AI Is Rewriting Developer Roles: Snowflake, NVIDIA and the Rise of Agentic Software

Control, this is Agent Dev. I'm in position. Copy that, Dev.

Standby for go. Standing by. Hey, everybody.

Welcome. You've joined us for another episode of Agents of Dev. I'm Mitch Ashley.

I lead the software lifecycle engineering practice with Futurum Group, co-hosting this podcast with Brad Shimmin. Welcome, Brad. You are, the practice lead of...

Data integration. Sorry, data engineering. Sorry.

Uh, data intelligence, analytics, and infrastructure. I, I'm, I'm trying to grow beyond the basics 'cause we're apparently, we're moving past all of those mundane, use, use cases and, and job roles now. Everything is engineering.

We're all builders. We're all... That's what we're becoming.

Oh, no, we're just intent shepherd. We're just shepherding intent. Intent shepherds.

Yes, there's a lot, there's a lot of truth to that. You know, it is, it is fascinating how, you know, just my mind getting around what this change really is about, and it's just, I feel like I'm just starting to really grok it, and, Graff it, and everything is- Well, I think, I think you're, you're ahead of the class then, sir, 'cause, I, I, I think- Oh, I don't know that. I, I- I'm, I'm...

This, this week I'm, I'm at Microsoft FabCon and the first ever SQL Con, which- Uh-huh ... I love the fact that we're actually starting up a conference in 2026 about SQL. Oh, Renaissance Week.

Okay. It's brand new. Uh, never, never been s-seen or tried before.

Uh, anyway, it, it is, it is amazing to me, just how much energy continues in our little industry around AI and the complete, in the midst of a complete lack of understanding of how it actually works. Yes. I don't know, but it's gonna be great, right?

Exactly, right. When we get there, we'll know it, something like that. Will we?

Will we? I don't know. Will we?

Well, it'll... The target will have moved. That's the challenging part of it.

That's, that is exactly it. That, that was the target. The, the sta- the end, the, you know, Zeno's paradox where you never get to the finish line- Mm-hmm ...

'cause you're always just partly there and partly there. It's this journey. It's the journey, for sure.

Mm-hmm. Well, hey, let's do the call-out segment. You wanna kick that off?

Yeah, sure. So, I, you know, try to keep my eye on the news while I'm on the road, which is never easy, but it, it did capture my attention, a small release by a certain, data warehousing company called Snowflake. Uh, they rolled out a new product called SnowWork, which may sound somewhat familiar if you're, if you're familiar with, Anthropic Claude Cowork, uh- There you go ...

because it is literally the same idea but envisioned and delivered within the ecosystem of Snowflake. And what's great about it, I mean, I, I, I think that you and I talk about this quite a bit is, agentic software development is really a bellwether and, and a pointer for where other markets are gonna go. Mm-hmm.

And I, I think that the things that we've learned a-about agentic development are now trickling into or, avalanching, snow, get it, into, other, other aspects of, like, data, data practitioners. And so Snowflake is, is really, you know, taking the idea, from Anthropic and applying it to things like, you know, having a conversation with your data that can take action, that can do things, and do things with a much more, much more trust and belief in the data that you're actually looking at 'cause- Mm-hmm ... you know, for those of you following, on, you know, at home, within the data space for quite some time now, we've been trying to be able to talk to data and have conversations with data, and that was, you know, like, through NLP and other type technologies which forced you to know, you know, exactly the names of the columns and whatnot when you, when you typed your question, or it would be wrong.

And we, are, are apparently, hopefully moving beyond that. Uh, and this is what we're seeing from, from Snowflake with their SnowWork. Ah, the semantic layer.

I know that's where you were going eventually. It is exactly. Yeah.

That is, it is big time at this conference, at the, at the Microsoft, conference that I'm at this week. Is there, is there a... Do you sense just kind of a change in tenor, tone, where it's headed?

