(14) The Claude Code Era: Mastering Autonomous GTM Agents (Jordan Crawford, Founder & Chief GTM Engineer) - YouTube https://www.youtube.com/watch?v=2BJpYTbNQvw

Transcript: (00:00) Jordan Crawford is an adviser to hyperrowth startups like Clay and Fullenrich. He's the founder of Blueprint GTM and one of the most impressive GTMai practitioners out there. >> I have given Claude code a goal and it will continuously work to accomplish that goal. And by the way, hands-free. >> Jordan joins us to explain why we are moving past the chatbt and clay eras and entering the cloud code era where the constraints on what you can build simply vanish. (00:27) You can remove all those things that could be orchestrated at a much better level by building your own tools. You now essentially have an engineering department for any problem. But this episode isn't just about tools. It's a warning to every CRO and VP of sales. If you would like a job, you must understand these tools because all of your organization could be rewritten with these tools. (00:48) If you're not able to deliver an 80% improvement in a quarter, there's someone that's willing to take your seat that will. And this is what's most valuable about the conversation. Jordan's at the cutting edge, so he sees what's coming more clearly than most. >> It is an alien intelligence that will swallow my job. (01:04) It will swallow your job. You will be much, much, much better with it, but not if you don't. >> Welcome to the revenue leadership podcast. >> Momentum is a powerful tool for turning sales and customer conversations into go to market intelligence. Using Genai, it extracts, analyzes, and automates customer intelligence across your GTM or the best part, it's not a new platform for your team to adopt. (01:26) It integrates seamlessly with your existing stack or it can straight up replace your conversational intelligence tool. At owner, we ripped out Gong and went all in on momentum. It writes back to our Salesforce directly, captures forecast risk, autofill CRM fields, shares product signals, and tracks sentiment. Companies like Cursor, Zscaler, Ramp, and 11labs use it every day. (01:48) Check it out with a free trial at momentum.io. All right, today's guest is Jordan Crawford. Uh, coming on the podcast for the second time. Was an episode that I got a lot of messages about and people want more from and I learn uh from Jordan all the time with his content and through my incessant uh text messages. Uh, for those of you who don't know, Jordan is the CEO, founder, chief GTM engineer code wizard at Blueprint GTM, his company. (02:20) Uh, and prior to Blueprint, he founded Scout, which was postcard marketing. Uh, and he advises a bunch of startups that, uh, all of us would have heard of, Clay Fullenrich, Tenor. Uh, he helps me a ton at owner.com as well. uh and his expertise is really in outbound sales strategies, datadriven GTM operations. He is on the absolute forefront of how AI is reshaping GTM. (02:47) Um and we are going to dive into what the heck is cloud code because uh it seems like we really hit an escape velocity on cloud code over the last like couple of months. Opus 4.5 plus the cloud code update. I don't know when whenever that was feels like it hit some tipping point to where the non-technical world has really gotten pulled in. (03:11) I spent a bunch of my holidays cooking some stuff in cloud code that uh I'll eventually need your help fixing. But uh we're going to unpack like what is cloud code? What are agents? What are sub aents skills? like should CRO's be doing this and like spending their time in in Cloud Code and and other tools when and how does it fit into this landscape? Um this is not a paid episode despite uh our collective enthusiasm. (03:38) Uh >> I know those bastards. We should send us some money. We got plenty of it. >> Yeah, I really should have thought of that before we started recording, but uh I'll pretend we haven't done it yet and I'll send them a message. Um, so what did I miss on your background? Like maybe just not even like your career background, but what type of stuff are you building today? I I think it's really valuable for people to get a sense of >> like you run a fairly sizable business now. U you have a bunch of customers and (04:09) are doing like a lot of work and you're a oneman show. It's just it's just like you and Claude. And so like give people a sense for the art of the possible on how you can how how much you can have agents do on your behalf. >> Sure. Sure. Um I will say this I also in the last year I have uh created uh the cannonball substack. (04:32) So top 40 substack in under a year because people want to see real work and that's what you get to see on the cannonball. Um so what am I doing now? Well, let me actually I'm I know you may hate me for this, but I'm gonna dive real deep and I'm gonna talk to you about like an actual use case that a customer had. (04:50) Well, they wanted to basically do 12 unique enrichments. And this would just basically web searches, right? Like if you were to Google it yourself, you could Google it and you would know what to do and what to look for. And so I said, 'Well, what I'd like you to do is take five example customers and go do each of these 12 researches yourself on them and tell me what you found. (05:13) And at every point in the transcript when you've done with one type of enrichment, just say the word alligator because you know, we have to talk to our AI overlords and and if we say alligator and not paperclip, they like us better. So, um, the the nice thing is that, uh, I fed that two-hour transcript in, uh, uh, in, you know, I pulled the transcript and I said, "Hey, Claude, in this case, Claude Code, uh, here is a transcript of my customer doing manual enrichment. (05:46) Can you go help me invent a prompt to go do this reliably and test it on 10 new customers?" And so if you sort of think what's happening there, the first thing is it it can go and find the transcript locally. So I have it saved to a file. Then it can go test that. So it can deploy a bunch of agents. Um and uh and then it can evaluate the results. (06:09) And so because remember it has like the actual client talking. Um and so if you think about the the capabilities here these might be long running sessions Kyle. So this is not try this then do the next thing then try this right it's like I have given it a goal and it will continuously work to accomplish that goal and by the way handsfree so I just talked to this thing and it keeps going and so the As long as you click accept all. (06:41) >> No, no, you can you can skip that. Bypass permissions. Engineers hate when I do this, but you can. There is a dangerously skip permissions flag in Claude that will just uh so I I shouldn't say this publicly because someone will find a way to take advantage of me, but I dangerously skip permissions. So, it just it just rocks. (06:59) And you know, I actually I sort of joke about this, but you hear all these doom these engineers are like, "Don't use it. It's dangerous, etc." everything >> injection. Yeah. Yeah. I'm just doing everything locally. So, it's just like writing code locally. It's like, you know, calling some services, but it's not like it's on the internet. (07:18) It's not like it's, you know, I'm not and also I'm not trying to rebuild Salesforce.com. like we're not there's a difference between um uh what I'm talking about here which is just like I I want help automating a particular task and like go recreate this 100 million line code of some big SAS company right it's like that's not what we're talking about and when you think about this the the capabilities of what a tool like cloud code can do it's as if chatbt could take more actions that's what you should think about it as like if chatbt (07:51) could do more if it could send emails as you or and that's a bad example but if JGBT could like >> it can and mine does so. >> Yes. Yes. Yeah. >> Um so but but I that's like a scary thing. I don't want to scare people. >> And can you explain how like what what is what like what's happening under the hood uh in cloud code that's not happening in Gemini and and chatbutt for example. (08:16) >> Okay, that's a great question. So basically what it's doing is it can write code and what the code can do is it then can interact with things like APIs which are like structured information. Um it can pull things in and out of its context window. So like for example Kyle you have let's say you have a 100,000 transcripts. (08:38) Well you can't just paste those in a chatb right? And let's say you're like, you know what I want to do is I want to find anytime someone talks about a competitor. Well, what it can do is it can write code, find all the competitor keywords. It can go search online to find your competitors and then say, "Okay, great. (08:56) What I'm going to do is I'm going to pull just the five paragraphs around every every mention of competitors across all of the transcripts." Well, first, the transcripts are too large to house anywhere except locally, right? Maybe they're hundreds of megabytes and chatbt can take a 250 megabyte file. You also here's a here's a quick tip for chatbt cheaters here. (09:19) You can zip up files and upload a chatbt and they'll unzip them. So if you want to get a file that you can't get into chatbt, just like make a zip of it and upload a chatbt and chatb will do it for you. >> Or just use Gemini with a bigger context window. >> Well, it's No, no, it's not the context window. It's the file size. (09:34) It's like literally uploading. So if you want to upload it like a zip file of all of your transcripts, um you can get more transcripts in. Um and by the way, what chatbgt is doing in that case is it is writing code. It's not pasting it into its context window. Um but so when you use cloud code, the benefit is that it can determine what it needs to do. (09:57) Should I pull this into a sub aent and it sends a bunch of sub aents out. Should I pull this into my local context window? should I write code and go use code to go determine what to do? And so it basically has access to more tools. And by the way, it can sort of run forever. So um you might not know this, but Claude has this concept called compacting. (10:23) So if you're vibe coding for a very long time, what it does is it summarizes the last session and brings it into a new context window. And why this matters to you is that just like you or I, if we're working on a task for a very long time, we get exhausted. Well, if