Skip to content
Hermes Agent: Agents that grow with you episode artwork

May 21, 2026 51 min

Hermes Agent: Agents that grow with you

from Practical AI Hosted by Daniel Whitenack and Chris Benson

Open Source AI is entering a new era, one shaped by self-improving AI Agents, recursive learning systems, and rapidly evolving AI Tools that blur the line between software and autonomous collaborators. In this episode, Daniel and Chris sit down with Nous Research co-founder and CTO Jeffrey Quesnelle to explore Hermes Agent. Along the way, they discuss models vs. harnesses, the changing role of developers, and one of the biggest questions facing the AI Future: what remains uniquely human as AI capabilities continue to accelerate? Featuring: Jeffrey Quesnelle – Website, LinkedIn Chris Benson – Website, LinkedIn, Bluesky, GitHub, X Daniel Whitenack – Website, GitHub, X Links: Nous Research Hermes Agent Sponsors: Framer: The enterprise-grade website builder that lets your team ship faster. Get 30% off at framer.com/practicalai Prediction Guard: A self-hosted AI control plane for running agents in high impact environments. predictionguard.com/practicalai Upcoming Events: Register for upcoming webinars here! Midwest AI Summit 2026

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

Hermes Agent: Agents that grow with you

0:00 51:42

Chapters

  1. 0:00 Welcome to Practical AI!
  2. 0:59 Introduction to Noose Research and Its Evolution
  3. 8:55 The Role of Open Source in AI
  4. 17:51 Sponsor: Framer
  5. 19:10 Understanding Agents and Their Importance
  6. 24:25 The Future of Hermes Agent and Its Unique Features
  7. 27:20 Harnessing AI for Enhanced Learning
  8. 30:54 Market Fit and User Experience of Hermes
  9. 33:06 Real-World Applications of Hermes Agents
  10. 34:22 Sponsor: Prediction Guard
  11. 36:06 The Role of Automation in Human Processes
  12. 39:01 Learning from AI: A New Perspective
  13. 45:04 Optimizing Human-AI Collaboration
  14. 48:17 The Future of Work and Human Agency
  15. 51:01 Outro
of matches

Transcript Auto-generated, may contain errors

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 Blue Sky to stay up to date with episode drops, behind-the-scenes content, and AI insights. You can learn more at practicalai.fm.

Now, onto the show. Welcome to another episode of the Practical AI Podcast. This is Daniel Weitnack. 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 are you doing, Chris?

Hey, doing great today. How's it going? It's going really good. I've been excited for this one, I guess, ever since a conversation that we had back in 2024 on the show with one of the co-founders of NUS Research. Today, we've got another one of those co-founders with us, Jeffrey Kanell, who is co-founder and CTO at NUS Research.

Welcome. Hi there. Thanks for having me on. Yeah, it's great to catch up. Myers of a lot of the things you all are doing and really enjoyed the last conversation.

That was, though, in 2024, so it's been a couple of years, and that's eternity. That's probably – That's when you say I time, yeah. Yeah, yeah. 20 years in AI time. So I believe, if I remember, at that time, NUS Research, which for listeners, I would encourage you to go back and listen to that episode, which was, at a certain point, primarily, a kind of distributed community of folks on Discord and elsewhere, but I believe that was kind of morphing into more of an actual company or organization at that time.

Could you help us understand how that's evolved over the last couple of years? Maybe some highlights from the NUS history books over the past couple of years? Yeah. Like you said, it was two years ago, so 20 years in AI time. And we did sort of start out, like you said, sort of this loose collaboration of the homies on the Discord, as I always like to say.

And that sort of grew organically just through Twitter and other places like that. People who are fundamentally interested in open source AI and making sure that this tech that we think is the transformational technology of our generation wasn't going to just get locked behind a few closed companies. And at the time, we were sort of looking up at GBD 3.5, it just come out. The chat GBD thing had happened fully. And us who cared about open source, like, how is this ever going to keep this alive?

Because it seemed like the sort of curve of capitalization was already starting. If you didn't have a ton of money, you're never going to be able to catch up. But what we were able to find was that because the research space in this is actually quite at the time, especially two years ago, was really quite nascent. And there were a lot of low hanging fruit sort of things that could be discovered by just one or two people doing independent research. And we brought together some of the people who had made some of these discoveries and it kind of gave us a creness of the idea that maybe David really can be alive or at least get on the same field.

And so we brought everyone together and decided to say, it was really just sort of a way for us to say that we have these people who are doing this for free basically, on their spare time. Is there a way we can form this into a company so that we can take people who care about this and let them devote their whole experience time to it? So we brought the company together maybe about two years ago and sort of went through a path of different experimentation. The North Star was always like, we have to keep this tech open and make sure that as many people can use that. And that was always the North Star.

