Sign in or Join the community to continue

What Happens When Engineers Stop Reading Their Own Code?

Posted Nov 16, 2026 | Views 32
# Agentic AI
# AI Coding Agents
# Cloudflare
# Miro
Share

Speakers

user's Avatar
Matt Carey
Senior Systems Engineer @ Cloudflare

Matt Carey works on Agents and MCP at Cloudflare and is a maintainer of the official MCP TypeScript SDK. He focuses on applying Cloudflare's infrastructure primitives, including Dynamic Worker Loaders and Durable Objects, to agentic systems while helping leading teams build their own AI agents. Before entering the tech industry, Matt was a professional windsurfer, representing Malta at multiple World and European Championships.

+ View details
user's Avatar
Scott Crooks
Senior AI Platform Engineer @ Miro

Scott Crooks is a seasoned technology professional with extensive experience in site reliability engineering, DevOps, and cloud infrastructure. Currently serving as a Senior AI Platform Engineer and Senior Site Reliability Engineer at Miro, Scott leads initiatives focused on technical debt resolution and security within the Growth stream. Previous roles include Senior Site Reliability Engineer at Shell, where Scott contributed to the stability and development of internal tooling, and positions at Paige, Lucid, StackState, ParkBee, and Travix International, where Scott specialized in infrastructure monitoring, CI/CD deployments, and security practices. Scott's educational background includes a Master's in Computer Science from Georgia Institute of Technology and multiple certifications in languages and data science.

+ View details
user's Avatar
Demetrios Brinkmann
Chief Happiness Engineer @ MLOps Community

At the moment Demetrios is immersing himself in Machine Learning by interviewing experts from around the world in the weekly MLOps.community meetups. Demetrios is constantly learning and engaging in new activities to get uncomfortable and learn from his mistakes. He tries to bring creativity into every aspect of his life, whether that be analyzing the best paths forward, overcoming obstacles, or building lego houses with his daughter.

+ View details

SUMMARY

In this episode, we sit down with Matt Carey and Scott Crooks, engineers at Cloudflare and Miro, to look at how two very different companies are building their own AI software factories, and what happens to engineering when the code mostly writes and reviews itself.

