Modern Creator
Nate Herk | AI Automation · YouTube

Claude Code + Clay Makes Lead Generation Actually Fun

An 18-minute walkthrough of wiring Claude Code into Clay's data platform to source, enrich, and write cold email copy for 50 leads from one natural-language prompt.

Posted
1 weeks ago
Duration
Format
Demo
educational
Views
40.5K
1.2K likes
Big Idea

The argument in one line.

Connecting an AI coding agent to a B2B data platform through natural-language goal prompts turns lead sourcing, contact enrichment, and personalized outreach copy into one workflow that costs cents per lead instead of hours of tool-switching.

Who This Is For

Read if. Skip if.

READ IF YOU ARE…
  • You're doing cold email outreach yourself and keep stalling on finding accurate contact info for the right businesses.
  • You already use an AI coding agent for other tasks and want to see it orchestrate a paid data platform instead of writing code.
  • You run or want to run an agency and need a repeatable way to generate a fresh batch of qualified leads without hiring an SDR.
SKIP IF…
  • You're looking for a free lead-gen method — this workflow runs on paid Clay credits and an AI coding agent subscription.
  • You want inbound or warm-network strategies — this is entirely a cold-outbound data-and-copy workflow.
TL;DR

The full version, fast.

Cold outreach usually breaks on three points: finding the right businesses, getting real contact info, and writing copy that doesn't read as mass AI spam. This video pairs Claude Code, used purely as an orchestrator, with Clay, a B2B data platform whose 'waterfall' checks multiple providers per lead to lift email-match rates from around 30% to 80-90%. A single natural-language goal prompt has Claude Code spin up parallel sub-agents, source and enrich fifty HVAC leads across six cities, and write personalized subject lines and bodies for roughly $12-24 in credits. The resulting CSV imports straight into Clay to launch a warmed-domain email campaign, with no new dashboard to learn — just plain English.

Free for members

Chat with this breakdown — free.

Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.

Create a free account →
Chapters

Where the time goes.

00:0000:58

01 · What We're Building

Cold open shows the finished result, then frames the episode's premise: Claude Code as orchestrator, Clay as the data source, run entirely in natural language.

00:5803:01

02 · The Data Problem vs The Tool Problem

Cold outreach breaks on three points — finding the right business, getting real contact info, and writing non-spammy copy. The fix splits into a data problem (Clay) and a tool problem (Claude Code).

03:0104:25

03 · Why Clay and the Waterfall

Clay blends its own dataset with negotiated access to other B2B data providers, paid for with credits instead of separate subscriptions. Its waterfall lifts email-match rates from ~30% to 80-90%.

04:2506:06

04 · Setting Up Clay and the Plugin

Sign up for Clay, grab an API key, then install the Clay marketplace plugin — which must be done from the Claude Code terminal, not the desktop app or IDE extension.

06:0607:26

05 · Connecting Your Account

Reload the plugin, ask Claude Code to authenticate with Clay, follow the generated authorization link, and confirm the Clay MCP server is connected.

07:2609:37

06 · The Goal Prompt

A single detailed prompt sets the target (50 enriched HVAC/home-service decision-maker leads with emails, pain points, personalized subject lines and bodies) and an explicit end condition, using Claude Code's /goal workflow.

09:3711:40

07 · How It Runs and What It Cost

The goal prompt spins up six parallel sub-agents (one per city), each sourcing and enriching 25 leads, then merges, dedupes, and verifies the results. The full run cost about 172 Clay credits, roughly $12.

11:4013:32

08 · The Enriched Data and Email Copy

Walkthrough of the 50-row output: verified emails, phone numbers, business pain points, personalization hooks, and a written subject line and body for every lead.

13:3217:02

09 · Launching the Campaign in Clay

The CSV imports into Clay as a table, gets attached to a new campaign via merge variables for subject and body, and new sending domains get purchased and warmed up for outreach.