It was the modality in which that was really going to express itself. We spent some time looking at different aspects of the AI pipeline as it is and figured out where are the ways we can democratize this. And we started first through what we had done, which is through academic research. We spent lots of time, we published several papers that said something that's currently extremely expensive in the AI space or behind huge capital costs. And can we do 1,000X improvements on that?

That can bring that back down to the scope of us. Although we have some small amount of money, it's the rounding error. It's the catering budget. It's over these larger places. But it turns out that a lot of things in the AI space, because everyone's scaling so fast, you can for some times just kind of throw down money at it a little bit and it does get better.

But if you're a little bit smarter about it, there were big efficiency gains. So we spent around several years just doing research and putting out fine tunes that were aligned to the sort of models that respect you and are going to be like moralizing and stuff. That was our original Hermes series of models that were very popular. This is of course pre-thinking, pre-reasoning, pretty deep-seat kind of style models. We did that and had a lot of success and people enjoyed that.

We spent a while looking at distributed training and whether that was a viable path and put out some interesting research there about how you could train models over the internet. This was also in response to some political things that were going on and kind of still were going on, to be honest with you, about what would happen if people tried to outlaw even using open source AI and stuff. So we did research on that space too. And all of it kind of was coalesced around this idea of needing these 1,000X hacks. So one of the interesting 1,000X hacks that we tried to take on, which eventually turned into this thing that is now Hermes agent, was the idea of recursive self-improvement.

And recursive self-improvement is where the model is able to somehow train itself or do experiments on itself and automate that path of the pipeline. Because you can think of high-end AI research engineers. The people who really know are like end of a quarterbacks now, basically. You've got to pay them like end of a quarterbacks and they are going to decide whether your chain gets to the play out. They're that important to your composition of the structure and places the large corporations because they're more capitalized, have better access to this limited talent pipeline as well.

So we started building this tool internally for our own model research team to automate what some of the research they were doing. And that was kind of just like a, let's see if we can do this. And that tool was internally just called Hermes agent. We started this about six months ago. And it was about six months ago that this was our tooling.

And we used it internally for several months. And that's why if you go back to the genesis of Hermes agent, you look at those first commits that were open source. It was basically all around model training. Like all of the stuff that we had built into it was all like all the stuff we used internally for AI research. But we had this idea, and once we had built it, we were like, why are we keeping this secret?

You know, that's, you know, we were sort of default open source unless we can save as a reason or not to. So we released this, the repository for Hermes agent. And it was just a floodgate of product market for a lot of the better where, you know, but things were, you know, a lot has been said about what has happened over the last several months with agents and your harnesses and stuff. And I'm happy to talk all about that. But it was kind of like right time, right place.

And over the last several months, it's kind of just like, get over every aspect of the system, which is awesome because like I said, when we were talking a little bit earlier, is that, you know, the North Star has always been open source AI, bringing this to as many people as possible. Now the vehicle, sort of the delivery mechanism that we were going to use to do that kind of, you know, we were starting out, but it's really in the last several months, crystallized for us. So that's sort of the history of news in the last few years and maybe five or ten minutes. So, you know, that's awesome. Love that.

So, and you introduced a whole bunch of things we can dive into. So I'm going to pull you back for a moment and actually want to go back for a moment because I think there's something that's kind of tangential to what you were bringing us up to date on. And that's that the story of news can be very inspirational, I think, for a lot of people out there who are interested in getting into the space and they're perceiving the big giants and the massive amount of money that they're throwing at and stuff like that. And also, you know, at the same time recently kind of looking at, you know, the perception of open source taking a hit like with llama, you know, kind of coming toward the end of its life and meta now not champion opening source within the big players and stuff like that.

Could you kind of lay out for a moment like a little bit of a combo like how do you see open source working in the modern AI world and how has and as you guys have formalized into this organization, you know, from that informal network and you're you're having to make choices and you have this North Star which is keep everything open. But also, I mean, you have you have bills to pay, you know, paychecks to make and and all those kind of things. Can you talk a little bit about how, you know, not only you guys see up in general philosophically, what's how do people navigate that space to if you're looking at news as kind of the paragon to pursue and say, Hey, I can go do that to to some degree.

How do you see that? What's the role of open and what's the role of being a company now? Yeah. Well, I can say there's kind of the inside baseball, you know, version of open source is like what's actually happening in the industry and it has shifted several times over the last few years. So, you know, we start out with, you know, the golden age, your llama comes out, right?

And you have this, you know, you have one of the fabulous five companies or whatever, you know, saying that they're gonna, you know, do open source AI. It was driven largely by Zuckerberg's personal, you know, I would say emotional motivation, but like he just decided he wanted to do it and like, you know, he's in charge of the company. So that's what was gonna happen. And the fact of the matter was, though, is this created an ecosystem of people who were able to research AI and every, you know, ton of the researchers now at places started out by downloading llama and stuff like that. So it really was quite, quite important at bootstrapping the AI researcher space that we have right now.