+ View details

CONTENT & TRANSCRIPT

Matt Carey (00:00) The biggest use case internally is we have this, I think, the best AI code reviewer I've ever used. I have no idea when we're ever going to share it externally, or if we ever will, but it is amazing and it's built on Flow. Yeah.
Demetrios (00:10) Is it primarily for humans to read or for…
Scott Crooks (00:12) It's only for agents to read. When people approve or reject um our AI review kind of looks at that and says, okay, this is not only like what I think needs to be fixed, but what is important to people. Because that's that's the more interesting statistic that we've found with our internal tool is how many PRs get opened, how many get merged, and how many get closed.
Demetrios (00:32) PRs are cheap, man. PRs are very cheap.
Matt Carey (00:34) Well, yeah, it depends on your model, but yeah, potentially they're they're they're cheap. And maybe this is super sad. Like I think agents are bringing us into the terminal and away from people. You got to get out and meet people and do things like this, yeah?
Demetrios (00:45) I think my first hot take is almonds are the only nut that you should eat with chocolate. [music]
Demetrios (01:03) We're back. I'm with Matt and Scott. How you guys doing? >>
Matt Carey (01:07) Yeah, pretty awesome, hey? >>
Demetrios (01:09) Awesome. Dude, I want to talk about so much with you. There you're at Cloudflare, you're at Miro. There's so many different things that we can go into. I think we were just talking about AI Gateway, right? And it's funny the last conversation I had with the Booking.com team, they were talking about the MCP Gateway that they put together. What do you define as an AI Gateway?
Scott Crooks (01:29) Yeah. Um I can tell you how we define it. Um I'll give the maybe like the the quick understandable version, which is similar to I think a lot of companies did this. It's, hey, we need something really quick. Let's just throw it together. Yeah. So it was whatever use cases were amalgamated to create that. For Miro, what that means is it's it's two things really. It's an AI Gateway that actually does the model calling, right? So, like there's the there's the backend, let's of models. In our case, we have a good mix of self-hosted versus just regular LLM calls. And then the other part of that is the business logic. So, uh Miro has some very specific things um that we need to do in order to make sure that customers are happy with our product. A good example of this is you're in Germany, you say I only want to call European based models, right? That's a very simple use case. Uh we code that in and so these sort of things is what's kind of self-contained.
Demetrios (02:28) Is it also routing?
Scott Crooks (02:29) It's also routing, yeah. So, one of the things that we've seen is an evolution in how the models, particularly with the cloud providers has has gone. We started with AWS. You would have models that were really only in certain regions, right? And so as they were also figuring out their infrastructure, we said okay um let's route everything to this region, get everything working. As we've gone along, we've seen sort of dimensions come along. So, we've not only seen multi-regionality because we deploy in multiple regions, but also multi-cloud. Yeah. So, this is like we have Opus five. We want to deploy this not only in all the regions that we can within AWS, but guess what? You can also serve that through Azure, through GCP or Anthropic Direct in certain cases. And so, it becomes this sort of like three-dimensional problem of like multi-region, multi-model. In the end, what our model gateway does is you know, we have a pool of providers that allow us to essentially define okay, for this model, what kind of requests per minute can we get? What kind of tokens per minute can we get? And all of that just gets aggregated and then we make routing decisions based on this.
Demetrios (03:40) Dude, I totally forgot back in the day where you could only get OpenAI through Azure.
Scott Crooks (03:44) Exactly.
Demetrios (03:45) And you saying that reminded me of like oh yeah, when you remember when you would get rate limited? Like after two prompts, you're like what happened?
Scott Crooks (03:54) All the time.
Demetrios (03:54) And so now yeah, okay, you've got these as you call it, multi-dimensional and you have not only for the same service if you're dealing with the Anthropic models, but then I imagine you've got these other models that you're dealing with. Yes. And so maybe you've got some open source ones and are you routing depending on the complexity of the tasks? >>
Scott Crooks (04:14) Uh we are. Yeah, so Miro has a a program or a capability called Psychics. It's a it's a fancy way of saying AI agents. And it does exactly this. So, so, we have default models defined um and then there's sort of a layer that also does a a an analysis and says, okay, the customer requested this, uh but they also, let's say, want to maintain costs and they talk to us about this. So we also give them some logic around, yeah, like kind of an auto mode. Nice. Uh so yeah, this was also something that came about pretty quickly. And because we have the model capabilities and the pool, as I said, it allows us to do a little bit more complex things on the back end.
Demetrios (04:54) You guys built something like this, too?
Matt Carey (04:56) Yeah, we have a AI gateway for customers, yeah.
Demetrios (05:00) Yeah. And you came out with the um the OS what recently too, right? What can you tell me more about that? >>
