Let’s Talk About FOMAT – Fear of Missing Agent Time

Talk transcript

1. 0:00

   [upbeat music] Thank you, everybody.

2. 0:16

   My name is Michael Richman. [lips smack] Um, I lead several teams at Bitly, the link shortener, but today I'm here to talk to you about FOMAT, uh, fear of missing agent time.

3. 0:29

   You know FOMO, fear of missing out. You also know FOMAT, you just didn't have a name for it.

4. 0:35

   Um, what is fear of missing agent time?

5. 0:40

   It's being out on a walk and having an idea that you want to task your agent with, [lips smack]

6. 0:48

   and having to wait to get back to your dev machine to actually do it.

7. 0:52

   It is when you get up from your desk and you had an agent working 30 minutes ago, chugging away, and you get back and you realize that after two minutes it actually stopped to ask you a question, and it's been waiting there blocked the entire time. [lips smack]

8. 1:15

   We all wanna believe that our agents are low touch-- or sorry, are low touch and high autonomy. But we all know the truth, right? It's back and forth, it's babysitting, and you cannot predict when you're going to be needed for input.

9. 1:36

   Right now, a coding task might typically take anywhere between five minutes or 45 minutes, and you kind of know when to check back.

10. 1:45

    There isn't that much time that's spent in agent idleness. [lips smack]

11. 1:50

    But that window is only gonna get longer, and the longer the agent waits for you, the more agent time that you have missed. If a task is running for five hours or eventually five days, you can't just check back in a bit.

12. 2:05

    You need to know when it needs you and you need to know when it's done, and that might be whenever you are, wherever you are. It might be whenever.

13. 2:15

    You can't predict it. You may not be at your dev machine.

14. 2:19

    Did I go back? I went back. Sorry. So like once I s- once I... Once again, my name is Michael Richman. I run several engineering teams at Bitly. I also co-lead our AI coding tools strategy.

15. 2:31

    Um, I'm a really hands-on engineering leader. I run teams and I also write code.

16. 2:37

    I co-wrote the Bitly MCP server, and I train our engineers on AI skills and best practices. I think about tools a lot, the tools that we use every day, how they work, whether they are effective for our workflows or not.

17. 2:57

    And agentic coding has really changed the world of software in the last year, and the road is very much being paved as we are driving on it. So I built a system called Command and Control in order to help me work with coding agents outside of the terminal or the IDE, because I really needed it and nothing

18. 3:19

    existed to solve it yet. Anthropic recently released some ways to address this with remote control and, uh, the teleportation mechanism, and I think it was just two days ago Cursor came out with a solution in the space. [lips smack]

19. 3:34

    So I wrote Command and Control. One of the things that is nice about Command and Control, and I'll show you it in a minute, is it is a way to get all of your coding agents in one place, uh, on your mobile device or really anywhere.

20. 3:47

    So this is what my setup looks like. I have multiple terminal windows. Each of these windows has multiple tabs. Here's Claude Code. Here's what Codex would look like here.

21. 3:57

    Here's Gemini. Here's the Cursor IDE. And at any given moment, I might have multiple sessions running multiple agents across all of these in various states of completion. And here's the thing, I don't know about you, but I cannot keep track of more than two or three sessions at a time.

22. 4:17

    As soon as I get to four or five, I don't know what session two is doing anymore. I don't know which one needs my attention, and I have no idea which states of completion things are in.

23. 4:28

    So how do you know when an agent is stuck and needs d- a decision from you? How do you know to check in on an agent mid-task, uh, and that, to find out that it's gone off the rails? [lips smack]

24. 4:41

    What if you wanna start a new session and you're not at your dev machine? That's exactly why I built this system.

25. 4:49

    So this is what it looks like on an iPhone app. It's on Android, it's on the web, and it lets you monitor and interact with agent sessions and launch new sessions from anywhere, from your phone, from the web, even from your watch.