17:0218:02

10 · Final Thoughts

Wrap-up noting Clay's own agent connector can't yet manage campaigns end-to-end, plus a plug for the creator's free community where the full project write-up is shared.

Atomic Insights

Lines worth screenshotting.

  • Cold outreach fails for three separable reasons: finding the right business, getting real contact info, and writing copy that doesn't read as AI-generated spam.
  • Splitting lead generation into a data problem and a tool problem lets one system own sourcing and enrichment while an AI agent owns orchestration and copywriting.
  • A single data vendor typically nets a working email on around 30% of leads; a 'waterfall' that falls through several providers in sequence pushes that to 80-90%.
  • One natural-language goal prompt can spin up six parallel sub-agents, each sourcing and enriching 25 leads from a different city, then dedupe and cross-check the merged list.
  • A thorough goal-prompt run with multiple verification passes and rewrites took about an hour for 50 leads; a simpler one-shot version of the same request took five minutes.
  • Fifty fully enriched B2B leads with verified emails, phone numbers, and personalized subject lines and bodies cost roughly $12 in data-platform credits.
  • At even a 1% reply-to-client conversion rate, spending about $24 in credits per 100 leads is cheap next to the value of a single closed client.
  • An AI agent can only write outreach that sounds specific to a business if it's first given that business's actual context: offer, case studies, FAQs, proof, and website copy.
  • A completed lead-and-copy CSV can be re-imported into a data platform as a table and mapped straight into an email campaign with merge variables, with no re-typing.
  • New sending domains need to be purchased and warmed up with a capped daily send volume (roughly 30/day) before they're safe to use for cold outreach at scale.
  • As of this recording, the data platform's own agent connector could source and enrich leads but could not yet manage campaign creation or sending — that step still required its own UI.
Takeaway

Split cold outreach into a data problem and a tool problem

AI LEAD GEN

Pointing an AI coding agent at a data-enrichment platform turns lead sourcing, contact verification, and personalized outreach copy into one natural-language workflow instead of five disconnected tools.

02The Data Problem vs The Tool Problem
  • Cold outreach has three separate failure points: finding the right businesses, getting real contact info, and writing copy that doesn't read as mass-produced AI spam.
  • Splitting the workflow into a 'data problem' handled by a lead-data platform and a 'tool problem' handled by an AI orchestrator means you're not learning a new dashboard for every piece.
03Why Clay and the Waterfall
  • A single data vendor typically nets a working email on roughly 30% of leads; stacking several providers in a fallback sequence pushes that to 80-90%.
  • Paying for enrichment by the credit instead of by the subscription means cost scales with actual usage, not with how many tools you're renting.
04Setting Up Clay and the Plugin
  • Wiring an AI agent into an external data platform's connector removes the need to learn that platform's UI — you describe the outcome you want instead.
  • This kind of integration usually has to be installed through the terminal version of the agent, not the desktop app or IDE extension.
05Connecting Your Account
  • Before an agent can act on your behalf inside a paid platform, you authenticate it explicitly — it doesn't get standing access by default.
06The Goal Prompt
  • A single upfront 'goal' prompt with target criteria, required fields, and an explicit end condition is enough for an agent to plan its own multi-step approach.
  • The agent can split work across several parallel sub-agents (one per segment), then merge, deduplicate, and cross-check the combined results before calling the goal met.
07How It Runs and What It Cost
  • A run with multiple verification passes and rewrites took about an hour for 50 leads; a simpler one-shot version of the same request took five minutes — the extra time buys accuracy checking, not more leads.
  • Fifty fully enriched B2B leads with verified contact data and personalized copy cost roughly $12-24 in credits, which is cheap next to the value of even one converted client.
08The Enriched Data and Email Copy
  • An agent can only write outreach that sounds specific to a business if it's first given that business's real context — offer, case studies, proof, FAQs; without it, the copy defaults to generic AI phrasing.
  • Personalization that references something concrete and public about the prospect reads as researched, not templated.
09Launching the Campaign in Clay
  • The output of an agent-run enrichment workflow can be re-imported into the sending platform and mapped to email fields with merge variables, so nothing gets re-typed.
  • New sending domains need to be purchased and warmed up with a capped daily send volume before they're safe to use for cold outreach at scale.
Glossary

Terms worth knowing.