Matt Carey (05:06) Yes, so, uh we have like a full sort of like agent stack. So, the AI gateway uh can route to external model providers and can route to like the Workers AI hosted models. And then we also have like the application layer on top. So, we have the agents SDK, which is for people building their own stuff. Uh we have Flu, which is like a big old framework for building agents. It's kind of taking um new dev ex around. It's like from the from the makers of Astro. It's really, really interesting actually. And then we also have this brand new thing. I was going to go through all of them. But this brand new thing, which is like this full application that's open source that you can deploy yourself and it's like the uh uh you can think of it's like the off the AI agent office suite for your company and we call that Coplet OS. So I have a version of it deployed for like um literally like me and my my girlfriend as well and we like we have it in in our house, which is kind of fun. Uh but then you can also deploy cases in the house? Uh it's like just like shopping stuff. Like like like literally food shopping is like the is the easiest one. But um people like come like there are a bunch of companies. I'm no idea which ones I'm allowed to name. So that have it deployed like internally as their like all-in-one office suite. You can make slides out of it. You can build these things these apps like blueprints for these apps. So you can have like your finance team building like special dashboards and then you can save them as blueprints and then you can other teams can spin them up. You can have like skills via by like job title and things like this and like job and it's a really really fun and it's built on this capability model where the agent only gets access to the app that it's looking at. And like all internal to the Cloudflare network.
Demetrios (06:43) And what's the Astro one that you mentioned?
Matt Carey (06:45) Uh Flu, the the Flu framework. Yeah. So um we released that well the the makers of Astro sort of went out on on a tangent actually and released that and it's it's really really cool. It's a dev experience. It's kind of like a React like functional dev experience to build agent control flow and it just natively deploys to anywhere that JavaScript runs. So it can you can deploy it to like a Node.js server. You can deploy it to like Vercel fluid compute or you can deploy it to Cloudflare workers. >>
Demetrios (07:14) Ooh okay. Have you played with Flu like the
Matt Carey (07:16) Yeah, yeah, the Flu I work on Flu like a bunch. So yeah we we we it's running a bunch of production workloads internally. We hack on it. We build stuff with it. We build applications on it and we give applications to our customers on it yeah.
Demetrios (07:30) What have you been building? >>
Matt Carey (07:32) Uh, like I think like the the biggest use case internally is we have this I think the best AI code reviewer I've ever used internally to Cloudflare.I have no idea when we're ever going to share it externally or if we ever will, but it is amazing and it's built on Flu yeah.
Demetrios (07:48) Why built on Flu with the code reviewer if it's just is it just like reading these files? It's reading your commits?
Matt Carey (07:57) Yeah, all of the above and there's there it's got its own custom tools and like it it's you're building your own harness. Like some people might want to run like Claude code in a container, or you might want to run uh like open code on a durable object or like Pi or like it you can run all of these things, but it's very much like a lower-level thing or you can Flu is a whole framework, so you write in in JavaScript, but you write like Flu semantics and then it'll deploy wherever you want to deploy JavaScript.
Demetrios (08:26) And you can specify all of these details.
Matt Carey (08:27) Yeah, like uh you can specify tools, prompts, you can um it's really the innovative with uh thing with Flu is like the control flow. So depend you it's very easy to do things like lazy loading of tools and like more interesting harness engineering stuff because of the way that uh Fred and the Astro team have done the control flow. I see. It's it's it is really good fun. It's really good fun. And it'll run anywhere that JavaScript runs, so it's not just like tied to Cloudflare. You can you can run it wherever. Even runs in the browser.
Demetrios (08:55) Nice. Dude, well as you're saying that, it just makes me think like, man, I haven't gone deep on personalizing my coding specifically like the PR reviewing agents cuz, I get so much lift with the ones that come out of the box. How much of a difference do you feel like there is between those two when you're going in and you're tweaking everyone versus the uh just like is a skill that you get off the shelf, maybe it's a ponytail skill or something.
Matt Carey (09:29) Yeah, I think it it's all about like how much collective context you have about your company um and about like what your company denotes a good PR, I would say. Um, at least that's the way we started. Uh Cloudflare cool in a few months ago well actually almost a year ago we started developing this uh internal engineering codex, which I think is public now, but it's like how much it's like what denotes um what what what tools we're allowed to use, what tools we should be using, how to make exemptions to this, how to like think about approaching an engineering problem at Cloudflare. And a lot of other companies have similar versions to this. Like I know um the very famous ones like the Airbnb style guide for for code, right? Like people used to write JavaScript in the Airbnb style guide. Now, I think you can build whole applications with the Cloudflare Codex. I think that's how we're trying to think about it.