we could take a rewind back to, you know, the time after we had finished our workout or whatever and we had more energy, we would do that. (10:46) Um, and so, you know, >> with all of the learnings that you got through that session. >> Yeah. Yeah. Exactly. Um uh so I I don't know we kind of meandered there a little bit but um >> so the the question was like okay so like what is cloud code doing under the hood that the other models aren't really doing and it's writing code to accomplish tasks sometimes building things that you might use repeatedly and we'll talk about skills and and sub agents >> and it has more access to different things that I find the ecosystem is is (11:19) much more open. Yeah, and I'll say another thing is that the way in which it's designed is more aligned with work than um the web-based tools. And by the way, I'm talking about Claude, Chatbutt, and Gemini on the web. So like when we talk about these models like it's probably a misnomer to be like what's chatbt not doing? Well, chatbt has a version of claude code that they call codecs. (11:42) And so so um I just want to be really clear here. Um and the thing is that >> when you pop into catchbt, every new session is sort of brand new. Now, both of them have concepts of memory, but that's not really how you would work because that exists in a model where it's like, I'm going to take everything you've ever said to me and try to help you with task, which is like unreasonable, right? People don't need to know what you bought your daughter last Christmas, but like your Gemini or HBD has like that history, right? But that's not helpful if you're (12:12) accomplishing a task. So when you set up claude locally, you're generally saying you're creating a project and in this case is a folder and you're saying in this folder this is what I'm trying to get done and in my case I deliver campaigns. So campaigns have a couple of components which like I need the closed one transcripts and by the way the transcripts are different per campaign. (12:35) So if I pasted other transcripts into historical chatbt um like those may not be relevant for the task at hand. >> So this is sort of the benefit of doing the stuff in cloud code is you're saying this project is for this type of task. In my case it's campaigns. >> So all of the context is only relating to that problem and that can compound right. (13:01) That context gets better and better and better. Yes. And you're controlling it because it's all in the same folder locally on your computer. >> Yes. Yeah. And the folder has by the way like I can pull in all the transcripts say read. So I can have a session that says read through all these transcripts and create a summary of the thing the reasons I win and the reasons I lose. (13:19) And then it writes that to a a document. This they call it a there's a markdown file which is just a fancy way of saying a it's a text file with some formatting in it. Um, and that way the next time I pop open cloud code, it doesn't have to go read all of those transcripts again. It can just read the closed one reasons, the analysis. (13:38) And so that's where my context compounds, Kyle. So I go from just like unstructured information to structured context, and then I can take that context and accomplish other things with it. >> And it's creating files within this local environment that then can be cross referenced, and you can say, "Oh, look here. Don't look there. (13:58) " And so, so I want to zoom out. I want to do a couple more zoom out questions before we get into some details and maybe actually walk people how to do some stuff. >> Um, what do CRO's really need to understand about this? So like this is a fairly we're now like fairly out on the sophistication bell curve and but you see really uh forward thinking go to market people tons of of um AI native companies like sort of living in this in this like cloud codecentric world but if I'm a CRO at a series C SAS company and I really want to bring more AI to my company. (14:41) Like, how deep do I really need to go on this? >> Well, I'm kind of the opinion that I mean, I can talk about eras here or what I can do is I can talk about how I think that uh the role needs to be realigned. Which is a better path. >> Cool. Let's do it. Which which of these path is the question? >> Oh, I thought you said the second one was a better path. (15:11) >> Um, let's talk about the eras. I think that's better landscape setting. >> Okay. So, >> we'll probably talk about both. >> Yeah. So, generally I think of the um sort of the go to market world in sort of three eras. There's the the um chatbt era, the clay era, and the cloud code era. (15:30) Um, and so and and these are just like tools that kind of uh bookmark where we're at. And they're helpful to think about because they give some context as to the problem that we are able to solve. >> And as our tools can do more, it's important to know what they can do because then we know what to give them and what not to give them like what we shouldn't expect from them. (15:51) And so the chatbt era uh was defined by well now I can take unstructured task and I can just accomplish tasks and I can accomplish in my browser and that might be research a company. It might be something and it also can be more impressive than this which is like you know write me a Google Sheets formula or or take these five files and merge them right this is like a task >> and and the more about answering questions though like some tasks but like >> basically word tasks word and and like data tasks I would say. (16:28) >> Yeah. Yeah. That's right. Yeah. So like you could upload a a CSV to it and say categorize this. So you wouldn't have to use Excel formulas anymore. You could upload a CSV to chat and say what are the reasons I'm losing based on these fields or whatever. Right. >> Um >> and so yes, you're right. (16:45) Word-based tasks is probably a pretty good way to say it. Um the Clay era was more about workflow automation and these are deterministic workflows. So when this happens then do X, Y, and Z. And even within a deterministic workflow, you can do non-deterministic things, which is what the models are good at. So you could say, "Go research and tell me if this is a good fit for me, yes or no, and here's all the criteria I use for a good fit. (17:14) " So, um, a a thing that would be really perfect for the sort of the clay era is, uh, go when a new deal comes into my CRM, run this agent and define these qualifications and if it is qualified, write yes and if yes, then go push X, Y, or Z to HubSpot and that can go trigger an SDR to make a call, for example. >> Mh. >> So, this like this is an example. (17:37) It's a it's a very u defined workflow and what you would do and mo most I mean most I guess most people are probably still in the chat era there's like a good number of growing people in the clay era um and the way in which you would get benefit here is you would stack these kind of brittle tasks and these brittle tasks >> and and you know things could change and you had to keep you know so so the way in which you got value here is you said well these 50 brittle tasks are going to solve a lot for me and this is going to (18:07) be very valuable to me but I have to go in and change something if I change my schema or whatever >> and and by the way those workflows don't know me >> they don't know what I'm trying to do they have no understanding about my context they don't know that I'm a sero there know when HubSpot comes in do this thing run this AI agent push this here and this is like it's it's really good for observability you have a very clear understanding about what's happening Um, >> and they can know some stuff, but you have to like put that context in the (18:42) prompts in the table basically. >> Yeah. Yeah. In Yeah, exactly. In the prompt. And by the way, when you go create the new thing, you got to go fetch that context yourself. So, you have to go and by the way, if you want to improve that prompt, you had to copy and paste that into chatbt and say, "Improve it, fix it, fix it, fix it. (18:58) " And and actually, it's kind of funny. I just released autoclavagent.com which creates clagents for you in cloud code. And this is actually a pretty good segue to the sort of cloud code era. >> So um I should give a I'll put we'll put a promo code for a discount or something in the in the show notes. >> autoclavagent. (19:17) com you said >> autoclavagent.com. Yeah. So and this this is a pretty good way to introduce you and it's really uh it's a gateway drug so people could get into the cloud code era. So a clay agent is basically Clay's AI agent. And the way in which you would build them, the way in which I used to build them is I would say to chat to I'm trying to do X, Y, or Z. (19:37) Help me. And then I would say here are some examples. Go improve the prompt. And then I would paste that into Clay and then I would run that Clay, you know, agent. >> Um, >> and it would fail and you go back and you fix it and it would fail then. >> Yeah. Yeah. Yeah. or or or it's like or even if it didn't fail, what I would do is there's like a little button in clay that says copy all the JSON and what that is is like all of the actual steps that it took and the outcome >> and I would feed that back into chat and (20:07) say how did it do and it said well it did okay here's where it changed here's where it could have done better and so the autoclagent tool is sort of a perfect example of where I think this claude code era um uh can take us And and how the tool works is you you get Cloud Code set up and it's really a lot easier than you think and you just say go. (20:33) And what it does is it says, "Okay, Kyle, well, what do you want to do?" It's like, "Well, I'd like to qualify accounts." It's like, "Okay, well, do you have examples of qualified or disqualified accounts and you can just dump a bunch of information in the folder? Here's things you could talk to it." And it says, "Great. Downloaded a I downloaded a whole report from Salesforce. (20:51) " And then it's in this folder of like things you should know folder. >> Yeah. Yeah. And it's like and maybe you just have like look I don't even know what you're like I don't even know what qualified or disqualified looks like but here's here's accounts we lost. Here's accounts we won. You figure it out >> and then Claude will go say okay well let me learn about owner. (21:09) com and then let me have an understanding about like why they lost. Let's like