But as we saw as the release on the one, llama two, llama three, you know, the price tag of that kept going up. And with llama four, they made some, you know, decisions that were, you know, architectural decisions within the model, seemingly minor thing at the time, you know, could have gone one way or the other, but they made a few mistakes and the model really didn't come out that well. And you know, they had to look down at themselves and say we just spent $200 million, $300 million, $400 million on like essentially a paperweight, right? And so that's kind of what I think, you know, that question really became everything's fun and good when everything's working, right? Like, and I think that first failure case sort of, you know, made people question what are the motivations for having open source models, right?

So one thing you have a great American, you have one of the largest American companies sort of have a company Jesus moment about what are we spending our money on this floor? I was aligned with business objectives. And then you have the deep-teak sort of situation, which happens, right? You have this Chinese company drop a model that's, you know, was trained and was trying nearly soda equivalent, come out of nowhere. And now you have this, now it goes from being a dollars game within the Western AI space to having a geopolitical underpinning to it as well.

And I was going to get here, but like, it was forced to there. And you now have open source, squarely within, you know, the vectors of this geopolitical, of this geopolitical thing. It wasn't just that there was a close model provider out of China that, you know, was soda. It was that we had an open source one that was, you know, that was near soda coming out of China. And then now this playbook started to get replicated with throughout China as sort of a growth hack mechanism, right?

So within China, they realized that if you put out an open source model, you could, you know, you could get your company, you know, to the top and get it in the press. So insofar as in America, it was sort of realized that this was played out and wasn't going to be profitable. As that fizzled out over in China, it still was quite profitable in the sense to throw your money into open source models with the hopes that it sort of elevated you to this, you know, top tier of, you know, players in the game and we'll figure out the money stuff later. And, you know, for different, various reasons that may or may not work differently over in China than it comes over here. But the functional difference was that all of the open source was now coming exclusively, you know, the models are coming exclusively out of China.

And so that's sort of the inside baseball. And then, and that's more or less where we stand right now, except for what I would call a very significant recent development, which is NVIDIA and Jensen. So NVIDIA and Jensen at his last GTC came out and said, you know, we are going to be the, we're going to try to carry the financial flag of Western open source models. And he committed less something like $20 billion over the next several years, you know, Twords training open source model, Western, prominent open source models. And I think this is an interesting development because if you sort of pull the threads of the sweater about who does it really make sense for someone to be training an open source model, you know, I think NVIDIA is a company where you could actually credibly make that argument that it does make sense for them, you know, it's because, you know, at the end of the day, they're all running on NVIDIA, you know, what happens, it all ends up running on NVIDIA chips and more things that need to run on NVIDIA chips, you know.

So for them, it is like aligned with their business interests. And anything where you can't sort of eventually really see how it's aligned in the business interests, those things will always kind of follow the money, right? Like that'll tell you, show me inside of your outcome. So I think NVIDIA doing that kind of is a potential game changer, really on the Western side, because it's the full, but really the only people that has it because it's kind of, you know, you inside, NVIDIA, you in a bit, you in a bit, but guess what? The house always wins and it gets to be like the house here.

So on the inside base, well, I think there's some interesting developments right now. And I'm very, I'm currently very, you know, enthusiastic or optimistic about where it actually will go and lose to the short term, right? You know, we can't predict anything outside of the several years out. So that's kind of like the inside base wall story. The sort of larger question about how to how does someone fit into, you know, the new story is it replicable?

Who are you as a person in this space? I mean, I would say now that there's never been a time more where a single person's leverage can be more, you know, multiplied or maximized. AI is a technology is a human capability multiplier. And I'll give you like this is a crystal example. And it's really like the and it is really Hermes agent itself.

So Hermes agent was developed by was first developed internally at News by a guy named Technium. He's got you guys might know who he is on Twitter all the time. Technium is not a developer in the sense that he didn't doesn't like really know code that much when previous to this sat down and been able to write huge, like a program that would run from scratch, you know, and and so, you know, previously he would have been unable to make an application, right? But you know, with the current AI tools, he was able to architect and write and build an application that is now the number one open source for Pository.

I get up, you know what I mean? And like, so that goes to show you that like if you have the vision and the drive and the care, this technology can make you a thousand acts, you know, on what you are. So there's never going to be more where a few people can have outsized impact on the industry on the world than it is right now. And so don't think that the opportunity in any way has passed you by. I think it's really we're only at the very every industry is right.

The industry, every vertical is right for someone who has laser focused vision uses these tools to, you know, completely take over and win. So I think the area is still, the grass is still green. Wow, it seems like we need to make an update to our website all the time. Our marketing team needs a new landing page or we've got something really cool in our product that we need to create a new section of our website. All of this needs to happen fast and I can't wait days or weeks for these things to go live.

