284 | How To Use Claude Code To Get More Leads (detailed playbook) with David Yu

0:00David Yu:Hello and welcome to the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business and advance your career. This is Isar, Maitis, your host, and we have an awesome episode today. If you've been listening to the show for a long time, you know that I say that a business can live without marketing, a business can live without operations, a business can work without HR. A business cannot work without clients because then you don't have a business. And in order to have clients, you need leads. In order to have leads, you need to be able to do a lot of tedious things to actually do this correctly.

0:39David Yu:And to be more specific, you don't just want leads, you want the right leads. It's actually relatively easy to get leads, but most of them are going to be junk, which means you're going to spend a lot of time and a lot of money and a lot of resources not getting new clients. And the goal again is getting clients. and to get the right leads, you need to know, first of all, who they are. You need to be able to define your exact ideal client persona or ICP. You need to be able to know what their pain points are. You need to be able to research potential leads and know if they are actually aligning with your ICP.

1:09David Yu:You need to understand how they talk, what they say, what their needs are, what are their pain points, what's going to provide value to them. All these things take time and effort. And it used to be lots of human labor. That's how we did everything. And now you can actually build a system that uses AI to do all the research and all the qualification of leads for you and even help you create personalized communication, at least in the first step, to approach these people. And so now you're getting the right leads. You can do it at scale because it doesn't matter how many people you run through the system.

1:45David Yu:You can run 10 or 10 ,000. it's going to take you the same exact amount of time, zero. That is a very, very attractive thing for any business because again, that's the bloodline of any business. Our guest today, David Yu, has been building automation systems for clients in the last two years or so. And he's an expert on building exactly these kind of things. And he's going to show us today exactly that, how he has used or how he's using cloud code in order to build a funnel that goes through a list of potential random leads and finds the needles in the haystack, the diamonds in the rough, call it whatever phrase you want to use, but finding the ones that have the highest likelihood of actually turning into clients and how to approach them at scale.

2:33David Yu:He is the founder and CEO of Futureman Labs, which is a company that does exactly that, provides AI automation services for other businesses. So so he knows what he's doing. I know this is going to be extremely interesting for all of you. He is really, really good at explaining what he's doing. He has amazing processes and systems. And so I'm really excited to welcome David to the show. David, welcome to Leveraging AI.

3:02Thanks a lot, Sar. I'm really excited about this topic too because I've been getting really good results with the code you know.

3:09David Yu:So we'll jump into it. Yeah, I think that, you know, I totally forgot to mention the fact that it's a cold email system, which I think makes it even more interesting. I think most businesses, especially small businesses, are afraid of cold email outreach because you don't really know how and what. It's kind of like this mystic thing. Like there's the people who know how to do cold outreach and the others won't even try. and once you build a machine that can do this at scale and do it effectively it's a whole new universe that opens up to you of being able to get more clients for sure because i i used to do it like the old-fashioned way where people copy templates and all that stuff and i got zero replies and i thought call me you know didn't work and i think we're really lucky in this internet section where ai can do a lot of heavy lifting for us um so so i'm just gonna show some results first and we'll jump into it.

4:04So this is instantly a cold email software that I'm using. So the past two campaigns that I ran on there actually had 20 % reply rate and 31 % reply rate. And that was really surprising to me because I thought the market reply rate was around no, two to 5%. So yeah, I'm not a cold email expert. I actually just started studying it and actually try to understand how I can use it. to do this effectively. I'm just going to show you the system that I use.

4:36David Yu:Yeah, that's fantastic. And again, I do think these are crazy high. Because if you think about, I think newsletters gets open around 30 to 40%, right? And these are people who actively signed up to a topic they know they want to consume. And I'm talking about open rates, not even response rates. And so those numbers are really, really high. Yeah, it's crazy for me too. So yeah, I made this little presentation with Gemini. Here it goes. I'm going to talk about the different phases. And there are different phases to doing a successful code email campaign. First thing to gather the data, right? And I'm just going to go through quickly.

