Screaming in the Cloud - Building the Backbone of AI Agents: Telemetry, Open Source, and the Future of Developer Infrastructure with Brian Douglas

Episode Date: April 30, 2026

AI agents are moving fast,  but the infrastructure behind them is still catching up. In this episode of Screaming in the Cloud, Corey Quinn sits down with Paper Compute CEO Brian “B Dougie” Douglas to explore building telemetry for AI agents, open-source infrastructure, token economics, and what it takes to create developer tooling in the AI era. From local-first observability to agent runtimes and the future of AI workflows, this conversation dives into what’s next for AI-powered development.Show highlights: (00:00) Open Source Trust Signal(00:16) Show Intro and Sponsor(01:07) What Paper Compute Builds(01:55) Telemetry for Agents Explained(04:10) Local First Data and Sharing(06:18) Second Time Founder Story(09:06) Token Costs and Pricing Psychology(14:20) Stereos VM and Safer Runtimes(20:34) Open Source Strategy and Vibe Coding(24:54) Whats Next and Wrap UpAbout Brian: Brian is the founder of the Paper Compute Company, a distributed systems primitives for AI agents.Brian previously founded Open Sauced, a company dedicated to increasing knowledge and insights of open-source communities. In 2024, Open Sauced joined the Linux Foundation, further solidifying Brian’s commitment to advancing open-source initiatives. With a passion for open source, Brian has consistently supported and mentored new contributors through Open Sauced, empowering developers to excel in the open-source ecosystem.Previously, Brian also led Developer Advocacy at GitHub, where he fostered a community of early adopters through content creation showcasing the newest GitHub features. His experience spans across notable companies in the tech industry, including Netlify, where he worked as an advocate. Brian’s dedication to open source extends beyond his professional endeavors. He currently hosts two podcasts Open Source Ready and The Secret Sauce: A podcast focusing on developer insights and experiences.Through these platforms, Brian continues to share valuable knowledge and promote open-source culture within the developer community.Links: LinkedIn: https://linkedin.com/in/brianldouglasWebsite: https://b.dougie.devSponsored by: duckbillhq.com

For what we're doing and who we want to talk to, like, open source is actually a value ad for them to be able to see what's happening and like what controls and like what policies they can set before they even get to the conversation. Welcome to Screaming in the Cloud. I'm Corey Quinn. I am joined today by CEO of PaperCompute, Brian Douglas or B. Dougie as the kids today call him. Thank you for joining me. I appreciate it. Yeah, glad to be here. This episode is sponsored in part by my day job, Duck Bill. Do you have a horrifying AWS bill? That can mean a lot of things. Predicting what it's going to be. Determining what it should be.

Negotiating your next long-term contract with AWS. Or just figuring out why it increasingly resembles a phone number, but nobody seems to quite know why that is. To learn more, visit duckbillhq.com. Remember, you can't duck the duck bill bill, which my CEO reliably informs me is absolutely not our slogan. So I have to say that my discovery of what you do was a tale rife with disappointment. I was so excited for a brief instant that when I heard paper compute, oh wow, it's an E-ink company, and I finally will have something other than a Kindle that uses the technology.

But no, it's an AI thing instead. Yeah, I was sorry to rug pull you on that one. It was a quick one, though. Yeah, paper compute. Yeah, we're doing distributed systems for agents, infrastructure for agents. So we've been added for about two months at this point and it's been quite the ride. Obviously, AI is moving pretty quick. I am hesitant to say too much about the current state of AI because between the time we record this and the time we publish this, which is not that long, there will doubtless be a bunch of things that come out that made.

But when you say infrastructure for AI agents, what does that mean? Yeah, so we started with two different open source projects. One is telemetry. So traces, if you think about Opt Hotel. We started this back in January, and at the time, O'Tell did not work with LMs. It works, but it was kind of ham-fisted. No, that's just O'Tell. That's basically its entire tagline.

It works, but it's kind of ham-fisted. It's right on their website. Fair enough. Yeah, yeah. Not from my mouth, but they have been sitting around and, like, doing their sort of weekly meetings, and they're going to, like, have better structure for this. But what we want to do is, like, telemetry for agents in particular. And that is the first project, open source.