merge that with the transcripts. It's like okay great. I have now gathered all the context I need. I'm going to ask you questions Kyle. um I think this is the case and you're like well that's not really true this changed this changed and you could talk to it and then >> and this is mostly when you're in plan mode like just to go >> no this is this is the tool that I built that but but it it's a perfect example of what claude code can do because I've (21:36) set it to be that claude is prompting you not the other way around >> um and so it's like okay give me this context give me this context and um and then from that point um it will go and it says, "Okay, click these two or three things in Clay and then it will go run 10 agents and send them back to Claude." Send all that context back to Claude automatically. (22:00) >> So it's like, "Okay, this is what Clay did." And then Claude can say, "How did it do based on all the context I already have?" And then Claude can say, "Well, it didn't do this right. It didn't do this right. It took too many steps here. This isn't the right way to." And then it can do it again. (22:18) And so you have this loop that can happen without, you know, go off and have a sandwich, Kyle. Um or a salad because I know you're you're a health nut. Um but uh but like that that type of loop means because it has your context, it can make judgments and it can improve itself. And so this is why the Claude could era to me is about um uh making autonomous judgments within very very narrow lanes. (22:50) Um and so this is why like in my lens it's like I a campaign is a unit is a lane is like sort of a unit of um building that I want and every time I build a campaign all of those primitives because I if you say a fancy word people love fancy words. So primitive sounds like a real fancy word. Um, so all of those primitives of all the campaigns, every time I improve the concept of the campaign, it gets better for the next campaign. (23:15) So it's like >> going and writing that back to the skill or >> the local repo, right? So it's like or the folder. The repo repo is a word that engineers get paid $500,000 a year. Regular people call folder. The only difference between a regular person engineer is and $500,000 a year is the word repo. So it's it's just a folder. (23:35) People call it >> that might actually be true now that we all have cloud code. >> Yeah. Yeah. Exactly. It's like uh there's the there's an old joke which is like um uh like the difference between a great engineer and like a bad engineer is like knowing what questions to ask on Stack Overflow or something and it's like it's like kind of true. Um yeah. (23:54) So this is >> so the cloud code era. So campaign is a unit of building. The cloud code era is about like recursive improvements. more autonomy and what anything else that like defines anything. >> Yeah. And and this is why you know you sort of ask what is a CR of the future? Well, if you were to understand the task of maybe an SDR or something or even you know we talked about this um uh before the call, but like even deal review, right? Like that's a task that you probably have a heristic that you as a human you're like look these are the 40 (24:28) things that people do wrong like very consistently and so and every day what you do is you like go into gong you like ask for the transit adio or whatever you're using momentum um and you say okay great do x y or z you look at that and the the your context on that particular task like isn't crazy you're like these are the standard things that I look for and you just and if you could do it every day >> um you know you might have better pipeline or whatever you you could you could offload that task using a tool (25:00) like cloud code because it can connect into your systems you build the context that you want you say pull this information use this skill evaluate according to my rubric and then when you're done push to an email or push to some other sort of tool and and by the way if it fails if it failed in the sort clay era, you'd have to go back like what did I do in the table? What is it? And you'd have to like muck with the user experience. (25:26) You got to click a bunch of things and like like clay is a beautiful tool, but it just is not designed to do it like this. Um, but with cloud code, you could basically say everything is totally screwing up. Here's the 10 things that it's doing wrong. Can you go rerun these 10 things and check to see if it's doing right according to my rubric? >> Which is a crazy thing to be able to talk and have it do those things. (25:48) and cloud code can >> just explain for folks like what is it doing like uh I think it's important for people to understand sort of like what are the units of action that's happening because you're like cloud code just does this thing and it seems like this m weird magic box but but just explain what's actually happening under the hood >> yeah and actually a good way to talk about this is uh the new claude co-work which is available on the $100 and $200 a month plans Because what Claude is doing is or sorry what Anthropic is (26:22) doing. Enthropic is the company Claus. Um what Anthropic is doing is that they're saying the world will look more like people who use cloud code but not in cloud code. So they're trying to like bridge these two worlds of like you just can go into chat and it has all the power of cloud code but you you as a user won't know the difference eventually. (26:46) And that's kind of what co-work is intended to do. Um, and so like for example, one of the things that it that co-work can do and we'll we'll sort of go into a deeper thing about how cloud code works, but um and co-work is basically access to a lot of cloud code like things in a in just using the desktop version of the claude chat app. (27:07) So, it's the desktop app in Mac, but it's basically cloud code because normally you you access cloud code in your terminal and we can fire up a terminal and show people how to like install it and whatever, but this is like a more friendly interface to cloud code because the terminal takes some getting used to. It's like a CLI. (27:28) >> Not quite, but it's getting there is my point. You can see these worlds merging. There's a lot like it can't write code. So, which is like actually kind of important to this >> co-work can't. >> Uh, no, no, no. It's like sub agents, professional outputs, longunning tasks. Like I don't think it can write code. (27:45) I mean, this was released at 5:00 p.m. yesterday according to win. So, it's like I haven't I haven't played with it, but everything I've read is like it can't actually write code. >> Um, >> so but but let's talk about some of the things that it can do that are available in cloud code and then we'll talk about what cloud code can do now that co-work can't. (28:05) And I think eventually they will merge. Um, so creating a plan, this is really important, right? Sometimes you have a task, right? And everything in the past was just a prompt, but now there's like kind of these two concepts like plan and do. And um, in plan mode, what it can do is basically says, okay, I I need to this is a complex task that you've asked me. (28:28) I need to go figure out all of the components of the complex task and break them out into subtask and create a you know generally these are like one to two page docs that are like here are all the here's the 78 things I'm going to do and the nice thing about this is they have these um like subtask or taskbased agent. (28:49) So it says great I can go send off basically you could think about this as like another chatbucht window another cloud window that can go do this other thing and when it's done bring it back to me right and so there's there's these other pieces that it can go do autonomously and this is like kind of invisible to you >> but it just means that it can do more things um yeah >> and so that's really really helpful because now what what would take you five different chats to do Claude can do it in this sort of plan mode and then deploy those, you know, you could call (29:20) them chats or just independent agents if you want, sub agents, yeah, is the right is the right word. Um, and then bring that back to the main agent that coordinates all of that, right? So you you have this like kind of army of tiny little chatbts that are off and can do things for you >> and are connected to more things and can run these local commands these like bash commands that can do things and actually like take make work happen. (29:47) >> Yeah. actions like search search the web you know and we haven't talked about this but cloud code has a Chrome extension too that can literally open up a browser window take basically what it's doing is taking a screenshot every time and loading it back into cloud and it's like where do I click now where do I click now where do I click now and so you can imagine that if you you're like I wanted to go shop on Whole Foods and I wanted to go to XY or Z it can go take screenshots and make those and this is a (30:14) silly example but um or you know load a Salesforce report while you're logged in. There's a better way to do that, of course, but but just to give you a concept that it has the notion of >> clickbased work too that it can go execute on your behalf. >> Still a little bit work in progress, but >> Oh, totally. Yeah. It's not there yet. (30:31) I mean, >> yeah. And and so I I think the important concept here for people to understand because one of the things that was like a little tricky for me is trying to be like wait so if I'm building an agent does that mean I'm coding an app and then I'm co I'm like building myself other apps that this one app can can click into? And that made it seem scarier and bigger. (30:59) And I think when I like tried a couple projects, I think the easiest way to think about it is like cloud code is basically an agent. So like cloud code in your terminal is the cloud code uh product was supposed to be like a a place to go help you write code. And then a whole bunch of people were like, "Oh, like you can sort of do anything. (31:18) You can just tell it to do random stuff and it will go figure out how to do these non-coding tasks." And so you can follow if you want if you want people that like h have gone down this path. Alex Finn FN or Peter Yang are like good YouTube uh follows of um that that are like in this in between zone of technical people that are using cloud code to build nontechnical solutions and like