Demetrios (10:18) Is it primarily for humans to read or for…
Matt Carey (10:20) It's only for agents to read. Oh, okay. Yeah, so it's only for agents to read. So it's built by um agents based on like extensive research about how the company operates. And we're trying to like write down how the company operates and like trying to be aligned across the whole company. Like Cloudflare is 4 and 1/2 thousand people, I think, and trying to be aligned about everyone's coding agents should know how the company works and how the company operates, where to go for different things. Um yeah, it's a massive task. Uh but when if you can do that and you can generate this like Codex uh Codex is such a loaded word now. Uh but if you can generate this like this like uh um context pool, then you can have really good success with internal agents because the internal agents can also do um can do like best practice.
Demetrios (11:04) Yeah, one thing that I find super difficult is just knowing how well my stuff's performing versus like what it should be at or what is the top end of this performance. And so like evalling it and going through and even just something as simple as documentation and the agent's ability to understand and read the documentation. And evalling that, you know, is something that you wouldn't necessarily think about when you're making it for humans. Yeah, because it's a human. All right, like I want to write the best I can. I want to make sure that these docs are well written. But you're not like having to go and then like say, can we eval these docs, right?
Matt Carey (11:48) It's this whole new field of like agent experience. Yeah. Um and I think we we had Liat uh uh presenting here in in MCP Agent Con. Um and their whole company is around like Aura is around like agent experience. There's a bunch of other startups that are trying to crack this like agent experience. At Cloudflare, we have a team called Agent Experience. And they do awesome stuff. They maintain all of the they maintain the dashboard agent, but they also maintain like uh every other uh interface um what they help with other interfaces. So, they help with the MCP server to interact with things, and we're constantly experimenting on that front. Um and there yeah, we have the coolest thing I think they did recently was uh a full benchmark for how well do the frontier uh coding agents, how well can they use Cloudflare natively? How well can they use the APIs? Like do they know our open API specs? Can they deploy a worker from scratch given like literally nothing, just internet access? I I think that's that's really fun. Have you guys experimented with anything like this?
Scott Crooks (12:43) Yeah, we have uh we have an internal bot that does exactly this. So, it it seems like there's there's a common pattern emerging. Um so, we call it uh so, Miro is the canvas, so we call it Easel Bot, right? It's pretty cool actually. Yeah, so um what we noticed was with the code review problem, we actually have like kind of three three checks, and they all are similar, but they all seem to they seem to hit different areas, and I think that's why we've kept all three of them. So, we have uh Easel Bot like that is more of like a getting the whole company context, um fixing errors where it finds them, but it's also our our application that gets access directly to our application logs. So, when you wake up in the morning, typically on our our bigger uh more active code repositories, we'll see yeah, two or three PRs. Hey, I saw this has been appearing like 10 times in the last hour. This is what I think is the potential fix. So, we have that level. Um and then for the individual reviews, we have just just normal Claude, right? It's like hey Claude, like just can you review this please? And then we have our own uh AI review bot. This one uh is also automated in our pipelines. Um it's kind of a combination. So, I think what it it it takes a lot of the um potential fixes that have come from Easel Bot. So, when people approve or reject, um our AI review kind of looks at that and says okay, this is not only like what I think needs to be fixed, but what is important to people because that's that is the more interesting statistic that we found with our internal tool is how many PRs get opened, how many get merged, and how many get closed. Um and so, we find like there's about a 50/50 split. So right now we're still trying to trying to find that sweet spot. cuz, Yeah.
Demetrios (14:20) A lot of PRs can be open these days. I'll tell you what.
Scott Crooks (14:24) Yeah. So, we and the good news is that like we have still like engineers who are looking into this and and you know we have on duty people saying yeah this is relevant this is not. So, it's kind of like a you know we're experimenting through reinforcement learning like this PR is not relevant close it and then that just feeds back into the system. Yeah. So it's nice cuz we have uh not only multiple streams for when some some when you're just opening something and then you get the review but then we also have on the back end like looking at the contents and see if it were if it was relevant or not. Um so we get it from both sides. In addition we also use Oplane. That one's a really good security uh if you guys have discussed it. Has it come up before? Okay.
