How I manage 15 AI agents 24/7 as a solo founder | Ryan Carson

1. 0:00 – 2:55

   Introduction to Ryan Carson

   1. RCRyan Carson0:00

      If you're out there listening and you are doing engineering, you're doing your work locally, you really need to open your eyes. I think the future is pretty much 100% cloud agents. I went all in, so much so I spent $5,000 on Devin, and then it went up to $20,000 one month. You know, I think one of my big messages for today is that all of us have to up-level our ability to manage agents. Like, that is our job. How do you effectively manage 10, 20, 100, 500 employees? This is the whole reason that organizations were built as pyramids. Like, humans can't scale and have 1,000 directs.

   2. CVClaire Vo0:37

      What is in your stack right now, and how have you structured stuff to make you successful and build things effectively?

   3. RCRyan Carson0:43

      So what I'm doing is figuring out how to manage, you know, throngs of agents. And in Devin, what, what you're seeing is, uh, is folders. And you'll notice P0 is the big stuff. The- these are the, the main things I need to move forward as the business, new features, P1, P2. So our priority is zero. We got bugs. Let them work. Usually give them a goal, and it's just such a crazy different world we live in now.

   4. CVClaire Vo1:08

      Welcome back to How I AI. I have a super special guest, Ryan Carson, one of our earliest How I AI episodes, who is here to show us what has changed in the last 12 months in the age of coding agents. We're going to wax poetic about our favorite little AI intern, Devin, talk about all the ways you're underutilizing your coding agents, and give maybe the most anti-AI episode of How I AI, where we talk about where AI can't solve your problems, how you need to get out in front and actually talk to people, and how pen and paper still have a place in his stack. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch, it's a massive lift. That's where WorkOS comes in. WorkOS gives you drop-in APIs for enterprise features, so your app can become enterprise-ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using WorkOS to move faster and meet enterprise demands. Join them and hundreds of other industry leaders at workos.com.

2. 2:55 – 7:35

   Ryan’s update: Untangle, the divorce PMF pivot, and B2B growth

   1. CVClaire Vo2:55

      Start building today. Ryan Carson, number one episode of How I AI-

   2. RCRyan Carson3:03

      [laughs]

   3. CVClaire Vo3:03

      ... from our early, early days, is back again. I am so happy to have you here, my friend.

   4. RCRyan Carson3:10

      Oh, this is lo- it's so fun to reconnect. Um, and the reason why the show is good is because of you. And, uh, just everybody listening, I'm not just kissing ass here. Uh, everybody that I meet, I say, "There's one show. If you're stressed about keeping up on AI, just listen to Claire's show."

   5. CVClaire Vo3:25

      Oh, thank you.

   6. RCRyan Carson3:26

      So.

   7. CVClaire Vo3:26

      Well, I'm stress keeping up with AI.

   8. RCRyan Carson3:28

      [laughs]

   9. CVClaire Vo3:28

      So I, um, will take all that stress on behalf of the audience and pass on what I know. What I also am so excited about this conversation is, you know, we did, we did our first episode a year ago, or even a little more than a year ago, and like, it's so different now.

   10. RCRyan Carson3:44

       Oh my God.

   11. CVClaire Vo3:44

       We were such babies.

   12. RCRyan Carson3:45

       I know. It's, it's l- it's kind of funny, like-

   13. CVClaire Vo3:48

       Yeah

   14. RCRyan Carson3:48

       ... what we chat about now.

   15. CVClaire Vo3:50

       Yeah.

   16. RCRyan Carson3:50

       And it'll be funny what we chat about now in a year, right?

   17. CVClaire Vo3:52

       Yes, totally. And for those who have not gone in the archives, uh, we did a really, really popular episode about how to manage your agents with like... It was like pre-skills even. It was like three-step mark... Like, you invented skills from first principles.

   18. RCRyan Carson4:09

       [laughs]

   19. CVClaire Vo4:09

       It was like three-step markdown file. We were in an IDE, which I-

   20. RCRyan Carson4:14

       Yes

   21. CVClaire Vo4:14

       ... hadn't opened an IDE in like months. Um...

   22. RCRyan Carson4:16

       Yep.

   23. CVClaire Vo4:17

       We were in an IDE, and, and we were really... You were very, uh, prescriptive and directive of your agents. You were very worried.

   24. RCRyan Carson4:24

       Very hand-holdy.

   25. CVClaire Vo4:25

       Very hand-holdy. And now, you know, I don't know about you, I'll speak for myself, what the agents are doing is none of my business. [laughs]

   26. RCRyan Carson4:34

       No. [laughs] Let them, let them work. You know.

   27. CVClaire Vo4:37

       Let them work.

   28. RCRyan Carson4:37

       Usually give them a goal, and yeah, it's just such a crazy different world we live in now.

   29. CVClaire Vo4:42

       Yeah.