That's why I'm so impressed with what our partner, Framer, is doing. They're an enterprise grade, no code website builder used by teams that companies like Perplexity and Miro to move faster. Framer has a built in robust CMS with everything that you need for great SEO or even AB testing and changes to your website go live in seconds, not days or weeks. And so if you're launching a new website or you need a new landing page or you need to migrate your full.com, Framer might be for you. Learn how you can get more out of your.com from a Framer specialist or get started building for free today at Framer.com slash practical AI for 30% off a Framer Pro annual plan.

That's Framer.com slash practical AI for 30% off. I'm wondering now we've kind of shifted into this discussion about agents and Hermes agent. I'm wondering about your perspective, Jeff, on kind of it seems like we've seen this shift around in initial initially with AI. Everyone was like, what model are you accessing, right? What model are you using?

I'm going to put in an input and get an output from a model. So I need to choose a model. And now everybody's talking about agents or agent systems. Some of that is obviously kind of jargon and marketing in the market. But also there is a fundamental architectural thing that's happening, which you mentioned agent harnesses and kind of this way that these applications can operate over a distributed system of things or have all these connections that matter to tools and take action and maintain state.

And we saw with, for example, when we looked into things that people were using all the time like cloud code and that sort of thing, like the importance of that agent harness, which is also, of course, like a big part of that Hermes agent project. I'm wondering if you could kind of help me and our listeners understand, like, what is the importance of the model? Now, in these types of agent systems and how does that shift in this world where, you know, is the important part in a lot of the potential value IP, however you see that in this kind of harness and the model is just sort of something you can swap in and out?

Or what is the importance of the model within that world? So here's an analogy that's not perfect, but I'm finding it to be instructive. So the model is the brain, the harness is your body. Think about like that inside yourself. So, you know, the brain was something we previously couldn't build before, you know, like that is like the true quote, quote, magic of AI is still like within the model is all within there.

That's the zero to one thing that allows any of this to happen. We could build robot bodies before they could do anything kind of deal, you know, so that's really it, right? So the model is your brain and the harness is the body. So let's go on this analogy a little bit more, right? So suppose you are, you know, you have an IQ of 150, you know, but you're in an invoice, you're stuck in a wheelchair, right?

That will simply limit the amount of things, things you can affect in the world, right? You can try and go talk to someone and tell them to do it, but like, you know, there's some amount of limit that you have. So imagine in fact that like most of the work you want to do needs to somehow touch the world itself. You'd be limited in that aspect in some capacities. Meanwhile, if you had someone who had an IQ of 95, but has an athlete's body, you know, there's certain more things that they're able to do just by virtue of being able to manipulate the world more, right?

So both sides are like important and I think they exist within a sliding scale. A better harness with a worse model can beat a better model with a worse harness and both of them are symbiotic and working with each other. And it's just the harness itself though is the thing that touches ultimately what it is that we humans care about, which is the world in which we live in. This thing that we call reality around us, right? The model itself has very little ability to touch the world.

All it can do is output tokens, right? And we need to somehow allow those tokens and we don't speak to them. We need someone to allow that output to become instantiated into the world around us. And we ourselves are instantiated in a world where we have persistence, where we have causality, where time moves forward in a direction. And so all of these pieces, the harness sort of allows the model to exist within the reality that we all care about.

Now, as far as like ownership of, you know, where's the value of crew or all those sorts of questions, I don't want to get ahead of my voice here and like make some sort of like, you know, silicon valley pronouncement about all I, you know, this is where all the money goes or something like that. I would phrase it rather in a different way. I would say we are getting to the point where people will want to pay for outcomes, right? Just as when I hire an employee, I am paying him to do a job, right? And ultimately I want that job to be done.

Otherwise I wouldn't have hired that employee, right? Like the prime motivating factor for me is in getting some sort of material economically valuable outcome to be done or something I do is economically valuable. And so I think that is also the similar model that will eventually pull out of this whole AI system, which is that these systems will be paid to do certain things and they'll be valued in so far as they get the job done. Now, who owns the harness? Who owns the model?

All that will kind of get worked out in the end. But again, if you pull back and say, where's the prime motivating factor? It's I want to pay for something to get done in this world and it would be cheaper. It's cheaper, faster, you know, more cost effective for me to do it this way than to do it any other way. And that's water going downhill.

Follow that path that'll take you that'll take you to the promise land. Well, Jeff, I love that analogy about the brain and the body and the harness and the model. I think that will be really helpful for people. I'm wondering now in terms of Hermes agents specifically, could you kind of, I guess, walk us through some of the agent or automation stuff that you were seeing kind of out there as you all were starting to develop Hermes agent and some of the key opinionated choices that you made about what you want Hermes agent to be uniquely in the midst of kind of all these other things out there? And really the key piece of it was the idea that the agent ought to get better the more you use it.

