← Back to search

Bridging the Gap Between AI Builders and Domain Experts

Agentic Conversations (formally mlops.community) · 2026-10-12 · 22 min
relevance 53 3924 words Episode page ↗ Audio ↗
Show full episode description
Everyone is racing to build one agent that can do everything. Justin Schroeder , co-founder of Standard Agents , thinks the future looks more like thousands of tiny ones. Ahead of his talk on domain-specific agents at AGNTCon + MCPCon North America, he explains why tightly scoped agents might be the smarter bet, even if it feels like a step back toward the single-purpose machine learning models of a few years ago. We dig into standards as metadata you pin to an agent, so that it shows up with everything it needs in its harness. Then we test the idea against the obvious objection: if a big model can already handle the task, why scope down at all? The answer covers forcing functions, a microservices mindset for agent design, and small agents that quietly check issues or unread messages every five minutes. It also covers the surprise $1K bill waiting for anyone who leaves their agents running. Then it turns into a proper debate. Our host is 99% sure the agent marketplace will never happen, and Justin arrives with a counter that might change his mind (hint: think about where your skills come from). Along the way, we cover agents as tools versus a big-brain router and how anyone keeps track of a thousand agents. We also talk about why the people who know what agents can do and the people who know what they need still have to meet in the middle. Demetrios Brinkmann: https://www.linkedin.com/in/dpbrinkm Justin Shroeder: https://www.linkedin.com/in/jpschroeder Timestamps: [0:00] Cold open [1:03] The future is domain-specific agents [1:51] God models vs specialist agents [2:20] The perfect Gmail agent [3:14] Why standards are missing [3:29] Train the prompt, not the model [4:30] The harness beats the model [6:07] Standards and runtimes for agents [8:17] Why scope down at all [10:07] Why model routing won't win [10:29] The surprise $1K bill [11:12] Agents that build agents [12:09] Agents as tools [13:23] Managing a thousand agents [14:24] Agents for Main Street [15:37] Agent marketplaces will never happen [16:52] Skills are just bad agents [18:04] Skills are already a marketplace [20:12] Domain experts build the agents [22:12] Wrap up
✨ Episode Outline — click any point to jump to it in the episode
Problem solved
Why the future belongs to small, narrowly scoped domain-specific agents, and why shareable standards and agent runtimes are needed before that ecosystem can exist.
Benefits
  • Narrow agents with only task-relevant tools squeeze far more value from small models
  • Provable efficacy: pin exact prompt, model, provider and tools so shared agents behave identically
  • Cheap recurring background jobs (e.g. checking GitHub issues every 5 minutes) without burning big-model quotas
  • Composable agents that can be shared, deployed to the cloud, or handed to coworkers
  • Agent runtimes (like Node/Bun/Deno for JavaScript) let one spec run anywhere with different trade-offs
Use cases
  • A Gmail-only agent whose sole tool is 'check latest messages' — perfect at one task, then shareable
  • Background agent polling GitHub issues on a 5-minute loop, which burned ~60% of a weekly Fable allotment on a big model
  • Friend Raul left agents running and got an unexpected $1K bill — motivation for scoped, cheap agents
  • Hermes/OpenClaw-style personal assistant built as a coordinator with many sub-agents (tree/graph structure)
  • Back-of-house butcher shop agent estimating pounds of meat to order each week, costing almost nothing to run
KPIs / results
  • ~60% of a weekly Fable allotment burned on a simple 5-minute issue-checking loop
  • Unexpected $1K bill from agents left running
  • Prediction: agent runtimes become a 'no-brainer' within ~8 months
  • Coding agents carry half a dozen to a dozen skills plus several MCP servers
Tools / build
  • Domain-specific agent spec and runtime (Justin's talk 'The Future is Domain Specific Agents' at AgentCon / MCPCon, San Jose)
  • Hermes
  • OpenClaw
  • Fable and Codex coding agents
  • MCP servers and skills
  • GEPA paper (prompt optimization over model training)
0:00 / 0:00
[SPEAKER_00] There's going to be a future where our agents are tuned to perform one small task and perform it really, really, really well. And in that case, you could actually sort of measure the efficacy of how good it can do whatever that thing is. [SPEAKER_01] That's literally my buddy Raul just told me like, oh man, I left my stuff running and I got a 1k bill I was not expecting. Like software factories are hard, man. If you throw something at a big model and it does it, like is there really the need to go and then scope down like you're talking about? If you've got these thousand agents, isn't that so taxing on the human brain to figure out like, where's that like issues agent? [SPEAKER_01] I can barely keep track of my freaking chats that I have right now and