Is, like, it's, this is, it's kind of, or it's starting into something definitely different? Yeah. I, I think that, many of the problems that, we, we used to face, such as, you know, building and maintaining data integration pipelines as but one of many examples, we're, we're starting to think of AI as a means to a layer of abstraction above that- Mm-hmm ...

such that, you know, it's, it's not just being able to automate it, 'cause we could do that before, but it was brittle. These things were always breaking. And you would be perhaps not shocked to, to know how many companies currently rely on nightly, you know, secure FTP uploads of CSV files to get stuff done.

Um- Yes. Yeah. They aren't going away anytime soon, but they may have agents doing it.

Well, they might not have to. I mean, maybe it doesn't matter. Maybe, you know- Mm ...

if you can have a non-deterministic system that can see the context that it's operating in and take action, you know, as, as we talk about so often in, in the stuff we're working on, maybe you don't need to have a, somebody that's dedicated to keeping that thing running. Maybe it can be self-correcting. Maybe it can be, you know, preemptive in alerting me to a problem that I might not even know is happening.

Mm-hmm. I, you know, I had not heard about SnowWork. Sounds like, uh- SnowWork ...

what they do in the Colorado mountains when we ha- when we do have snow. You know, they do- There's snow work to do. Unless it's yellow, and then you don't Yes.

No, stay away from that. But there, there's enough territory there you can usually avoid that. Um, well, let's get...

You know, th-this, this was, NVIDIA GTC week, and, uh- Yeah, yeah ... Nick and I had a chance, Nick Patience and I had a chance to do a, do a, report on that, and, uh- But you couldn't, you couldn't cover it. N-N-N-NVIDIA GTC is now the S- the Steve Jobs announcement equivalent, where- Yeah ...

all the oxygen left in, out of the room, it was the event horizon of which nothing else was happening. Um, but I think in this case, the difference is, and everyone else and their brother, sister, mother, and uncle are announcing something with that NVIDIA at the same time. Right.

They're riding the coattails. Riding those coattails, yeah. Yeah.

And at big time. It, it, it was really fascinating, but what caught my eye was, well, my ear, was, Jensen spent, I don't know, the first 45 minutes, maybe an hour, talking about software. He didn't talk about hardware.

That is really weird. Yeah, that, that's- He talked about software ... that's freaking me out, yeah.

And applications, and it's like, you know, he, he got, he got the memo about software's eating the world. Like, hey, that's very, you know, in 19- 19-whatever. That is still...

Was it '12 when he did that? Yes, but it's still relevant. Still relevant.

Um, and he went, you know, of course, he went into the whole Neo cloud, we'll get into that, but, what, what jumped out to you about, about GTC? Yeah, I mean, a couple things. The, the first one I think you and Nick probably wrote about and, and I think, those of you who, sort of, you know, know of our, our little ecosystem perhaps watched one of our Utilizing AI podcasts recently where Nick and I chatted about, the show.

Um, and he made note of the fact that Jensen sat down with, a good number of very influential open source model makers. And, you know, it is something that we as analysts have, have chided NVIDIA about in the past, mostly with, with regards to the, you know, the software layer that sits between the GPU and the operating system. And, uh- Mm-hmm ...

that's not always been the most open, but you can see in what, you know, Jensen's prioritization from this conference and this, this panel I'm talking about just how critical the open source ecosystem is to NVIDIA, and how they want to support it. They see, for instance, that, you know, in the United States anyway, there's a bit of a pullback right now away from open source. Um, and I, I should say, actually, perhaps that same thing is happening elsewhere i- in China, and we can chat about that in some detail.

Um, but, you know, for NVIDIA, they live and breathe with developers and data scientists and those people that work with software. So they need to, they need to not just honor but, but support that, that, community that's driving- Mm-hmm ... so much innovation in AI.

Well, developers, you can spread that, you know, spread that out to, are the tip of the spear. I've said that for a long time. It's like this is where the highest degree of innovation and- Yep ...

the application of AI and the transformation of what that works look, work looks like. That isn't happening in other areas, but developers are just wired differently. They seek this stuff.

They figure out what they can do with it. They're excited about it. They don't mind changing their jobs because they don't want to do the same boring stuff.