That was kind of like the motivating factor here. And that's maybe different than how people used to design software. So we've always been trying to break out like the paradigm is different. We have to act like the paradigm is different. And so how do people use to design software?

They would say, I think I know a problem. I think I can design the best solution for that problem. And they're going to wipe it all out and have all these systems. And we said, well, we don't have to be like that anymore. The ARs are smart enough to just see what we do and then figure out what they should be doing.

And so what we said is just get out of the way of the model. Give the model the ability to do what we want to do and then you lean on it as much as possible. So a couple of the opinionated decisions was we created a very limited number of sort of bundled in hard coded features. We gave it the minimum sort of ability to touch the world to run code jobs to browse the web and stuff like that. And then everything after that is an emergent property that is encouraged to develop through the prompts.

And that is the two main ones are sort of the memory system and the skill system. The skill system is extremely interesting to me because it is the thing that the first time it were it happens to you, it feels like magic, which is that you use the agent. You're trying to solve some problem. It does something for you in the way you like it. And it notices without you telling it that this is like I've learned something important here.

It will create a skill that says how to do a specific thing. And then the next time you do something that is sort of like that, it will just use what it figured out before on how to do it. So I have an example of this. Our team was going to an off site and we were like flying in and I was like I want to see if I get her his agent to make a restaurant reservation on the flight. So I'm doing it.

And there is actually a bunch of stuff on these websites to keep automated systems from doing this. There is all these bot caffes and stuff like to try to do that. And it is like going around and it is not working. It is not working. It is not going black out.

And eventually it does fine like the API backend for how they are at the book. And it is like I see all the things here. And it was like okay I found the data which one you want to book it. And this took about actually like 30 or 45 minutes of real agent runtime to do this. And then at the end of it it goes oh wow I learned all these things and you just see skill created like Las Vegas restaurant booking.

And then the next day I took it and it knows how to do it. The next day I come back and go hey dinner was great. I said can you book this other one. Boom instantly it knows exactly how to do it. It just takes those learnings and applies it.

And sort of that rather than be like we need to design all these different skills or stuff like to just let the model, it is encouraged through self reflection. So internally in the problems we have a new we have a couple of like I would consider to be like the world's best like LM, like LM whispers like they just talk to them all day and they just know the right words and phrasing, car and being number one in the world I would say in my opinion. And so they you know we put in the problems to like nudge to have that right self reflection be like when you see things being used all the time or if it feels to you that some you know important achievement has been has been met that would be useful to you in the future. Make note of it and put it in your skill system.

And that's all we really do. And then like I said about getting out of the way of the model we let it use its judgment about what it thinks is important you know we just encourage it to do that. So to give it the guidelines of what not not not how to solve the problem but how to think about how to think about how to think kind of deal and then and then just you know let the model go. So that was in the skills system and that was sort of like our first opinionated one was just like let the model drive it. And then the second one was was the memory system as well which is sort of this we have this like hierarchical memory system where it will create notes about you about how it seems feels like you want to be treated and then it has like a layer of the previous sessions that it's talking about that it can go through and there's like this many layer memory system that we have as well.

But all of it is mainly operated through the LMS own discretion about when to activate any of those pieces. And what it means though is that like when you know GPT 24 you know when the next GPT or the next opus comes out or the next thing. Hermit agents just better like it's just it has better judgment I'm using those things too you know but it just kind of drops in and gets better. So yeah so it sounds really cool. As you're as you are talking about this and people are listening right now to the podcast can you position it a little bit like so one of the things that have hit people is there's there are you know a lot of harnesses have come out over the last few months some are proprietary some are open source and and they they have some different capabilities there's a lot of overlap how would you position Hermes for like both the users and like the context architecturally or you know like cloud versus like there's a whole bunch of different like this or that or this or that how like when you guys are working on this and trying to get it out there for the world what are some of those use cases and specific audiences that you're seeing it being really well suited for compared to the competition that other people may be looking

at and stuff. Can you talk a little bit about that like it's market fit? It's primary market first is through your sort of power user person who wants to use AI you know to its full capability. That was sort of the first segment that we we we aimed at and like I said it's it why use it it it's the agent that gets better as you use it more that's the best to tag I can we can come up with and try it so if you want something that just works and gets better as it just works more Hermes agent is the agent for you and it is open source native in the sense that we keep everything open you can run it locally using local models if you want that's a first class citizen for us and or you can have us host it for you as well and wherever you sort of fit on your you know kind of like you know lying there is where is is where we are.