I don't have these thousand agents. [SPEAKER_00] It's a good question because of two things. One. [SPEAKER_01] All right, Justin, I'm excited for your talk at AgentCon and MCPCon in October in San Jose. This is a North American talk. What are you going to be talking about? [SPEAKER_00] So the title of the talk is The Future is Domain Specific Agents. And it's basically that. There's this sort of rustling in the trees right now about this thing called domain specific agents, although everybody has a different term for it. So Jensen calls it super agents. Jensen calls it super agents. Elon has called it like specialist agents. [SPEAKER_00] But the idea is that there's a huge unlock where you have small agents that are around a very narrow set of tasks. So where our models right now are being trained to be sort of God models that have, you know, they know how to code, but they also know how to like create a water filter to survive an atomic apocalypse for some reason. [SPEAKER_00] Like they can do both of these things. There's going to be a future where our agents are tuned to perform one small task and perform it really, really, really well. And in that case, you could actually sort of measure the efficacy of how good it can do whatever that thing is, however small it is. Like maybe the entire agent's job is to like check Gmail. And that's all it can do. So it's even more fine tuned than what you'd think of like a GrokBot or something like that. [SPEAKER_00] And if you could do that, if you could have a little agent that was just like it was perfect at checking Gmail, like that's all it has to do. How hard can that be? If you could do that, then maybe you would want to share that agent with other people. Right. And you could post it online and you could have it on a thumb drive. You could have it however you want. And then that agent could work with another agent. And these things could compose a little bit like we do with skills right now, but with agents instead. [SPEAKER_00] And the only reason that this doesn't exist is, well, first of all, it's sort of a higher order thought process that we haven't quite, you know, like we're unpacking this as we're all learning together. But the only reason it really doesn't exist is that there's no standards around it. So if I create that incredible Gmail agent and I give it to you, you can't use it. So we have to solve the standards problem. So my talk is going to be a lot about that. [SPEAKER_01] Ooh. All right. So thousands of agents that are hyper scoped in a way or thousands of agents that have very, very tightly scoped tasks that they are trying to do. It feels like we are going a little bit back in time and just like machine learning models used to do that, right? [SPEAKER_00] Yes. Machine learning models did used to do that. The cool thing now is that you don't have to train the model so that the GEPA paper or JEPA, however you choose to pronounce this word, was really instrumental in setting the stage for some people. But it basically says that it is more effective to train your prompt than it is to train your model. [SPEAKER_00] And there's a really weird relationship between a model and a prompt and the tools that are given to it that is not very well explored right now. And you've seen the labs hint at this from time to time when, like, for example, OpenAI recently said, hey, actually, it turns out that our model performs way better on this test if it's not using this old broken down harness. If it's using this harness, then it's way better. [SPEAKER_00] Well, that's actually true for literally everything. Everything is like that. You can have an unbelievable output from one harness and a terrible output on the same prompt with the exact same model. And the only difference is the harness. Now, I've got tons of examples of this. So what you're searching for is to find effectiveness. Effectiveness. [SPEAKER_00] You want your agent to be very effective. And once you've locked in that effectiveness, it almost doesn't matter what model it's using or how old it is or something like that. So our coding agents right now, everybody is being trained that we just like, oh, we see a new model release and we just switch our coding agent to the latest model and boom, we're good. That's actually fine at these, like, really large scale models. It, like, kind of can figure it out, although you are losing something in there. [SPEAKER_00] But with small models, this is not possible. So we really need a type of specification that says this exact prompt with this exact model hosted on this exact provider, you know, this entire chain of things has provable efficacy for doing the task that it's made to do. And then when I share that with you, you're getting the exact same efficacy. [SPEAKER_01] Ooh. And so you see standards as almost being, like, metadata that you can pin to an agent so that it knows everything that it needs in its harness to be effective? [SPEAKER_00] Yeah, not only that, I think that there really should be a runtime for agents. So imagine