Clay
A B2B data and workflow platform that sources, enriches, and can send outreach for lead lists, combining its own dataset with negotiated access to many other data providers.
Claude Code
Anthropic's coding agent, used here purely as an orchestrator that calls an external tool's actions through natural language and writes the resulting outreach copy.
MCP server
The connection layer that lets an AI agent call a specific external tool's actions directly, instead of requiring a custom-built integration for each tool.
Waterfall enrichment
A lookup sequence that tries one data provider for a match, then falls through to the next provider on a miss, raising the overall chance of finding a valid contact.
Goal prompt
A command that gives an AI agent an end condition to work toward, letting it plan its own multi-step approach and keep running until that condition is verified as met.
ICP
Ideal Customer Profile — the specific description of the business or decision-maker a lead search should target.
Domain warming
Gradually increasing a new email domain's send volume over time so mailbox providers don't flag its messages as spam.
Clay credits
Clay's usage-based currency, spent per lookup or enrichment action rather than paid as a flat subscription.
Resources

Things they pointed at.

00:00toolClay
00:00toolClaude Code
05:00toolVisual Studio Code
13:12channelPodcast episode with Savam on cold-email strategy
Quotables

Lines you could clip.

01:30
The workflow I'm showing you guys today, Clay is going to fix the data problem and Claude Code is gonna fix the tool problem.
crisp two-part framework, no setup neededTikTok hook↗ Tweet quote
03:40
If you're looking at just one vendor, then you might just get, you know, 30% of your leads, you'll find the right email. But with the waterfall, that number is going to increase somewhere up to more like 80 to 90%.
concrete before/after number, explains the core mechanismIG reel cold open↗ Tweet quote
11:11
This costed us a 172 clay credits, which is only about $12.
specific, verifiable cost figure for the whole demonewsletter pull-quote↗ Tweet quote
17:51
Clay's MCP server cannot yet manage all of this. I'm assuming maybe by the time you're watching this, that's already out there.
honest limitation + forward-looking bet, good closerTikTok hook↗ Tweet quote
The Script

Word for word.

Read-along

Don't just watch it. Burn it in.

See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.