building stuff for themselves. (31:51) And so like cloud code you could think of you like this is your master agent. I can just like give this master agent a bunch of instructions. I can talk to it in a really unstructured manner and it knows how to use plan mode and think through a complex task and then build these sub agents uh to go like spin off and do other work. (32:11) And so >> then and like skills are like a thing that claude code as your like master agent could go do. And I know I'm now >> like bastardizing the use of the word agent and if like engineers listen to this they'll be like that's not what it is. >> Yeah. >> And I and I but I think conceptually especially for my audience the CRO crowd just think of cloud code as your agent and like you can just speak things in and it will go do things and the method of it doing things is either running and writing code to like break down a task. (32:45) So it could be running code to analyze data or running code to move a document or running code to build a file in your folder that then it can reference later >> and then eventually and what we'll talk about maybe right next or or or if we've got more stuff on this like uh setup building tasks which are basically like these sub agents or tools you want to give to your master cloud agent. (33:12) So I think that's my my non-technical guy version of the trying to explain it even though I know I'm like now >> dis I'm disappointing many anybody who's >> well I mean >> well well I mean the best way for me to talk about this is like in a client deliverable and the the best like unit is to think about this as a spreadsheet >> and because when when I generate campaigns I I generate a spreadsheet and in that spreadsheet There are deterministic things like email. (33:44) So I'll just use a tool to go get email, right? There's like nothing nothing earthshattering there, >> but but I may want to write a message, right? And like oof boy, a message is a hard thing to write programmatically, right? And and so, you know, in in the way that it looks like today, it's like, well, I know your title and I know your company, so I have all the personalization I need to write the worst message I could ever receive. (34:08) But but but imagine if that row had a bunch of context um not just about you but about the situation that you were in and um and in this case like that row like I have a company that I work for a lot of companies that do in the in the healthcare space and there's a lot of public healthcare data and so when I say okay I want anyone that meets this criteria well it can query uh a tool called Mimi data labs which I' love, which is just like a a database of all the public healthcare information. (34:41) It can pull all the doctors that have x, y, or z challenges. Um, you know, that maybe they're they don't have certification or whatever. And then it can say, okay, great. I've looked at a hundred of these and based on your value prop, they fit in these five buckets, right? And that's wild to think about, right? is that it can and here's a here's another example of like kind of you could think about what the value of this I had an opinion I was like okay well I think that negative Google reviews are a good way to go figure out what we (35:17) should p pitch them basically what which are they a good fit for what we do and if so which of our value props are they a good fit for so I pulled like some ungodly number of Google reviews like 200,000 Google reviews and Claude downloaded them all locally. And by the way, think about how you do this in the pre-World. (35:37) You just what are you going to paste those into JGBT like Jaggbt can't even probably access all the Google reviews, right? For whatever reason. >> So, I had it call an API and don't worry about that. I pulled all that information locally and then it wrote code to analyze because the reviews are just they wouldn't fit in any context window. It's too big. (35:55) and they would say, "Well, we looked for we we fed a little bit into the context window and we looked for these keywords and it turns out that only in 2% of cases are there any good, valuable, useful things in the negative reviews for this problem." And it's like, >> I would have never been able to do that before because you couldn't get access to the data. (36:15) You couldn't have a way to crunch it. It didn't have and basically every time it makes a choice, Kyle, it takes my context into mine. So, it's like, "Oh, okay. Well, this is a negative view." and it says I left hungry. It's like, okay, well, how does that relate to my product? So, we probably don't want the word hungry, you know, and it's making those decisions when it's writing the code. (36:35) It's like, okay, great. These are the keywords. And so, because it has your judgment and it knows what you're trying to do, it can take many more steps on your behalf doing things. And instead of it going off, you know, way far left field, which we've all had that happen at chatbt, it's like, nope, that's not what I'm doing here. (36:55) And that's kind of the benefit of of cloud code safe. >> So I want to go back to this notion of the CRO of the future. And so I think you said something interesting. You need to be able to see tasks and then eventually like translate that into agents or or skills. And so just like say more about how you think a CRO so now you have this new sort of magic set of capabilities in this super agent known as clock code. (37:29) >> Um so what does a CRO need to know about that and what action should they take to figure out like how to take advantage of this skill set for their this capability for their team? >> Yeah. So if you think about the way we we built jobs for people, not for robots. And so the way in which a job description is written is what is a unit of work that a human can do. (37:54) >> Um and we're not writing jobs for agents yet. We haven't created a I'd like to hire an agent to do X, Y, or Z. And the one of the reasons we aren't doing that is we actually don't know what they are capable of. Like most people don't really understand what they can do and can't do. (38:11) And so it becomes a really hard thing. It's like, okay, well, can an AI agent call my customers? Like, you probably don't want it to do that. Like, could it do that? Like, yeah, sure. It could probably make phone calls and it could like um but that is both capability and judgment together, right? But to be able to write that job description, you can't just say, "Hey, Kyle, why don't you send me over your SDR job description? I'll just use that. (38:33) I'll make some tweaks and post it." um because all of the capabilities are sort of brand new and every six months or so they make some big leap. And so this is why it's important for you to know what your people are doing and at least the capabilities of those tools because it's your job to extract the tasks out of your team that are perfect for robots >> and automate those. (38:57) And so you need to be able to understand at the individual person level what are you doing? What are you spending your time of? And the nice thing is these two things blend together because imagine a world where Kyle you say, "Okay, I've spent time with you. I kind of understand what you're doing." Um, and I also know Cloud Code. (39:17) So you could say, "Hey, um, Jordan, why don't you record your screen all day and just send me the recording?" Well, you could use Cloud Code to even help you figure out what you can automate. So this is why these two things go together is like now because you have lived in the weeds and you sort of understand what they're doing and you played with cloud code to help say how can I automate some of what the team is doing. (39:38) >> Um then you could also say okay well because I know these two things this is a virtuous loop. >> You can actually use the tools to get better at helping your team improve and that just like skyrockets productivity um because you're systematically pulling out both the tasks that take up the most amount of time and that this master agent is capable of doing. (40:02) And knowing the intersection of those two things is not easy. And and every time one of the other mental models that I've been sharing with people is like once you spend the time to extract that task and I feel like to figure out what an agent can do, you want to go down to like the smallest unit unit possible of that work. (40:27) Like what is the prime number cannot be divided by anything else. >> Yeah. >> And and have an agent do that thing. So, it's not like, oh, do all of the do all of the data manipulation for a BDR. That's too like broad. But you can build one agent to do their pre-all prep or like the the the lead enrichment, then this a different one for scoring, then a different one to prepare their opener, and then their hypothesis need. (40:57) And it can you can break these things down, but once you build that thing, it's like you have unlimited effort and unlimited uh supply of that job now. And so um if you can figure out a way to break down and be like, okay, you know, like one of the jobs that my BDRs do is they look through this report and they figure out who fits this sort of criteria and then they like pull them into another thing and do it. Okay. (41:26) Well, now you can have an agent do that same job for you and you could get unlimited supply of that thing and so do it across every single record in your entire >> TAM. And and I find like that's the >> you have to go down to this really small scale to then like scale that task now infinitely and you just go piece by piece through your revenue function and you continue to to to knock down those those barriers. (41:53) We ran a pilot last week. I won't give away too much on this because it's a pretty nice competitive advantage, but we we ran a pilot last week to uh better prepare reps to make calls and reduce the amount of time in between calls. And this pilot group made 85% more calls and produced 85% more opportunities than than their baseline >> because there was like a couple tasks and we've got this like >> super sick GTMAI lead and a really good bisops team and the the these two guys of those guys were here sitting like right next to the to the XTRS the four (42:29) XTRS who were in this pilot group >> and and it's just like okay we there's this task that BDRs were doing. And now we've like figured out a way to fully do that with an agent. And now we've scaled that uh infinitely across every single across every