Demetrios (15:02) No I don't know what this is. >>
Scott Crooks (15:03) Um Oplane, o-p-l-a-n-e um it's it's kind of like a uh a security check let's say. So um you open a PR it gives you kind of like a breakdown of of compliance and um it can really range from anything. So, it could be something as simple as like you have a we use GitHub right? So we have GitHub actions. It could say hey you haven't sharpened uh this action and so it'll give you an explanation of like why this is important. And then after the fact it'll also get more into detail about like your specific change. So, it's like a kind of like an all-encompassing security review so that like when you merge it you feel confident like okay like I've hit uh or the agent has hit like kind of the basic >>
Demetrios (15:45) Not exposing any secrets.
Scott Crooks (15:45) I'm not exposing it yeah exactly. So, it'll give you like uh recommendations on like how do you redact data. Like it really is kind of an all-encompassing tool. So, it's great.
Matt Carey (15:56) I think like the upshot of I guess this conversation I didn't realize how much you had internally. That's so awesome. But like everyone is building these like software automations. I think they're still with like the intention of them becoming like full factories. Like everyone's trying to close the loop at some point to become full factories. Uh and I think the cool one of the fun examples that people can can have a look at because it's very public is how some of the open-source repos are actually doing this like close the loop. Um, Astro, the um, the people I talked about earlier making this JavaScript web framework, they got to zero open issues today.
Demetrios (16:29) Wow.
Matt Carey (16:30) For the first time ever. Like from like literally thousands of open issues, they got to zero. Um, and they are they are going for inbox zero from now on, which is insane. Like because up until now I think like open-source repos had really had this like deluge of people, I want to make a I want to make a contribution. I'm going to throw my agent at this potential problem and see what see what it comes out with. Or I'm going to scan the repo and find these like security vulnerabilities. Um, which are potentially…
Demetrios (16:57) I know the guy who created Superpowers, that pack, Jesse, he told me that for his open source projects and Superpowers, he was like I get a lot of PRs for Superpowers and a lot of times it's very low quality because obviously yeah. Uh, but he built out ways to just like automatically sift through the low-quality ones and then the ones that should get the humans time get bubbled to the top by having like some very firm rules.
Matt Carey (17:30) Yeah, I think everyone everyone is doing this like in in the extreme cases for a lot of the MCP SDKs, I can't speak for all of them, but that we've actually turned off external uh, non-collaborator PRs and people just make issues and they can if they want to have a go at making a patch, they can link the patch in their issue and then we can go in and do it. I think there's this like whole there's this whole thing about how can you reduce that maintainer burden and how can how can you actually automate each of the points but have some type of human review and like whatever people are comfortable with.
Demetrios (17:59) Dude, because PRs are cheap, man. PRs are very cheap.
Matt Carey (18:01) Well, yeah, it depends on your model, but yeah, potentially they're they're they're cheap. Uh, but also a lot of the time I think open-source maintainers have a very like strong idea of where they want the project to go. And so, them knowing about issues is very useful, but then actually the implementation has to fit with the direction that the the is going. And that's often that previously involved like a lot of backwards and forwards uh between maintainers and the person wanting to fix the issue. But now it is just cheaper. The backwards and forwards is sad. And maybe this is super sad. Like I think agents are bringing us into the terminal and away from people. Um >> You don't got to get out there and Yeah, you got to get out and meet people and do things like this, yeah? We've spent like the last two days in MCP maintainer meetings and it's just been so fun just to like riff on ideas and things when normally it's uh it's just it's it's very much agent to agent in in the world right now.
Demetrios (18:52) Yeah. You're talking to your LLM too much and makes you delusional sometimes. You got to touch grass.
Scott Crooks (18:59) We'll say I hope that this also has another an opposite effect. Like uh a few years back at KubeCon it was the one that was here in Amsterdam and uh Kelsey Hightower who of Kubernetes fame. Yep. I went to a talk that he did and it was talking about open-source contributions for companies, right? So, it was specifically like okay, you're coming to this talk because you you're at a company, you want to open source something, like let me give you some advice on that. Um at the end of the talk what he said was like you know you have to think not only about uh the the monetary implications, right? Does this make sense for your company to uh put time into open source? But it's also a reputation thing. Mhm. And so he said you know I used to work he mentioned a company. I won't mention it here. He said I used to work and consult for this company, you