WEBVTT NOTE Sentence-level transcript of https://www.youtube.com/watch?v=YIVkERhy8xo NOTE One cue per sentence. Cue ids are the line anchors on /transcripts/YIVkERhy8xo.html. A cue ends where the next begins, or 2 s after its last word. s1 00:00:21.039 --> 00:00:21.359 Okay. s2 00:00:21.359 --> 00:00:22.240 Hi everyone. s3 00:00:22.240 --> 00:00:23.840 Uh I'm Solomon. s4 00:00:23.840 --> 00:00:31.359 I am the creator of ATMCraft and I also created MCPUI which became MCP apps and MCP steering committee. s5 00:00:31.359 --> 00:00:33.040 I've done a bunch of other stuff. s6 00:00:33.040 --> 00:00:39.680 Uh but we're here to talk about why we're the bottleneck and why we don't have to be. s7 00:00:40.000 --> 00:00:44.960 So, uh as you all know and use every day, agents are amazing. s8 00:00:44.960 --> 00:00:51.200 There's so much they can do uh from generating cat memes to B2B SAS apps. s9 00:00:51.200 --> 00:00:55.840 So if they are so amazing, we have to ask why aren't we all unstoppable? s10 00:00:55.840 --> 00:01:00.879 Why doesn't everyone have an army of agents that just does whatever they want? s11 00:01:00.879 --> 00:01:02.800 So it should be relatively easy. s12 00:01:02.800 --> 00:01:09.439 I mean you just have a bunch of monitors and you spin up 25 cloud code agents and you're done. s13 00:01:09.439 --> 00:01:14.400 So the reality is that it's just not that simple to do something like that. s14 00:01:14.400 --> 00:01:26.159 you need to a really want to use agents and secondly once you actually spin them up each one of these agents requires you to steer them direct them review them s15 00:01:26.159 --> 00:01:38.479 and when it's at scale especially it's just exhausting we need to find the skills to allow us to do it without burning out so in reality we are the bottleneck s16 00:01:38.479 --> 00:01:51.200 and the the cool thing here is that while we are the bottleneck The skills that we need to do these things to uh find ourselves not burning out every time we use an agent s17 00:01:51.200 --> 00:01:52.799 are with us all along. s18 00:01:52.799 --> 00:02:02.560 Uh if you try to compare it to other stuff that you've been doing outside of programming, for example, playing video games, it's not really that different. s19 00:02:02.560 --> 00:02:11.920 Like if if you're playing Warcraft, for example, or Sims, and you have a bunch of different uh units running around, you need to understand what they're doing and supervise all of it. s20 00:02:11.920 --> 00:02:15.840 How different is that from from actually inspecting agents? s21 00:02:15.840 --> 00:02:30.480 So I took this concept uh too far and I created agent uh which is a game inspired orchestrator uh that tries to bring all that good stuff together into work. s22 00:02:30.480 --> 00:02:41.519 So let's take uh a quick look of what that actually looks like and try and understand the journey that we can go through to really raise the ceiling of how humans and agents can collaborate. s23 00:02:41.519 --> 00:02:43.519 So, uh, this is AgentCraft. s24 00:02:43.519 --> 00:02:46.160 Uh, there's really a lot to unpack here. s25 00:02:46.160 --> 00:02:49.519 Uh, so we'll just go through the basics really quick. s26 00:02:49.519 --> 00:02:52.160 Um, what you see here is an agent. s27 00:02:52.160 --> 00:02:59.920 Uh, it's an actual representation of a cloud code or openclaw, whatever agent that you can imagine. s28 00:02:59.920 --> 00:03:06.640 Uh, it can be detected on your device or you can actually spawn new ones directly from a craft. s29 00:03:06.640 --> 00:03:13.840 Uh, so like I said, you have like codecs and uh, open code etc. at your command. s30 00:03:13.840 --> 00:03:16.159 Uh, and these agents can do everything. s31 00:03:16.159 --> 00:03:17.760 They're just normal agents. s32 00:03:17.760 --> 00:03:22.400 Uh, so I can just prompt them in this nice side panel that also has voice. s33 00:03:22.400 --> 00:03:24.720 So there's multimodality here. s34 00:03:24.720 --> 00:03:27.840 Uh, and just do something for me. s35 00:03:27.840 --> 00:03:28.319 Prompt. s36 00:03:28.319 --> 00:03:29.519 Prompt. s37 00:03:29.519 --> 00:03:33.280 And now these agents can do whatever. s38 00:03:33.280 --> 00:03:37.680 Uh, and if you look around you would see that the map has a a bunch of different elements. s39 00:03:37.680 --> 00:03:38.640 So you have buildings. s40 00:03:38.640 --> 00:03:40.400 These buildings represent functionalities. s41 00:03:40.400 --> 00:03:52.560 So for example, if you can manage your plugins or skills, uh you have like integrated terminal, integrated git, uh you can do in your all of your work from within this space. s42 00:03:52.560 --> 00:03:59.040 So now that we have this and we understand the basics, let's look at what we can do uh to raise the ceiling. s43 00:03:59.040 --> 00:04:01.360 So the first step is obviously visibility. s44 00:04:01.360 --> 00:04:03.120 I need to understand what's going on. s45 00:04:03.120 --> 00:04:04.959 What are my agents doing? s46 00:04:04.959 --> 00:04:12.640 So, I have this nice side panel and it shows me the different agents and what their task is and what the last thing they did is and what they're currently doing. s47 00:04:12.640 --> 00:04:17.759 Everything I need to quickly understand who needs my attention and who doesn't. s48 00:04:17.759 --> 00:04:20.959 The second part of it is we're not just limited to this. s49 00:04:20.959 --> 00:04:22.160 We have a map. s50 00:04:22.160 --> 00:04:30.080 So, I can take let's say my file system, project it onto the map, and now I can see exactly what my agents are doing. s51 00:04:30.080 --> 00:04:32.320 Not just by looking at a list of stuff. s52 00:04:32.320 --> 00:04:39.759 I can actually see okay this agent is now working on this directory or this file and these files are represented as runes on the map. s53 00:04:39.759 --> 00:04:45.600 So I can really look at each one and see exactly what each agent did and when. s54 00:04:45.600 --> 00:04:56.080 And now I can take this nice information because we are the orchestrator uh and use that to create linkages and now I can create cool stuff like heat maps. s55 00:04:56.080 --> 00:04:59.440 So I can really easily see what's going on. s56 00:04:59.440 --> 00:05:06.639 And the the other aspect is that now that we have this visibility, that's not really enough. s57 00:05:06.639 --> 00:05:08.800 We need to be able to react to what's going on. s58 00:05:08.800 --> 00:05:12.720 If someone needs my attention, I need to be able to quickly jump to it. s59 00:05:12.720 --> 00:05:22.800 So much like video games or RTS games or Civilization, whatever, you would click uh spacebar and it would just take you to the nearest thing that actually needed your attention. s60 00:05:22.800 --> 00:05:25.360 So you can really easily understand what's going on. s61 00:05:25.360 --> 00:05:34.960 and jump from one thing to the other and answer questions or approve plans, etc. That was nice. s62 00:05:34.960 --> 00:05:40.240 I mean, it's a nice step just to have that visibility, but it's not really enough. s63 00:05:40.240 --> 00:05:49.360 It's pretty exhausting to keep looking at what the agents are doing in the granularity of what files are they using and what tools are they using at the moment. s64 00:05:49.360 --> 00:05:51.039 So, we need something else. s65 00:05:51.039 --> 00:05:55.360 Uh and the reason is that we have like two two main problems here. s66 00:05:55.360 --> 00:05:58.479 Uh one is that there's just too much to hold in our heads. s67 00:05:58.479 --> 00:06:03.759 Even if I can understand what's going on and I can see everything, I can't really do like 20 things at the same time. s68 00:06:03.759 --> 00:06:10.160 I can't even think of the next thing I want to do if I have this, you know, huge coding project or whatever. s69 00:06:10.160 --> 00:06:12.400 So I need to find some way to fix that. s70 00:06:12.400 --> 00:06:26.319 Uh so we can I mean we can tell the agents uh you know go through my codebase, find out what the next things I need to do are, create these tasks for me and I just click a button, I accept the quest and there's some agent that does it for me s71 00:06:26.319 --> 00:06:27.199 which is fun. s72 00:06:27.199 --> 00:06:28.560 Uh it's cool. s73 00:06:28.560 --> 00:06:38.880 Uh but the next problem here is that okay now I have 20 stuff going at the same time and I have to babysit each and every one and that is completely exhausting. s74 00:06:38.880 --> 00:06:53.039 So you could ask okay we have agents agents are amazing as we've established so I can just go ahead and tell the agent to do it for me now it's called software factories but at the time it was just doing stuff autonomously s75 00:06:53.039 --> 00:07:02.880 uh so you can give it like a general sense of what you want it would spawn an orchestrator and break it down for you and run it all in well in this case it's a local