing value that we provide today that our customers have built, how do you build on top of that to make sure MCP is layered on that in a secure way that honors all the guardrails, all the compliance, and all the logic that you’ve built in? How do you dynamically launch with tags the categories of tools that you want to use?

William Collins • 51:27

And how do you also generate that or leverage that on a persona basis? So, like with our MCP, if you were to plug it into like Claude Desktop or anything LLM or something or another, you connect the MCP and it’s controlling what you have access to within our platform, and then you just let’s just keep it simple. Say you have like a an operator persona or an engineer persona or an architect persona or something. Well, the operator persona may be able to do like read only things. They may be able to reset Certain adapters, visibility stuff, health check stuff.

William Collins • 52:09

So when they leverage the MCP, it’s the only thing they have access to. They don’t have access to push config or do anything that might be dangerous at like a level one operations level. But then when you get a little bit higher to that network engineer, how do you leverage the power of this MCP server in tandem with our platform is a network engineer when you need to do some more complicated, you know, maybe you want to back up some ad hoc configs on some stuff that you don’t have in your existing process. Or maybe you’re getting into just taking context from a partner like Selector, piping it through with Itential, and doing some auto remediation with certain things. So having that persona based approach is something we really focused on and being able to control, filter, and categorize the tools that are actually exposed in tandem with like all the industry best practices with OAuth, with the way we do role based access control at Itential. So the way that this sort of plays through is like starting at the least the the least thing that would cause any sort of issue again doing the read only stuff and then slowly giving the AI a little bit more a little bit more a little bit more and then when you get towards the end of actually like pushing config changes um like the other day with our MCP I actually connected our like our gateway product to our platform our gateway manager platform and then from there I just started creating services with the MCP like a bunch of hello world services and then I stitched them together and then you know I ran them and then I did concatenation with the different ways that each thing said hello world and I was just kind of experimenting and it was really easy to do you know building this stuff you know through MCP and through a chat interface.

William Collins • 54:06

You know, because it’s like however way that I want to think about doing it, I can do it that way that fits my the world that I live in. So yeah a lot of advanced features not just your run of the mill pass through the tool and out pops out an MCP server design.

Dakota Seufert-Snow • 54:23

You know that that is 100% I feel like the future and you know speaking of the future I kind of want to pick your brain about what we’re gonna see over the next couple years. But before we kind of go down that rabbit hole um if people want to connect with you if they want to check out itential if they want to connect with you personally where can they find you where can they learn more about iTential you know

William Collins • 54:45

Yeah, absolutely. So itential.com and I would go to the GitHub/itential , which I’m sure you can link in the show notes. Um I would look at the MCP server. Again, it’s open. Uh check it out. And then we announced our Flow AI product. I can give you a link for that as well.

William Collins • 55:04

So that’s um just got announced this month. And if you want to find me, you can find me at WilliamCollins on LinkedIn. And then I have a link tree which kind of links to everything else. It’s uh macroengineered. So, like on YouTube, Instagram, TikTok, all those places, that’s my um handle. So you can find me. And then of course the Cloud Gambit, if you go to Packet Pushers, um, you can find the Cloud Gambit podcast that I hop host with uh Avon Avon Sharp.

Dakota Seufert-Snow • 55:39

Awesome. Yeah, we’ll definitely make sure and link to all those resources down in the show notes below. Now, again, like I was saying, I kind of want to talk pick your brain. You know, you are definitely more in the weeds than I am. Um what do you see the next, you know? I I normally I’d ask what the next five years look like, but I think that’s too far out. I think too much is gonna be happened between now and then.

Dakota Seufert-Snow • 56:00

What are you seeing the future look like in the next year or two of you know AI and networking? You know, what what are some new things that excite you so much?

William Collins • 56:10

I know that’s a loaded question because I we we can never possibly know how fast it’s evolving, but yeah, I’m always like shrewd when I think about these things, and I usually underestimate, but I think with AI that’s gonna be a little bit different. So I think. MCP really making it to Main Street now has really because AI, this AI agentics stuff was kind of catching fire a little bit and gaining some momentum pre pre MCP. People were talking about agents. It was kind of a thing. But now MCP has actually rapidly accelerated the ability to do that. So what I see in the short term, and I’ve actually worked with customers and talked with customers that are actually doing this today in production.

William Collins • 56:57

Some of them are ISPs. But bringing in and integrating something like MCP into their process with what is known as so you have like human completely in the loop. So basically human running the loop doing all the things completely manual. And then you have something that’s human on the loop, which you’re bringing AI in to do things, but the human is really involved in the whole process. Watching each change, vetting stuff before it happens. Like the AI has control to do some stuff, but not all the things. And then you have this human out of the loop, which is everybody’s dream.

William Collins • 57:34

Like, hey, you know, we don’t need humans anymore. Get rid of your knock and you know, blah, blah, blah. Which for some things, way out in the future, I think is gonna be a thing. Not for there’s Many parts of the tech stack that AI will never touch, especially with certain verticals and certain technologies. It’s just reality. Let’s be real.

William Collins • 57:55

So I think short term we’re going to see more human on the loop use cases where you’re doing a lot of read-only stuff. You’re testing it out in your lab, uh, in the data center, and companies are trying to figure out how to do it. And then there’s also going to be a proliferation of customers, or I mean companies like Itential that are rolling out a lot of good innovation and productizing a lot of what AI can do for the enterprise into a package that you can buy, use, and you know, have some sort of influence on the roadmap. And then you’re going to have startups coming to market that are doing brand new things that are, you know, productizing. AI and packaging it up to where an enterprise can buy it, use it, get an SLA of you know, all the things that enterprises do. So really short term, a lot of human in the loop use cases, small things. And then going into the future, like five maybe three years and beyond, I bet you will probably see more agentic human out-of-the-loop uh use cases as well.

Dakota Seufert-Snow • 59:01

Yeah, and I feel like having that human in the loop makes it Easier for organizations to adopt. You know, there’s a little bit less fear of, you know, the you know, Skynet at that point, just put it in layman’s turn. Um, right. Absolutely. You have to make sure you know you’re doing the right things because um yeah, it it it is scary when you kind of think about what AI could do um if things went off the guardrails if you didn’t build those guardrails properly for it. Um so having that human loop definitely makes it a more palatable thing for organizations to adopt.

Dakota Seufert-Snow • 59:41

And I definitely see that becoming the future. That’s what that’s what’s coming down the pipe now. That’s what we’re seeing as of right now, I feel like. Um slowly but surely it’s becoming more mainstream. But yeah, I I a hundred percent agree with your your predictions there. I I really appreciate you you’ve dropped so much knowledge, so many so many useful tidbits that you know I feel like some people are gonna have to rewatch this episode to get again to get them all. But uh I really appreciate you taking the time to join us today and just offer so much great information.

William Collins • 01:00:12

Absolutely. Thank you. It’s having I had a blast uh getting to chat and nerd out on these things. Yeah, so thanks for having me.

Dakota Seufert-Snow • 01:00:18

Absolutely. I and again, I’d absolutely love to have you back in the future because I feel like there’s so many more things we could have dived deeper into that we just can’t even cover in the amount of time we have.

William Collins • 01:00:28

Wide topics. Yep.

Dakota Seufert-Snow • 01:00:30

Yep, exactly. Everyone, I really hope you enjoyed this episode. I hope you took some some useful knowledge away, some motivation to go out there and start practicing and learning these things because this is the future. This is how you’re going to advance your careers nowadays. And just go out there and start learning. Start tinkering with things and start messing with things. Everyone, again, until next time, keep learning.