They want to. Right? They seek that out because- Exactly ...

they don't want to write code or document it. And they wanna show their friends. They wanna like go and be, you know, "Hey, look at this.

" You know, put it up, there's open sources, whatever. Yep, yep. So it, it still is, and I think it's gonna be that way for quite some time.

Um, the builder- Thankfully ... builder community will expand. And I think that- Yeah ...

you know, it, it's... You can see... I was just talking to a salesperson this afternoon and, and he was talking about, "You know, I like to make my job more efficient, and I'm not really a technical person, but, you know, I do think about ways I could do...

" You know, uh. It's like, "Yeah, you're a builder. " We're all builders.

If you're not already there, and if you wanted to download OpenClaw, you could. Um, well- 'Cause speaking of that, can we, can we talk about OpenClaw? Can we talk about Malt Book and OpenClaw?

Um- Malt Book, yes. What happened? So I, I don't know.

The non-join network? Hmm. I am still trying to wrap my head around why Meta would acquire, hire, acquire, that asset, because anyone who followed what was going on with that would, would certainly s- cast, you know, tip their head like a dog trying to hear and understand better, you know, to say, "Well, wait a minute.

" Mm-hmm. Wasn't this really just people trying to drive, you know, this, this, unrealistic vision of AGI, that these Claw, you know, Clawbots at the time were all having a conversation on their own, and it wasn't actually happening. So don't know.

But maybe we should put that aside and just talk, talk about NVIDIA, who, is jumping on the OpenClaw, bandwagon pretty heavily- Yeah ... with GTC, and their, their Nemotron and OpenClaw announcement. Yeah.

Which to me, I, I, I saw that and I'm like, yeah, they're the ones to really make this realistic, and by realistic I mean something that isn't going to cause immediate and irreparable harm to whoever uses it. You know, that's what they're doing. They're gonna bring down the internet.

Or, or your, your MacBook, or not MacBook, sorry, your, your, uh- Mini ... Mini, your Mac Mini, yeah, right. So-You know, I, I, here, here's what I think is interesting.

And one thing is I think, you know, Jensen definitely got right, and he gets a lot of things right too. Of course, he tends to create his own reality. But, is- Might be like she- You know, last year MCP was a thing that was the viral- Yeah ...

changed everything, right? Yeah. 'Cause it just opened up what you could do with agents.

Solved the problem everybody had, is everybody had, had, had, tin can vegetables, but nobody had a can opener. And suddenly here, here's the can opener. Every- everybody jumped onto it, right?

To make a really poor analogy. This year it's OpenClaw, and I think it's OpenClaw because what it's done is shown... It, it's dropped the barrier to get into the agent creation and management and do stuff with AI.

Now, maybe it's not safe all the time or done, done well, and, you know, Enterprise has a little different requirements, which is what Jensen went after- Yes ... with their, with their offering. But everybody's drop- is dropping an OpenClaw offering, right?

Or they're dropping something like it. So you talked about the work, Snow Work. Yeah.

Right. That, that could be seen- Complexity computer ... very similar.

Or complexity computer, and com- Yeah ... they're gonna come out with personal computer version of it. So I think- Or, or anyone using Ralph to, to have their agentic tooling do pro- work on problems till they're done.

That's the same thing. We, we've gone into this, you know... What, what was the utility knife everybody had to have?

If you remember that. Oh, the, um... Not the Swiss Army knife, but what came after that?

Yeah. The Leatherman multi-tool. The Leatherman, that's what it was.

Yeah, yeah. Like, everybody's gotta have the Leatherman, right? You gotta have my tool kit.

And so then that-- I think that's what this year is about, is everybody getting... being able to start to exercise what this means to use it and create agents. I think the other part of it too, you didn't say it this way, but, you know, the edge is the new cloud.

H- how, when did we rush out to buy Mac Minis for anything or the latest edge computer for what? Yeah. Maybe to do a LAN party, to, to gaming, you know.

But, but I mean, really, the fact that we have run on hardware to be able to do this stuff locally on your own, you don't need the cloud- It is amazing. Yes. Do, do you know why that it actually works?