H-EPL. The other one in stereos, which is the place that you play tapes, and the idea is having an agent runtime. So it's a VM built on NixOS, and that's kind of a TLDR. I could go into way more detail of the why and how, but I realize we also only only have 30 minutes. Well, I do want to dive into this a little bit, because when you say telemetry for AI, that usually means a few things. There's the metadata around it. What was the duration of the call? What application was this tied into? What was the provider? And notably the one I like, what were the tokens, but then you can also get into it, what was the actual conversation? And that's where I start to feel a little bit hunted. Which side of that divide do you come down on? Yeah, so we're doing

a bit more of the telemetry where you have like the tokens and the time duration. We do have the prompt stored from the agent and from the human. So like the agent does have a bit of the, with the thinking, we'll have like, hey, Brian asked this thing and I'm looking at this thing. And I remember this folder here, which is always fun to look at. I think a lot of that gets squash and cloud code and codex now. But back in my day, last summer, agents would spit that out when I was thinking. It's also dangerous on some level because this has been the case for 20 some odd years, where if I want to make one of the smartest people I know look like one of the dumbest people on the planet,

all you have to do is just do a readback of things they have typed into search engines, like things that, even things that I know off the top of my head, but I want to validate, like, what is S3 cost? Yeah, I do know that off the top of my head, but every once in a while I like to make sure that it hasn't changed on me. And also I have brain farts, which you. tends to happen as we age and yeah let's just make that work the idea now of oh something's watching me and actually seeing the dumb question i'm asking the robot that's scary i'm going to have to make sure that i grease some palms yeah yeah so like the way it works today so we're we're still open

source first and only right now and it works sequelite it basically writes to your your home directory oh so it's local telemetry yeah so it is local local first and that's what we have today by the time this comes out we will have a cloud product will be multiplayer uh we'll we'll be multiplayer uh we'll where if you choose, you can send your tape sessions to the cloud for your co-workers to also comment on. You're funded by HeavyBit as am I, and so is Atwin, L.A. Huxdable. And that's always been an interesting problem, too. It's, oh, you can take your show history and share that to your colleagues as well.

It's like, oh, God, can I pay you extra to not do that? Like, even now, if I run Atuwenrapped, which is the whole summary thing on this, where it tells me that with the number of unique commands, yeah, My commands failed 23.1% of the time, which, as someone who spent 25 years in the Linux admin space, that's kind of a high number. Yeah, it's a high number, but I imagine it's more like golf where, no, I have no idea. But I feel like with like, because I'm a pretty heavy VEM user. So like I'm definitely hitting like leader key and like hammering like a bunch of stuff that doesn't exist because it's just all muscle memory. I'm a big fan of like seeing the data and like you can interpret that data in whatever good and bad it is.

So I'm not a big fan of like, oh, well, 90% of other companies are failing only 40%. Like your company is failing. And now you're never going to make it to unicorn status. Like I think that's a, yeah, it's a bit of a myth, but I can see what a competitive nature and leaderboards would come in there, which a big fan of Attoin as well. Yeah, which I highly recommend not looking at the Atun wrap summary. For example, in 2025, apparently I typed 17.5,000 commands. 1,700 of them were CD, which is my number 1.

number two is NPM run, and the third is L.S., which is just, hmm, all right, all right. Yeah, where am I? And what else is here with me is sort of the thing that I'm always wondering. Yeah, LS is that. That's definitely top three for me for sure. I don't think, actually, I have no idea. I don't run at you in actively right now. So I just wipe the machine. So I'm still catching up with all the stuff. It's pretty great. So one thing I find interesting is folks who do a painful thing and get hurt and decide, you know what, let's do that again. This is, of course, a terrible segue into the reality. You are a second-time founder.

Tell me about that. Why would you do this again? Yeah, so I'll mention my first-time founder project, which is open sauce. dipa, which now dot pizza is actually not working anymore. Dot com is the only way you can see it, unfortunately. But we built insights in the GitHub repos. So I'm just a big fan of looking at data. I got to see in statistics in college.

