Tech Talks Daily
00:00:00 · Neil C. Hughes
Ad[00:00:00] S0: The leading issue of agentic AI in businesses right now is ensuring agents act with compliance guidelines, and Denodo applies guardrails across your entire data estate. By aligning your company's data infrastructure under one system, these guardrails perform consistently across your platform. So start scaling your business and start with Denodo. Simply visit denodo.com to learn more. What can an AI agent reach once you give it access to your business systems? The answer to that matters when software could move from suggesting an action to carrying it out alone without your permission. Because even a legitimate objective can still produce an unexpected result, especially when the permissions behind it are broader than the task actually requires. So my guest today is Jonathan Trayers. He's a director at Ekco, spelled e k c o. And today, we're gonna discuss securing agentic AI and doing it through disciplines such as identity, access control, monitoring, and ensuring clear ownership. So we will look at why organizations are struggling to predict every possible failure, how to limit what an agent can affect, and learn where human review belongs as teams begin delegate in work. And Jonathan will also explain a practical sequence involving controlled testing, supervised operation, and reusable deployment patterns. So if your company wants to benefit from AI agents, today's conversation will give you a lot of questions that you could be asking before handing over the credentials and leaving the software to get on with it. But enough for me. Let me introduce you to him now. So a massive warm welcome to the show. Thanks for joining me today. Can you tell everyone listening a little about who you are and what you do?
00:02:00 · Jonathan Trayers, Neil C. Hughes
[00:02:00] S1: Neil, thanks very much for having me. My name is Jonathan Trayers. I'm a director of security and automation at Ekco. Ekco is a managed cloud and security provider across Europe. And I've got fifteen years working in security solution architecture and automation. And I think a large chunk of that has been with large enterprises across financial services and government. So I think where I'm working right now, I spend a lot of the time day to day working on secure automation. So I help organization build workflows. There are kind of two steps in it. Deterministic ones, which is rule based and do exactly what they say. And then agentic ones, so where AI reads the situation and makes decision on it. So I think a conversation that we're having today, what's banging center. So the skill that I'm doing is putting it together safely, and I think it's probably where most people are worried about at the moment. So... [00:02:57] S0: Yeah. I mean, what you've spent fifteen years in the field there, probably picked up more than a few war stories, certainly earned your stripes. And certainly, in recent months and years, we've seen so many different incidents where AI systems have reached into another organization's environment during controlled testing. That is before we even talk about unleashing hundreds, if not thousands, of agents all talking to each other in in different organizations. But what do these recent cases... What do they tell us about the maturity of AgenTek AI today, do you think?
00:03:29 · Jonathan Trayers
[00:03:29] S1: Yeah. Look, I I think the first thing is to say, right, in short, what's my snapshot around it? It's incredibly mature in how it's gotten to, and that's over over the last year. I think for someone listening, I always look at what are the big changes. Right? And we can go... You go all the way back to .com, but look at something recent. We went to the cloud in 2020 when everyone went remote overnight. I think we might get to it later on, but the aspect is if you had the guardrails in place, you know, you were actually better off when it all happened, but the sudden... But the difference now is the speed. Right? The the maturity of AI has come from since 2022. When we started with ChatGPT, it was essentially a very simple LLM data in plus a model... Large language model equals data out. Risk was quite low to agentic AI in 2026 with OpenClaw, OpenAI, and the latest models. The capability now is really mature. And I think, as you just said, when the best resource labs in the world and their test environments are also getting leaked, you can only assume that when we productionize this across every organization, every every customer trying to adopt AI, that the, you know, the deployments will have challenges too. Right? Yeah. Look, if if you want, I I I find the hugging face example really, really interesting. Well, don't explore all this.
00:05:01 · Neil C. Hughes
[00:05:01] S0: Absolutely. Go for Maybe just explain what it was for... I mean, myself and many people listening will know, but if there's any business leaders that have somehow missed that that huge story this year that that appeared in our newsfeed, just give me a bit of brief synopsis of exactly what happened and why that matters to them.
00:05:16 · Jonathan Trayers
[00:05:16] S1: Yeah. Look. Like, firstly, it was a it was a test. Right? So Yeah. Maybe I don't have all the exact elements. But, like, OpenAI, we're testing one of its newest, most persistent models, and they were looking at it from a a benchmarking perspective. So they were working with Hugging Face as a solution to benchmark this. And they provided a a task as to... The goal is to prove and pass the test. Right? Yeah. So instead of just going and hacking the test, the agent took the goal that had to passing the test and then found whatever means necessary to do so. I I find that really interesting. Right? Yeah. But, like, the problem was it broke out and and hacked Hugging Face. But the scary thing in the item is it's the capable... It wasn't just one really capable agent. And I only found this out recently by listening to kind of the the information that they've shared within Blackhat OpenAI. I've been quite transparent on this. It was actually about, I think, something like 700 agents working together, communicating with each other to solve that problem. Right? So that's that's scary. Right? So to build on that further, you know, they found some platform, a repository that they could talk to each other through, which they weren't trained to do so. And they've been doing it for quite quite a while. And I believe that OpenAI had actually seen this happening and they shut it down and they found a way around it. So look, it's really interesting and and like the scale where, you know, the agents have been able to exploit a vulnerability within Hugging Face to be able to pass the test that it was provided.
00:06:49 · Neil C. Hughes
[00:06:49] S0: Yeah. And there's been so many other incidents like this as well. I think there was one. I think it was at Meta where they were trying to shut it down, and it checked... Started speaking in its own language and prevented it it from actually being shut down. There's another way. I think there's a manager being blackmailed when he tried to shut it down. He was having an affair, so he threatened to spill the beans if he didn't play ball. But, I mean, when we look through our news feeds, the most dramatic framing of all these instances that AI has gone rogue. I mean, mentioned Hugging Face. There are 700 agents working together. But what we don't talk about enough, I think, is they were working together to solve a legitimate problem. It wasn't anything sinister as such. It was, I've been given this mission. I'm gonna complete this mission no matter what gets in the way. So why do you think the the more realistic danger is often an agent pursuing a legitimate, objective in in a way that nobody anticipated.