   30. RCRyan Carson4:42

       It's so exciting.
3. 7:35 – 16:29

   Ryan’s current Devin stack: folders, P0 threads, and the paper list

   1. RCRyan Carson7:35

      Very excited.

   2. CVClaire Vo7:35

      But you haven't yet.

   3. RCRyan Carson7:37

      No. [laughs]

   4. CVClaire Vo7:37

      And so I mean, the, the, the good, the good in p- part of the story is you were able to get to rapid iteration, lots of prototypes, product market fit with you and our mutual intern, Mr. Devin.

   5. RCRyan Carson7:53

      Mr. Devin. [laughs]

   6. CVClaire Vo7:54

      Um, Mr. Devin. And so, you know, when, when you were starting out, again, you were, like, really coding, doing requirements, documents, all of that with AI-

   7. RCRyan Carson8:05

      Mm-hmm

   8. CVClaire Vo8:05

      ... but you were very human in the loop. And as I've watched you over the past year, I've seen you slowly turn into AI bro who runs agents overnight.

   9. RCRyan Carson8:16

      [laughs]

   10. CVClaire Vo8:17

       Um, so tell us about, like, what is in your stack right now. What is, like, very different from what we talked about a year ago? And how have you structured stuff to, to make, make you successful and build things effectively?

   11. RCRyan Carson8:29

       Totally. Um, I like to say I'm in max Q right now, for those of you that are, are, um, you know, SpaceX fans. It's like-

   12. CVClaire Vo8:37

       Mm-hmm

   13. RCRyan Carson8:37

       ... the maximum pressure that I need to hire somebody. I'm doing all the work. And so-

   14. CVClaire Vo8:41

       Yeah

   15. RCRyan Carson8:42

       ... yeah, what am I actually doing day to day? So I'll walk you through it. Um, I started off, you know, in, uh, a more specific agent like a Cursor, um, like an Amp. Um, and, and then I, I, I saw cloud happening. I'm like, okay, I'm really limited 'cause I have to be at my machine. And there's a lot of things I need to... You know, quick PRs, like here's a bug, need to sort it out, or what about this piece of data? Need to, you know... And I was like, why, why isn't cloud... Like, I feel like I should be working on the cloud. And I thought, what about Devin? Like Devin, you know, they've been doing cloud for like years now. It was kinda crap in the beginning, right? But maybe it's good now. And I tried it, and I was like, wow, [chuckles] this, this thing's r-really good. This is not-

   16. CVClaire Vo9:29

       Real good

   17. RCRyan Carson9:29

       ... It's really good. And, you know, and I, and I thought, okay, I'm gonna try it. And I was just blown away by how mature the cloud agent was.

   18. CVClaire Vo9:37

       Uh-huh.

   19. RCRyan Carson9:37

       And, and if you're out there listening, and you know, you are doing engineering, you're doing your work locally, you really need to open your eyes. Like, I, I think the future is pretty much 100%, you know, cloud agents. There, there's gonna be some local dev, but... So I started looking at that and was really impressed. So now, uh, I went all in. Uh, so much so, I, I spent... At one point, I was like spending $5,000 on Devin, and then it went up to $20,000 one month, and I'm like, whoa, wait a minute. I have a big Twitter account. I'm gonna go talk to the Cognition guys and tell them to give me free credits, and they did. So, [laughs] so anyway, I, you know, get 20 grand of credits per month in Devin. Great. But the point is, I live in Devin. I live in the cloud, right? So all of my engineering almost, I... And it's Devin's right here on my screen. I've got probably, you know, 10, probably 10, 15 threads, and I bucket them in folders. 'Cause I remember one of your shows, you know, uh, it was either you or your guest was saying, it's sort of like four or five concurrent tasks you can actually keep track of, and I agree with that. So what I use is folders. Okay.

   20. CVClaire Vo10:47

       Is there any way to show it?

   21. RCRyan Carson10:50

       Um, I can show it. I'll show you one thing, which is this piece of paper. [laughs]

   22. CVClaire Vo10:54

       Yeah. Perfect.

   23. RCRyan Carson10:55

       And... [laughs]

   24. CVClaire Vo10:57

       This is the AI podcast-

   25. RCRyan Carson10:58

       And the reason why it's a piece of paper-

   26. CVClaire Vo10:58

       ... we're doing where we say we're gonna hire humans, and we're just gonna show you pieces of paper we scribble on. [laughs]

   27. RCRyan Carson11:04

       [laughs] Okay. The reas- But, but there's a, there's a... I'm doing this for a reason, okay? So the reason why I have folders, uh, for threads, and the reason why I have a piece of paper is because it, the skill is managing throngs of agents. Like, that is what I do now. And to, to keep it straight in your head, y-you basically have to bucket these things. And so I have, uh, one bucket, um, uh, that I'll, I'll try to show this to you. Let, let's see how, let's see how dangerous this is gonna become, everybody. [laughs] Okay. So everybody, this is Devin. This is my real setup that I'm literally working on today. And, uh, you know, I think one of my big messages for today is that all of us have to uplevel our ability to manage agents. Like, that is our job, right? And so how do you do that? How do you effectively manage 10, 20, 100, 500 employees, basically? Um, this is the whole reason that organizations were built as pyramids.