So for whatever reason, it's been a chip in my shoulder to build more stats in the developer products. But yeah, so built that, sold at the Linux Foundation. It worked out pretty well for us. I thought I was never going to do it again because I felt like I got like a sort of boulder lifted off my shoulder. I went and worked at another company and then immediately saw any AI space infrastructure was this like not even a thing we were thinking about in 25.

So now in 2026 we're like, oh, maybe computers should like be more agentic friendly and like we should probably lock these things down and like they'll give it access to your Gmail or like time out the runners. So all those questions that I had around like, building stuff in the AI space. It had to be answered with some software. And like in December when I had the ideas, none of it was built. Now it feels like everyone's building it right now.

It's almost like if you go back in time. And there's folks of us at a certain generational era where we struggled mightily with the advent of the internet and social media in some ways that kids today don't. Because they grew up knowing that they're at a fishbowl and everything they do is going to be discoverable. It feels like I have been using my computer. computer in such a way that I assumed I would be the only person using it and that AI would not come along and start trying to pick up the pieces behind me. And if you give me a wiped machine and

now this is my new computer and from day one, the expectation is that AI is going to be looking over my shoulder and using any of the email that I interact with and the browser and the rest, I can use it more effectively in ways that aren't potentially disastrous when a robot gets confused. Yeah. You're in like a weird world like about a year and a half ago, everyone had like these pendants that you'd like record conversations with or you have like the metaframed glasses that you just like recording TikTok videos nonstop all the time. And now we're in a space where like now your, our shell history is being recorded or now our prompts are being recorded. Now we're basically being judged on how many tokens we're leveraging or if we're not spending enough or we're

spending too much or we're doing side work on our main machine and all this stuff. Like it is very, very interesting in this current state of the world we are in today. And I know the world's going to change in like three weeks. So like today, like I think we don't know what we don't know yet. And I think what's interesting in this space is like I want to build something that we can at least understand like what we're

sort of passing through and like what tokens are leveraging. I think I've been actually super hyper fixated on is quad code has a max max subscription for $200. I easily will spend $4,000 in tokens every week. So like I get that in Q4, they're probably not IPO.

So at least I should start tracking to see how much I'm spending so I can sort of brace for impact. But what I found that also in the last couple weeks is prompt caching and quad code is saving 93% of those tokens. So this is basically all the stuff we're building. We'll have this. Actually, you can see this in the tapes deck. If you record your tape sessions, tapes is the product,

the open source projects. Tape sessions, tape deck is the command line interface. You can see a dashboard to see your tokens. And what's cool about that is you can see the prompt caching, and you could kind of brace for that, but then just last week, and they shipped this thing called Fast Mode, where you can get faster L-L inference, but she'll just pay extra money on top of your Max-Mex subscription. It's pretty wild.

People had some experimentation with it and said the results were not materially different, and it was expensive at the top of it. So I get it. If your production is down, we really need to figure this out. Okay, turn on, hit the turbo button on the old tower. But it's a strange thing. There's also a psychology part of this where we saw back in the day when cell phone companies would offer fixed amounts of data instead of unlimited plans. A number of folks, I'm one of them, would wind up going for the unlimited plan every time just because I don't want the mental overhead.

I still find myself thinking like that when things that are charged on a usage basis, even though the actual amount of money is irrelevant. We've raised millions of dollars. Terrific. I don't necessarily need to hyper-optimize around $4.68 worth of tokens every day. Maybe that's not the biggest bang for buck of what I should be focusing on right now, but I don't know how to turn that off. I guess for us, I can speak for myself.

For us, you don't come from money. Like, sometimes you've got to hold on to money longer. I was also at AT&T, like, unlimited plan for years with the iPhone until eventually it's scrotched, like, up until, actually I was on T-Mobile up until last summer. and I had like this grandfather like $80 a month planned for the entire family. If they were first trying to beg you to changing and then trick you into changing over the years? That was the thing is like when you go through the BART tunnel, you get no fast internet, you get nothing, basically. And it's because you were on the lower tier plan that they can't give you like high throughput.