5:16Maybe some of you already know the sources to get leads. But in case you don't, things like Apollo and Aerscale, these are the two that I use the most often. and based on the niche you can go on gemini or google wherever you like just search the industry and then lead source and then you will come up with the different sources that you can find and for my niche i try to target e-commerce the sources i i tried with the store senses and build with those are two platforms that you can buy leads you can pay for the subscription and if you don't want to keep on subscribing to it and you can just cancel the subscription after you export your leads you can always save money that way um and there they're all also another way where you can try to scrape information or use a third-party scraper to get you the information another thing is called appify appify aggregation of bunch of apis where you can get data programmatically and that works perfectly with things like cloud code on ai agents just because they understand api and you just give it access so if you're targeting like regular more stores this will be perfect because you can store scrape Google Maps and then you can find like local businesses and offer them whenever your services and lastly which is very specific to Cloud Code just because Cloud Code initially was made for just coders but I think it goes way beyond coder now because market can use Cloud Code now and you just tell it what you want to scrape and it will tell you if it's possible or not possible and you can actually run the scraper for you underneath it will write code and then execute the scraper for you so yeah i'll say something

6:58David Yu:that connects two of these dots in most cases so i already have and it's actually really cool to see i have several different similar data sources already connected to claude because of previous things that i've done right so i'm connected to apify i'm connected to a bunch of other tools like this even data for seo like different stuff like that and every now and then i i ask claude to do something and it just goes to the right API. So once I don't ask it, I don't tell it, but it's like, oh, I know this kind of data exists through this tool that you gave me four weeks ago. So I'm going to go there and I'm going to check if the data exists.

7:35David Yu:And if it exists, I'm going to run the API and do stuff like that. So the cool thing about the cloud ecosystem and any, it doesn't have to be cloud, but both David and I use it a lot. It's just really, really good at understanding what are the tools that it has at its fingertips. And it knows how to, and sometimes like, why are you going to this API? Like, oh, they have this thing and then they can do that. I'm like, okay, go. And you know, I know it's going to cost me a few cents to test it out, but I don't care. And so it's beyond the fact, the one-time thing. Like once you connect these tools to your favorite AI coding platform, if it's an agentic environment like Cloud Code, it knows how to go back to these tools because now it has access to it and it can help you or suggest it in the future when you're doing other stuff.

8:19Yeah, for sure. I think the most powerful thing access to internet, right? So you can access all the documentations. It all knows how to implement it. It can simplify it, tell you exactly what it does. You just tell it to do whatever you want to do.

8:37David Yu:This episode is brought to you by training courses by Multiply, which is my company. We currently have registrations open for two different courses. The first one is the AI Business Transformation course. It is a course we have been teaching since April of 2023. So for three years now, at least once a month, thousands of business people have learned AI fundamentals through this course. So if you are looking to build a solid foundation and learn multiple business use cases as well as tools and exactly how to apply them, including data analysis, writing proposals, creating videos, images, and so on.

9:16David Yu:Basically, solid fundamentals across the board for AI usage in the business world. This is the right course for you. I am the one teaching this course over Zoom, so it's actually me, not an AI avatar, and it's not a recorded session. It is me. You can ask questions. You can interact with other people like you. And the coming cohort starts on April 20th and it goes for four weeks in a row every Monday, two hours every single time. And in the middle of the week, you can come and join us for our AI hangouts and ask questions in between the sessions as well. It is probably the best course out there to give you solid AI fundamentals if you want to learn how to apply AI in your business.

9:54David Yu:The other course is our multi-agent orchestration course. This is a more advanced course that teaches how to build, like the name suggests, multi-agent orchestration solutions using Cloud Cowork and Cloud Code integrated with other tools, integrated with your entire ecosystem and tech stack. And so if you are a little more advanced and you want to start your way into the agentic era and be able to automate literally any digital work in your business, build entire teams of employees, come and join that course. We have launched the early bird registration last week, and it is almost filled up two early bird sessions when I was planning to do just one, but the demand was absolutely crazy.

10:37David Yu:So you might make it into the early bird session, but if not, we are opening another regular cohort just the following month and you can find out more information and register for any of these courses, either one or the other or both if you want to, because you can start with the basic course in April and then join the other course later. And you can find all of that information in links in the show notes that will take you to the specific courses. And now back to the episode. Yeah, now we're going to jump into the terminal, but fear not, it's really just really simple, like step by step. And it's laid out here, six different steps.

11:14We have to set up, we verify the email because sometimes emails, they might not be 100 % valid. If you send an email that's not valid, they can hurt your email domain reputation. It will increase your bounce rate. And then the third step is the most powerful thing you can do with CloudCo or any AI agent is because you can do deep research. So you can have the leads, for example, e-commerce store. Usually you will get the store URL as well. So you can research into the store information and you will do a review scraping. In this case, I do Trustpilot review scraping and then gets all the reviews, especially negative reviews.