single uh customer that's in our um that's in our database basically. (42:57) And and so I I feel like that is the different that is like the different mentality that you need to have as um as a CRO in this world because the companies who can figure that out like okay this was two weeks of work and we're rolling this to every BDR uh next week as soon as we've like finished the enablement stuff. (43:22) there's a potential that like our our volume per BDR goes up like 50 to 70 to 80%. Like with three weeks of work, it's just like the the outcomes are crazy. And I think the CRO just needs to understand how to build the team around him and point people to the opportunities and understand the art of the possible. >> Yeah. (43:48) Yeah. I It's not just the art of the possible. I think the other things is really defining the most leverage atomic task >> and that's really really key which is that because your job is actually you're like so what I do is I go here and then I determine if they're a good fit. You're like well what does that mean? It's like well a good fit mean X Y or Z. (44:09) And it's like okay well when you said Z what do you do? It's like, okay, well, I do X, Y, or Z and and you know, >> look on this website and then I like do this other thing. >> Yeah. >> Yeah. Or or like I the first thing I do is I go and look to see the three nearest customers, right? And that's a very easy thing for AI to do. (44:29) It's a hard thing if you say, well, what I do is uh when I'm talking to the customer, I get a sense of their tone and then I determine how if their tone is such that I should ask for their credit card. It's like, okay, well, AI is not going to be able to do that. So, it's like, don't have AI do that. (44:47) Like, tone analysis is like something that, you know, the tools don't have the capability to do, but everything else around that. >> Um, and you have to be able to divide these things into like as as deterministic choices as possible and the agent will do really really well with that. And it can take nondeterministic data, it can take the website, whatever, right? Um, but that's I think the CR of the future is really going to be able to need to say not only do I understand the sheer number of tasks that are happening in my team, I have categorized those tasks (45:21) based on time suck and agent capability because I know agent capability. Yeah. Value. Exactly. Yeah. So time suck is the inverse of value here which is like just I'm assuming you're removing time from people. Um, but if you can do that, then you can say, I know the tool can do that and you have a team around you that help. (45:40) And the training piece you just kind of glossed over, but it's like you have you're going to have to start using the output of these tools. And if you don't have an understanding what the the actual end user of these things, you can't improve it. And this is like a death nail for a system because the second this happens all the time, right? It's like when when your ground your your frontline team starts to distrust the data like you've lost, right? And if they're not part of the process and so they are the the the CR of the future will be able to build these loops that (46:14) understand both agent capability and also the um the leverage that they can get from their team. Yeah, that I think is a great call to action for CRO's because this is a question I get all the time. It's like, well, like dude, like I can't I don't want to go as deep as you or like I don't have the time. (46:34) I hear that all the time and and I don't have a great answer to be like, well, this is like the minimum effective dosage and I think the minimum effective dosage and now you know we talked about uh name or like uh name dropping the word repo. This is the product management equivalent. You have to develop some taste >> and uh you have to develop enough taste and intuition for what models can and can't do that you can properly understand how to like orchestrate resources and and get an idea. (47:07) It's like okay like an agent could probably do that really well. It's repeatable. There's a pattern. I have examples to feed it that it's like it doesn't need to talk to 10 tools. needs to talk to two or three tools like that's probably a good that's probably a good um candidate and I do think like my my my stance on this has definitely evolved. (47:31) I think you just need expertise now. You know, like I see I've seen how rapidly we have advanced since having dedicated applied AI people in our go to market organization and you need somebody on the team that can do what you do which is like translate all of these things to to actual solutions because I I think like >> now things are so technical >> um that without it you can really flounder unless >> Yeah. I'm I'm just I'm with you here. (48:03) And what I what I'll tell my clients is that my job is to fire myself. I'm trying to get the repo going for you. I'm trying to get the folder with all your context. Um we're going to do it one or two or three times, then you're going to start doing it. And I have um I've got a client and um this this person is amazing and she's just like so on top of it. (48:24) She's like, "Jordan, I wrote the 47 steps that we have to take to launch a campaign." I was like, "God bless you." And I just like dropped that into uh to Claude and I said, "Every time we launch a campaign, we should do these 47 steps." And Claude's like, "Got it. I'll commit that to memory." >> Yeah. >> And that becomes a skill or that's just goes into your markdown. (48:43) >> This is just a markdown file. It's like it's just like, so it's like, "Hey, so every time Claude boots up, I say I'm trying to run a campaign." It's like, "Okay, great. I got to pull in all of this intelligence um uh on how to do this, all the the check boxes, etc., and go run them. (48:59) " So essentially becomes a plan. No, in this case a human made it and by the way now this person is in cloud code and she and she'll come to me and you know I don't know two weeks ago she came to me said can you make this change I said nope but you can make this change >> and so like you have access to repo whenever I work I commit it to the cloud you pull it down from GitHub and if you get some feedback from leadership you just say change this copy it writes code it updates all of those things and to do this in clay you'd have to be like (49:26) change the prompt but claude can not only do it. It knows what you're trying to do so it can go check it, >> right? >> And so you ask kind of, you know, it's funny that you say, "Oh, Sierra, I was like, I don't want to get that deep." I'm like, >> "I'm sorry. You if you want a job, like that's how I feel about it is like >> if you would like a job, you must understand these tools because um all of your organization could be rewritten with these tools. (49:53) And that doesn't mean it could be changed, but but certainly the whole playbook could be rewritten. And if you're not able to deliver an 80% improvement in a quarter, like there's someone that's willing to take your seat, though. >> Two weeks. >> Yeah. Well, I mean, but I'm I'm setting a reasonable bar so people don't get But you know, how long have you been doing this for? >> It's an example. (50:12) >> Yeah. >> Yeah. You've been doing this for a long time. And by the way, your two weeks maybe a year ago was a quarter was two quarters. And that's not just a tool capability. That is a your understanding of the tool capabilities, understanding training and greasing the wheels. So, not only are you getting better and improving, you're get you're getting better at improving improving, which is like a crazy thing to think about. (50:35) >> Yeah. Yeah. Yeah. and and like I think that it's the competitive pressure that's there because if you are competing with a company that that is building an actual like AI native GTM that is that has agents doing all of this work that humans used to do and it's just like so much more efficient you're going to lose and and that lesson is is is tough but okay so I want to move to like some more practical stuff to to teach people about like all right you, Kyle and Jordan, you have officially convinced me I'm going to go (51:10) like set up cloud code and I'm going to try to build something and it doesn't matter what it is. And I would encourage people to pick something like really small and predefined and only connects to like one system and just like get some practice reps and learn how to like deal with the terminal because you can't like can't even like copy the you can't even like highlight what you're typing. (51:30) This is like a it's just like a clunky >> goofy it's a goofy thing. Yeah, it's like >> it's a goofy interface. >> But I think the two So we talked a lot about okay, Claude is like writing code and executing things and it's building files and and building skills which are like things that are going to happen over and over in a defined way. (51:50) But just explain like uh to be successful two of the most important inputs are context and uh integration. So access to other things. And so maybe just explain what context is and why it matters so much and then we can talk about like how to build useful context. >> Yeah. And and the the context is really deeply tied into the thing that you are trying to do. (52:16) >> And so in my case, all I'm selling is the ability to to invent a campaign in your head and by the end of the day have everything ready for that campaign. all the copy, all the let's zoom out from that to like a one level higher of abstraction so that it's like not as campaign centric. >> We can refer back to it, but like cuz people would want to use Claude to help them with like forecasting and deal analysis like there's a bunch of other things. (52:49) So let's just like maybe set a broader context foundation. >> Well, yeah. So in that case what you would do the generic steps that you would take are >> like what is context first just explain that. >> Um yeah basically context and any given problem that you're trying to solve are very closely related and this is everything if you sat someone down and said your job is to do deal analysis and you said this is absolutely everything you need to know to be able to do that right that's like context for that task. (53:20) And so, and this is really much harder than you think because if I ask you a question like Kyle, like how do you be a good parent? Like, and how do you feel? That's like that that question you just