It's a crowded network in the Bart Tull tunnel. And that's the point you really feel it is like at the moment you're sitting at GitHub issue and then GitHub like this freezes on you on your phone. So I'm like, I guess I'll pay the $225 a month to like, get up my modern plan so that way I can actually send a get-up issue in the bar tunnel for the five, ten minutes that I'm in there. Yeah, I wound up adding Google Fi as a secondary sim for a while and then switched over to using it full time just because it was half the price of Verizon and seems to work reasonably well. But it's still the, it's unlimited, but they'll slow you down after a hundred gigs. And I think on my busiest month, I wound up using 20 of it. So it's, it's fine. I feel that way

about the clawed max plans as well, where I have hit session limits, before when I've been working on something. But I'm not one of those folks that winds up waking up in the middle of the night to prompt the fleet of agents to do things. It's when I'm sitting at my desk and working on something, I'll make the robot go build something. Okay, fine. I'm not the heavy user.

And in fact, I could probably cut my plan further than I have. I'd like not having to think about it. And I'll be sad when that goes away. Yeah, and it likely will go away. I think they're kind of like preparing us for this moment. I imagine we still get this unlimited plan, but it's not going to be $200. bucks it might be 2000 a month and I think that's the point where all like the haves and the have-nots would probably start showing themselves up yeah I've been playing a lot with a lot of local

models as well to see how far I could take those which yeah there's a lot of stuff you could do to like an almost a prompt router where great go ahead and do this is basically complicated find replace in this entire code base that can be done with a slower local model whereas architect the whole system maybe I want one of the frontier models to do that yeah and I've seen a lot of tools that outside of like the agent harnesses that have approached that problem but haven't done it very well. I think OpenRouter has a bit of a feature around this as well if you just go

straight open router proxy. But yeah, something I'll be experimenting with a ton. Yeah, exciting times. And I think you're addressing the right part of the problem, which is first, I don't know what CloudCode is doing under the hood. I have no idea what the usage looks like. I know sometimes it's genius. Other times it feels like it's not that

and I wonder how that's playing out under the hood or what's going on. I just know that I need to be careful enough around this when I'm having it do things. If this is going to make a mark, maybe make sure that that test coverage is where I think it is. This episode is sponsored by my own company, Duck Bill. Having trouble with your AWS bill, perhaps it's time to renegotiate a contract with them. Maybe you're just wondering how to predict what's going on in the wide world of AWS. Well, that's where Duck Bill comes in to help.

Remember, you can't duck the Duck Bill Bill, which I am reliably informed by my business partner is absolutely not our motto. To learn more, visit duckbillhq.com. Yeah, and one thing I'll mention as well, so I mentioned tapes in like the telemetry part, but stereos is the VM. So the actual computer, like essentially it's NixOS, you can run it on your Mac OS, you could run it on Linux. Currently not Windows yet, so we just need more people to care about Windows and we'll focus on it. So open the issue, please. That's what I keep telling people. Open the issue and then we'll track it.

But the idea there is like the same way quad code is sub-agents. It's great because it takes that token usage onto its own channel so you don't get that sort of, now it's a million tokens context for a session. Previously it was like 250. But what I'm getting at is like it will take that session off to its own session and then come back with a hash. So like with tapes, we're using a Merkel Dag, just like Git. You could take a session, you can hash it. You could search it based on the hash. So you can do lookups.

She could generate skills. but then you can also have separate sessions within sub-agents, and that's what we're doing with Stereo. So Stereos is more likely something you use on your own metal. There's a lot of these like sandboxes and computers that people are leveraging in the cloud. Our bet is that you probably want to build your own cloud or you're an enterprise that wants to do this, and that's what Stereos comes in in the question.

Yeah, what I've been doing is there are risks to it, and I'm aware of that, but I have a dedicated AWS account called Superfund because it is expensive and toxic, and it has no access to any data in it, or so I thought. And then I just run an EC2 instance there that is run Claude in Dangerous Permissions Mode. It has full root access to the box. Go ahead.