It is because of software. Well, yeah, there's that little thing called software. And it's successful because- I don't mean just possible.

I mean, the reason why it's actually feasible is- Oh, okay ... good software. You're, you're being real.

You're making a real comment, not a funny. I am. I am, seriously.

Like, you think of O- OpenClaw is built on, one of, one of... We-- I think we were chatting about this a week ago, about the pie of, you know, this, this, ev- you know, this rifle is mine, but in the form of an agentic harness. Mm-hmm.

And you know, Cl- OpenClaw is built on top of it. It's, it's built on other ideas. It's built on the work of many people.

It is. I mean, that's kind of that shoulder of giants. Maybe they're small giants, but a lot of small giants.

They were all- Add up ... a few big ones along the way. Yeah, exactly.

So I, I think it's, I think the sort of, kimono's open or the, you know, barn, the barn door's open and all the animals are running out and having fun in the pasture, right? It's, it, it is a good time, and what... what's, what's been exciting for me is just in my own work, so you'll, you'll love this.

I've saying this to you before. Mm-hmm. So I developed this, framework con- obser- observability native all around the premise that observability can't be an operations thing.

If agents are gonna build agents, and agents are part of all that workflow happening from spec plan all the way through deployment and beyond, whatever's beyond, it's everywhere. You can't just observe agents when they get into production. You have to observe the agents that are creating agents that are part of the- Yeah ...

underlying fabric. And so I created these seven, seven pillars and, and, four steps in an agent operating cycle, and had folks like you and Fernando review it. So I gave my write-up.

It's not a spec, but it's, you know, kind of a definitional, foundational document. It was very thorough, which to me is kind of a spec. Well, thank you.

I guess we can call it a spec. " But, so I gave it to my agentic operating environment that I developed it with, and it said, "Yeah, it's... We're doing some of these things.

We're doing one, three, and five already, and here's what we have... Here's the ones we need to address. Here's two, four, and six.

We can do those really easy. Here's what, here's what we need to go change, and then what we need to fix about it. " In an hour and a half, the whole thing was instrumented and implemented, all of it.

Now, there was a lot of things built, so your shoulder of giants, you know. There are a lot of things already in place, and it's- Yeah, right ... but if I was gonna start from scratch as a fundamental, you know, architecture or requirement or spec, I wouldn't have had to do any of that.

It would just be built in. That's the environment we're working in. That is heady.

It is, it is really... You know, there, there are a lot of downsides to, to agentic work, of course. Um- Mm-hmm ...

we, we've talked about many of them here. Um, but when I think about, you know, what it, what it means to be a builder, meaning a, a, somebody who creates something, and it could be anything, not just a piece of software even, but just an idea. Um- Mm-hmm ...

you know, remember when you used to sit down with your, your trusted friend and, say, "Hey, I got an idea. " Uh, and you would work through it and poke holes in it and whatnot. You know-That took time and opportunity and it was, you know, not fast, but we, we have like literally sort of collapsed the time to value, if you will, from idea- Mm-hmm ...

to, to value to almost nil with these- Yeah ... these tools. And that's...

What that means, I don't know. Well, you know, so I think about these, like you do, I think about these things a lot, and I was on a panel day before yesterday, and we were talking about... So the, the t- the, you know, the first mover advantage is going, shrinking- Yeah ...

right? 'Cause people quickly come up- Yeah ... with their own version of OpenClaw or whatever kind of in their products.

And, and it means- Call it the 10-day mover advantage. You know- Yeah, it is that ... it's, it's what we're talking about with Claude Open, right?

And that's, you know, that's gonna be- I think that's gonna get shorter. Also, I think we're gonna get to, maybe this isn't that far away, of, well, do I really need to maintain that code? Do I really need to modernize that code?

Ooh. When I want something- Yeah ... just rebuild it.

I don't, don't take the time to go and fix it, just rebuild it. Yes. Because we get better and better at building it.

