Develop at Idea Velocity

Talk transcript

1. 0:01

   Workshop setup. So, um, [clears throat] there are some people who kind of have, like, never installed OpenClaw, and I wanna kinda get them set up. And then the other people, like, wanna try an experimental thing, which I haven't even fully gotten working, but I think for more advanced people, that'll be cool, um, to get, like, a sort of staging

2. 0:19

   environment and run two OpenClaws. So I think if I'm not, you know, too busy helping new people set up, then I'll try to help people, like, finish debugging the last part, or maybe someone else will get it.

3. 0:32

   Then I think, uh, ten minutes Q&A, ten minutes some more advanced topics, and then just more Q&A. And, uh, probably after every five minutes or so, we can do a bit of few minutes of discussion.

4. 0:44

   So I'll just set some timers to make sure I don't go off track.

5. 0:49

   All right. Let me start. All right, can everyone see this presentation?

6. 1:07

   Yes. All right, cool. Yep. So this kind of describes, like, my setup. Um, I'll just keep it really high level for this part where when everything works, you know, maybe, like, seventy percent of the time, you describe your task, and then what's nice is OpenClaw will have, like, context of memory about what you're talking about.

7. 1:31

   So for example, like, let's say I'm like, "All right, fix this thing."

8. 1:35

   It's a very brief Slack message, but OpenClaw can remember, like, what I've a-asked it to do before. So for example, I'm working on this thing I'm calling a skeptic agent, and it's a custom code review thing.

9. 1:47

   But if I'm like, "All right, fix the skeptic agent," or whatever, right, it kind of knows what that is, which is nice. You don't have to re-explain a lot.

10. 1:55

    Um, I use multiple agents with worktrees. That's very key for parallelization. Uh, CI co-

11. 2:06

    integration. But you can kind of see, you can talk to it and be pretty brief, and then, you know, usually get reasonable outcomes, but sometimes you'll have to debug it.

12. 2:16

    So then it's like, all right, there's some timeout thing. I'm like, "Give it a longer timeout," right?

13. 2:24

    And then I asked it here, like, like, uh, you know, what are the priorities and what we're working on, and I'm reading it here. And then I might have just said, like...

14. 2:35

    I just made code for it, right? So another interesting thing about this is you can kind of see from, like, um, [clears throat] the types of responses I give, they're not that, like, um, special.

15. 2:48

    As in I h- I actually think an agent could replace me. So that's kind of what I'm working on right now to, like, get things even more autonomous, you know.

16. 2:57

    And you, and you'll see this with LLMs, like you're working with them, and they'll be like, "Hey, I've got this thing ready." And I'm like, "Okay, well, run the test," right?

17. 3:06

    Uh, all right, so I'll show the next slide now. Oops.

18. 3:17

    Okay. We'll go into some concepts right now, like what is OpenClaw? So I think what's cool about OpenClaw is it's not just about a particular repo or the code, but more of the concept.

19. 3:28

    So, you know, I've got this cool super diagram, but first concept is frictionless communication. So I know we have other things like Claude Cowork or whatever, but I think they still have a similar concept where it's like, can you, like, easily talk to your AI versus, like, you've got to, um, remote desktop into your computer, or you

20. 3:50

    have to go sit down. So that kind of enables a certain really higher level of velocity. Um, then I think the central axis is very important. So, you know, there, there's a spectrum.

21. 4:02

    Like, I kind of go, like, a little more cowboy, and I give it ac-

22. 4:11

    OpenClaw has these agent orchestrator managers that manage your workers for you. Uh, or sometimes when I want more personal control, I use tmux terminals. So tmux is like a terminal program, but it's pretty good for parallelization and, um, AI development.

23. 4:27

    Then I use the open source framework that I forked, agent orchestrator, to do the workers. And then once it gets to here, this part is, like, not really controlled by me as much anymore.

24. 4:37

    Um, so I'm calling them managed agents, but basically, like, you have a worker that runs Claude Code, and Claude Code itself can run agents, so those can have sub-agents.

25. 4:49

    So once you get to this Claude Code part, right, this part is not exactly my stack, just stuff I use, but this part of the stack I'm changing a lot more.

26. 4:59

    Um, I'll, I'll pause here to see if anyone has any questions or thoughts.

27. 5:06

    Um, can you hear me? So I, I have a question. So- Go ahead, yeah. The, the, the real question is, you know, why, why use OpenClaw versus directly use Claude?

28. 5:17

    So yeah, that's, that's definitely a good question. Um, [clears throat]

29. 5:21

    the reason I use OpenClaw is specialization. So when OpenClaw makes a decision, I want that context to be more about, like, the spec or the goals or, like, the history of what I want in the task rather than the code.