metaphor
00:00So in a matter of minutes and just one prompt, I was able to use Cloud Code to find all of these leads, enrich all of them, write personalized subject lines and bodies, and then we're able to take all of that and put it into a campaign, all using natural language and thanks to Clay on the back end helping us find the leads and enrich those leads.
00:15So today, I'm gonna be showing you guys how you can do the exact same thing by using Cloud Code as the orchestrator and using Clay as the data source. So one of the biggest problems that I always hear is about struggling to find leads. You know, I've talked a lot on my channel about how you probably wanna start with your warm network, and if you can do inbound, then utilize inbound.
00:31But when you're ready to scale or if you don't have those options, then you probably are gonna look for something like cold outbound. And getting your first client through cold outreach can be tough because of three main reasons, which are finding the right business, getting real contact info, and then writing outreach that isn't super AI generated and spammy.
00:48So there's the data problem, actually being able to find those businesses and finding the emails, and then there's the tool problem because you've got so many different, you know, softwares you could use and so many different tabs to switch between. And so the workflow I'm showing you guys today, Clay is going to fix the data problem and Cloud Code is gonna fix the tool problem.
01:03Because the way I'm showing you guys this today, you don't have to learn a whole new UI. You basically just have to create a Clay account, connect that Clay account to Cloud Code, and then let Cloud Code figure out the rest. Because it's really good at understanding the endpoints and understanding what you need.
01:16You just have to explain clearly what to do. So here's what this is going to look like in practice once we've connected Clay to Claude Code. We will open up Claude Code, and we will say something like, hey.
01:25I need you to get me 50 leads that look like, you know, x y and z. This is my avatar. Cloud Code will then reach out to Clay, and it will source those leads.
01:33It will scrape the lead list. It will set up everything for you, and it will pull back those initial leads. And then Clay, once again, will enrich those leads.
01:40So it will find data from the company. It will find the emails, the phone numbers, anything else that you're asking for. And then it'll send all of that data back to Cloud Code, and Cloud Code can then write you the personalized outreach.
01:50Now the important part here is the personalized outreach. Even though Clay can get you tons of leads and tons of enriched leads, is really important, that doesn't mean that you are automatically gonna get a client. So what you're gonna do is you need to make sure that Cloud Code can write personalized copy.
02:03So in this example, this is just a demo project I set up. You'll notice that I have context files here where I've given Cloud Code things like my business profile. I've given it some case studies.
02:13I've given it some FAQs about our business. I've given it some proof and our offer, and I've also given it our website copy. So the whole idea that I've been talking about on this channel a lot, you know, building your own AI operating system and giving Cloud Code a bunch of data about you and your business, this is kind of like a prereq.
02:28If Cloud Code currently knows nothing about you, it'll be pretty hard for it to write a really good, like, cold email copy for you. So, anyways, we'll talk about this more in a sec, but that is basically the flow of what we're looking to do. And then what's really, really cool is once you have, like basically, the output from this will be a CSV with, you know, the leads, the the enrichment, and the personalized copy, then we can upload that to Clay.
02:51And right in there, we can buy domains. We can get them warmed up, and we can just start the campaign right from there. So this is seriously the easiest way that I've ever seen doing lead generation and outreach.
03:01Now before I show you guys how to get set up, I wanna talk about why did I choose to use Clay for this video because you probably heard of a bunch of different other platforms out there that might have, you know, like b to b data. The reason I chose Clay is because they have the best data.
03:14First of all, they have their own dataset, but then they've also negotiated access with a ton of other providers where instead of having to pay for subscriptions on a ton of different platforms that have b two b data, you can bring in your API keys, and you can just pay for credits. So if you have a subscription to Clay and you have credits in Clay, you're gonna be getting the best data that's out there.
03:32And then what's really cool is as we run through this enrichment, they have this waterfall. So they basically check their top provider, and if they don't get a hit, they'll move down to provider two.
03:40And if they still don't get a hit, they'll keep moving down the waterfall until they're able to actually get a hit. So if you're looking at just one vendor, then you might just get, you know, 30% of your leads, you'll find the right email. But with the waterfall, that number is going to increase somewhere up to more like 80 to 90%.