It's not like our skills are staying the same, or s- or gradually incrementing and our skills increasing. It's if you follow the curve of models and how quickly they're improving, and just how much claw code has improved in, I say claw, Claude code in, in six months is just, like, not even the same tool. It's not, no.

Um- It's not. I think we're gonna be at a point where, you know, software is just, you know, it's like mixing up a new batch of whatever. Okay, cool.

We're good. Maybe it's not even what we knew software to be. Maybe- Maybe ...

there's a paper I would love us to, to dig into and talk about, um- Okay ... that came out recently that, that talks about using a directional acyclical graph, you know, a DAG, to, define, basically an intent to outcome map, if you will. Mm-hmm.

And the, the idea behind it is to, make that a deterministic system that uses a non-deterministic system, meaning a, you know, generative agentic system, to actually implement. So you have a fixed route and a fixed outcome, but the route, the way that you get there, is up to the, to the, you know, agents and the models. Um- Mm-hmm.

Mm-hmm ... " Uh, make it so, number one. Yeah.

Yeah. Well, so you're, you're pointing to something too that also I had a bit of aha this week is there's the model of request response- Right ... linear in-interaction with AI.

Do this. Yeah. Create that.

No, don't do that, do this instead, right? This, this sort of what, what I thought originally vibe coding was. And, and I, I don't know if vibe coding is a thing anymore, but I think the model really is about it's, it's a co- it's not a linear process anymore.

It's, it's letting AI figure out what to do. You might wanna ask it, like, you know, the tools that I work with I say is, "There's, there's a relationship we have here. " Yeah.

"So I want, I don't want it to be opaque, I want to understand," right? Yeah. Yeah.

And what it caused me to do is realize that, oh, that work was over there, but I did, I forced it down a linear path here 'cause, because I gave it, I made it go do an assessment- I didn't give it- ... on a certain project that I was working on ... right, I didn't give it the freedom to maybe choose a better route.

Yeah. It said, "This is a table lookup. We don't need to do it.

" So, well, how do we make it agentic? Let's... So I had to really step back and say, "I'm not gonna tell you how to do it anymore.

Tell me what- Yeah, yeah ... you wanna do. " "I don't have to- Yeah ...

" Yeah, yes, you do for security and other reasons. But it's a change in how we work and interface with AI. It's pretty drastic.

It is, and it's fairly recent. You, you remember how we were talking about prompt engineers as a job a couple of years ago? Um, and this year, and then over the last year, we've been talking about context engineering, which is still highly relevant.

Um, but- Mm-hmm ... in the day, you know, a year or so ago, if you worked with a model, you had to be very prescriptive, and you would use techniques like chain of thought, for instance, to, to help guide the model to an output. And what I found e-experientially is that, the less data I give it, the less instruction I give it, sometimes the better the result because I give it that freedom- Mm-hmm ...

to, to wander a bit as, as you're talking about. There, there's a, there's an old Zen koan, or just actually a, a saying, and not a koan, sorry. Um, but it is a, a Zen Buddhist saying about if you really want to, keep your cattle, horse or, or cows or whatever, don't watch them constantly.

You know, just keep an eye on them every so often. You don't have to chain them up. You don't have to do anything.

Just, you know, let them roam in the f- the field, and they'll be okay. They're not stupid, mostly. Mm-hmm.

Yeah, they, they may wander off the, off the land here once in a while, but then go get them and bring them back, and- That's right. That's right ... they're gonna stay there forever.

But, but if you're holding the cow, you know, constantly, then you're not doing anything else. Okay, it's time for the drop You had suggested the, the, the drop for this one, too. Unsloth Studio.

Ah. Yes, yes. That sounds like a prompt, too.

Another great name. What, what is Unsloth Studio? Yeah.

It's, it's yet another L- you know, ML- LLM studio, and yet another Ollama. Um, do we need another one? Yes, we do.

Absolutely, we do. Yeah. Um, these are for those who, who don't use those tools.

Uh, you know, means for interacting with AI locally. And, with Ollama and, ML Studio, you have a lot of great capabilities, you know, a lot of control. You can use, you know, VLLM or, Llama CCP to, to do your inferencing, for example.