know they were very famous very early on uh when the microservice kind of trend was taking off. You know they released a lot of products, uh a lot of libraries, things that took off and they didn't they didn't maintain them. Mhm. I hope uh in the future that that this will also kind of encourage companies to take something that they really are developing internally and say um you know this is something that should be public. The more recent one uh the talk from Spotify just a couple hours ago. This is exactly they're like hey, we have uh this MCP MCP gateway that we want to um internally have people use. The fact that they're developing this they already had success with backstage and so I think people are now like please yes like release it. So, having this agent uh agentic kind of world also, I hope, enables that to get more quality products out the door.
Demetrios (20:30) And there's certain companies that it feels like it's in their DNA a little bit. I know that before backstage even, Spotify put out uh was it Luigi in the data world? I don't know if you're familiar with that. It was like a Airflow competitor. And I think the guy that wrote it Do you all know Modal? Uh Eric Bernhardt.
Matt & Scott (20:49) Yes. Yeah, yeah, yeah.
Demetrios (20:51) He I think he created I I want to say the name is Luigi. Somebody can correct me in the comments. But it's um it was that. And then >>
Matt Carey (20:58) I've heard this story and I've asked him about this as well.
Demetrios (21:02) And then he put that out and then Airflow went out like a little bit before or a little after and then kind of took all the air out of the room. And what I'm trying to say though is you've got some companies that are very much like, yeah, cool, let's release it, let's put it out there, and let's make it a thing. And then other companies, I think they they're learning how to do open source cuz, maybe it's not as big of a priority.
Matt Carey (21:27) And I guess I would say like the LLMs are making um allowing people to generate vast amounts of code very, very quickly. Whether, whether, your company wants to support that code in the long term is interesting. And maybe the value of like fun ideas goes down um or like fun fun demos goes down. Like previously you'd see a fun demo and maybe they didn't release the code and you were like maybe a little bit bummed out by that because you're like, oh, I like want to see that. But now like >>
Demetrios (21:55) That's so true. I can just make it myself.
Matt Carey (21:56) Like from the front demo you can make it yourself. So maybe they don't need to release the code. Maybe it's still helpful. But if they do release the code then it's worth like marking it as like this this is like static in time. Like this is a yeah, this is a this is a moment and like we're not going to carry on from that. And I think a lot of companies who have like an open-source direction like Cloudflare we have like a bunch of people working on open source. I work on the MCP SDK like half time. Um we it's very hard to work out like what what you're going to support longer term and also how you deprecate things in an in a nice way for customers. Like, how can you be like, this was a time in a place, but actually the whole industry has moved on right now and this is going to be the last thing, guys.
Demetrios (22:39) Yeah, how do you set that expectation?
Matt Carey (22:40) We donate it to someone? Can we If people are still using it or can we have like like we don't want to support this anymore? I'm not saying I'm not going to name specific projects, but like that is definitely a thought process.
Demetrios (22:50) It's a life cycle of a lot of different projects.
Matt Carey (22:53) >> Or can we make something stable so that people who are using it can they can carry on using it, but like we're not going to continuously develop this. >>
Demetrios (23:00) Yeah. Well, speaking of which, that reminds me of the idea that I wanted to get after with you guys, your hot takes. You got any good ones for us? I can give you mine.
Matt Carey (23:11) Oh yeah, go for it.
Demetrios (23:12) Wait, I have I have a whole list of them on my phone around here that I wanted to share at some point. I think my first hot take is almonds are the only nut that you should eat with chocolate. [gasps] Walnuts no good. >>
Matt Carey (23:28) That's so hot because of the hazelnuts.
Demetrios (23:31) Yeah, hazelnuts no. It's too much chocolate on chocolate. I don't like it.
Scott Crooks (23: 33) I guess does like the whole Dubai chocolate craze like fall fall into that? Is Okay, so that's out.
Demetrios (23:39) Pistachios, I'm not I'm not a fan of the Dubai chocolate. Again, almonds are the nuts. That's my hot take. >>
Matt Carey (23: 46) Yeah, it's too hot for me. Hazelnuts work so well. Yeah. No, I am out.
Scott Crooks (23:52) I I do have a hot take and I have to I have to give credit to my fellow Miro engineers, so there's a lot of us here. So it was Let me see. It was Sanket, it was Svetlana,
Demetrios (24:02) Shout out.
Scott Crooks (24:03) yeah, and Murad. So we were Hot take it's more of like a we're coming to this conference and all of us are from, you know, different backgrounds, different countries, and I think the one interesting thing that we all sort of came to the conclusion of is is that because now software is so easy to write, the time you're a little bit free to think of other things and one of the things that we all agreed on the combining of something in the physical world with with software now becomes just that much easier and and will make life that much better. Mm. Um not only that but being somebody who is maybe from a different background than software. So, for example I was my background's chemical engineering. >>