11:53And it summarizes the pain points of that business. So when you go into personalizing the email and proposing an offer, you can tailor it to exactly what they're struggling with. I actually get a few thank you emails just because they're struggling with that problem. Thank you. I was actually thinking about this. I'm glad I got it. So I think that's the game changes because you're starting from their POV of I have this problem. And not just because you're trying to sell something, but actually trying to solve their problem. After deep research, personalization, then we import to Instantly. You can choose any other code emailing platform, but I choose Instantly just because they have API access, which goes well with Cloud Code.

12:38It can just import that data directly into the platform. Then it builds the email sequence. You can have usually at least a two-step email sequence, but you can do three or four more if you want. But usually a two-step email sequence is good enough. So I'm just going to show you the terminal real quick. I ran a test. I created a new project, imported a few leads. So I'm assuming at this stage, you already have a lead. Usually that lead is a CSV file. And then just tell Cloud Code where it is and tell it just to run the process and generate the CodeEmail. So in the end, I will have a link where you can download all the CodeEmail CloudSkill.

13:23So you can actually import the cloud skill into your own cloud code. So you don't have to worry about setting up the cloud MD file or the setup of the folders and everything. You can actually just download cloud code skill and just import it into a cloud code. And when you ask this question, help me run the process to generate code email, you will just pick up that skill. You can see it loads the skill and it runs through the different steps. And then these are the six phases that I mentioned. And it just runs it for you. and at each step if it needs more context you will ask you for example if he doesn't know like what's your offer or what's if he sees a problem with with the email source nearly he thinks like email source is not good enough it's not personal enough it will tell you maybe you should find like a different source or um find a different point to to mention um and in here i i kind of quickly we talk about what I do for my business.

14:18And it continues and it builds through step by step into phase one. And you can see that it writes a bunch of code, but actually usually I just tap on yes, yes, yes because usually they just get it right the first time. So I want to pause you just for one second.

14:33David Yu:So a few things kind of like for those of you who are not using Cloud Code or are afraid of the concept that it's writing code and so on. So there's three main ways you can use Cloud Code. All of them are relatively simple. Some of them are a little more geeky, but they're all still simple. So the easiest way is you install Cloud Desktop on either a PC or a Mac, and there's three tabs on top. There's chat, there's co-work, and there's code. That's probably from a user-friendliness, probably the most user-friendly way to use this, because you don't need to know anything, you don't need to install anything, you don't need to do anything.

15:06David Yu:You just have Cloud on your computer, and you go to the Code tab, and you can use Cloud Code. And so that's option number one. Option number two is you can run Cloud Code inside a terminal. What is a terminal? It's like the most basic way you can communicate with systems inside your computer. And you can open it in the same way inside of Mac or a PC. You just go to your little search thingy and you type terminal and it's going to pop it up. And then all you have to do is install Cloud Code, which is one command and it's going to install it. And that's it. And from that moment on, you just type Cloud and it runs Cloud for you.

15:42David Yu:and you just tell it what to do. The third option is to run it inside a development environment, something like Cursor or Replit or whichever, it doesn't matter. And it just runs a terminal inside that development environment. Again, you don't need to be a developer to do any of these things. The benefit of running it inside an environment is that it has more of a human-style user interface when there's buttons and menus and windows and you can see all your files and stuff like that, where in the regular computer terminal, you don't have all of that. So that's the benefit of running it in that kind of environment.

16:21As far as a skill, in the AI universe,

16:26David Yu:now it's actually a Claude invented it, Anthropic invented it, but now it's available everywhere. You can create a prepackaged set of instructions and reference files and so on that these tools know how to then reuse as needed. And so when David is saying, oh, I'm just telling you to use the skill, is because he took the time to explain to Claude what he wants to do, what are the steps, how to do the research, where to find the information, all these kind of things. And then he packaged it as a skill. So now Claude, when you tell him to go and do the thing, he said, oh, I have a skill and I know how to do this.

17:02David Yu:But the skill is something very, very simple. when David is saying MD files is a markdown file. A markdown file is basically text, like readable English. And the difference between that and like a Word document is that it doesn't have the fancy formatting. It's just text. And because it is just text, it has a much, much lighter file. And hence, it's a lot more efficient to use. And that's why all these tools, wherever you go, everything today is.md files, which are basically simple text. But what's in the text is a set of instructions on how to do the entire process that David's going to show us.

17:36David Yu:And Claude just knows how to use it. So it reads the file and says, oh, I know how to do this now. I know Kung Fu from the metrics, right, that he suddenly knows Kung Fu. Then Claude suddenly knows how to do this process. So now let's go back to your story and I'll bring everybody back. David uploaded a CSV file of a list and he told Claude, OK, go and work on it. And it knows how to do all the steps. So now we're in step one? Yeah, exactly. Yeah, thanks a lot. Yeah, I think I went a little bit too fast. You know this, so don't think. Perfect. It's so good. So yeah, it writes a lot of code, but you actually don't need to learn how to write code just because it will write it for you.