Um, or if you're on a Mac, you know, you can use MLX inside of ML Studio, and, and run your models quite rapidly. But, um- Mm-hmm ... you know, what, what those really kind of focus on is, are basically interacting with models as you would if you were logging into Gemini or, or Claude or whomever as a chatbot.

Um, what Unsloth is known for, for, for those of you who perhaps aren't familiar with them, they have been early... an early, sort of, proprietor of, fine-tunes, and the tools that you would need to fine-tune a model. And not just fine-tune, but do all, all kinds of work, like distillations and whatnot.

And, they put together a ML Studio style interface, that focuses on or, or really elevates some of the work you might be doing with models, such as fine-tuning. It's just one of many. Uh, and, and one of them, for instance, I'm, I'm quite anxious to, to try out is, being able to...

They'll, they'll have what they call recipes, where you would have a recipe for creating triads for unstructured data. So I, like, I could feed it a whole bunch of PDFs, like, you know, presentations that we, we get from vendors, for instance. Mm-hmm.

And I would be able to, to have it basically create a knowledge graph or just a, a, you know, property graph, probably, out of that with, you know, all the nodes and edges that, that are represented in that text from those PDFs. And there's a lot you can do with that, such as, you know, use that to fine-tune models and, and generate, you know, refined data to do more work with that. And so it's for, for folks who are in the, you know, AI and, and data fields, this Unsloth Studio is just awesome, and I, I encourage everyone listening to, to check it out if you haven't.

Um, it's, you know, it's just a UV pip install away, for everyone. Another example of taking what took massive resources and, in this case, data sciences to do, now making its way into everyone's hands, right? It'll become more and more accessible.

Yeah. More and more people. You too can train a model.

Like, you can train your dragon. Here, train your model. Right.

Train your dragon. Yeah. It's, it's, um...

You know, frontier models are, are critical. Uh, but they're not the only game in town, and, and we have seen research from early on that indicated that for more task-specific, you know, duties, like name density extraction, you would be absolutely wasting resources to throw that at Gemini or Claude. 5 is free.

I mean, it may be rate limited or whatever, but it's free. Yeah. Yep.

Or, or you can run, you know, Gemma on your own hardware. Yeah. Right.

Yeah. Pick your model, whatever it may be. You know, Neoco if you got, if you got the right hardware.

Um, but that's- Nemotron, uh- Nemotron ... speaking of Nvidia. Yes.

Nemotron, exactly. So it, you know, it's the... So here, here's my drop for the week, and it- it's sort of a collection of, drops that form a, a rain, a rainstorm, you know?

It's many drops, huh? It's many drops. Is...

It's... I, I am... I wouldn't say I'm inundated, but every day I get either a briefing or multiple emails or signals from the stuff that find out what's happening out in the world, letting me know about it, is, um...

You reviewed, and I'll be issuing the agent control plane framework document- Mm ... this week. Probably come out the end of this week, maybe first part of next week.

And everyone is coming out with their, just like their studio or their claw or their whatever for building and operating agents. Now vendors are also starting to lay claim to, "Well, here's the agent control surface, control plane that has things like observability built into it- Yep ... " So you know how...

You can not only manage it, but you know what your agents are doing, and are they fitting within the guardrails, and are they compliant? Uh, can you do governance on that? Um, Tricentis announced theirs for...

You know, they're a testing company. "Okay, here's the agent control plane- Ah ... " Yeah.

Right? And- That's brilliant ... that can name a dozen that I think I've gotten hit with in the last week of people coming out with parts of that functionality, which I think is good.

Um, but the sort of great sorting, maybe the clone wars of the future are agent control planes fight for dominance and who's gonna control the control planes. We'll see what, what path that takes. Can't they all just get along?

As a way to skin it isn't Is, isn't there like a, you know, o-open semantic interchange idea for agent control planes? That's- There should be. Somebody should make- We need an agent control plane semantic layer.