in the same way that we have a runtime for Node, and Node can run in Bun or it can run in Deno or it can run in Node QuickJS. There's lots of different runtimes that you can run JavaScript in or the browser. We need runtimes for agents. That's very similar. [SPEAKER_00] But all of those languages or all of those runtimes are complying with the same standard specification. So there's going to be variations in them. The V8 runtime is just really fast, you know, and it's faster than other ones. So you might want to use that runtime to run your, you know, mission-critical application, but that's not the only thing that matters. [SPEAKER_00] And so I could see an ecosystem of runtimes that exist that are all able to run your agents in a guaranteed way that have different pros and cons. But that is the world that I am 100% convinced is going to emerge. People don't believe this right now, but I'm 100% convinced that eight months from now, this will be a no-brainer for everyone. [SPEAKER_01] Oh, dude, I'm so glad you just said that because I already see the clip forming in my mind as a lip of just like we start with that. And then we go like Elon calls it this and Jensen calls it that. And then boom, like I have the voice overlay of Justin is bringing blah, blah. And then I talk about what you're doing. And then we rock and roll with a few more clips of like, but we need standards. And that's the key here. [SPEAKER_01] And then there's your little trailer that we've got. So note to editor. That's how I'm seeing it in my head. And all right. But there is, there's a few cool things that I just want to like satisfy my own itch for when I, when we talk about this, I've found that you get to a certain place. [SPEAKER_01] And you need this out of, or you, you take this step of going very, very small scope with small models or smaller, like scoped models. It doesn't necessarily have to be a small model when you have like a forcing function, right? It's not necessarily, you don't necessarily think like when you wake up in the morning, like, wow, cool. [SPEAKER_01] Let me go and make a thousand super small agents that just do one thing really, really well. Yeah. And you take like a microservices paradigm to your agent building. Because if you throw something at a big model and it does it, like, is there really the need to go and then scope down? Like you're talking about. [SPEAKER_00] This is a great question too. There must be. Because on multiple vectors, on one, there's the efficacy itself. And you're right that a big model is generally going to have better efficacy than a small model on any given domain. But that's not true on any given domain if you've had like a really reinforced prompt and model. [SPEAKER_00] Like, for example, my coding agents have like, I don't know, half a dozen to a dozen skills on them, a few MCP servers. And so every time it needs to do work, it's sort of wading through this ocean of stuff. And it has tons and tons of different tools. But if I were to create that Gmail agent, it would have Gmail-related tools. Like it would have a tool to be like check latest messages, right? And like that's all it can do. [SPEAKER_00] And so you actually can squeeze out way more value from a smaller model very quickly. And this is actually why I don't think routing is going to end up being the answer. I don't think model routing will end up being the answer because even the big models don't really know how hard a problem is on the front side. You know how hard a problem is on the front side because you are faced with it just like you said. At some moment, I like have a need. I need this thing to like do a background job. [SPEAKER_00] I just like I just needed to go check issues on a five-minute loop and then notify me or queue up something else. That's all I need. And it turns out I just burned 60% of my Fable weekly allotment on that exact problem this week. [SPEAKER_01] Dude, that's literally my buddy Raul just told me like, oh man, I left my stuff running and I got a 1K bill. I was not expecting like software factories are hard, man. Dude, they are. Especially it can get away from you quickly. [SPEAKER_00] So imagine if like when I hit that exact problem, then I tackled it. I was like, oh my gosh, this is ridiculous. There's so many advantages if there's standards. First of all, when I say, okay, I need to build that agent. My agent knows exactly how to build it. I mean, what I'm not saying here is like I have the spec and I have the runtime. So that exists, which is why I get to play with these things all the time and I can see that they're very effective. But I can just spin up any of my coding agents, Fable or Codex or whatever. [SPEAKER_00] And I just say like, hey, I need you to build an agent that does like this discrete task. And then it just goes and does the discrete task. It creates the agent with the precise tools and everything. And now I can deploy it on the cloud. I can give it to my coworkers. It's like a very distilled thing. I'm specifying absolutely everything down to