03:55And once again, the thing to me that was really important about making this video is that I didn't wanna teach you guys a new UI, and I don't like learning new UIs. I like to have my agent, Cloud Code or whatever other agent I'm using, I like to have the agent figure out how to navigate the page, how to hit the endpoints, and how to do what I need.
04:11So all I wanna do is just sit here and talk in natural language, and that is basically the way that we're able to work with Clay. And I have been talking to the Clay team themselves about making this video. They're also planning on making everything in their platform way more agent friendly, so the future is looking bright.
04:25Okay. So the first thing you're gonna wanna do is go to clay.com and sign up for an account. Clay has been around for a long time even before this, you know, AI stuff has blown up.
04:34You can see here there's automated inbound, there's lead scoring, there's automated outbound, CRM enrichment. There's a lot of things you can do here inside of Clay. But that also means if you open it up, it might feel a little bit confusing, which is why I'm going so hard on, like, orchestrating it with Cloud Code.
04:46So anyways, get in here. Go ahead and start a free trial. Sign up for an account, and then all you'll need to do later is grab your API key from there.
04:53Alright. Now to actually install the Klay plug in and marketplace, it's pretty easy.
04:57So I opened up a fresh project. You can see there's literally nothing in here just so I can show you how this all works. Now the only thing to note here is that in order to get this installed, you have to do it through the Cloud Code terminal rather than the desktop app or in, like, the Versus Code extension as you see right here.
05:11That does not mean that you can't use this plugin in the Versus Code extension or in the Cloud Desktop app. It just means to install the marketplace, you have to do it this way. You'll have to go through the terminal.
05:21So if you have never installed Cloud Code before, just go ahead and Google Cloud Code install and click on this page, and it's really as simple as just copying and pasting one command based on your operating system. Once you have that set up, you can open something like Versus Code, which is what I'm in right now, which is also a completely free download as you can see.
05:35And then I'll open up the terminal inside of Versus Code. I'll type Claude. You could also just open up, like, your command prompt or your PowerShell or whatever you're using.
05:42And then once you have this open, you're gonna do a slash marketplace. You can see right here we have slash plugin, and we can see marketplace. I'm gonna click on that, and then we're going to install a new one.
05:51So install a plugin from a marketplace. I'll open that up. All I have to do now is click on add a marketplace, and then I'm going to paste in this link, which you can see right here.
05:59Take a screenshot of it. And then once you actually put that in there, it will go ahead and install this one, Clay, build with Clay and Cloud Code. Cool.
06:06So now that I have that installed, I can go ahead and do reload plugins as it prompts us to in order to apply all those changes. And then all you have to do is ask it to help you authenticate. So, hey.
06:15I just installed this Clay plugin. Can we go ahead and connect my account? Can you help me authenticate?
06:20You can see that clay actually loaded up its own skill, which is meant to help you guys get set up super easily. So then what happens is it gives you this link that you will be able to just click on and open up. Also, for some reason, the terminal wrapping can be weird if you try to open this up, so you might have to just copy it manually and paste it in.
06:34You see we got this weird one. But if I copy the whole thing and paste it in now, the link actually works. And all you have to do here is choose the workspace that you wanna connect to Clay, hit authorize, and then you should be good to go back into your terminal.
06:44And now we are fully set up with Clay. So now that everything has been connected, let's go ahead and see if Cloud Code can use Clay. Check if you can use Clay and tell me what available actions and tools you have.
06:55Awesome. So you can see that it loaded the Clay skill. It looked at the Clay plugin.
06:59We're trying to connect to this Clay MCP server, which is connected and authenticated. So we can execute clay actions, which has a ton of different actions as you can see here. This is things like finding emails, enriching a person or company, looking up a phone.
07:11These all cost you credits. So once we do our demo run, I'll show you how much that actually costed me in real money. But we can also look at a table.
07:18We can read. We can edit node. We can validate workflow.
07:20We can do a bunch of other stuff. And like I said, because Cloud Code understands this, we just have to ask a natural language, which is pretty cool. So anyways, I'm just gonna clear this out, and what I'm gonna do is real quick tell you guys about my fake business setup here.
07:32So the business profile is Tradewind Automations, which is a small early stage AI automation agency for home service businesses. And that's where we've put in a few case studies here, which will be potentially used in the copy, some FAQs, some proof, and our offer, as well as our website copy.
07:48Our avatar here is gonna be like small HVAC businesses. We're trying to obviously get in front of business owners, so that is what I'm gonna ask it to find for me. And something that I've been playing around with with Clay lately is using goal prompts.