Demetrios (24:45) Oh nice.
Matt Carey (24:46) Mine's mechanical.
Scott Crooks (24:47) Yeah, so so, the same it's you you come from this background it's like well what does that have to do with software and it's like well some would say nothing. But but others it's like yeah but you're also learning kind of like generic concepts that you can then apply to to other domains right? And and that's the power of it.
Matt Carey (25:04) Yeah I've been meaning to write this article about like the scholarly engineer which is like which is like I guess as like I'm still a software engineer even though I write less code than I did previously. I also actually I went through a phase of being like oh but I would just read all the code um and I that's like how I like imprint my mark on it um when the LLMs are writing it. Now I'm like not even that pro that idea like I read actually much less of the code but I still understand the ideas and then there's going to be a point where maybe like I understand less of the ideas and so that's the bit that I'm like struggling with where if I'm not reading if I'm not writing the code um uh and I'm reading less of the code at least um I'm doing less code review than I was before uh and I'm leaning much more on like my own understanding of how the system works then actually in those previous two times when I would have been like like hunched over a laptop like writing and reading uh I should now actually just be learning more about the concepts of my industry the things that I can build upon like knowing how to prompt is actually just like knowing more about the world that we live in and like knowing more about like given this situation I should be thinking about this as an idea. Like that the scholarly engineer is like something that I'm really like…
Demetrios (26:17) it's the higher level concepts that you need it's almost like the abstraction is going up and so you're going to be much more effective if you understand what you need to use the right tools you need to use or the right words you need to say in the right moments.
Matt Carey (26:35) So Sunil on my team calls it the his he calls it his gentleman gentlemanly scientist era which I find hysterical and it's like this vision of this like gentleman scientist with a big top hat and maybe a pipe just pontificating about the world and like reading like massive books and yeah philosophizing about philosophy yeah. They're they're yeah they're like their their their impact and then doing very very small experiments that actually have like exponentially large results. >>
Demetrios (27:05) Yeah exactly that's the key is like all right we'll gathering a bunch of inspiration from random places around, yeah the world and around like the the educational sphere and then implementing that into what you're working on cuz, I can't remember where I was reading it but it's pretty obvious that like being able to take ideas from outside of your little bubble and then implement them in your bubble is going to give you much richer results.
Scott Crooks (27:33) Yeah, perhaps it'll be in the future where you know instead of having like one career path and saying oh I'm going to be this for my for my career it'll be more like what what problem do I want to solve or problems and then it'll be looking at the space and saying what information do I need in order to get to solve that problem and then kind of combining things at the very end.
Matt Carey (27:55) You heard of the idea of like general managers general managers are a problem I'll send you afterwards but it's it's more of a thrumthropic viewpoint of like there is theory these large problems in the world like I want to be the general manager of this like singular thing like yeah I don't know I I wish that LLMs and I hope that LLMs move us more towards spending our time upon these like more philanthropic is maybe the wrong word here but like that sort of good for the world like ideas.
Demetrios (28:23) Yeah. You get to level up and that's the cool part is that you're not spending your time being there which some people love I will say that like so if you love it it's just like you know, working on old cars, whatever, or your motorcycle. It's not totally necessary, but if you love it, do it. Go for it.
Otherwise, yeah, you can abstract away and hopefully get these bigger ideas and and find be able to chase what you enjoy. So, I think with that, man, that's a great place to end it. Feels like a good note.
Matt Carey (28:54) Nice. I feel warm and fuzzy inside.
Demetrios (28:56) Yeah, it was good. Guys, awesome for doing this. Thank you so much.
+ View details

Watch More

Who Does What (And When) in MLOps?
Posted Oct 24, 2022 | Views 1.2K
# Maturity Level
# Team Agreement
# MLOps Journey
What is the role of Machine Learning Engineers in the time of GPT4 and BARD?
Posted Apr 27, 2023 | Views 1.5K
# GPT4
# BARD
# API
# Digits Financial, Inc.
# Rungalileo.io
# Snorkel.ai
# Wandb.ai
# Tecton.ai
# Petuum.com
# Mckinsey.com/quantumblack
# Wallaroo.ai
# Union.ai
# Redis.com
# Alphasignal.ai
# Bigbraindaily.com
# Turningpost.com
MCP Security: What Happens When Your Agents Talk to Everything? // Rosemary Nwosu Ihueze
Posted Dec 19, 2025 | Views 156
# Agents in Production
# Prosus Group
# MCP Security