All you're going to blow up is my bill. And then one day I realized it had access to read things off of my calendar, which was not expected. It turns out that at some point in the last few months, Claude's skills and connections were now tied to your Anthropic account, not to your actual, not to just the machine you installed them on, which is great. great most of the time and terrible in this one use case. So first thing I did is slap the control into the settings.json to make sure it doesn't do that anymore

just for data isolation reasons. But yeah, that is not something most people are going to do. They're not going to build a box that does this. Claude code gets very greedy with the RAMs. So this is a couple hundred bucks a month for the EC2 instance to sit there running four or five of these things. And there needs to be a better solution. I'd love to have something like that on the laptop, since I'm mostly around when I want this stuff doing things.

Yeah, I run it on, actually on this machine I'm talking to you on, just as of last weekend, I did OpenClaw in a box is a repo I put together. Just so like if you want to spin up this and you want to have like constraints and you want to have like network shut down on certain interactions. So the use case I use is on Sundays, I go through my email. It labels a bunch of stuff for me. And it only times out at two hours. So if it can't get it done in two hours, it's probably it's too long.

Or I need less email. So like I can figure that. I'll go call the government until. and stop sitting up email or whatever the uh i'm thinking of the side fell uh when kramer said no more mail not sure if that's possible yet yeah i have a in the next room i have a kubernetes singular running on a cluster of 10 raspberry pies and one of the things that runs on there is billy the platypus who's now my virtual EA where he'll wind up receiving the email writing a barely professional sarcastic response and now with an additional fun feature he'll go out to a data enrichment API figure

out what you look like and then integrate a cartoon of him dunking on you in some way into the insulting response, which is just amazing. It is terrific people trying to sell me things or be obnoxious in email in various ways. I feel a little sorry for some of the entry level business development types and SDRs who are reaching out trying to sell me something that doesn't make sense. But other times, this stuff is so scattershot and send to the entire world. I like to buy land in Napa. No, no, thank you for asking. I would not. So, yeah, have the insulting potapus smack back. I love that.

But there is risk to this if it starts tying into all the other stuff. I mean, the scary thing that I need to defend against and why there's a human in the loop is it can now schedule things for me, which is great. But it'll casually look at my calendar and then say, oh, he can't then he's meeting with insert company here. It's, ah, how about no? Maybe that's, maybe it's fine. Oh, he's having another meeting to yell at AWS. Yeah, that's a real rarity. but maybe I'm meeting with a confidential client.

Maybe that's not something that needs to be disclosed in an email. My challenge is like, I just started paying $20 a month for chatDB which gives it memory. I think you have to enable it, but I did enable it because I was building a computer with a GPU in it.

I was like, oh, let me just like prep the chat TBT to like know everything I know about my computer and then like recommend like, well, not RAM at this point, but like there was actually last year before RAM was too expensive. Yeah, good luck money bags. Yeah, but I was just like looking for different parts

and like seeing if what would work with what. But then, like, randomly, I'll ask a question about, like, something like actual work-related. And like, oh, yeah, why don't you run on your GPU machine? Like, what do you mean? Oh, the machine you built last year is like, well, completely out of context. Not as bad as your sort of confidential call, but, like, it feels like it's like, oh, remember that one, like thing you built for your daughter? It's like, dude, stop. Not the time of the place.

Read the room. Yeah, that's part of the problem that all these agent things have. Like, there are different personas that I take on when I talk to folks. When I am in a board meeting versus when I am pitching to a customer, versus, versus when I am writing a sarcastic newsletter, versus when I am being a parent, versus when I am shit posting on the thing formerly known as Twitter, I act very differently. And if you cross those streams, it doesn't go super well. Like, there's a time and a place for all of this. Like, I do a mean conference talk and I do some great stand-up jokes. Maybe don't do that when I'm

putting together a wedding ceremony or something like that. There's time and a place. And that's something that gets lost sometimes. Yeah, but it's great for a LinkedIn post. I think it could be the LinkedIn, whatever, I don't know what that vibe LinkedIn has on posting, but I don't Claude has a good, does a good job of self-reference posting. Oh, absolutely. And the problem is, is you can't even say that that's not what LinkedIn is designed for. You go to LinkedIn now and it interrupts you when you're writing stuff. Hey, you want to rewrite that with AI?