   28. CVClaire Vo12:02

       Uh-huh.

   29. RCRyan Carson12:02

       Right? Like, humans can't scale and have 1,000 directs unless you're like Jensen Huang, then you can. But- So what I'm doing is figuring out how to manage, you know, throngs of agents. And in Devin, what, what you're seeing is, um, uh, is folders. And you'll notice, um, we've got bugs, right?

   30. CVClaire Vo12:19

       Mm-hmm.
4. 16:29 – 18:09

   Watchdog playbook: account monitoring across every firm

   1. RCRyan Carson16:29

      practical tip I wanna talk about is I have, um, it's a playbook, but y- it could be a skill if you're not using Devin.

   2. CVClaire Vo16:35

      Yep.

   3. RCRyan Carson16:35

      It's called Watchdog.

   4. CVClaire Vo16:36

      Mm-hmm.

   5. RCRyan Carson16:37

      And, and you know, we're starting to pick up a lot of family law firms now, and they have a lot of cases, right? And, and I'm literally doing customer success and engineering and sales, right? And so it's like, whoa, how do you keep track of actually what's going on in these cases? W- you know, where, w-where are clients hitting UX bugs? Like where, what... Oh my God, how do you keep track of it? So Watchdog, what it does, and I-- this is multiple iterations, everybody. So w- what you want is like when that moment where you feel like, "I need to know what's going in the business right now. I feel stressed. I don't know what's happening," uh, this is when I run Watchdog. And, and what it does is it basically it, it has a skill for that, that's repeated for each firm. So think of these as customers, right? Uh, it, uh, and it goes into each account and says, "What's going on with this account? Like, what was the activity since we last did Watchdog? Where are the errors? Where are the Sentry, uh, uh, um, errors? You know, where does all this happen?" But then, but then you don't want just data. You want it to be transposed and filtered and sorted for you. So then it comes up with the top three things that are going wrong, and then either like, well, wait, have they been fixed? Because we're shipping a lot of PRs. Like I'm shipping probably 40 PRs a day now. So did it get fixed, or is it currently being fixed, or is there an open PR that never got merged, right? And it just gives me all that, and then I talk to that thread about Okay, let's dig in a little bit, and that's how I manage

5. 18:09 – 20:32

   Managing agent decision fatigue: Ryan’s method vs. Claire’s

   1. RCRyan Carson18:09

      th- the chaos.

   2. CVClaire Vo18:10

      Yeah, I, you know, you asked me how do I manage the, the decision fatigue, and I feel like I start a business for every child I have, so, like, three kids, three businesses.

   3. RCRyan Carson18:19

      [laughs]

   4. CVClaire Vo18:20

      I have a lot of decision fatigue.

   5. RCRyan Carson18:22

      Hmm.

   6. CVClaire Vo18:22

      There's, there's a couple things that, that I do. I approach it very differently, which is I think about bucketing my time-

   7. RCRyan Carson18:28

      Hmm

   8. CVClaire Vo18:28

      ... more than I think about bucketing the tasks, which is like-

   9. RCRyan Carson18:32

      Huh

   10. CVClaire Vo18:32

       ... there's time in the day that I do, like, very, very specific tasks where I'm co-piloting with AI. There's other time where I'm just like, I dedicate to spinning off everything or checking in. So I have to bu- as a solo founder-

   11. RCRyan Carson18:45

       Hmm

   12. CVClaire Vo18:45

       ... I have to bucket my own time-

   13. RCRyan Carson18:47

       Interesting

   14. CVClaire Vo18:47

       ... on things. The other thing that I use is I use decision fatigue as a prioriti- prioritization heuristic-

   15. RCRyan Carson18:55

       Hmm

   16. CVClaire Vo18:55

       ... which is functionally, if there is a feature that I'm working on that I let die on the vine-

   17. RCRyan Carson19:01

       Hmm

   18. CVClaire Vo19:02

       ... that is my [laughs] This is-

   19. RCRyan Carson19:04

       That's your symbol

   20. CVClaire Vo19:05

       ... that's my symbol for-

   21. RCRyan Carson19:07

       Y-

   22. CVClaire Vo19:07

       ... maybe this one is not the one I really care or believe in.

   23. RCRyan Carson19:10

       Yeah.

   24. CVClaire Vo19:10

       And so, um, I, I sometimes think that people, you know, don't, don't tell anybody, I know I'm a token maxer and you should let your agents run 24 hours a day and ship as much code as humanly possible and software everywhere, and I really don't ship more than I think the market-

   25. RCRyan Carson19:29

       Yeah

   26. CVClaire Vo19:30

       ... wants. Like, I really try to res- like, constrain my output capacity.