the model. There's all kinds of problems that come with this that you have to solve, which is why it's sort of an unsolved problem at the moment. But it will get solved. [SPEAKER_01] I think I've heard this called agents as tools. Would that be the same thing? [SPEAKER_00] Yes, it could be. In fact, that's like a way to solve the problem. [SPEAKER_01] Yeah, because what I'm understanding from you is more like, okay, there's the... And you're saying specifically, maybe it's even not agents as tools because the model router of the big brain that goes and chooses and kicks off tasks to subagents isn't necessarily the best way of going about this. Especially if you already know, hey, I just want this thing to run every five minutes. [SPEAKER_01] And it's not like it's this very complex thing. And I can hyper-optimize this thing that just needs to happen. It grabs issues or it tells me what my latest unread messages are. Or, you know, like those things can happen on a very frequent cadence. And you don't need a big model for them. And you know that it needs to happen. So you just set up... You set up this specific agent to do that. [SPEAKER_01] But where I am kind of still questioning is how this looks in practice. If you've got these thousand agents, isn't that so taxing on the human brain to figure out like, where's that like issues agent? I can barely keep track of my freaking chats that I have right now. And I don't have these thousand agents. Such a good question. [SPEAKER_00] It's a good question because of two things. One is like this distinction between sort of a coordinated with sub-agent structure. Like a tree structure of agents or graph engineering is kind of what people are calling it now, right? But basically a tree of agents where you have some sort of a coordinator sitting above a bunch of other ones. That's a great architecture for all kinds of things. [SPEAKER_00] So if you were to take this same idea and try to build like a Hermes open claw style personal assistant, that's what it would look like. You would have like one that you're speaking to. It has a lot of sub-agents. They're all going and doing their different tasks. It would look like that. But that is by no means the only mechanism by which agents are going to find penetration. So yes, it can do that. [SPEAKER_00] But also it can just be this like tiny little back of house thing that's running for a butcher shop. And it's like figuring out how many pounds of meat to order for the next week. That is like super realistic. Like a very realistic tiny little agent that would cost them absolutely nothing to run every week. And this is like an advantage that I actually have not living in the valley right now. [SPEAKER_00] Is, you know, when I go to the valley pretty frequently and when I'm there, it's like, oh my gosh, this is amazing. There's so much hype and excitement. And then I like come out to, I'm in Virginia. I come out to Virginia and it's like nothing. Nobody. Zero penetration. Yeah. Absolute crickets. I can walk around and be like, what are you guys doing with agents these days? Nothing. No. Yeah. [SPEAKER_01] What are you talking about? ChatGPT? Yeah, yeah, exactly. Yeah. [SPEAKER_00] But like this is sort of, in my opinion, the missing link. Like it is the thing that will turn this into a Main Street tool is being able to say like, actually, we've got this very narrow implementation that meets your needs precisely. Rather than a $200 Claude Code sub or something. [SPEAKER_01] You know where I have heard, and I actually was just thinking about how strong of an opinion I have on this, that it won't happen. So potentially we can talk about why you think it will happen right now is since 2022 or whenever agents started getting popular. The first thing that a lot of people went to try and build was an agent marketplace. [SPEAKER_01] And I am convinced that is never going to happen. It's like Mean Girls, like stop trying to make Fetch a thing because it is not going to be a thing. In that, again, like me as a person, I'm not going to go sift through a bunch of agents that random people built on the Internet and see if it might potentially work for my use case. But then I got to tweak a few things or I got to tell Claude to tweak a few things. [SPEAKER_01] Instead of just, why don't I just tell Claude to start it from scratch and exactly what I need? And I create that agent. And then if I can distill it down and make it a smaller agent like you're talking about, I see the value in that. But an agent marketplace, I'm 99% sure that's never going to be a thing. I think it's already a thing. All right. So good. You got the counter. [SPEAKER_00] I think it's already a thing. Everyone just has their own marketplace. And the only place that we've shared any sort of agreement on this right now is MCP and skills. But MCP and skills are effectively just like really bad agents because they're just trying to convert the agent that you're using into one that can do these other things, which has this like incredible upside, which