couldn't I could ask you until you're blew in the face that you you would always remember new things about that. (53:35) You're like, "Oh, yeah. Yeah. Yeah. Don't let them drink spoiled milk. I forgot. I didn't I didn't specify that, right?" Like, that's a much harder thing to do. But if you said um like what's the best way to um uh you know to to read a revenue book or something, right? That's like this is like a lot easier. (53:53) It's like well first you skim the end, you go backwards and blah blah. And that's something that you could legitimately provide an agent context on because this the sheer amount of information that you need to be good at that that well- definfined thing is low. >> Um >> and so this is what you're trying to do. You're trying to find a unit of work that isn't doesn't take like all of everything that you are to do. (54:15) So then what you're trying to do is >> let's use like close one analysis. >> So to do close one analysis well >> you can't just like have the calls and be able to do it. >> Yeah. So, so, um, uh, and you're going to have to fill in some of my context here because I don't do this often, but, um, what I would do in this case is pull all of the transcripts of closed, lost, closed one, and pull two CSVs. (54:40) And this is why it's like important to structure this context. So, Claude has it doesn't have to go do it for you. It's like this is a CSV of all the accounts that are closed, lost. This is a CSV of all the accounts that are closed, one, an Excel file, if you will. Um uh and then here are all of the transcripts just for closed lost and just for closed one. (55:00) And there's some join key between them so that Claude can connect it up some Salesforce ID or whatever. Right? This is very helpful. And you've done and by the way don't get crazy about this. You can have Claude do just that for you. But it's important to think about that and saying, "Okay, great. Now I have closed one, close lost. (55:18) I have the transcripts and uh and those transcripts also have rich information." So it has the the name of the person that said it. Uh >> their title and and like a good thing for example, this is why building context is important. One thing I loaded all the transcripts for a client in and I have a I have a gong prompt that if you're trying to get stuff out of Gong I can give you that will do all this in cloud code and clay and but it grabbed all of the names and I said go look at all of the names and all the transcripts (55:46) and identify my people versus the customers. So if you see them more than three or four times, label them as owner.com staff. >> And so that's that's a thing that you would do to build context, right? So now the model knows, okay, well, if I see Kyle Norton and Kyle Norton talks about like blah blah blah, that's not a customer. (56:07) So remove his, you can include it, but like remove the analysis about what he said because he's on my team. And so this is why you need to break this up into like you need to just say everything that's in your head and you can say it to Claude too. And so you say >> and another example like is like what's your sales methodology? >> So you've got all this unstructured all this unstructured stuff. (56:29) It's like my sales methodology is challenger force management but I don't like these parts of force. I actually use these parts of GAP instead and I use medic as whatever and blah blah blah blah. you just like, okay, that's another important piece of context. If you if you it's like if you were training a person to do it. (56:47) You have an intern. The intern has infinite amount of hours and they're going to do this task. They're going to read every single transcript and they're going to categorize things like how would you teach this intern who doesn't know anything about your business enough to go do this task? Well, they need to understand >> your your ICP and your positioning. (57:05) Okay. Well, you have documents for those. So just like upload those as >> as files into this folder. >> And and the nice thing too is you can reverse you can reverse this so you have to do less mental work. What you can say is um and ideally what you do is you just record yourself doing this like you know get on get on your own Zoom with just you and record yourself and say everything out loud. (57:28) I'm making this choice for this reason. I'm making this choice for this reason. Here is why X Y or Z. Um, and then you can say here, I did this manually for 20 rows. You go run it and then test against these 20 and ask me questions. So, you can have Claude try to close your own internal. You're like, I forgot. Well, that doesn't apply because um Jessica is an early stage SDR and so she's ramping and so we wouldn't do blah blah blah whatever, right? >> And so, >> so that's really important. (58:00) And then you can just work just on testing that context over and over again. And then you can say, "Okay, great. Now reliably, this thing will get, you know, 50 out of 50, right?" And now it's ready. >> Um, and that's the kind of thing. And by the way, you go to sleep and you wake up in the morning and cloud can pick up right where you left off. (58:18) >> And that that's not true. And it doesn't matter how much because it's remember it's managing the context. It's just trying to organize the context around the problem that you're trying to solve. And that's really, really, really key because the the more you can compact that context just to the most useful things, both compact and divide it, so it's like only calling the context that it needs, it gets really really good at doing what you want. (58:45) >> Yeah. And one of the skills that I um saw on X and then put into my Claude instance is um this idea of like recursive learning. Like when you learn a thing, then like write that back into my like core principles. Like when when you >> Yeah. when we when you learn something from me about like a structured way I do things, write that into I've got like a principles markdown file. (59:16) So there's like owner there there's >> my decision-m principles and then there's a bunch of owner principles in the in there as well. Our company values, some of our operating methodology and one of the things to know about context is that you can build it up over time that then uh you can use across a bunch of other tools. (59:35) So like you you you build and I don't this is outside of my depth like should this a lot of this context list lives in this like mastercloud markdown but some of it lives in like these other markdown files in in different folders and I think mine is actually a bit of a mess >> but um >> it but like it doesn't matter. (59:54) That's the crazy thing sometimes. >> Yeah. Yeah. >> Is CL just figures it out. you can over time just like keep building onto the context into the context of your library of your folders. >> Yeah. >> And and so then eventually it can understand like I'm I'm trying to build >> like a something to help with decision- making at scale. (1:00:19) So I don't want to go to as many meetings. I'm in too many meetings and a bunch of the meetings like 80% of the meetings I agree with the decisions being made and I probably didn't need to be there but 20% of the time I'm like well man I'm glad I'm here because this would have gone a direction that's probably not good. >> That's my job as an executive is to like make sure that that doesn't happen. (1:00:37) >> But if I can go to 80% fewer meetings because there's I have some other tool. And so what I've been doing is I um I have a bunch of decision-m heristics that I've written down and then I had cla I want to build out so I want to build on top of this document. This is going to be our like our decision-making principles doc. go read. (1:01:00) And so I mcped into notion where all these um >> um call transcripts are and I'm like go go read all of these call transcripts and tell me about decision-m principles I am using that I have not yet documented >> and it caught a bunch of really interesting stuff and these are now the principles that it uses >> and it works pretty well but it actually like it like over relies on the principles in this document uh compared to like just general good like decision- making. (1:01:32) But yeah, I mean this is >> just another way another way that you might even think about this and this is why it's really important to use the tools because you might say here are 10 meetings where I disagreed vehemently with the pro with the thing at hand. And by the way, all of the context for those decisions came from these other meetings >> or whatever, right? So you can start documents >> Yeah. (1:01:57) So, it's like you can sort of map that out, which is like look, if it's any of these topics, always escalate to me. These topics are too complex. You're not going to have the context, right? If it's any of these topics, like here are my triedand-true, you know, frameworks that I use. Um, but what I want you to do is I like these are the hundred meetings that I had where in in 80 of these meetings, I said I'm I have no opinion. (1:02:20) 20 of these create a test case against these against my heristic frameworks. go make go make independent Kyle choices and then go see if they matched up with real Kyle choices and then tell me what's wrong >> and it's like well here's Y X Y or Z and you can say okay great this is how I close the gap now that's a and the beautiful thing about this type of task is that you might realize Kyle that this is foolhardy because you're like I want to outsource my judgment and you're like well that's a big thing to outsource but but it might be possible to say I just (1:02:49) want to know with some confidence If someone submits a a meeting, like do I need to attend this meeting? And it might even be send an email that's like if we are going to talk about any of these topics, I'll join. If it's not about these topics, like I don't need to be there. >> Yeah. (1:03:06) My my goal is actually not to outsource my judgment, but it's to not go to those meetings, get us have my like it's called Kai, my Slack handle's Kai dollar sign. And so this is K AI dollar sign is my AI chief of staff that I'm building. And so Kai's job is one of one of the the skills is to re is to take the transcript, summarize it into the context, the decisions that were made >> and like who what were the other options for that decisions and and that that decision and like what did we come to and then sort of the action items >> and so one job of one