   27. RCRyan Carson19:35

       Yeah, your output.

   28. CVClaire Vo19:35

       Not on quality, not on bugs, but, like, because I don't-

   29. RCRyan Carson19:38

       Yeah

   30. CVClaire Vo19:38

       ... I don't think I get multiples of quality off of multiples of output.
6. 20:32 – 22:47

   Producing more output does not make a better product

   1. CVClaire Vo20:32

      No.

   2. RCRyan Carson20:32

      [laughs] They're kind of a joke.

   3. CVClaire Vo20:33

      No, and, and I, and I tell people it's also because all of this intelligence has not magically created markets where there were none before.

   4. RCRyan Carson20:41

      Right. [laughs]

   5. CVClaire Vo20:41

      Other than AI markets, right? It's like-

   6. RCRyan Carson20:43

      Yeah

   7. CVClaire Vo20:43

      ... it's not like all of a sudden there are these, like, buyers that have shown up for s- solutions that somebody-

   8. RCRyan Carson20:50

      Stuff

   9. CVClaire Vo20:50

      ... yeah, for stuff. And so I do think there's this, like, mismatch between the quantity of output of code and, like, commercializable product.

   10. RCRyan Carson21:02

       Amen. So I wanna double-

   11. CVClaire Vo21:03

       Yeah

   12. RCRyan Carson21:03

       ... click on that. I think what, what, what is happening is people are not getting out of their chair enough and actually talking to real people. So, so, you know, w- the way I figured out PMF for Untangle was, y- you know, I went outbound with an email. I did a s- uh, a Google Meet with a potential customer and I talked to them. Boom, that was step one. But then step two is like, as soon as we landed them as a customer, I was like, "Can I come to your office? And I just wanna sit and I wanna talk and I wanna..." And this is all, like, obvious product stuff, but I think because we can ship so much and build so much digital product, we're, we're not getting out of our chairs enough.

   13. CVClaire Vo21:43

       I agree.

   14. RCRyan Carson21:43

       Um, so people-

   15. CVClaire Vo21:44

       I totally agree

   16. RCRyan Carson21:45

       ... go talk to humans for real.

   17. CVClaire Vo21:47

       Go talk to humans, yep.

   18. RCRyan Carson21:48

       And, and build something neat.

   19. CVClaire Vo21:50

       This episode is brought to you by Jira by Atlassian. The Teamwork Graph in Jira delivers 44% more accurate agent results with 48% less token usage. That's a huge difference when working with AI coding agents like Claude, Cursor, Codex, or Copilot. The hardest part of shipping with AI isn't the code. It's the context. What's the right ticket? What did the spec say? What got decided in Slack? The Teamwork Graph pulls all of that from across your entire stack, from Jira and Confluence to GitHub, and feeds it directly to your agents before they write a single line. You assign the work, the agent gets everything it needs, and a PR surfaces when it's ready. No digging, no context switching, no broken flow. Same team, smarter agents. Try 'em free at jira.dev. That's J-I-R-A.D-E-V.

7. 22:47 – 25:14

   Using cloud agents for ops beyond just code

   1. CVClaire Vo22:48

      The other thing I wanna touch on, because I think you breezed past it, but it has been a game changer for me in terms of using background agents, and in particular Devin, which is I think people have still bucketed these cloud coding agents as coding agents, which is like-

   2. RCRyan Carson23:02

      Hmm

   3. CVClaire Vo23:02

      ... their only job is to write code for a product or software product. And in fact, Devin runs deal desk for me.

   4. RCRyan Carson23:12

      Hmm.

   5. CVClaire Vo23:13

      So Devin's doing-

   6. RCRyan Carson23:14

      There you go

   7. CVClaire Vo23:14

      ... coding, custom coding for me.

   8. RCRyan Carson23:17

      Yeah.

   9. CVClaire Vo23:17

      Like setting up-

   10. RCRyan Carson23:19

       Operations

   11. CVClaire Vo23:21

       ... operations.

   12. RCRyan Carson23:22

       Yes.

   13. CVClaire Vo23:22

       Um, documentation, customer triage. Like, j- I, I always think, you know, what would you do with somebody who both knew your code base and could write code to solve anything in your business? That's how I use these, these background agents, and I do think that, um, people really don't ask enough of their back- background agents, and especially ones that are very good at coding. I think this is why it's so interesting Cursor just yesterday came out, or Cursor or Grok, whoever. Whoe- uh, whoever they are at these, came out with GrokBot, and I was like, you know what? The Cursor chat experience f- as a, as a background agent was a great one. We... It was, like, one of our first, first episodes, and so I'm not surprised to see these, like, coding platforms start to generalize into business agents in general. And I also feel like more than engineers need to get hands-on with, with background agents and cloud, cloud agents, because there's so much that they can do for your business pretty autonomously.