We feel pretty good about where the story is right now on that and the broad product market on that and we're currently working now on really expanding out what does it mean to have an agent or a piece of like Hermes agent in a workplace setting or like a collaborative setting. I think like the sort of one agent one person model is currently like pretty we're pretty happy with where it is now and I was sort of exploring the multi tenant how does it fit to have lots of these things work together on that and we have a couple of really high level partners that we're working with right now that we don't know anything to announce quite yet but that is sort of where our brain is going to right now and we are ourselves sort of our dog food in this 100 percent so a Hermes agents written 99.99% of our Hermes agent but we also have several home use agents deployed within our organization doing real quote unquote like work to sort of what you know just to be the first people to figure out this sort of enterprise or at least like organizational story and it's really powerful I'll give you an example so we have a we have one of our the agents whose job it is it's connected to all of our back and infrastructure for all of our servers and it can get access to the databases and it's like read only but it can like see everything that's happening and we've

used it as a started out as like a debugging tool where if someone comes to us and they say oh this isn't working on the website so on and so forth and these systems on the back end they're kind of spaghetti you have your databases versus all these different you know you know to get it all going so it's kind of like a little bit of a mess with all these different services and you know we start saying hey can you figure out what these problems are we're seeing 500 is on this sort of thing and our our engineers who actually know this are talking to the agent and it's all I can't find this I'll go look here and what's actually happening is over the course of like a month it is built up a huge repertoire of skills about how to actually do everything that we need with the company so now someone who's like our support person who's like our disorder like a email can just come to that agent ask now about like a specific customer account and it can do all the things that we need to do and give you all the reports and do reco's and that wasn't something that was that we had to code ourselves it just emerged it we got created as the engineers used it but the difference is now that that one engineer had to use it once had to show it kind of once worked or once and sort of passively the agent was just got better and better and better and now like our whole organization can leverage that the learnings from that that one engineer so we're trying

to work out that story to when we think it's quite quite powerful and interesting and so that's kind of where we're taking it from here. If you've been listening to the show over the past few months you realize just how transformative agentic AI is whether that's cloud code or Hermes agent or custom built software that you're deploying for operational efficiencies or as new products to your customers regardless of your maturity now this is the world that we're headed towards this agentic AI world and there's a lot of security and governance teams that aren't letting these agents go into production because of risks related to agency and autonomy and how do you take care of things like prompt injections or insecure tool usage.

There's a lot to take care of and that's why I'm personally spending my time outside of the show working with an amazing team of AI engineers to build prediction guard. Prediction guard is an AI control plane that you run in your own infrastructure behind your firewall. Developers can build on top of this control plane using everything that they want to use, open AI and anthropic compatible APIs, MCP servers, frameworks like Linkchain but all of this is plugged into a built-in governance harness that enforces your organization's AI policies and all of that telemetry goes back to your monitoring and alerting systems. I would encourage you to check out what we're doing at predictionguard.com slash practical AI.

You can schedule a demo with me and the team and I'd love to get your feedback on what we're doing so visit us at predictionguard.com slash practical AI. That's predictionguard.com slash practical AI. I have an interesting, well, I hope it's, I guess anything I ask in a podcast I hope is interesting but in my mind this is a particularly interesting thing to think about which is Chris and I have talked about this on the on the show a lot which is the way that you should maybe automate things or mechanize things is often different from the human, the corresponding human process or it should be you shouldn't assume kind of a one-to-one mapping and I'm wondering like on both sides of this because you're finding like the agent is developing those skills if you've actually learned from how those skills are developed maybe how to do things better like as humans within the company and maybe on the on the on the flip side of that, you know, what is what is the I guess the create some of the creative ways that you've

seen agents solve things that might be totally different from the way that a human would go about the problem but it works because you've kind of fully bought into this agent process which I think are people are gradually learning through like agent coding tools. There's some of these like sacred cows that they just have to get rid of, right? Like it doesn't matter if this function is duplicated a couple places like the agent system like it's fine for the agent system. I don't need to think about that. So are there are there cases of that that have come up for you?

Well, I would say like as far as like a guiding principle about what where to think about what to automate and when think of the agents as humans with infinite patience and I think this is really kind of like like infinite patience but very low creativity. All right. And so the question is where would I need that, right? And if there's a place in your workflow that doesn't require creativity but requires infinite patience and that's a great place to put it. And so for something like I said with our logs, and human theoretically could just read all the logs, right?

And like step through all of them and like but no one has the patience to do that, right? And no one has the long context memory to like see it all at once, right? So those sorts of areas and if you have to do it all the time. So you know, like that's really the areas to think about. What you don't want to be doing is sort of like you said this wonder when mapping of like, oh, we need a CEO agent, we need a CFO agent like that is, that is, you know, the wrong thinking and you need to blow those ideas out.

Rather you think of them like an operationalistic perspective of what is the thing actually doing and would a human ever really not could a human do this but not really want to do it. And those sorts of workloads are the best to be put through. So that's where we start out here is anything that like theoretically could be done by a person who isn't like a genius and super creative but we just doesn't make sense to you. As far as you know, solving things and what things were learning in a different way. I mean, through the coding thing, I, I started coding around like seven or eight years it was the thing that made me different when I was growing up.

