What Is an AI SRE?

**SPEAKER_1** (0:00)
This monday.com ad was created by a team of people and AI agents. Reese, our content agent, wrote the copy based on our best practices, like mentioning monday.com three times. That was the second. Johnny, our coordination agent, built the timeline and kept everyone aligned. Olivia, our human creative director, stayed in the loop, because agents are great, but they don't always know when a joke lands. She had one note, tell listeners it only takes minutes to build an agent, so minutes. Create your own AI agent today on monday.com.

**Birol Yildiz** (0:30)
Of course, I wouldn't start with that, and it's not something I'm seeing as of today consistently, and I wouldn't even recommend it, that you run an agent that works exactly like that, fully autonomous, only pages you by exception. But I think that's where we're heading.
That humans will only be page for novel incidents when an agent gets stuck.

**Darin Pope** (0:54)
This is DevOps Paradox, episode number 360
What is an AISRE?
Welcome to DevOps Paradox. This is a podcast about random stuff in which we, Darren and Viktor, pretend we know what we're talking about. Most of the time, we mask our ignorance by putting the word DevOps everywhere we can, and mix it with random buzzwords like Kubernetes, Serverless, CI-CD, Team Productivity, Islands of Happiness, and other fancy expressions that make us sound like we know what we're doing. Occasionally, we invite guests who do know something, but we do not do that often since they might make us look incompetent. The truth is out there, and there is no way we are going to find it. Yes, it's Darren reading this text and feeling embarrassed that Viktor made me do it. You're your host, Darren Pope and Viktor Farsic. Viktor, can you picture this? It's 3 a.m. Your phone doesn't ring. In the morning, you wake up to a clean incident report. The system fixed itself, and there's a slight message saying, hey, agent resolved the problem at 3.15.

**Viktor Farcic** (2:12)
Oh, if you remove the incident report from this story, then you're unpicturing my retirement.

**Darin Pope** (2:18)
Don't you wish you could retire today, since I'm already retired? Would you trust it?

**Viktor Farcic** (2:23)
Not initially, but I feel that that's the same as with people, right? I don't trust anything or anybody initially, and that includes the tools, the platforms, the services, whatever, right?
Trust is earned over time. But let's say that if you ask me would I trust it a few months later, and it didn't mess it up, then the answer is yes.

**Darin Pope** (2:45)
On today's show, we have Birol Yildiz from iAlert. Birol, how are you doing?

**Birol Yildiz** (2:50)
Good. Thank you. Thanks for having me.

**Darin Pope** (2:52)
Does that story sound familiar?

**Birol Yildiz** (2:55)
Absolutely, yes. I think it's something I've been telling over and over again.

**Darin Pope** (2:59)
Here's the question.
What's the difference between that that we've been doing for years and what everybody is pitching now? What makes a big difference? Because we had self-healing back in the Tivoli days. For anybody that's not familiar with Tivoli, it's a really old thing.

**Birol Yildiz** (3:16)
True. I think the difference is the capabilities in diagnosis. Those have changed. And applying the self-healing, I think, yes, I would agree that it's probably...
If you know what the underlying problem is, then that's something you could have automated, right? And that's not the part where that's fundamentally different. I think what's fundamentally different is being able to automatically diagnose the root cause and then knowing like what fix to apply.

**Viktor Farcic** (3:45)
I feel that the difference that in the back to your statement is that self-healing we had or have still is based on predefined patterns. If you take Kubernetes kind of, oh, pod crashes, what do I do? What's self-healing? I bring it back up.
What goes after the predefined patterns? Let's call it automation, right? You could have a script or a cron job that does the same. Is then if predefined patterns do not match, then we evolve, I'm going to call it today intelligence, which is carbon. And now we're talking probably about silicon intelligence, but hey, something happened that is not in a list of predefined patterns that we figured out how to solve. Is that close?

**Birol Yildiz** (4:31)
That's very close, yes.

**Darin Pope** (4:33)
So we move from hammer and nail to fuzzy.

**Viktor Farcic** (4:37)
No, we're still hammering the nail.

**Darin Pope** (4:39)
Oh, we're still hammering the nail after the fuzzy decides which nail to hammer.

**Viktor Farcic** (4:42)
Yeah.

**Darin Pope** (4:43)
That seems too easy. You have a whole company around this. It's like, how does it even make a difference? Again, I'm still trying to get my head. I mean, I think back, fortunately, Tivoli was right on the edge for me. But I'm thinking back to, I guess I'm old, but I'm not that old. Well, actually I am.