   14. RCRyan Carson24:26

       A- 100%. Um, but let's talk about, though, why probably both of us are still using local agents, uh, for some things.

   15. CVClaire Vo24:34

       Oh, yeah. Oh, yeah.

   16. RCRyan Carson24:34

       So it's inter- so right now as well, I have Codex running.

   17. CVClaire Vo24:37

       Yep. Same.

   18. RCRyan Carson24:38

       Um, and I have, and I have it using Goal.

   19. CVClaire Vo24:41

       Mm-hmm.

   20. RCRyan Carson24:41

       And I find that in particular, like the low latency plus the browser on my machine pairing, like-

   21. CVClaire Vo24:50

       Yep

   22. RCRyan Carson24:50

       ... plus like basically infinite tokens, you know-

   23. CVClaire Vo24:52

       Yes

   24. RCRyan Carson24:52

       ... from, from OpenAI.

   25. CVClaire Vo24:54

       Yeah. Thanks.

   26. RCRyan Carson24:54

       Um, yeah, cool. I'll take the subsidy. Um, that, you know, plus Goal really, really is good for when you have this kind of, "I've got a feature, it's a lot of front-end UI."

   27. CVClaire Vo25:06

       Yep.

   28. RCRyan Carson25:06

       "I just need you to grind for a lot, and I need to be here and kind of hold your hand."

   29. CVClaire Vo25:10

       Yep.

   30. RCRyan Carson25:10

       I find Codex unmatched for that.
8. 25:14 – 27:15

   When to use Codex vs. Devin vs. Claude Code

   1. CVClaire Vo25:14

      'Cause what we said we would do is compare and contrast our solo founder AI setups. So I would say I am personally spending my time in Codex-

   2. RCRyan Carson25:22

      Hmm

   3. CVClaire Vo25:23

      ... when I'm pair programming or, or managing a product. It's, it falls into a couple categories. It's gonna be like large feature initiatives that span front end and back end that both, like, again, need like a lot of code written and you have to grind on it, and needs that, like, intervention every now and then to narrow it to the experience that you want. Um, a lot of like r- long running refactors and tech debt stuff. Like, again, I think the latency is unmatched. Its Goal is really, really effective. Subagents are really, really effective. Um, and then I use Codex a lot for verif- I think it's very good at verification. And so a combination of Goal plus a CLI tool inside your code base that can verify core flows, or I use Goal and browser use to do front-end verification a lot. So I say write user stories, use Chrom- pull up the preview branch in Chrome, go through it as a user, list which user stories pass, identify bugs, fix them until you're good. Those are kinda what I'm using Codex for. When I'm using background agents, it's a lot of, like, auto-fixes on bugs. Um, one o- like when I'm on calls with, with customers and they say, "Oh, do you have this MCP?" I'm like, "I do now." Um, so one-off things and then sort of, um, operations, as you said. Like I use a lot of agents for, for operations and then, you know, I do have a couple like purpose-built agents in the stack. So I use BugBot a lot for PR review, and then I just built this thing delightfully called Merge Mommy that d- [chuckles] that does risk assessment on my PRs-

   4. RCRyan Carson27:10

      Smart

   5. CVClaire Vo27:10

      ... and auto approves low risk ones, um, 'cause-

   6. RCRyan Carson27:12

      Yeah

   7. CVClaire Vo27:12

      ... I am also shipping a lot of PRs.

9. 27:15 – 28:15

   Merge Mommy recap

   1. CVClaire Vo27:15

      And so that's, that-

   2. RCRyan Carson27:15

      And is that-

   3. CVClaire Vo27:16

      ... generally my purpose stuff

   4. RCRyan Carson27:16

      ... tell me about Mer- tell, tell me about Merge Mommy. Like that's-

   5. CVClaire Vo27:19

      Oh, yeah

   6. RCRyan Carson27:19

      ... 'cause th- and then I'll tell you about my land PR skill. I wanna compare and contrast.

   7. CVClaire Vo27:23

      Yeah. So I did an episode on this a week or two ago. It's an Eve agent, so it's deployed on Vercel.

   8. RCRyan Carson27:28

      Uh-huh.

   9. CVClaire Vo27:28

      And whenever a PR is opened and then passes all its CI checks, including BugBot, Merge Mommy gets triggered, and then what she looks at is she scores the PR on like five aspects of risk. Like-

   10. RCRyan Carson27:43

       Cool

   11. CVClaire Vo27:43

       ... how big a blast radius, security, whatever it is. And then if it, um, gets scored as a low, Merge Mommy stamps it with an approval and we can merge without a human approval.

   12. RCRyan Carson27:56

       Cool.