of those skills is (1:03:46) to pull out all of the action items that I should be aware of. So, if there's an action item assigned to somebody on my team, I need to like have that in a in one and it writes it into this notion page of like stuff I'm monitoring >> and it's like, okay, you know, Jordan, you're on my team. (1:04:04) You said you were going to do this thing and I just needed to to to be able to like see that you need to do that thing and and be like, hey, Jordan, like you you said you would do that and it's not moving. >> This is how this would go, by the way. Yeah. I would commit to do something and be like, you said you would do that thing and I'm using AI to check on you. (1:04:20) I was like, "Don't use my tools against me." >> Yeah. And then eventually Kai would just nudge you and be like, "Hey, Jordan said he would do this thing." the most demeaning >> because I built so there's a slack bot now in uh in our Slack which is the Kaidal Assign Slackbot which is which is basically my way >> to reach >> take my AI chief of staff and reach it into into Slack to like do things to like read messages respond and so so what I want is I want what were the decisions made so I can read so instead of going to five hours meetings. I can (1:04:59) skim five hours of meeting trans meeting summaries with decisions in 20 minutes and be like, "Cool, cool, cool, cool, cool." Oh, like that one's no bueno. like I want to go talk to that person and like explain you know a different viewpoint because I I find that um you know my boss and I will agree on 80 90% of stuff but then the stuff we disagree on like we want to be in that meeting to to like share the other person's viewpoint to like you know run it to ground or me and my like VP of ops we agree on like most stuff but like we (1:05:36) he wants to check me when I'm going rogue and doing like, you know, >> my thing and I want to make sure that, you know, I've I've I've supplied him with the right insight. And so, so there's all these people's there's all these people that like don't need to be in the same meetings all the time, but do need this ambient awareness of the things that they they care about and have opinions on. (1:06:01) And so like there the the uh my vision for this thing is I get a summary of all the meetings, all the action items and and important decisions and then it tags me in the ones that are most likely for me to want to pay attention to and then I'm I'm getting like massive scale on my judgment. And this is also why understanding context is really helpful because you you talked about you talked about something that if you think about the way in which you would deploy what you're doing to the team, you are building something yourself to be able (1:06:33) to um remove to be able to like deploy as much of your your own internal context as possible. And the only thing that you want to do is like where the circles don't overlap, I just want to work in that unover overlapping part. Right. >> Yeah. Exactly. >> But the other thing that you're doing in doing that is that you're understanding the edge of what's capable. (1:06:57) And then what you're doing is you're you have the ability to then go inside your organization and start to saying I want everyone's job to look like this. If the job is either that you're doing something that you don't need to in your case it's meetings and judgment but in other case it might be actually like >> literal work you know not meeting it's like someone's had to click on something or or and it's like okay great so you know how to do the hardest piece of this and that means that if you understand all the task of your team you can start (1:07:26) to say I'm going to enable you to either it might be at your job remove your thing that only exists at your job so this problem that you have is like maybe it exists at the execut Ive leadership but it's not it doesn't exist all the way down right like >> um but they have their own version of that and then you as a co need to determine do I enable my SDR to learn cloud code and that answer is like maybe no um uh but uh there are some things that we need to implement at the company level to make their jobs easier and to (1:07:57) remove the task but there are are going to be things that they do in their daily lives that they probably should have their own tools to do for whatever reason. Um, and so that has compound interest because you teach the organization, you do it, you teach the organization how to do it. And most importantly from an organizational perspective, you can remove all those things that could be orchestrated at a a much better level by building your own tools. (1:08:25) You now essentially have a an engineering department for any problem, which is a wild way to think about it. Yeah, it is just a different it is just like a different way to see the world and and I think I don't know if you'd be able to really understand it without getting hands on the tools and sort of experiencing that one like little win. (1:08:53) And you know like I vibe coded a couple things. I tried like replet and bolt. I don't actually think I built anything in lovable and it just like never got and it was never enough. >> Yeah, I know. >> I spent I spent two hours and it's like, "Oh, we can't do that." And I was like, "Son of a bitch." >> Yeah. >> Why would you not tell me that the beginning? >> It was really exciting and I had a lot of fun and I felt like I learned. (1:09:16) But like I never shipped a thing that was actually useful. >> But then >> in Cloud Code, especially over the break, >> I I had it like >> checking my email and like responding to emails. Cloud code can finish things. >> Yeah. It can actually like take it and and and do the thing and you're like, wow. >> Okay. (1:09:37) Like what else can this like what and my brain was just like I don't we could do that. We could do this. And so yes, >> it's it's a the best way to think about this is it is an alien intelligence that no one has built a great translator for yet. And so you have to build your own. So, and the only way you can do it and and the the alien will have as many conversations with you as possible and it will try to explain things to you as possible. (1:10:01) >> And so, it's not like another, you know, I always sort of joke um it's like >> you could learn Apollo like one could learn Apollo like >> but this thing is infinite. There's no there's no end to it. It's not like one day I wake up like I'm done. I know I know I now know all that I know about AI and I understand everything that it can do and I understand how that relates 100% to me. (1:10:25) >> And so this is why it's like fundamentally different than other technology shifts because not only is it sort of infinite and also growing at a faster pace which is like a little scary. Uh, but also you need to be able to figure out how you can talk to the thing because it's not just a person. Like it's not you can't just talk to it like you would talk a person. (1:10:50) It it it it works in a different way than that. And if you don't do that, well then what you're saying is that like this thing that will swallow the world. It will swallow my job. It will swallow your job. Um uh because you know it's it's coming for us. um you will be much much much better with it, but not if you don't just constantly dance with it. (1:11:12) >> Yeah. Yeah. And I don't know if it's hyperbole to say that like most of our jobs are going to be like building and managing a agents like that feels like >> well AI hype. Well, I mean, >> at the same time, >> yeah, >> I mean, I'll just say this, like I have designed my company around what AI can do autonomously. (1:11:37) So, I'm doing the opposite, which is like usually a company gives you a job and it's like, this is your job. Here's everything that your job entails. >> And I'm like, that sucks. Like, I would rather define my job by what AI can do exceptionally well. And this is what allows me to have leverage in my job is that I can package it around taking the future to you and include in that package only the things that I know that AI can do exceptionally well >> and not the things that it can't. (1:12:08) Um, and so like I told a customer the other day, we built a whole, you know, we took 12 prompts and we did all this enrichment and I was like, ship this manually to Clay because it's just going to be a better workflow for you. You'll be able to edit it. Uh, you'll be able to push to your systems. You have observability. (1:12:29) It's a better tool for this. Cloud code was a much better tool to do the original, write all the prompts, to test them, etc. But now the best place for you to deploy them is in clay >> and so >> yeah just like through the UX so you can see it and because I don't want cloud code cuz I I basically have shipped off my understanding about what it's doing which is a wild thing. (1:12:52) It's just like I don't know it's like so an engineer asked me so like what what framework are you using? I was like what do you mean by that? Like like like are you talking about like a window like um I'm using a double pane framework is what I'm doing for Windows. >> What framework? It's called Whisper Flow. >> Yeah. Yeah. >> That's my framework. I yap and it does. (1:13:12) >> Yeah. Yeah. I what I told him was I was like you check out the repo. You you tell me what thing I'm using. Um, but that's that's the thing though is that you can uh if you have that discernment about what the tool is good and is not good at, you can say cuz I'm just not I'm I don't trust the tool enough to like vibe code and like write to your CRM. (1:13:35) Like I'm not I'm not I'm not a gambling man. You know, it's like oh I'm sorry, you know. I guess I guess what like Jason Lmin like deleted his whole production database because like someone gave him the wrong access token and it's like don't do that like don't if you're an engineer only give me read access. Um and so these are the types of things where it's like okay well because I don't in your case I don't have a whole team that can go validate everything it's it's doing here. (1:14:04) It's like if I develop a net new campaign, brand new, new prospects, I can exclude. I don't have to touch any of your own systems. I'm just structuring data from the world. >> And then it's so much easier to take that and then to inject that output into your workflows. And AI can be amazing at that because I don't have to worry about all the complexities of, you know, like sending an email as