Multiplayer agentic engineering: enabling your whole team and your best agents to work together

Talk transcript

1. 0:00

   [upbeat music] All right. Hey, everyone, I'm Arjun Singh.

2. 0:15

   Today, I'm gonna talk to you about multiplayer agentic engineering or how to enable your whole team and your best agents to work together. If you go to the talks or go around the expo, you're gonna see that a lot of people are just talking about putting the agents at the center of everything.

3. 0:27

   Makes sense. They're really powerful and really cool. But you don't see a lot of people talking about the people. Like, this is all for us to make us, our lives better or more, more productive or whatever.

4. 0:37

   And so we're gonna really focus on how the people fit into these agentic workflows.

5. 0:41

   So just a little bit about us first. So our team has worked together building software for over a decade. Uh, my co-founder, Sergey and I, we met in the PhD program at Berkeley.

6. 0:51

   I worked on robotics. He worked on computer vision. And during that, we co-founded a company called Gradescope. Some of you may have used it. It's used by millions of students worldwide at thousands of universities, helped instructors grade their students' work.

7. 1:04

   And, um, pretty much the entire team working on Superconductor used to work together on Gradescope. And so we've had a team that's worked together productively from first user to acquisition, working on something new together again.

8. 1:15

   And I think it's kind of an interesting experiment because o- you know, over the past year, we've very aggressively integrated agents in our workflows, and we've kind of surfaced all the different bottlenecks and friction points that come up and how to do that productively and keep collaborating the way we used to, but with the new power of

9. 1:29

   agents. So today I'm gonna talk to you about how, you know, we, we-- the lessons we learned from kinda solving those friction points and solving those bottlenecks.

10. 1:38

    And in the talk description, I mentioned, uh, five lessons, and I'm gonna be an engineer and start from zero and add a sixth one in there. Um, the first one I'm gonna start with is just to be model and harness agnostic.

11. 1:49

    So there's a few reasons for that. The best model and harness can change weekly. It could change 'cause a new one comes out. It could change 'cause the best one got taken away.

12. 1:58

    Um, things happen, and you don't want that to disrupt your entire team's flow. The other thing is that open-weight models are actually pretty good now. We've been really happy with GLM 5.2.

13. 2:09

    They're much cheaper. Um, and you wanna be able to kind of explore with them and integrate them without, again, having to change your entire workflow.

14. 2:16

    And the last thing I'll mention on this is that the incentives of the people selling you tokens aren't really aligned with yours. You're here for a reason. You're, you're-- so you're working on things for a reason.

15. 2:25

    You're trying to make your customers' lives better, make your product better, delight your customers, and they wanna sell you more tokens. And you might be happy to pay for as many tokens as it takes, but you don't wanna pay for more than that.

16. 2:36

    And so, again, kind of being able to switch between things lets you stay in control of all of that.

17. 2:43

    And so, um, you know, as I go through the talk, I'll mention a couple of places where our product makes it easy for us, but whether you use us or not, I'm just gonna leave things with you that I think are really important, um, for you to be able to work collaboratively, effectively.

18. 2:58

    So the next one is to turn every human interface into an agent and human interface. So, you know, typically, when people are working with coding agents, they're on their laptop, kind of stuck on that laptop.

19. 3:09

    Nobody else can talk to that agent. So the first place people go to kind of expose more interfaces for them is Slack. Claude has a Slack bot. Codex has a Slack bot.

20. 3:19

    We have a Slack bot. It's really cool. You can say, "At Superconductor, do XYZ." It does it. Somebody else can talk to it. But it's not enough 'cause now we've taken it from trapped on somebody's laptop to kinda trapped in Slack.

21. 3:30

    And a lot of work happens in Slack, so that's better than, than, than nothing, but certainly not all work happens in Slack.

22. 3:36

    So what we really wanted was to be able to work with the same session from every relevant interface. Could be Slack, could be our app, could be GitHub, could be elsewhere.

23. 3:45

    And so one possible flow is you start and collaborate on a session in Slack,

24. 3:51

    and then maybe you continue in a kinda more engineer-focused environment in the desktop app or the mobile app, and then you can finish it up in GitHub. And it re-- the important thing here is it's the exact same agent session, so it's like the agent didn't forget what you did in one place in Slack when you go

25. 4:05

    and talk to it from GitHub. It's the same session. It's got the same context.

26. 4:10

    And the second lesson builds on top of that, which is to make the agent work visible and collaborative across the team. And so obviously, Slack makes it more collaborative, um, but here we've got that kinda app view and, you know, Sergey made this ticket.

27. 4:25

    I've been talking to the same ticket. A growth person hopped in as well. And so you can kinda see at the top here all the different people that interacted with it.