I'm not going to try to take away from it, which is that now I get to still use the same user interface or something like that. [SPEAKER_00] Yeah. The downside is that it's all context injection. It's like a giant rag pipeline just getting shoved into the brain of this agent. And like not only do the agents get worse when you do this, they get dumber on like completely related tasks. [SPEAKER_00] So like if you were to take that same model in the same agent like Sol and give it the job of a skill exclusively, it will do it way better than if you have that skill get injected on top of its preexisting everything. Right. So the argument here is not that like people are going to need to go out and like assemble these things carefully themselves. [SPEAKER_00] They're going to use them very much in the same way that people use skills right now, which you probably have already done this. Somebody somewhere in your life has been like, dude, you got to check out a skill. I know skills, skills. Superpowers. [SPEAKER_01] Shout out to superpowers. Exactly. It's always superpowers or the grill me or last week it was show me. It's true. I have downloaded a whole lot of skills. You've already done the thing you said you're never going to do. I did. That is a marketplace. You're right. So that is a marketplace. [SPEAKER_00] But imagine if what you were installing was like actually effective agents. So there's no reason why the interface for domain specific agents couldn't be your existing agent. There's no reason why that's not the way it's exposed. It could be exposed that way. But it just needs its own guaranteed way to execute and run and so on and so forth. So that could be one output. But I'm not even really interested in what that final interface is. [SPEAKER_00] I'm interested in trying to say we need a way to share and distribute these things. And that might be the winning outcome. Maybe the winning outcome is every human on Earth has their own website with its own chatbot on it. That sounds very unlikely, but I don't know. Or maybe Grokbot ends up becoming like the thing and everyone has a Grokbot. Yeah. Because they're doing it too, right? Like they have their own marketplace. If you use Grokbot, they have their own marketplace. You log in there. [SPEAKER_00] You find their plugins. Like you want to use Google. It's got to be one of their plugins. I mean, most of them are MCP related. But it's still this pre-approved marketplace of things that plug into Grokbot. [SPEAKER_01] Actually, as soon as I created my Hermes agent, the first thing I did was like go out and scour the internet for what are the best Hermes use cases and skills that I should have with my agent. Yeah. And so if you look at it like that. Oh, man. It's true. [SPEAKER_00] The use case, I know, like already over time. But the use case thing is actually one of the most interesting problems too. Is like when you go and you talk to people about like, hey, what would you use a personal agent for? Yeah. If somebody is not using it already. Even if they are using it. They're like, calendar maybe? Like maybe my email? I had to do some digging. It was exactly that. [SPEAKER_00] This is why domain specific agents are the win. Because people in different domains know how they would use it in their domain. Right? Like when you're at work and if you're not working on agents, which is sort of this vicious, you know, what is it? Something eating its own tail. So self-licking ice cream cone. [SPEAKER_00] If you're not doing that and you're like a nurse or you're, you know, some sort of doctor, like you immediately are like, oh my gosh, I have so many use cases where I could have it, you know, be doing the transcription or the notes or it could be doing. Like there's so many different use cases that we in the tech world are just like sort of immune from. But the domain experts need to make the domain specific agents. So they need a way to just do that. [SPEAKER_01] Yeah. They need a way to do that. And then I think where I've seen it fall down in the past is that they don't realize what the possible is. And so like the transcription, for example, it's like, oh, it can do that? Oh, well, yeah. Like I would love to get transcribed. That's true. All of these different things that happen. Right? And then you start, you start to unlock these doors and you realize, wow, that's, that's a, that's possible. Okay. Well, yeah. And then I want that agent too. [SPEAKER_01] And so then there's this merging of the two worlds of the tech where we know everything it can do, but we don't necessarily have the use cases. And the folks that have the use cases who want to know, like, what can it do? [SPEAKER_00] Yeah. This, this, we need to figure out a way to empower that. [SPEAKER_01] Well, I'm so excited for your talk. You've got me convinced. I'm going to be there enjoying it and hearing about this whole world of domain specific agents. And I'll see you October 22nd and 23rd in San Jose for AgentCon and MCPCon. Looking forward to meeting you and everyone else.