s76 00:07:02.880 --> 00:07:10.319 uh container so everything is just done in isolation and I don't need to do any babysitting the agent does it for me. s77 00:07:10.319 --> 00:07:14.080 On top of that, you have loops, which everyone really likes right now. s78 00:07:14.080 --> 00:07:23.280 So, you can do cool things like just tell it to, I don't know, scan Twitter for cool stuff you want to build or scan your GitHub, and it will just create these nice s79 00:07:23.280 --> 00:07:29.680 uh features for you in the background without you needing to do too much up front. s80 00:07:29.680 --> 00:07:39.680 The bad thing is that I mean this is nice uh but what do I do when I have again I don't know I would say 20 but even five things to review s81 00:07:39.680 --> 00:07:41.039 at the same time. s82 00:07:41.039 --> 00:07:45.440 Uh it's very very hard to get that out of the way. s83 00:07:45.440 --> 00:07:49.120 So what I did is create uh this like review kit. s84 00:07:49.120 --> 00:07:57.759 So I get the entire changes I need and I get uh what files changed if you want to go like file by file or you can get just get visual evidence. s85 00:07:57.759 --> 00:08:08.960 So you can actually see videos of what changed or photos of what changed so you can really quickly understand what you want or even run a few uh instances in parallel and just pick the best implementation s86 00:08:08.960 --> 00:08:11.280 out of these. s87 00:08:11.280 --> 00:08:21.759 So now that we have this we have uh visibility and we have autonomy uh it's pretty cool like we reached a pretty good place in raising the ceiling of what we can do with agents s88 00:08:21.759 --> 00:08:24.639 but it's still pretty exhausting. s89 00:08:24.639 --> 00:08:26.319 I mean it's it was fun. s90 00:08:26.319 --> 00:08:31.120 Uh, but now I have to ask myself, do I really need to be the only one doing this? s91 00:08:31.120 --> 00:08:40.959 It's pretty lonely to just talk to agents all day and trying to and you know, if you look at uh what a team does, for example, if it's just me, that's fine. s92 00:08:40.959 --> 00:08:45.279 But if I have a team, I might not even be the right person to review what's going on. s93 00:08:45.279 --> 00:08:47.360 So, I need something else. s94 00:08:47.360 --> 00:08:50.160 Uh, and that something is collaboration. s95 00:08:50.160 --> 00:08:54.320 We can just have other people join us. s96 00:08:54.320 --> 00:09:07.279 So the way that looks in agent craft is that I can create these uh you can call it you know war halls war room whatever uh host them it's like completely local but you can do like tunnels s97 00:09:07.279 --> 00:09:14.560 and people can join you h so I can create a room and let's say I have a product designer in my team in this case uh it's my wife s98 00:09:14.560 --> 00:09:28.399 and I can approve uh her otherwise she'll be mad uh so I can approve her and she does her thing she designs whatever and I as an engineer can not only see that that's that's her s99 00:09:28.399 --> 00:09:35.680 um I can not only see that on my map uh I can actually take that and follow off off of it s100 00:09:35.680 --> 00:09:36.959 prompt prompt s101 00:09:36.959 --> 00:09:54.080 yeah that's just like her um so I can take that design follow up on it implement it while she keeps working uh and the cool thing here is that not only can I hand off or fork and kind of have this shared workspace so I'm not really bound anymore or to Git. s102 00:09:54.080 --> 00:09:56.080 I can use Git, but I'm not really bound to something. s103 00:09:56.080 --> 00:09:57.519 Everyone is working together. s104 00:09:57.519 --> 00:10:06.480 Uh you can see that there's also some kind of chat between not only between the people within the room, but also between agents. s105 00:10:06.480 --> 00:10:11.360 So we can have this really nice notice board of exactly what each person is doing, what each agent doing. s106 00:10:11.360 --> 00:10:17.360 They're all aware of each other and they can collaborate much more closely uh than you normally would be able to do. s107 00:10:17.360 --> 00:10:22.959 Uh so for example, here I can say, okay, I took off this design task. s108 00:10:22.959 --> 00:10:34.800 Uh so now we have oh by the way this is also from devices you can have like mobile and and if you like telegram you can use telegram whatever floats your boat. s109 00:10:34.800 --> 00:10:40.320 So we have visibility and we have autonomy and we have