28. 4:31

    So I can see who's getting notified about this session, who's seen it. Um, that's especially important when you have work triggered by not technical people, right? So it's like, you know, our customer support person created a ticket.

29. 4:42

    It's working really well. I wanna understand, like, has this been vetted by an engineer or not, and kinda see who's involved really easily.

30. 4:49

    And then if I'm reviewing something, I can just pop in and say like, "Hey, why did you do it this way?" And again, because it's the same agent session, I don't need to wait for Sergey to kinda get my notification on GitHub and respond to me.

31. 4:59

    The answer to the question's almost certainly in this thread.

32. 5:04

    I also don't wanna read the entire thread, so I can just ask, ask the agent. Or

33. 5:09

    how we most often kind of make the work visible is with artifacts. So it doesn't matter where the work started or where it's finishing. The agent can show you the work it's doing as a screenshot or video or other, and you can see it from everywhere.

34. 5:23

    So again, you don't have to worry about, like, oh, where is that thing? I gotta go to GitHub to see the image, or I gotta go to Slack to see the image.

35. 5:28

    It's just everywhere. Work is visible everywhere. You can collaborate from anywhere.

36. 5:35

    So the third lesson, um, I'm gonna talk about here is to turn every external signal into code that your team can quickly evaluate. And I was hoping to show this live, but the Wi-Fi is not quite there, so I'm gonna show you something from yesterday.

37. 5:51

    But what do I mean by external signal?

38. 5:53

    So it could be Slack conversation, could be a meeting you have with a customer, an onboarding call, a sales call, could be an internal team meeting, could be something from Sentry or a bug tracker, a bug report from a customer, an email, feature request.

39. 6:06

    And right now what's happening is, like, all that stuff is already exists. It's, it's in all those different systems. People hook them together with MCPs, so now your coding agent can check the email or check Notion or whatever it might be, but, like, how do you-- how, how does it know what to work on, right?

40. 6:19

    It's like it, it's still kinda stuck everywhere. And so, like, some humans are involved in, like, kind of taking stuff from one place and telling it, "Solve email number forty-eight or ticket number [REDACTED:generic_id]," but that's still a lot of coordination.

41. 6:33

    And so what we do is we, we have several different ways to automatically ingest these signals, prioritize what to, what to do with it, and, and kinda act on them.

42. 6:41

    And my favorite one, the most fun one, is what we call our meeting bot.

43. 6:45

    And so I'm gonna sw-switch over to my browser here for a second.

44. 6:50

    And, uh, okay. So we've got a booth at the expo, and we had the meeting bot running all day yesterday. So this is a four-hour meeting of a Google Meet.

45. 6:59

    You just kinda invite the bot to your m-Meet or Zoom or Teams or whatever it might be. And it listens all day, and it created all sorts of stuff as it was listening.

46. 7:10

    If it finds existing work, it'll link to it, right? So it's not gonna just, like, create new work if it's something you're already working on. Some of this is, you know, people testing the meeting bot out and telling it to do some weird things, um, or interesting things or just creative ideas.

47. 7:22

    But a lot of it's actually just, like, really good ideas that come out of people looking at what we're doing, asking questions, having new ideas on what to do with it.

48. 7:30

    And so it's kinda nice 'cause the last idea that was here was someone saying, "Hey, like, when I work with coding agents, I wanna make sure that the agent has clear criteria to evaluate whether it did a good job on the work before it tells me that it's done."

49. 7:43

    And, um, so they had that idea. The bot just picked up on it. N-none of us did anything manually. It created this ticket

50. 7:51

    and started working on it. And then I was able to just say, "Hey, take a screenshot of what, what you did," and here's that screenshot. And it kinda modified our ticket form to add these two new fields of acceptance criteria.

51. 8:03

    Now I'm gonna-- am I gonna ship this one exactly how it is? Like, no, probably not. But it's a new idea. It's concrete. I can play with it. I can go and actually, like, use the live preview and, like, see if this improves performance.

52. 8:14

    And so it takes, like, this, you know, y- you know, your hundreds or thousands of ideas that are everywhere and it helps you kinda move with the speed of what your customers are asking you for and what they're thinking.

53. 8:23

    And, um, it's really fun because every time we have an onboard or your customer call or, or team meeting, we almost always have dozens of new ideas that are prototyped, but more importantly, at least a few shippable PRs with very minimal intervention.

54. 8:38

    So we talk, stuff comes out, we look at it, we ship it. It's so much fun.

55. 8:45

    Put this back. So the next thing I'm gonna mention is that, you know, the, the- these three things that I've talked to you about really rely on having your workflow, your code base, your project set up to work in an isolated cloud environment, so that way the agents aren't trapped on an individual's machine.