It's, what do you think this network is for exactly? And then I read some of the insipid stuff on there. And you want to hope it's AI, but you're kind of scared it's not. Well, I guess we'll figure it out. someone's going to have to ship, is this AI or not? True or false? So I am curious, what would possess you? There might be a less confrontational way to phrase that,

but we're going with possess you. To start a company where effectively everything you're putting out so far is open source. That feels like it has some definite advantages to it, but it's also the sort of thing that can be fraud. I come from GitHub, I come from open source. I learn how to code because of open source. So it's in my ethos, but specifically for what we're building with tapes and stereos,

I feel like the telemetry parts is table stakes. If you ask any sort of YC company or any sort of VC, like, hey, we're doing telemetry for agents. We're like, cool. So we're 100 other companies. And then now we thought we were ahead of the game when it came to like the VM and like building the actual runtime. But then like a bazillion other companies came out and say,

we have a runtime too. Like, Deno has a runtime. Deno is doing something completely different. For what we're doing and who we want to talk to, like open source is actually a value ad for them to be able to see what's happening and like what controls and what policies they could set before they even get to the conversation. I spent a lot of time my first startup

where we spend way more time trying to convince people and having long conversations. Today we're just like, hey, use tape stereos. If that kind of fits within the thing that works for you, then we have this cloud

or we have this self-hosted on-prem thing that works one of the same. Not one of the same, but obviously one's going to cost more and be more complicated. But we feel like open source is a lot of easy for people to try

before they buy without setting up a 14-day trial or whatever. What about the current, lightgeist impression that folks are giving off where this is the bad days of SaaS, where companies are going to start vibe coding SaaS solutions instead of paying third parties for it. Yeah, I think that's the same thing of like I can write a bunch of C++ code, but also I can't because I've never written C++ code. So yes, I can vibe it, but also I don't know what bad like unsafe C++ code is. So when it comes to like SaaS products, like you can probably build

the thing. I built like a look at my LinkedIn connections and give me like a list of companies that I can like go reach out to and hang out with a bunch of friends and show my new thing. Like, I don't want to pay LinkedIn premium or sales thing for 12K a month when I can just like vibe code a thing. But there will be a point where I bring on a salesperson who I don't want to like use my vibe coded thing and I want to share information properly in like a Salesforce manner or HubSpot manner. Like there's a place we use kind of grow up into like again, I don't want a 14 day trial. I know what I'm doing. I'm just like running through the system and plugging and playing. And then on the end of like open source like I feel like open

sources table stakes as well, like where you can close source it and like keep your, keep everything close to chess. But also I think what we need is like more people building infrastructure. So like if anybody clones our repo and like says, I'm going to kickstart from this and let's get started. Maybe we're protected with AGPL. Maybe we're not. But at the end of day it's like what we need is this stuff to be out in the system and out in the infrastructure. And hopefully we're the ones that build it. But like someone else builds it. Then obviously we'll, we're at least not going in the right direction. Yeah. Like I've built a bunch of internal SaaS tooling that scratches certain itches I have that I'm not willing to pay a professional

to get of and running for me. But when we're building Skyway over at Duck Bill, it's not hard software in that it is effectively a data platform that manipulates data and normalizes it. Yeah, we know how to do that. We're not pushing the bounds of computer science here, but the data must be correct. It's not the sort of thing that you can vibe code and expect good things to fall out of. Lord knows, we've done experiments. around that. Now, you can come out with something that sounds very good and looks good at first glance until you start digging into it. But if you're making sincere business decisions based on that data and it turns out that data's wrong, no one wants to be in that position. It's the same reason

that Anthropic vibe codes a lot of stuff, but they pay, I think it's ADP for payroll. They're not just paying for the software that arranges the paychecks. They're basically paying for expertise. You know what, your super-based table to be completely open and like read and, right? Well, obviously, the thing that happened in the last week is delve, like everything was accessible. And I imagine a lot of the stuff was just kind of shoot from the hip. And at a certain point, you kind of want to bring in the experts to come clean up and polish the stuff. Naively, I thought compliance was one of those spaces where you wanted to have expertise in shows what I know. That's why I've never been on the 30 under 30.