   13. CVClaire Vo27:56

       But if it's medium or high, then it pings us in Slack and says... It pings, um, either my colleague or I or somebody else in Slack and says, "This one's ready for you to review," 'cause for our SOC 2 compliance-

   14. RCRyan Carson28:08

       Wow

   15. CVClaire Vo28:08

       ... and all our controls, we require kind of like alternative review. Um-

   16. RCRyan Carson28:12

       Smart

   17. CVClaire Vo28:12

       ... it just allows us to like get through our PR

10. 28:15 – 30:20

    LAN PR skill: review loops, video walkthrough, and auto-merge

    1. CVClaire Vo28:15

       queue-

    2. RCRyan Carson28:15

       A lot

    3. CVClaire Vo28:16

       ... very efficiently.

    4. RCRyan Carson28:16

       Okay.

    5. CVClaire Vo28:16

       Yeah.

    6. RCRyan Carson28:17

       First of all, I'm annoyed I missed that episode. That sounds amazing. I'm gonna go watch it.

    7. CVClaire Vo28:20

       It's a good one.

    8. RCRyan Carson28:20

       Um, but number two, interesting. So I have something called LAN PR, where basically it's, it's a playbook in Devin, but you can think of it as a skill, and it's bas- usually it's when the agent comes back and says, "Okay, the PR is done," you know? And, and then, uh, I trigger it, and then what it does is it basically makes sure that, number one, it runs a fresh Devin review on the PR, which... And Devin Review is like an actual product inside of Devin, which is another reason why I think people should just pick... Oh, I'll t- I'll sort of rant about that later. But the code factory, like it should have a good, a good built-in review that is a real review product, right? So it triggers a review, and then it basically allows up to two loops on that, right? You know, okay, all right, find all the, all the bugs, check that all the comments are, are, are resolved, and then, and then there'll be some more that come up, do it again. Does it twice. And then, then the thing is, is it records a, uh, a video walkthrough. Um, and, and this I find Devin is just really good at. Like the... So what it does is it records in the browser, and it actually na- kind of narrates over it. It's got captions about what it's doing, and it's got this cool little, little test, you know, list of tests it's doing and whether they're red or green. And you get all this out of the box. Like I tried to build my own code factory and get all this stuff, and I was like, "I don't have time to do this." And so the LAN PR, basically it has to show me that video, and then I, then I say, "Video approved. Land it," and then it will merge. Um, so that really works for me. It's kind of that, I think this is where CI/CD and DevOps, like now you have to be even better at it, like, and really care about it. And, and we use merge queues in GitHub as well. I'm loving merge queues. Um, so couple of the nitty-gritty, this is what I'm actually doing stuff.

    9. CVClaire Vo30:13

       Have you... Okay. You all know, this is how you know, not, not sponsored by Cognition, but you all are welcome. Um, we love

11. 30:20 – 35:58

    Slack vs. Devin threads for async team communication

    1. CVClaire Vo30:20

       you.

    2. RCRyan Carson30:20

       [chuckles] Yeah, come on.

    3. CVClaire Vo30:22

       I can't get Devin video verification to work. I can occasionally get it to screenshot.

    4. RCRyan Carson30:30

       Really?

    5. CVClaire Vo30:30

       And like on front end stuff, it taps my, um, my credits for the session and then just falls over. I don't know if it's probably a problem. It's probably a me problem. All AI things are probably a me problem.

    6. RCRyan Carson30:43

       [laughs] No.

    7. CVClaire Vo30:44

       But I have not been able... But I, actually, I do wanna show this for folks that, um, wanna know exactly what it looks like, 'cause I found an example of it. So-

    8. RCRyan Carson30:52

       Cool

    9. CVClaire Vo30:52

       ... I'm claiming that it doesn't work, but then I'm gonna make it work.

    10. RCRyan Carson30:55

        [laughs]

    11. CVClaire Vo30:57

        Devin will actually go ahead and test it and record-

    12. RCRyan Carson31:03

        Oh, cool

    13. CVClaire Vo31:03

        ... a little video of it using... And you can see these little-

    14. RCRyan Carson31:07

        See the captions?

    15. CVClaire Vo31:08

        ... captions down here. Um-

    16. RCRyan Carson31:10

        Isn't that cool?

    17. CVClaire Vo31:10

        ... it's, it's exposing its, its reasoning. It's super cool. It's very useful. I can just only get it to work 50% of the time.

    18. RCRyan Carson31:17

        I ca- So a couple interesting comments I have of that. Number one, interesting that you're in Slack. Um-

    19. CVClaire Vo31:21

        Oh, I, I'm never in Devin UI. Never.

    20. RCRyan Carson31:24

        Okay. So interestingly, I'm never in Slack.