26. 5:08

    I have a couple of video demos that I'm gonna play and show you a few of the features of it, and the point here really is like this is a solution to a workflow problem.

27. 5:18

    One solution. We saw this morning, uh, what was it called? AgentCraft, which is the gaming version, uh, uh, of something similar, which I thought was awesome. [lips smack] So here's the first demo slide.

28. 5:28

    Okay, here I am in the terminal. I'm gonna start a Claude Code session, and I'm gonna issue a command that's pretty run-of-the-mill. I'm not actually exercising Claude Code functionality.

29. 5:40

    I just wanna demonstrate Command and Control. So if I come over here to my phone simulator, you'll see that I've got a Command and Control app over here. And what I've got here is my sessions.

30. 5:54

    This is all of my sessions grouped by...

31. 5:57

    Ones I want notifications for and ones that I wanna keep my eye on and recent ones. And here you'll see the one we just issued here 27 seconds ago.

32. 6:08

    Let's get out of this session over here, and what you'll see here is the response I got from the agent is the same one because it is the same session.

33. 6:17

    Now, the beauty of Command & Control here is that let's say I wanna subscribe to this particular session for notifications, and I'm gonna issue a, um, response to this one.

34. 6:29

    I'm gonna say, "Sleep for one second and say hello." And as soon as I hit this, I'm gonna leave the agents working. I'm-- I left the app 'cause what I wanna demonstrate here is the push notification that I'm gonna get once it actually completes.

35. 6:48

    And there it is. So I can click right into that guy, and I got the hello. Now, if I come back over to my session and I resume this guy,

36. 7:00

    my response is right there with the agent response as well. The beauty of this is that I don't have to stay in my terminal. I can walk away with my phone, get notified when there are answers, and respond right from there.

37. 7:19

    So that's one basic feature of Command & Control, interacting with sessions from anywhere. Let's see another one. This is starting a new session in the mobile app.

38. 7:31

    I was gonna do a live demo after I recorded these videos backups, so I was like, "I'm gonna show the videos." So here's the next one.

39. 7:39

    I wanna demonstrate another important feature of Command & Control, and that is that I can start a new session right from the Command & Control UI. I can pick any configured agent that I've got here.

40. 7:52

    I'm gonna stick with Claude Code, but you see I've got Codex and GitHub Copilot and Cursor here. I'm gonna stick with Claude Code, and I'm gonna switch my directory to a testing directory, and I'm gonna just ask it what time is it.

41. 8:10

    Now, the reason I'm showing you a pretty simple prompt, the prompt doesn't matter 'cause the point is that I'm issuing a prompt to my agent, and I'm getting a response.

42. 8:20

    Now you can see I'm working late at night here. And the beauty is I can go over here and resume the session, and here's my session right here that I started from Command & Control.

43. 8:31

    I can go into it here and pick up where I left off. And if I issue a command here, what is the, hmm, date tomorrow, let's say.

44. 8:45

    What I will see over here is the same conversation, and that is the beauty of Command & Control. I often start my day

45. 8:56

    with prompts that I issue from bed, honestly, and start up a bunch of sessions and resume them either in the CLI, or I continue them right on my phone.

46. 9:09

    I hope you're starting to see the power of Command & Control here. And like I said, this applies to any of the coding agents that I've got configured on my machine.

47. 9:24

    Now, to the problem of keeping track of sessions. This third video, and then I'll talk a little bit more about the importance of this, is, uh,

48. 9:34

    session management. Now, I mentioned how hard it is to keep track of all the sessions you've got going. I mean, if you just look at the number of sessions I've got here, um, there are a lot.

49. 9:49

    And I wanted to revisit the different sections that are available in Command & Control. So, uh, as I mentioned, you can subscribe for push notifications. That's this top section here.

50. 10:03

    Uh, the on my radar section is ones that I just want to keep my eye on, but I might not want to have, um, be as chatty as push notifications for every message.