There you are. Well, the OSI could actually work for that. Um- It could actually ...

but they're not, but they're not actively promoting it to do that, but it definitely could. It is a model to build from, to be able- Mm-hmm ... to do that.

Mm-hmm. For sure. So I think, I think, you know, the effect of that is you need that to be able to get AI into production.

Enterprises won't let you take anything significant into production at scale unless you can govern it, control it- Yeah ... have accountability around it, secure it. So everybody is naturally doing that for their part of it, so their, their products and tools can get into production.

Um, but I think it's also gonna... It, it is gonna create some forcing function to sort that out. Okay, I can't have 50 of them.

Maybe could have five to 10. Maybe I'd like one or two or three. You know, where, where is that balance?

Oh, boy. Maybe it's, maybe it's 20 because you have agents controlling the control planes. I, I don't know what the deal- Don't say that.

That's, that's way too many. I mean- There's a circular... There's your recur- recursive programming example.

Um- Yep ... you know, maybe it's a model that we're not thinking about yet, but that seems to be what's on the next horizon of, "Okay, I'm being overrun by control planes, folks. Help me out.

" We need a... It's like, you know, you have catalogs of catalogs. Uh, we, we need meta- you know, control planes of control planes.

Parts are made of parts. Yes. The old- It's all, it's all an abstraction game.

Oh, boy. It's turtles all the way up. Well, next week is RSAC, the week this will drop, so I will be there doing some live Textron gang, videos there.

What are you up to next week? Oh, next week I'm, I'm recovering from, Fab- FabCon and getting ready to, to visit, with, with people, in their, their conference at the end of the month. Mm-hmm.

Google Cloud Next. Yeah. Yeah.

Yeah. That's coming up. I'll be going to SUSECON, in- That should be interesting ...

July. Um- Yeah ... with all the talk of, operating systems being required to, to capture age verification.

Yeah, verification, you know, lack of TSA people. Can you get back in the country? You know, hey, it's an adventure.

You know, who knows? I mean, who knows when all... But I'll be somewhere I can join by, by digitally to, to say hello and see what we're doing.

I'm also going to the, to the MCP Dev Summit- Oh, I'm jealous ... which is hosted by the- Yeah ... Agentic AI Foundation, part of the Links Foundation.

Yeah, I was like, did- didn't even know it was happening and, you know, they reached out, and I'm sure they'll be re-reaching out to you for the next one, but- Do, do you think they'll have a session about what comes after MCP, because we all over-rotated on MCP? That's what... Well, that's my main thing is, is MCP gonna stay this or is it gonna become what?

What is it? Right. What is it next?

I don't know. Yeah. You know- And I gotta believe it's just a lookup.

Maybe it's, you know, already past its sell by date. Could've been something else that it hasn't grown into yet. Is it SMP version two waiting for version three?

Or is it like, "No, we're going, we're going open telemetry here, you know, full out. " Mm-hmm. We'll see.

We'll see. I'm really excited to see what happens there, so... And we'll get to do the next one together.

There's another one in the fall. I forget what it is. Um, but I think that's in San Diego, so we'll find out what's happening there.

So that's on the horizon too. So lots of great things happening. Agreed.

Well, safe travels, my friend. Enjoy the rest of the FabCon SQL, crunch or- SQLCon. Don't, don't say that.

SQL... Oh, so sorry. SQLCon.

SQLCon. Enjoy the- Rath of Con. Uh, yes.

And, truly safe travels this week- Same to you ... as you get ready to go and head into Google Next, and while I'm heading out to San Francisco myself, so... Well, thanks everybody.

You survived another episode of Agents of Dev. Congratulations, everyone. And, uh- And thank you ...

it is an accomplishment. So, you know, do... We have participation awards for everybody.

You'll get your, you'll get your prize soon. No, seriously, thanks for, for being with us for part of this discussion. Please reach out, follow, share.

We appreciate everything you do to, be part of this community, and we'll look forward to talking with you soon. Control, this is Agent Dev. I'm in position.

Copy that, Dev. Stand by for go. Standing by.