56. 9:10

    So there's several reasons why this is important. So the first one is to eliminate what some people are calling lid anxiety. You wanna be able to close your laptop.

57. 9:17

    You've probably seen people running around the conference with their laptops open, all stuff is working or at the airport or, you know, there's some posts on Twitter or whatever about, um, you know, like people having their laptop tethered to their phone in their car as they're driving home.

58. 9:29

    This was actually probably the impetus for, for me and for a few people on our team to even start working on this. You know, last year I started working with Cloud Co- with Cloud Code a lot.

59. 9:39

    I had a, I think at the time, like, [REDACTED:age]. I, like, didn't want to, like, be tied to my laptop or have that stress. Just like I, I don't, I, I don't ever wanna think about whether I can, like, step away from a laptop or not.

60. 9:50

    And so we moved everything to the cloud. Things are working always. It eliminated that problem for us that people have been talking about for the past year.

61. 10:00

    It's really helpful. It's important to me. But I don't think that's the most important reason to do this. I think the most important reason to do this actually was, was touched on in the previous talk, if you were here for it.

62. 10:12

    I think you should only give your access-- give your agents access to only what they need, right? So if you think about what's happening, you have a bunch of developers with these agents running their laptop.

63. 10:23

    Their laptops, unless you have, like, impeccable hygiene, probably have a bunch of stuff on it that you don't want the LLMs or the agents to have access to. And yeah, like, everybody's working on these sandboxes and approval flows, and so you...

64. 10:35

    But, but, but really you're in one of two camps. You're either approving a bunch of stuff or you're hoping that your auto approval flow or your Yolo mode or whatever is configured properly and your sandbox is configured properly and doesn't read a bunch of stuff on your laptop that it shouldn't have.

65. 10:50

    And, you know, as, as the previous talk mentioned, like, these agents are getting more autonomous. They're getting really resourceful. They, they're trying to please you and do what you said.

66. 10:57

    And so when you say, "Hey, you know, wipe the staging database," and it finds a token on your laptop that it can use and it thinks it's working with staging, but actually it's production and now it just deleted everything.

67. 11:07

    I'm not trying to say this is happening constantly, but it still happens. And for us, the peace of mind of just, like, letting anybody run with these experiments and ideas and prototypes and, and, and real code without having to worry about this is, is, is, is really worthwhile.

68. 11:24

    To go one step further on that, um, it's not just, "Hey, make sure they don't have the credentials that they shouldn't have." It's also make sure they can't exfiltrate your code or your projects or your secrets or your content to somewhere that you shouldn't be able to.

69. 11:38

    And so you have a configurable network sandbox and you say, "Look, these are the places you're allowed to access. These are the ones you can't access." And any time it tries to access something that it shouldn't, it just pops up and says, "Hey, tried to access something.

70. 11:49

    Do you wanna give it access? Maybe you're trying to integrate a new vendor and need documentation." And you can do it on a per ticket basis or for the whole project.

71. 11:57

    And so again, that peace of mind of, like, people can do things. If they need new access, it's easy to grant it, and, um, we're not going to leak a bunch of important data, uh, by, uh, running agents in Yolo mode.

72. 12:13

    And the last thing I'll mention about that is that this is the key for allowing your non-technical team members to trigger real work, right? Your non-technical people don't have development environments set up on their computers.

73. 12:26

    But we've gotten our support people, our growth people to actually be meaningfully impacting the product by just talking to users, seeing bugs, experiencing themselves, and just go to Slack or the wrap itself and say, "Hey, fix this."

74. 12:40

    They fix it, screenshots are shown, engineer gets it, gets merged. Without that, they'd have to put it in Linear, and engineer would eventually pick it up, and a PM would triage it or whatever.

75. 12:51

    None of that here. You just ask for it, and it's done.

76. 12:55

    Now, the reason people didn't do this, you know, up until somewhat recently, like this was really painful. Getting your full thing set up in this like kinda sandbox environment used to be really, really painful.

77. 13:05

    But the agents have gotten better. We have our own environment setup assistant that kind of takes your project and gets it to work under these sandboxes. But honestly, whether you use this or not, I highly recommend you get your project working this way, and you can just get Cloud Code or Codex to do this for you.

78. 13:19

    You don't have to use us, but, you know, we think it's the best way.

79. 13:25

    And the last lesson is to benchmark agents on your code base. So, um, the way we do this is we select pull requests that represent great engineering work. It could be agent-created, could be human-created, could be a hybrid, doesn't matter.

80. 13:39

    You pick the agents you wanna use and benchmark, and then you get a quality versus cost and time breakdown in your code base. Now, why do you wanna do this?

81. 13:47

    There's, there's many reasons, but one is that if you're kinda going off the public benchmarks, SWE-bench or Terminal-Bench or other stuff, like those tasks may have absolutely nothing to do with your task.