I could do this cool thing and open every pathway in my life and all my success in my life has been rooted at the basic idea that I could was a really good voter at some at this very specific point in time. I was born in the late 80s. I got to be there right as the internet started coming on, you know, at the time when software was starting to eat the world for real and I was young at that, you know, like all these things that lined up and I did create a whole bunch of, you know, in my mind up until only like six months ago, I didn't use AI really at all. I wrote on my code myself and I thought I'm still better than all the AIs like they can't do what I do. And then really like in the last three to six months through using her music, I had to, I had to admit that the time that that time has come gone.

But rather than being disappointed about that, I would say it only means that I get to one the clock back and be early again, like I was when I was young when there was like the eight, you know, software was even the world. So it actually is freeing in some way if you're willing to allow it to be an opportunity. So and and get back specifically to a question about learning things, say it differently. Yeah, I would just say that like anything that is aesthetic is based in the aesthetics. The AIs have they have no, they have no discernment for that.

They don't care if it's pretty, they don't and like, and it's not even that they don't care. It actually is what I'm finding is that, you know, they really don't know. Like they really don't have human taste and they're incredibly smart in the vector of like what we can, what you and I would consider to be a genius person who would, you know, we try to self select through to get someone in the Stanford and like, what is that that makes a person a genius? They can do that easy, as a space like solve math problems, write code, like, you know, you know, we needed to win the genetic lottery to do that. They can anything to do it right out of the box.

But what they can do and what something that like almost every human can do is really discern, you know, we have an innate sense of aesthetic that because, and I think the reason for that is just simply because our human sense of aesthetic is grounded in the lived experience that all of us share is common, as common, you know, as common men and women on this planet. And AIs, if you think about how they were trained, they're just so divorced from the experience that you and I went through, you know, being born, living in time, growing, and even our biology from the evolutionary pressures that created us in the first place. And so our aesthetic is actually something that is quite unique and is quite very like, you, there could be a million different ideas, animals have different ideas of what's exactly important in their pack structure, like, you know, different, there's a million one of those.

There's only one math, really. And there's only one like sign, you know, like, so like, it's interesting that, like, the things that are like the universal computational stuff the eyes can take, the things that are very unique to us, that's things that, but to us don't feel unique because it's the fish and water argument, right? Like, we don't feel them to be a unique thread because it's, we're so immersed in it. And it's only when we're sort of faced with this thing that's, that was finally, we have another example, there was only us to begin with. There's now another example that we look at and go, oh, why is this so different?

You can think about it about slop or whatever you want to call it. Getting back to what you said, they will solve things in an aesthetically unpleasing way. And you just got to have to learn to deal with that. And you should not rely on them at least right now for those things that are grounded, whose success is grounded within it being, you know, aesthetically pleasing to a human, whatever that might be. Yeah, there's, I got to, I want to, I comment that, to agree with you on some of you said a moment ago.

And then I want to actually draw out a thread that you've gone down a little bit. The comment is your is, I think something I say a lot is the models regress to the mean. So they're, they, they do things that may appear creative, but they don't do truly novel things. And then they have something, you know, that they've been trained on that's relative to that, that they can associate. And so if I'm going and doing something that's truly novel, there's nothing written that it can be trained on before that.

They're usually not very useful in that way. Having said that, that still leaves 99.999% of the usage out there. And one of the things I've noticed, not only in our conversation today, but in previous conversations that we've had on the show, and privately is that we are, we are retraining ourselves in, you know, if you have the capability here of a Hermes agent and what harnesses can do and then some of the things that you guys have done to make Hermes so amazing and what it does in terms of learning skills, they, you know, we tend to go to the common use case about coding and the fact that we're, you know, Daniel pointed out that maybe keeping just one version of a function, you know, like, you know, we all grew up, don't do, don't have one, keep everything really, really lean and all that.

But that's really for us humans. And you pointed out that we have so much more capability now, though it may not be aesthetically pleasing and it may require a different way of doing that. As people use a tool like Hermes agent, how should they be thinking about me and let's stay away from coding for a moment and look at the rest of the world of work activities that might be out there, how should they be looking for those opportunities to do it better in a way that they've never thought about before because it's no longer human centric, but it's now agent and model centric together in terms of what they're doing. How do you optimize the use of a tool like Hermes agent if you're the human trying to retrain yourself? Yeah.

I mean, number one would be, you know, don't tell it how to do something. Describe the outcomes and the conditions for what it is that you're trying to get to. And like I said earlier about like getting out of the way of the model in some ways, I think people when they first start out using these things, they have an element of control they want to keep on, you know, like, they want to say, okay, do this one step, do this one step, do this one step. And then you know, the model is only going to get better and better and better at longer rising planning. And I think ultimately thinking being goal oriented and then being goal oriented and then evaluation oriented, right?