30. 5:37

    And you can just imagine this, right? As soon as you open up Claude, it reads Claude MDs, it reads skills, it reads, um,

31. 5:45

    MCPs. A lot of those things are sort of independent of, like, the actual task. That's more about how to do the task. Um, so imagine, like, twenty-five percent of your context already taken up by implementation versus, like, when you think about OpenClaw, you're like, "Okay-" I wanna think about exactly what I wanna do and how it relates

32. 6:04

    to all the other Slacks Jeffrey has sent me in the last two weeks, and put it all together and give me, like, a reasonable spec.

33. 6:16

    Does every single thing a player does, but it does it without a browser, right? So you could use MCP, which usually is JSON or whatever, or HTTP. Doesn't really matter, actually.

34. 6:26

    And then the final thing is the browser test. So some things, like, are visual. I mean, maybe you could even have CSS tests or JS tests, right? And that kind of goes here.

35. 6:35

    But then the final thing is visual. So I would recommend you, like, try, um, similar approaches to this and be like, "Okay," like, which problems truly needed that human or not.

36. 6:45

    Um, and I think what's kind of cool is, like, every quarter or maybe even every month, like, it improves. So before, like, I had to really manually test a lot because, like, you know, this worked fine, right?

37. 6:58

    But these things didn't work that well with agents, like, last year, like, like a year ago, even six months ago. But now, like, um, agents are pretty good at, like, nailing down a lot of browser tests for me, versus, like, when I started, my agent would have a lot of problems, you know, finding a pop-up and entering

38. 7:14

    a password. Now, no problem. Um, that was a little long, but does that kind of address the theme of your question? Yeah, I think this is good. Good. Thank you.

39. 7:23

    Okay. Keep going. Just, just remind me for all these slash commands. I'll put, um, links here instead. All right, cool. Anyone have any other questions related to some of that stuff?

40. 7:37

    All right. If not, I will go here.

41. 7:43

    All right, so here's, uh, two websites that I've built. [clears throat]

42. 7:53

    Yeah, while that loads, I'll show this one.

43. 7:56

    So this is, like, a AI RPG. Um, what's cool about this is you can... I've got a default campaign, for example. Um, [clears throat] you pick some options. You got a avatar.

44. 8:09

    And, uh, what's cool about this is it builds a custom world for you that reacts to you, so you can, like, kind of say whatever you want, do whatever you want, you'll get a story back.

45. 8:19

    Um, the main difference between playing this versus, like, um, you know, you could just always go into Gemini Chat or, or ChatGPT or whatever is that, um, I have, like, a D&D system.

46. 8:30

    So if you play your own, like, games or novels, like, you kind of just win too much versus, like, with this you'll actually do, like, dice rolls and be like, you know, did the person actually, um...

47. 8:42

    Did you actually succeed in your action or not?

48. 8:45

    All right, so while this is going, I'll also, um, show this thing. Yeah, so this is funny. Um, this website is, like, a multi-AI analysis website. Um, so what I found was, like, whenever I was doing research or, or whatever, I would go to multiple models and I would be like, "What's the answer?"

49. 9:03

    Then I copy and paste them all. I put them into one model. Um, so pretty simple concept, but this does it for you. So usually I like these answers better than, like, asking one model, and I'm like, "Okay, how do I do this workshop?"

50. 9:22

    So I can be like, okay, get the status.

51. 9:31

    Add on to the latest PR now. And, um, what I like about this is it has that sort of vertical tab type of thing, 'cause when you go horizontal, it's really easy to lose track of your tabs.

52. 9:43

    Um, but we've got notifications too. So when this thing is finished or this is finished and I need to look, it'll give me a notification, and I can just focus on clearing the notifications.

53. 9:54

    So here, um, the way I'm using these terminals, usually it's more like a manager rather than a coder. Um, and it's kind of interesting, but it gives you a certain benefit where I feel, I feel like the worker's not biased anymore.

54. 10:08

    So when I ha- when I code with these directly, um, I usually feel like there's a bias where it wants to say things are really working or whatever, right?

55. 10:16

    Versus, like, you know... Um, and I'll show this. One sec.

56. 10:24

    If this had been working in PR 294 by itself, I think it would've been like, "This PR is amazing," like, "We gotta merge it," right? But then this one was like, no, like, there's another PR that should supersede it, and probably we should just close this PR, right?

57. 10:37

    So that's kind of the benefit you get, where the manager has a different context, um, than the workers.

58. 10:45

    Uh, let's see. All right, so this is compacting whatever. So it'll take some time to complete. Don't wanna wait for it, but when it completes, you see these notifications, and I think my efficiency has improved a lot with tmux.

59. 10:59

    Um, I think... Is Austin or someone from tmux here?

60. 11:05

    Yeah, I'm here. What's up?

61. 11:06

    Cool. Yeah, so Austin is, uh, [clears throat] one of the guys behind tmux. Um, you know, big fan of it and I'm not, I'm not paid to say this or anything, but- [laughs] ...

62. 11:17

    big fan of tmux. Uh, I've been using it a lot. I know you can spend a minute if you wanna talk about anything cool about tmux.