me, which, you know, I don't I don't have AI do the things that you're doing, but that's because I have the luxury of designing my job (1:14:32) around what AI can do really, really, really well without worrying about what it can destroy. >> Yeah. Hence, the like artifact of your work is just like a monster spreadsheet. >> Yeah. Yeah. Yeah. It's like here's a monster spreadsheet. like here's the whole campaign and here's how you can create monster spreadsheets like really really really quickly um and it's connected to databases and APIs etc. (1:14:55) But at no point am I like oh I'll just like write all change all your customer records. So I have um my business is about deploy not destroy >> and so the way that the way that I have um done that is to avoid even selling things where destroy can uh uh can can be involved. >> That's smart. Um I want to touch one more topic quickly. (1:15:24) So um where do people start? So like I want to start I want to like learn and sort of like build something for myself. What would you say are like the next steps for a CRO from right now after listening? >> So the first thing I would do is uh confine your ambitions. like just start really really small like and >> and that might be something uh as simple as like here is a spreadsheet of all of my customers. (1:15:57) Can you go search the web on them and tell me what about them that I don't know? I mean it doesn't matter, right? Just something really really really small and just do it in cloud code. And so you should you can if you Google cla bashin install script that's the exact Google result. (1:16:15) Um, you can copy and paste that into the terminal and there's a little thing that said you have to copy and paste echo. It's like just select echo and paste that back in and then type the word claude. C l a u d. And those are the only three steps. And then you're in claude code. Um, and >> and what happens when you you paste that first bash command? >> It goes and talks to the web and installs something locally and it does all the other. (1:16:40) And by the way, it might open >> setting up cloud code in your local files. >> Yes, exactly. And and by the way, it might ask you might see an installer pop up that is like Xcode tools and you'll hit yes to that. And it's like the other tools that you need, Python libraries and that kind of stuff. Um, and then the actually the last thing is like create a new folder and type the the CD as in it's change directory one you know cd and then space and then drag and drop that new folder into the terminal and then hit enter and then type claude and (1:17:12) from that moment out claude can do everything. So you can ask it to do things. You can say, "Here's what I would want to do. Um, research your own capabilities and tell me how you could do this and and you can say like here's like what I've done is I've recorded my full day and just talked about it and I put the whole recording and the transcript locally. (1:17:35) Can you help me tell me like what Claude could do for me?" >> And when you say record your whole day, it's not it it can't watch your screen and into it like you have to you have to narrate your whole day. just to like start the salesource report. >> Yeah. Just literally start a zoom in the background because it's just the transcript. (1:17:55) >> Yeah. Yeah. I mean it can um claude code could write things. Gemini can do this too actually. It can write things to extract the screens and and to take the audio and it will call whisp. It'll call OpenAI's transcript thing. And so Cloud Code could do all of that. But this is why it's good to have an understanding of what the tools are capable of because it's like just use Zoom plus the transcript. (1:18:18) Like if Zoom gets the transcript like you just have saved yourself hours and hours and hours of work and then just drop that transcript in and say help me understand what you're capable of and what are the things during the course of my day you could help me with. So like this is recursive intelligence, right? You can ask it what it can do and it can give you ideas and you're going to find that the first ideas are probably big and unmanageable and you'll try them and they'll fail and that'll be okay because it's you're you're not in danger like (1:18:48) you're you know don't ask it to delete all the files on your computer like don't do that. um just like be reasonable, right? Like um and as long as you're sort of reasonable and you say, "Hey, I want to automate this spreadsheet task. Like, can you help me?" And then you play with it and that's how you learn and you'll get some paper cuts along the way, but you generally won't have a a gushing neck wound. (1:19:09) >> Yeah. Let's hope so. >> Yeah. Yeah. 100% I'm not reliable if you have a gushing neck wound. >> And and something you said before is like aim small, miss small. So like >> take on something manageable. Yeah. Take on something manageable. >> Don't wire it up to everything with rewrite access. >> Yeah. >> You know, like you know, because one of one of the other things we didn't touch on is is the importance of um integrations. (1:19:39) And so like >> yeah, >> this is great if you're bringing stuff into cloud code. What most of us want is for cloud code to go out into our digital world and and do stuff. And so, uh, generally what you're going to do is just like be like, "Hey Cloud, I want to set up MCP access for my notion >> and it'll walk you through like Claude will tell you how to go to notion. (1:20:01) com or notion.so integrations and it'll tell you to click this thing and then take the >> the API key and paste it into cloud code and then you'll like give it the right access and it'll just it'll guide you through all these things. Okay, cool. Now I want to set up Now I want you to have access to Salesforce like >> read access to Salesforce. (1:20:23) This starts to be >> like a little sketchy on the info set. >> Just give a CSV. Yeah. Yeah. Oh yeah, that's right, too. Yeah. >> Like probably don't do that, but it could and it would it'd be like, okay, go get the give me your API token. And >> you could also ask another question. Is this good for AI? Is this wise for me to do? Can I get in trouble? >> Is there Well, okay. (1:20:45) thought it and actually >> could end up in the neck wound. >> Yeah. Yeah. Yeah. Yeah. But you can ask Claude that and actually Claude has a feature called security review. So you can do like slash security review or something and it will go check to make sure that you haven't done any like ridiculous security thing and it will go fix the security. (1:21:02) Like I did I'm not going to say the thing I did because probably someone could figure out um but like I did a silly thing um and I was like oh man. And so I had to go fix that silly thing. But I said Claude, did I do a silly thing? And it's like I can confirm that you did a silly thing like that that was bad of you and I was like can you help me undo was like, "Okay, great. Go do these things. (1:21:21) " >> And then I ended >> and you can start with like read access like just, you know, set up like my notion has read, >> right? My notion has like read write >> and because I can like pull in some documents and I'm like I actually want to update this document with this other thing like go do it and it'll just like rewrite the notion page. (1:21:42) it's that can get a little screwy and so maybe don't do that right away until you've like built built some familiarity and you know you like >> get a feel for for the process. So, um I have no idea if people are going to think that this is like their favorite episode and they're like this is awesome. (1:22:00) I learned so much or if you're like or they're going to be like you and Jordan just meandered your way through 90 minutes of nonsense and none of it is helpful. >> Yeah. I I mean I always joke that when I give talks on stage that um there's two groups in the audience. Those people are like I have no clue what just happened and uh like and I need to learn and I have no clue what just happened and I don't care to learn like 100% of the audience is still confused and that's okay. (1:22:29) like you just have to lean into it like and it can help >> and everything's on YouTube you know you can you can start with you can just search like claude code setup for non-technical people and there's a bunch of stuff there >> actually like to even tell you this meta thing there's a Gemini button on every YouTube video and you could say summarize this for me given this context and it'll go do that >> yeah that Gemini button is like an incredible piece of product. (1:22:59) I think I use it all the time. >> Uh well, this was awesome, man. I appreciate you doing it. And uh we didn't talk about co-work as much as as maybe we uh we should have, but that could be the other this is the last thought I'll live leave people with is like >> maybe a bunch of this is just available in co-work and you want to start there instead of the terminal thing. (1:23:19) >> Uh I have only played around with it for like 30 minutes because I couldn't get the workspace to set up on my flight yesterday unfortunately. Yeah, I was losing my mind. Uh, but play with Workspace. Try the terminal thing. Dive into the YouTube. There's a bunch of cool cool stuff about people using cloud code to like manage their personal life and just like explore and and this will the exploration and it'll feel like you're wasting a bunch of time, but you will learn the primitives and sort of the first principles that you need to to (1:23:49) know how to deploy this in your organization. Uh, because I think it is existential for all of us. Yeah, and you can make little fun web apps like I built playbooks.bloopprintgtm.com to like create G uh go to market playbooks for folks 100% vibecoded and so it runs everything in the cloud it runs the whole process and it produces you like a go to market engineering playbook that takes like 20 or 30 minutes but everything is agentically everything the website the design like claude's design skill is really good and (1:24:17) so you just kind of start building things that get more and more impressive. Uh yeah so do it. >> Cool. >> Thanks for having me. >> All right. Hey, thank you for listening to the Revenue Leadership Podcast. If you enjoyed it, don't forget to subscribe and you can find a link in the show notes. (1:24:34) And be sure to leave a fivestar review, share it with your network, and please join me next Wednesday for another great conversation.