40? Perhaps. Not even anymore. It has to be 50 under 50 at some point where I think we just call that folks. So what's next? You mentioned you're doing a cloud offering probably by the time that this one. ends up shipping. I mean, that will presumably address my biggest problem with your website right now, which is it doesn't have a pricing page. Yeah, yeah. So we will have a pricing page,

hopefully in the next two weeks. We're fastly approaching that. We have the infrastructure that works. We're sort of pending a UI on top of it. So next is basically you have tapes, you have sessions, you have agents, you want to play those in a multiplayer fashion. So like you and your team could all look at your weird prompts and all the tokens you're using. And then you can sort of like dictate what what is next. So something actually real cool I've been working on is like taking your prompts and then training a model with that. So if you want to do like some fine tuning off, let down the road for your local models. How heavy a lift is it to do something like that? Because I've toyed with the idea, but every experiment I come up with is like step one, you're going to need about $10,000

worth of GPU time, which, okay. If you know anybody, Nvidia, so friends that will give you some rental space. But yeah, if you have data, data is one of the hardest parts to get for training. I particularly have not done it myself. I've been in the room when this is how. happening at my last role at continue. So I've got an idea of how this works, but then folks like unsloft, they can help you do to fine tuning part. So like there's a bunch of like prosumer

like SaaSification ways to go about it, but also Claude's my friend as well. So I might just like chat with with them and build that six week pipeline to make this work. I'm still trying to figure out why when I prompt for certain things versus my teammates prompt for certain things, I get such vastly different results

in terms of tones, sarcasm, the way it builds things. And I have no answer for that. It seems like a telemetry play might be the right answer here. Yeah, I think it's got your taste down to, uh, let's get the first thing out to Corey and then co-founder gets the better, the better taste. Exactly. Yeah, Mike is the one that winds up doing all the serious button down stuff. Like, we can make this talk to Microsoft Excel. And I'm sitting over here going, we can make it rank the U.S. presidents by absorbency. And it's, it's one of those things where at some point, between the, the two of us, we're going to reach a happy medium where it's both whimsical and useful,

but we're not there today. The lipist stuff I have right now is WWJD, which is what would John do? And I ask that question every time I go right in one of his projects, which is like, I don't write a lot of go code. Like professionally, I've done some go code, but really not to the level that John has. So what I want to do is take John's sessions to help inform my prompt sessions. So I've been generating skills from his sessions. And so far going well.

This is your team skill of Corey Quinn voice. I need to go in and sabotage soon. Some of it gets uncomfortably close, and that's my space in the universe. Thank you very much. Amazing. So I want to thank you for taking the time to speak with me. If people want to learn more, where's the best place for them to go? Best place to go is I have a site called B.Duggy.dev.

That's my catch-all. I guess they would call it link trees back in the day. But LinkedIn, I'm happy to take a DM there. No promises on response. And then X at BWO and then Blue Sky at Bita. Because I wasn't taking that platform seriously, and I just picked the random Bureau. Yeah, I am having some challenges myself with the answer of where do I direct people to for all of these things that I have going on. And every time it feels like I wind up narrowing it down by

collapsing two projects into one, three more spring up, I don't know that there's ever a way to get away from it. Yeah, yeah, a fine man, Minecraft. There we go. It's similar to someone has showed me a SSO page screenshot once, and it showed all the different services you could use to log into it. Like they had GitHub, they had LinkedIn, they had Google, and they had the Lego website, apparently which acts as an identity provider, which is just absurd to me. I want to have that as an enterprise class SSO login just to see the reaction. The Lego Envoy proxy would be amazing. Like, let's get that to work.

Thanks again for taking the time to speak with me. I appreciate it. Yeah, have a good one. Brian Douglas, CEO at PaperCompute. I'm cloud economist Cory Quinn, and this. is screaming in the cloud. If you've enjoyed this podcast, please leave a five-star review on your podcast platform of choice. Whereas if you hated this podcast, please leave a five-star review on your podcast platform

of choice, along with an angry, insulting comment. Be sure to include the tapes replay because there's no way you were able to be that clever, all on your own.