18:21And after the step one phase is complete, we go into the phase two.

18:27David Yu:What's the output of step one? So the output of step one is it's just checking, it's just collecting all the information you need and then kind of setting up the project. It will ask you what's your offer, what's your company. Usually you can tell a little bit more. Maybe like what's your tone, like what's your voice, your brand, all that stuff. And you can work even then if you give it more context like that. And so then we move on to phase two where it is the email verification. So I mentioned that if you don't have a verification step for your email, then your email get bounced and then now hurt your email reputation.

19:06So in this case, I use an API called Million Verifier. You can use any other API that you want, but this API, I find it to be very cost efficient. You pay for the amount that you use. So what you do is that before it gets to phase two, you want to go into the file that it creates. So you will have a.inf example. That just means the variable that it needs to run the APIs. So a very important note to take here is that you never want to upload any of the credentials online like GitHub. whenever you put it notice this is not real value here but whenever you create a new actual.in file you just want to make sure that those files are not uploaded onto GitHub or anywhere on the internet not to get too geeky on this

20:00David Yu:but it is a very important point you are using GitHub which is what most people are using to upload their code or their processes into a reusable usable environment. So if your computer craps tomorrow, you still have everything you built. So it's good best practices. You do not want to upload your API keys, your passwords, and so on. There is a hidden file on your computer that tells GitHub what not to upload, but you need to verify that. And the way to verify that is to tell Cloud Code, because you don't need to know about that file and you don't need to know how it's written, even though it's simple English.

20:37David Yu:You can tell it, I would like to verify that when I sync this folder into GitHub, it will not use my passwords, my usernames, my API keys, and so on. And then we'll go and do this, and it will verify it for you, and then go and tell it to sync your whatever folder to GitHub. So it's a really good point from David. It's very important. Yeah, so after you have the.in file, you should have the instantly API key and also the million verifier API key. but at phase one you actually only need the mail-in verified api key just for the email verification but in the in the later phase you would need the instantly api key for the instantly campaign creation all that stuff um so let's go back so in here it goes to this process of verifying emails you actually look at the different emails and see if there's any like broken emails and try to fix it for you.

21:32And it noticed like, oh, there's a certain number of personal emails and there is like company emails and things like that. You kind of categorize them for you. You can take that data however you want it. Usually what you can do is like if you spot a pattern or just like a high array, bad emails, then you should just reconsider where you get the leads and probably just not use this bad shit. Right.

21:58David Yu:And, but again, here, what, what, what, what it's showing right now is again, step one, we'll just set up like it set everything up to be able to run step two. It verifies the emails and it found 12 valid emails across six different companies. It tells you what the companies are. So again, you are not doing anything. It's going behind the scenes, doing a third, using a third party tool that knows how to verify that your emails are actually real emails, which is going to keep your email score high, which means you're not going to get punished later on when you try to send additional emails. So this is a very important step.

22:32David Yu:But again, you don't have to do anything. It just goes and verifies it for you. Exactly. Does it add columns to the CSV with like the correct information? Like what's the actual output? You mean like the front step? Yeah, yeah, yeah. So you have a CSV file with emails. Does it add like the correct email or a good or bad signal? Like what's the actual practical output? Yeah, so the approach I'm taking is that always keep the original file and I'll tell you to generate a new file of the filter down, you know? So like you can always go back and verify if AI messed it up somewhere, deletes things.

23:12David Yu:So you get a brand new CSV with just the approved leads. Yeah, exactly. Got it. Okay, because at this step, we're not enriching information. We're just making sure that, you know, part is 100 correct yeah okay um then then that leads us to the re-enrichment part where it does the well first it does the categorization well for for e-commerce there are different category e-commerce right and people say different things so it's in e-commerce specifically it helps with categorization to put the different email groups into category maybe it's like baby products or pet's product, I'm putting in the same category.

23:54So in the end, like when you're trying to research, or tell cloud code

23:58David Yu:to research, you would have a better direction where to go. So after that, you will have information like the revenue, if they can get the revenue data, they will have the vertical. And sometimes, you know, depending if they have like review data or not, sometimes it's just not enough review data. so I only have a really small simple data but usually you will come up come back with like a lot of more review data where you can use it for personalization. Quick question about the instructions for this did you tell it which websites to go and look for the information or you just told it to the research and it does its own thing?