07:59So if you don't know what a slash goal is, basically, what it lets you do is just set kind of like an end condition, and then you can have Claude keep working until it hits that condition, which is pretty cool because what we want here is, let's say, we want 50 enriched leads all with the personalized subject lines and body copy.
08:15So that's basically the goal that we're telling Cloud Code to work towards. Alright. So I am looking for some more leads.
08:21I want 50 enriched leads that are HVAC or home service companies, and we're looking to get in front of decision makers. So business owners or, you know, presidents, people that might be decision makers at these companies, and we want them to be fully enriched leads.
08:35So we need their email addresses. We need their business' pain points, anything that's recently happened in their business, any notable achievements So that you can also get me the subject lines and the body for the email.
08:48Everything should be, of course, super personalized. And the CTA, the end result that we want this person when they receive the email to do is we want them to say yes to us sending over a ninety second Loom video that explains a little bit more about how our business can help them and solve their specific business pain points.
09:07So do not stop until you have all 50 of these leads for me. Use a dynamic workflow to verify that you've done everything correctly and verify that everything is accurate. And then once you are done, deliver me a CSV file that has all of this information in there.
09:19There should be no blank columns. Every single lead should have an email, a subject line, and a body, and they should be enriched with other data. So that's what I need.
09:27So I just went ahead and shot off that goal prompt. You can see right here it says goal active, and it's been active for about eight seconds now. So I'm just gonna come back once we have our finished results.
09:37Okay. So we're twenty minutes in. Just wanted to show you guys what's actually going on because there is a lot going on behind the scenes because of the way that I prompted this thing.
09:44So it's picked an approach. You can see here it launched six agents. So we're looking in Houston, San Antonio, Atlanta, Charlotte, Tampa, and Las Vegas.
09:50And each of these sub agents is looking for 25 shops and enriching them. And then after they come back, they're gonna aggregate everything and they're gonna dedupe and check yield and make sure that everything is pretty much exactly what we asked for. And that's the whole verification part of this slash goal prompt.
10:06You could see these agents down here running. If I was to click into the Atlanta one for example, you can see that it was prompted and now it is actually looking through the clay plug in and it is gathering all of these leads and enriching them. So anyways, I'll go back to the main session now and check-in with you guys again when we are fully done.
10:20Alright. So this just finished up. You can see if I open up the output folder right here, we can see that we have this leads on July 2, which is today.
10:28We also have a run summary, which we can look at, but I'll open this up in a sec. What you'll notice about this goal is that it took an hour. So they're not all gonna take an hour.
10:36This is because this thing went nuts. It did a bunch of verification passes. It fixed a bunch of stuff.
10:40It rewrote a bunch of the subject lines, and now what I would do is I'd probably build some skills around this, and then I'd shoot it off overnight so I could wake up with like 500 leads. But I just wanted to show you that I did this other request where I said, hey, use Clay to find me 50 leads in HVAC, and I just said, I'll put it here.
10:55You can see we have the 50 leads. So it just hit Clay real quick, brought back the data, and this only took five minutes. So not every time that you're looking for 50 leads is gonna take you this long.
11:03This is because we worked in enriching, verification, a bunch of passes. It even did some debates where it literally had the dynamic workflow agents debating on if the subject line and the body were actually good or not.
11:15So that's why this one took a little bit longer. But, anyways, we have all the data. Let's go take a look.
11:19And the other thing I wanted to call out here is that this costed us a 172 clay credits, which is only about $12. So if you think about that, let's say you are converting about 1% of the people you're reaching out to. This would cost you $24 ish to get a 100 leads, and that one person that you convert is probably gonna earn you more than $24.
11:36So that is really not too bad when you think about the return on that investment. Okay. So here you can see we have our 51 rows.
11:44So we've got 50 leads as requested. I'm not going to show you all, obviously, all this data, but let's look at the columns we got. We have the business name.
11:51We have decision maker. We have the title. We have the email.
11:55We have the email status. As you can see, all of these emails have been verified and validated, which is great. We got their phone numbers.
12:00We got their websites. We got the city that they're in. We got the Google rating.
12:05We got the review counts, business pain points, recent current signal, notable achievements. So as you can see, this stuff is just awesome. We've got a personalization hook.