51. 10:14

    Uh, and then there's a recent section here, which is basically the last 24 hours, and then the rest. Now, you can see there are thousands of sessions here. I couldn't possibly keep track of them all, but here they all are organized for me.

52. 10:27

    Another useful feature in Command & Control is what is referred to as the overview dashboard. One of the really nice features of this one is you can get a kind of stand-up summary of the most recent sessions, and this is just using the last several messages to kind of give you an overview of what's been going on

53. 10:50

    for each of those. So I hope you can see the, the power here, and I think this is the kind of thing that we need in our new world of agent orchestration.

54. 11:03

    This is a number of things. This is interacting with your agent sessions or starting new sessions from wherever you are. It is session management. It is notifications, so you know when your agent needs you, and you don't have to guess.

55. 11:21

    And it's also all of the coding agents that you might be using in one place. It's all those things from wherever you are.

56. 11:32

    A little bit about the architecture of this, which you might be curious about. So the-- each agent platform, Claude Code, Cursor, Codex, Gemini, OpenCode, they have a command and control daemon that runs alongside.

57. 11:44

    They talk to a control plane layer. They monitor lifecycle of the agent. When things change, it's blocked, it needs your, uh, help, uh, it cont- communicates up to the control plane layer, and then the UI talks back to that API layer and notifies you of things

58. 12:01

    The control plane aggregates all of the agents, regardless of where they're running or what framework they're running on. And so this could be your dev machine, this could be a cloud VM, or it could be both.

59. 12:14

    And this is an important point that I wanna emphasize. I needed a system that is a single pane of glass into all of my agent sessions, regardless of which platform they're running on, regardless of what machine they are on.

60. 12:31

    I might have Claude Code running out of my Mac and Codex CLI running in a cloud VM, and all of the sessions from both of those are available via a single UI.

61. 12:44

    And like I said, it's coding tool agnostic. By design, it works with almost all of them. I will also add that the daemon layer is open source, so you could plug it into any of your agent frameworks that you're working on, and then access it through this, uh, the single UI today.

62. 13:01

    Uh, so whatever your agent, you can reach it and it can reach you.

63. 13:06

    And this brings me to the point of, like, we all want our agents to be maximally autonomous, right? And the honest truth is that they are not yet, as much as we hype it, and especially not if you're limited to how you can interact with them to their native environments.

64. 13:22

    This is one solution that addresses that problem. And I wanna talk about a little bit of a broader concept here that this is related to, and that is that r- just in the last year, the agentic coding workflow has completely transformed what software development is.

65. 13:44

    It has transformed how we work, and it has also transformed how we enjoy how we work. So you know the old c- the concept of flow, which is like being totally in the zone, locked into your code, hyperfocused on a single thing,

66. 14:01

    you and your code solving a problem. And I think that the new type of flow in the agentic world is more about agent choreography, multiple agents working

67. 14:16

    in parallel with you moving between them, unblocking one, redirecting another. And the new flow comes from the elegance of that choreography and the results on the other side.

68. 14:33

    So then maybe some of that fear of missing agent time can be alleviated. Another thing I really wanna note here is that this paradigm of the always available agent is actually highlighting the value and importance of time away from your agents.

69. 14:53

    Matt Pocock alluded to this yesterday. I don't know if you heard the Simon Wilson interview on Lenny's podcast last week. The cognitive load of managing multiple agent sessions is really high, and it is exhausting, as you all probably are aware.

70. 15:12

    You need a break, and here's the thing. It is in those breaks that we often have our best ideas.

71. 15:22

    We need systems that make it possible to reach our agents during those breaks wherever we might be and whenever that happens. And that is how we truly alleviate the fear of missing agent time.

72. 15:39

    Once again, my name is Michael Richman. I'd love to hear about your workflows, your hacks, the pain points that you encounter. I invite you to give Command and Control a try if you're interested.

73. 15:50

    Here's where to find it online, and here's where to find me on LinkedIn. I'd love to connect and continue the conversation. Thank you. [audience applauds] [upbeat electronic music]