    21. CVClaire Vo31:27

        [laughs]

    22. RCRyan Carson31:28

        Um, I am trying to cut Slack completely out of Untangle, and, and, and the way the company is going to exist. Um, and I was laughing 'cause you have so many sidebar, you know, um, notifications and exclamation points and, and we were saying, you know, you're seeing the Devin preview in Slack, and, and I have a, a very kind of perfect experience with the video playback testing of Devin, and that's 'cause they use the web app. And so here's what I'm thinking, and again, this is probably gonna change, but as we hire people, I'm actually going to require, like, multi-user, uh, interaction to happen through Devin. So we talk in threads about what is going on, and that's thing one, 'cause, 'cause then you're not trying to always figure out, well, where's the context for this thing? You know, is it in your agent? Is it in Slack? Is it in Google Docs? Like, where is it? So I'm gonna try to do that. Now, obviously, that doesn't work for DMs and channels and all that stuff. But I also think, and Jack Dorsey, I think, was saying this. You know, they launched Buzz. It's kinda interesting. I think he banned DMs or somebody banned DMs in their company. Um, and I think, you know, as we scale, I'm gonna do the same thing. Like, I don't want any one-on-one chats. Like, if we're having private conversations, I'll have to call you. Um, so that's why I, I just think Slack is not built for the AI age.

    23. CVClaire Vo32:52

        Well, let me, let me tell you why.

    24. RCRyan Carson32:54

        [laughs]

    25. CVClaire Vo32:55

        I love Slack.

    26. RCRyan Carson32:56

        Okay.

    27. CVClaire Vo32:57

        'Cause I like to person-

    28. RCRyan Carson32:58

        Convince me.

    29. CVClaire Vo32:59

        I like to persona... First, I like to personify my agents.

    30. RCRyan Carson33:01

        Okay.
12. 35:58 – 39:00

    Claude Design plus Codex for building a technical design system

    1. RCRyan Carson35:58

       Um, but I just can't get around how good Claude Design is. Now, I don't mean in coming up with new design, I think it's bad, but I think for carrying forward, you know, a design system, it, it, it does something magical that Codex is hilariously bad at. Devin is terrible at, at design. And so I always have to go back to Claude Design. So am I missing something? Or do you do something magical design that's working for you?

    2. CVClaire Vo36:25

       Um, so this is a, this is a great question. I was telling you before this, I'm launching a new business. We've got a new brand, new design, and so I went through this process very recently, so I can tell you what I did.

    3. RCRyan Carson36:36

       Cool.

    4. CVClaire Vo36:36

       I think Claude Designs Create a design system is, like, unmatched right now.

    5. RCRyan Carson36:43

       Okay.

    6. CVClaire Vo36:44

       It's-

    7. RCRyan Carson36:44

       I agree

    8. CVClaire Vo36:44

       ... it, it does, it does a great job of decomposing either an example site or a Figma or something into relative non-slop design tokens you can reuse-

    9. RCRyan Carson36:57

       Yeah

    10. CVClaire Vo36:57

        ... across, across, um, across a property. Now, that being said, my most recent process is I went to Claude Design, I created the, the kinda like s- design.md and the, the design file in, in Claude Design. I downloaded that, gave it to Codex [chuckles]

    11. RCRyan Carson37:16

        Mm.

    12. CVClaire Vo37:16

        And said, "Take this, plus what's in the Figma, and actually build me a technical design system."

    13. RCRyan Carson37:23

        Oh.

    14. CVClaire Vo37:24

        And it built all the shared components. It made this nice, like i- interlinking in our monorepo.

    15. RCRyan Carson37:30

        Oh, wow.

    16. CVClaire Vo37:31

        Um, and then I, I also tested with Codex using the Figma plugin to then go pull all those design tokens back into Figma-

    17. RCRyan Carson37:42

        Oh

    18. CVClaire Vo37:42

        ... into components-

    19. RCRyan Carson37:43

        Interesting

    20. CVClaire Vo37:44

        ... that I could use. Um, and so I'm-

    21. RCRyan Carson37:46

        So once you had the design.md-

    22. CVClaire Vo37:48

        I had... Yeah

    23. RCRyan Carson37:48

        ... and ported it to Codex-

    24. CVClaire Vo37:49

        Once I had the design.md

    25. RCRyan Carson37:49

        ... then you were unlocked

    26. CVClaire Vo37:50

        ... and then I ported it to Codex. Yeah, that's exactly, exactly what I did. I mean, my problem with Claude, infinite tokens, very intelligent. My blood boils reading Claude output.

    27. RCRyan Carson38:04

        Oh, my God.

    28. CVClaire Vo38:04

        It, like, actually raises my blood pressure.

    29. RCRyan Carson38:06

        Yeah.

    30. CVClaire Vo38:06

        It makes me so angy.
13. 39:00 – 42:09

    EA tools: Polly the OpenClaw vs. Claude Code on a Mac Mini

    1. RCRyan Carson39:00

       It's so good. So last question I had before we go is-

    2. CVClaire Vo39:02

       Yeah

    3. RCRyan Carson39:03

       ... like, uh, we can both answer.