82. 13:55

    Like, SWE-bench is all in Python. We're Ruby on Rails. It is not the case that the benchmarks are identical for them. There's trends that do compare, but the results can be very, very different.

83. 14:05

    And I'm gonna swap over to my browser one more time here.

84. 14:10

    So this is-- the-these are results on our code base of all these different harnesses. This one here is quality versus cost. This one here is quality versus time. I'll start with this one.

85. 14:23

    You can see some trends here, right? You can see that the Anthropic agents have just been consistently getting better, but not really any faster. The Codex agents and Cursor are actually pretty fast and quite good.

86. 14:35

    The open stuff has been getting better and better over time, but they're kinda slow. This is for our code base again. I'm not trying to make any general claims here.

87. 14:43

    By cost, the Anthropic stuff is clearly just so much more expensive for us, and the Codex stuff has been cheaper for us. And so this caused us a change of behavior.

88. 14:53

    We still use the different models. There's different use cases for them. We like the variety. We still use all these things. But when we saw these results, they kinda matched our vibe check.

89. 15:01

    We wanted to kind of like have hard data too. We switched our default to Codex at that time. Then Fable came out, and it was great. Kinda switched our default to that for, like, the few days we had it, and then it went away, and we switched back to Codex.

90. 15:13

    But the most important thing is, like, because we're agnostic, like, none of that had any meaningful disruption on our work. Like, we were able to just kinda switch back and forth really easily.

91. 15:20

    So next day something new comes out, see if it's good, and go.

92. 15:26

    And the last thing I wanna mention around that is, like, I don't know if this resonates with you all, but I have a lot of friends that are like, "Okay, I heard Minimax is good, and I heard, you know, GLM is good, and Kami K2 is good, but, like, haven't had the time to try it out.

93. 15:38

    Everybody keeps telling me I need to 'cause it's so much better and faster and cheaper." And you kinda have that anxiety for a little while, and then, like, finally, you take the two hours to try it, and it's like, oh, actually, like didn't really work for us.

94. 15:48

    So, like, what's... You know, I just wasted those two hours. This kinda eliminates that. It helps you kinda stay on the cutting edge really, like, seamlessly.

95. 15:57

    Let me go back. So what that kinda turned into us-- for us is, you know, essentially a hundred percent, like ninety-nine point nine percent of our pull requests are, like, heavily agent-generated.

96. 16:08

    We know that quality and reliability and security are really important, so we still have humans look at everything. We have agents help with it all, but everything's human reviewed.

97. 16:16

    Um, you know, for our, our, our relatively small team, we had ten and a half billion tokens over the past month. And you can kinda see what we were saying about Claude here.

98. 16:24

    It's a little small, so I apologize, but we had thirty-three hundred Claude code runs that cost ten thousand dollars in token billing. We have plans, so we didn't spend ten thou-- ten thousand dollars on it.

99. 16:34

    And Codex had four times as many sessions, and it was cheaper overall. And so again, the vast majority of our work currently is merged through Codex. We still use the other models.

100. 16:45

     More and more is happening through GLM 5.2. Gonna invest in that. And one thing that we're really excited to do going forward with this benchmarking is automatically-- Like, like you've probably heard about people, you know, routing tasks to the right models and all that.

101. 17:00

     But how do, how does like some third party know what to route for your code base? Like, this is a way that you know what's gonna work best for which task for your, for your project, and working on kinda automatically routing that for you.

102. 17:13

     So I'm gonna leave you with a few recommendations.

103. 17:15

     So first, um, get your code base and agents working in a sandbox. It unlocks a lot of different things, a lot of different workflows, everything I've talked about and more.

104. 17:24

     Second, integrate agents into the relevant human interfaces so your team and your agents can work together and don't have to, like, context switch and copy context back and forth.

105. 17:36

     Obviously, we think Superconductor is the best way to do it, but plenty of people are home-rolling things, hacking things together. Figure out how to make this happen because if not, the friction is just really high.

106. 17:46

     And lastly, find a way to benchmark and become model agnostic so you're not tied to anybody, and you can just constantly stay at that right part on the frontier of cost, speed, quality.

107. 17:59

     So thank you so much. Um, we've got a booth in the expo. Please feel free to come by. You can sign up at superconductor.com, or you can email me with any questions at [REDACTED:email_address].

108. 18:08

     Um, I will be out in the back as well for any questions. Thanks so much. [clapping]

109. 18:16

     One, one, one last thing. Um, if, uh, you know, at the booth, we're mentioning we're giving away a MacBook Neo. If you are here 'cause you signed up through for that, just meet us outside, and we will announce the winner.

110. 18:26

     Thank you. [outro music]