Like what would be the conditions upon which I would think that this goal was met, right? And if you can succinctly describe those, that's what the agent that's what the AI can work towards. Let it work towards, you know, fulfilling those success criteria. Now, if you leave those success criteria is unstated, you know, let me give you say, write something and then you go, well, this is slop, you know, this is, you know, not X, not but Y, not X, but Y, all of the paragraphs the same way. Okay.

But you told the AI to write something and it did write something. So it doesn't have the judgment that like it should not sound like slop because it thinks slop is the best thing that, you know, it's the mean average of everywhere that's ever been written, you know, and it thinks it's great. So it's like your unspoken assumptions or your unspoken evaluation of the outcome if left unspoken can remain, you know, will remain persistent. So that's why, like I said, about the real value, we have these like L and Wiswers who can really articulate all of the suppositions that they have internally about what they want it to be in a succinct way. Now humans, we, that is a don't skill set, right?

Like knowing how to actively communicate actually communicate everything that you want and think and say is not something that we normally do because, hey, we have the shared history of human common understanding that I just don't have to say it to you because you and me feel the same way on most things that I don't have to say it. And therefore it's so ingrained, I don't know how to like put it all into words, right? But I think, you know, I'm thinking of step back and you know, instead of thinking like explain it to me like I'm five, explain it to me like I'm an alien, you know, or you know, because that's really what the AI is. It's an alien that never grew up on earth. So you really have to say what it is that you want in a way that's much more explicit.

But if you are able to say what you want explicitly and really write out your evaluation criteria about what you would all you would go into your own judgment, make it, it'll find its way. It'll find its way towards that goal. As we kind of draw things to a close here, I think I'm excited by the possibility moving forward. Like you say, it's kind of a time where we can look at a lot with fresh eyes and experience some of that newness, even though we've been working in technology for a long time. We always like to ask our guests kind of at the end, like what is on your mind as you're stepping forward into the next, it could be a few months or a year of your life?

Like what's at the top of your mind? What do you go to bed thinking about both either on an exciting level, on a challenge level, on an ecosystem level? However you want to frame that, we'd love to hear it. I have the business answer, which is making new research continue to grow through our enterprise offerings that we're working on. I think about that a lot.

It takes a lot of my time, but something a little more overreaching would be thinking about what the place of people are in work in the next years to come. Not even only from just an economic standpoint, but from a humanity standpoint. Using these tools, what will it do to us? What will it do to us? I think that there's going to be a society that's already moved towards a doom-srolly kind of tiktokki.

That's already the direction we're on. This could in some ways be one more domino on that effect, because now we can sort of check out a thinking as well. If your job is just doing the agent, do the thing, do the thing, do the thing, and just keep saying that over and over. What is that safe for your growth as a person? At News, we call ourselves being human-centric AI, and that AI should make you better today than yesterday and better tomorrow than today.

I think we're in that path right now, but it also requires some responsible usage by the people, by the users of it. I wonder in myself, for someone could easily get trapped into developing no critical thinking for themselves, and especially if you take this 10, 20 years from now, what do you take for someone who only ever grew up with this being the paradigm? That human innovation and thought and critical thinking was just not even see it. The answer is the computer knows, and that's all the only answer there ever could have been. It only takes one generation.

Like, once you grew up, whatever you grew up with is what you think is normal and right. I had a baby five days ago. What it means for her growing up to live in that. That would be the bigger things that are on my mind right now. Ultimately, you can take that one of two ways.

You can be pessimistic, be worried about it, or you can have agency. You can have agency and be part of the world and try to be part of the solution. That's why news research exists. That's what I'm trying to do is to be a part of the solution. Like I said, better yesterday today, better today than tomorrow.

Great way to end it, and also congratulations. Absolutely. Thanks for joining us on the show. We do hope to have you back. Maybe someone from Newst in less than two years coming back on the show.

We'll try to make that happen next time. Thanks for joining us. We'll talk to you soon, Jeff. We appreciate it. Thanks.

All right. That's our show for this week. Thanks. Thanks. And thanks guys for joining us on the show.

We'll see you next week at Fortnite®. Go to the site. Be sure to connect with us on LinkedIn,X or Lucie. 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 for providing operational support for the show. Check them out at predictionguard.com. Also, thanks to Breakmaster Cylinder for the beets, and you for listening. That's all for now. But you'll hear from us again next week.

Frequently asked questions

How long is this episode of Practical AI?

This episode is 51 minutes long.

When was this Practical AI episode published?

This episode was published on May 21, 2026.

Is there a transcript available for this episode?

Yes, a full transcript is available for this episode. You can read the complete transcript on the episode page.

Can I download this Practical AI episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.