    4. CVClaire Vo39:04

       Yeah.

    5. RCRyan Carson39:04

       You go first. Like, what's your current actual, um, EA? Like, who's your actual sidekick that does all of your agent work as an executive assistant?

    6. CVClaire Vo39:14

       Polly the Open, OpenClaw.

    7. RCRyan Carson39:16

       Interesting.

    8. CVClaire Vo39:17

       Still-

    9. RCRyan Carson39:17

       Okay, you're on OpenClaw

    10. CVClaire Vo39:18

        ... still, still live in OpenClaw.

    11. RCRyan Carson39:19

        Okay. So-

    12. CVClaire Vo39:20

        Just kind of committed there. [laughs]

    13. RCRyan Carson39:22

        Yeah. [laughs] I love OpenClaw. I love Pete. I love the team. I love it. I just moved off. Um, I was like, screw it, I'm just gonna run Claude Code, um, on-

    14. CVClaire Vo39:31

        Me too

    15. RCRyan Carson39:31

        ... my Mac Mini. Um, and I actually-

    16. CVClaire Vo39:33

        Yeah

    17. RCRyan Carson39:33

        ... wanna switch to Codex 'cause-

    18. CVClaire Vo39:35

        Yeah

    19. RCRyan Carson39:35

        ... I just love, love, love the UI of Codex. It... There's so... It's the... It's wonderful, the whole thing.

    20. CVClaire Vo39:41

        Yep.

    21. RCRyan Carson39:41

        So.

    22. CVClaire Vo39:42

        Yep. Yeah. No, I use... I still, Polly the OpenClaw is still-

    23. RCRyan Carson39:46

        [laughs]

    24. CVClaire Vo39:46

        ... still running.

    25. RCRyan Carson39:48

        That's a name.

    26. CVClaire Vo39:48

        But I do now have my emails constantly open in the browser in Codex, and Codex functionally runs my email. It, it, it, it ran through 2,000 unread emails in my Gmail the other day and just changed my life.

    27. RCRyan Carson40:04

        This has-

    28. CVClaire Vo40:05

        Mm-hmm

    29. RCRyan Carson40:05

        ... this has been a game changer. Um, so, like you, I've hired a lot of people in my life.

    30. CVClaire Vo40:09

        Yep.
14. 42:09 – 44:11

    Quick recap and final thoughts

    1. RCRyan Carson42:09

       this shake out.

    2. CVClaire Vo42:09

       Okay. Well, um, just to recap for everyone, the, the two most AI-pilled people on your timeline-

    3. RCRyan Carson42:16

       [laughs]

    4. CVClaire Vo42:16

       ... spent most of our time talking about how too much AI code doesn't really get you great product.

    5. RCRyan Carson42:22

       Amen.

    6. CVClaire Vo42:22

       You should just go outside with your human body and-

    7. RCRyan Carson42:25

       Yes

    8. CVClaire Vo42:25

       ... talk to customers.

    9. RCRyan Carson42:27

       Agreed.

    10. CVClaire Vo42:27

        Keep your priority on a piece of paper [laughs] on your list.

    11. RCRyan Carson42:32

        [laughs] It works.

    12. CVClaire Vo42:33

        Um, it works. But, you know, on the, on the technical stuff, s- set up your background agents, prioritize their work in a way that you can manage. Everybody's becoming agent managers. Your coding agent can do more for you than just code.

    13. RCRyan Carson42:48

        Amen.

    14. CVClaire Vo42:48

        And the new interview is just let 'em cook and-

    15. RCRyan Carson42:53

        Amen

    16. CVClaire Vo42:53

        ... and do a screen share. Um, and also to conclude, the solo founder AI agent managers are both hiring. So-

    17. RCRyan Carson43:01

        Yes. [laughs]

    18. CVClaire Vo43:01

        ... Ryan, where can we... We... I know we can find you online, but where can we find you, and how can we be helpful? Who are you hiring for?

    19. RCRyan Carson43:07

        Thank you. So, uh, I'm super active on X, so just Ryan Carson. Um, hit me up anytime. And then, uh, uh, if you wanna help people have better divorces, because people are gonna get divorced, okay? Um, uh, go to Untangle.us, check us out, and then just shoot me a DM with a video of you working. Um, and I think we're gonna hire someone pretty fast, so, so move fast, and, uh, and, and say hello.

    20. CVClaire Vo43:32

        And I'll say if you impress Ryan with your video, you're probably going to be an upcoming guest of How I AI, where you will show us how you use your background agents. Awesome. Well, Ryan, thank you so much for joining.

    21. RCRyan Carson43:43

        This has been a blast. Thank you.

    22. CVClaire Vo43:44

        [upbeat music] Thanks so much for watching. If you enjoyed the show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiai pod.com. See you next time.

Episode duration: 44:13