collaboration so we managed to raise the ceiling. s110 00:10:40.320 --> 00:10:48.079 Uh it's now possible especially if you're power users to do really cool stuff and use more agents and do more things. s111 00:10:48.079 --> 00:10:55.680 But the interesting thing here was, you know, if I looked at the feedback I got, it's not just that power users were able to do more. s112 00:10:55.680 --> 00:11:10.880 The cooler thing for me was that people that had even nothing to do with agents or nothing to do with productivity, uh, come and say, uh, okay, my kids really loved it and they use it all the time to to orchestrate agents, which they didn't do until now. s113 00:11:10.880 --> 00:11:18.320 uh or you know someone that flunked out of college because he played Starcraft and now you can suddenly do really productive stuff with it. s114 00:11:18.320 --> 00:11:27.519 Uh and a bunch of other examples of kind of bringing communities that so far were kind of behind into this new world of productivity. s115 00:11:27.519 --> 00:11:34.320 So we need to raise the ceiling but we also need to uh lower the floor. s116 00:11:34.320 --> 00:11:45.120 We need to have some kind of way to take no probably around 90% of the people in the world and bring them into this hygienic future without having them burn out. s117 00:11:45.120 --> 00:11:47.839 So again, I took it too far. s118 00:11:47.839 --> 00:11:54.640 Um, and there's this uh currently named TBD um potentially loopers. s119 00:11:54.640 --> 00:12:10.480 Uh the idea here is okay why don't why do we need something like you know Warcraft which is potentially very complicated uh especially or might be even daunting if you're not into the granularity of what files are there are or how uh complex the UI is and kind of try to find s120 00:12:10.480 --> 00:12:24.000 a lower denominator of what makes stuff accessible especially now that agents are much more capable so instead of granularity or having like exactly what files they're working on maybe I can have it more of a mobile s121 00:12:24.000 --> 00:12:43.279 game level uh have projects that they keep returning to and use loops and other stuff that rely on agents being more autonomous to have like a very basic level of I prompt I get the result I don't really care perhaps about the way I can see it if I want to and I have this really nice interactive s122 00:12:43.279 --> 00:12:58.959 and cool experience that makes me want to come back to this and obviously I mean this is one visualization uh it can really resonate with some people but might not might not present to others because we're not all the same and s123 00:12:58.959 --> 00:13:03.920 what may appear like amazing and easy to one person can appear very difficult to another. s124 00:13:03.920 --> 00:13:10.240 Uh but here uh I'm trying to look at a way to make this more customizable. s125 00:13:10.240 --> 00:13:17.760 Try and understand what it is that you as a person need in order to understand and want to use these tools. s126 00:13:17.760 --> 00:13:21.519 So this is a very very early draft. s127 00:13:21.519 --> 00:13:24.000 Um but if you want to use it, please let me know. s128 00:13:24.000 --> 00:13:25.760 So we're the bottleneck. s129 00:13:25.760 --> 00:13:28.720 I think we've established that uh pretty well until now. s130 00:13:28.720 --> 00:13:35.040 But the skills that we need to stop being the bottleneck and enable this new future are already with us. s131 00:13:35.040 --> 00:13:39.120 So we are the bottleneck, but we don't have to be. s132 00:13:39.120 --> 00:13:46.079 And I hope that you all can take what's relevant to you and your life and apply it forward. s133 00:13:46.079 --> 00:13:48.800 So I would ask you for two things. s134 00:13:48.800 --> 00:13:50.399 One, agent is already out there. s135 00:13:50.399 --> 00:13:55.920 Like you can just npx install agent as a website uh and do your thing. s136 00:13:55.920 --> 00:14:02.560 Uh this new thing that I just showed you uh potentially loopers uh is still experimental. s137 00:14:02.560 --> 00:14:11.279 I'm still trying to understand the interest and what people are actually looking for to uh get the floor that they want or the ceiling that they want. s138 00:14:11.279 --> 00:14:18.320 So, please uh go here and express your interest and tell me what you're looking for so I can know what to do with this. s139 00:14:18.320 --> 00:14:21.279 And thank you. s140 00:14:33.040 --> 00:14:35.360 I got it.