63. 11:24

    Yeah. So yeah, one of the creators of tmux. Uh, really happy to have Jeff as one of our power users, um, and also, like, kind of endorsing it for free.

64. 11:32

    Um- [laughs] ... but yeah, lots of, uh, yeah, lots of things that we're shipping. We shipped a Cloud Code Teams integration, so if anyone is using Cloud Code Teams and wants to actually see what the celebrations are doing, we'll automatically spawn terminals for that.

65. 11:46

    Uh, we also shipped, uh, tmux SSH. So if you do any SSH work, um, you can use our native tmux SSH to, you know, do your tail scale, et cetera, um, to other computers.

66. 11:57

    You can even use it to run your own OpenClaw, um, in your Mac Minis. Um, but yeah, just, uh, one of the creators-

67. 12:05

    Please feel free to email me if you have anything that you think is a bug or any feedback, feature requests. Um, I'm always available, and yeah, I just love seeing people using tmux and always wanna take as much feedback as I can to, like, get them as, get them-

68. 12:27

    Okay, so just download that.

69. 12:34

    Yeah. They actually have an app too, so the app might be nice.

70. 12:37

    Yeah. Okay. And then use that to help me get back in and set-

71. 12:43

    Yeah

72. 12:43

    ... set up.

73. 12:44

    Yeah.

74. 12:45

    Okay. Okay, cool. Thanks.

75. 12:47

    All right. Does using the sandbox... It should not. Where would you, um... Have you had, have you run into any troubles, Aaron, about sandbox token usage?

76. 12:57

    Uh, no. I'm just, I'm not technical at all.

77. 13:01

    Oh, yeah, yeah.

78. 13:01

    I haven't OpenClaw installed, so I'm just-

79. 13:03

    Okay

80. 13:04

    ... very newbie questions. [laughs]

81. 13:06

    No, no.

82. 13:06

    But I appreciate you-

83. 13:07

    No, no bad questions

84. 13:08

    ... pretty much, anyway.

85. 13:08

    It's all good. Um, yeah. Uh, no, the sandbox wouldn't do that. Um, I think if, if everything's working well for you, you know, keep using the sandbox. For me, I just, you know, don't use the sandbox and so, so far nothing bad has happened.

86. 13:21

    But I think if I had-

87. 13:22

    Yeah

88. 13:22

    ... an external bot, then I would use the sandbox too.

89. 13:27

    You changing the mo- testing a new model, like it'll go down, then I have to figure out how to get it back up again. So I think I want to set up the sandbox because-

90. 13:35

    Oh, sorry, sorry. Um, okay, wait. There's two kinds of things. Okay.

91. 13:39

    The sandbox that most people talk about means, like, they run it in Docker or they, like, have it running in-

92. 13:45

    Oh

93. 13:45

    ... an isolated part of their system.

94. 13:46

    Mm-hmm.

95. 13:47

    But the other one was the one where I made the staging instructions, where I was like, "Oh."

96. 13:51

    Yeah.

97. 13:51

    Okay. So-

98. 13:52

    That's what I'm looking for

99. 13:53

    ... that, that could double your token usage if you send the same work to both of them. If you have two-

100. 13:58

     Got it

101. 13:58

     ... right. Um, but I think the way I would use it is not like that. Like, I think I would do local development, and then I would run integration tests on the, um, sandbox or staging one, right?

102. 14:09

     So I have two of them, and then once, like, everything's good, then I would merge the code and deploy to the production one. Um-

103. 14:16

     I see

104. 14:16

     ... so it wouldn't double your usage, but it would definitely increase it, but then the benefit is you might have some more reliability. So-

105. 14:22

     Yeah. Got it

106. 14:23

     ... I, I made some instructions and I was kind of in the middle of setting it up, but then, you know, it's like competing with the other one, so I gotta debug it.

107. 14:30

     Yeah.

108. 14:30

     But I think, you know, it's, it's worth trying out though, so I add that for more advanced people to give it a, uh, give it a try.

109. 14:37

     Cool. Thanks. Well-

110. 14:38

     Or even if you're not as advanced, if you want it, you know, you can try. [laughs]

111. 14:41

     Yeah, I'm definitely gonna play around. But what, uh, what model do you use? Like, do you have a, something that, like a default orchestrator model and then you, like-

112. 14:51

     Yeah, so-

113. 14:51

     ... say for this, use that

114. 14:52

     ... I mostly use Codex 53. Um, I found, I found, uh, GPT-54 to just use more tokens. Um, and even 53, like, like I, I just get destroyed all the time, right?

115. 15:06

     So I might have to adjust that.

116. 15:08

     Yeah.

117. 15:08

     Um, so basically I use this until, like, this is getting low, and then I just switch to Minimax, which is not as good, but it kind of gets the job done.

118. 15:17

     Yeah.

119. 15:17

     And then this is more about money than, like, preference, but

120. 15:22

     some, some work I can still kind of just do, um, here, so I don't always have to-