12:12We've got our hook source, email subject, email body, and then anything else that needs review. Let's take a look at one email subject and body real quick. We can see your subject here is your one bad review is about callbacks, and then the email body is, hey, Ante.
12:25Saw the review about a customer still waiting on a callback about a month later, so a very specific pain point there. A few different people reaching out with no one following through. Rare miss for a shop at 4.7 stars across 4,100 reviews.
12:36We recently helped a local business turn calls it was missing into book jobs without adding anyone to the phones. Honest offer, I'm still getting this off the ground. No case study yet.
12:45Set this up on your line, run it free for thirty days. If it doesn't book jobs you have missed, you owe nothing. Only ask if it works as a reference.
12:51Can I send over a ninety second video? So not too bad. Keep in mind, like I said at the beginning, even if Clay gives you the best possible data, that doesn't mean you're going to get clients.
12:59What you need to do is make sure that Claude Code is prompted in the right way and has the right context about you and your business to actually be able to write all of this stuff at scale really high quality. And if you wanna dive a little bit deeper, I actually did a podcast with Savam a few months ago, and he basically broke down his entire strategy.
13:15He was able to generate over $500,000 in sales opportunities through cold email.
13:19So he breaks down pretty much everything. And literally what I did for this specific example is I took the transcript of this video and I fed it into my Cloud Code system right here, and I said this is how I want you to write cold email subject and body. So that's what I did here.
13:32Anyways, now that we have this awesome table of 50 enriched leads with our messages already crafted, now we're gonna go back into Clay. So I'm going to close out of the Excel sheet, and when I'm in Clay, what I wanna do is I wanna click on import data, and we're gonna import a CSV. So that's why we had Claude generate us that CSV.
13:49So I just have to choose this output right here, which was the leads table that it just built for us. I'm going to go ahead and import that, choosing the delimiter as the comma, basically just how it's gonna separate up the different columns, and then I'm gonna go ahead and click continue. What I'm gonna do here is add this to a new blank table, but if you already have an existing table you wanna add this to, then you can do that, but we're gonna go ahead and do a new blank table and then complete that import.
14:11Okay. Boom. So now we have that CSV in here as a clay table, and what I'm gonna do is go back to the home, and what we wanna do now is we want to create a campaign.
14:18This is how we can actually start firing off emails to those 50 people, and ideally, you're running this in a bigger batch. So maybe you have 500 leads in there or maybe a thousand, and all you have to do now is come in here and click on add lead list and choose that table that we just built, which is right here, leads July 2, and I can select to this table and bring it into this campaign.
14:36So you can see you could generate your messages here with Clay, or we can just pull in the ones we already generated in Claude, which is probably gonna be better. So I'll click on start from an empty message, and all we have to do here is we have to use variables.
14:46So this first one is the subject line. I'll go ahead and do a slash, and I will do from our rows. And then in here, I can just go ahead and choose the email subject.
14:56And then down here, I'll do the exact same thing, and we're gonna be choosing for our email body, which is right there. And then when I click on preview right here, we can see that we're getting the preview of what will actually go through in Gmail or however we send this. We've got the subject right there and then we have the body right there.
15:11And this would happen for every single lead. If I click through, this is now saving across all 50 of the leads that we just enriched and we created these personalized messages for all of them. Cool.
15:20So that's how you kind of set up the campaign. Now what if you don't have any accounts to actually send from? That's when you move on to the next step here and go to sender accounts, and this is pretty cool because you can actually purchase accounts right here inside of Clay.
15:32And if you've never touched cold outreach before with email, then there's some things you have to think about like warming up the domains and then making sure you don't get put in spam. And so what you can do is you can buy domains right here in Clay that are gonna be warmed up for you, and they're gonna make sure that you're only sending 30 per day.
15:46So they're gonna make sure that your emails are pretty much good to go. So what you can do is you can click on select accounts. If you have any, they'll be right here.
15:53Otherwise, you could click on add account down here, and then you can buy some. So right here, buy email accounts, I'll hit continue. And then you can choose between Gmail or Outlook, but you just type in something that is similar to your business.
16:03So in this case, what was our business called again? If I go back to our context to our business profile, we are called Tradewind Automations. So if I go in here and I just type in Tradewind, I could see what domains I could buy real quick.
16:16So I could buy all Tradewind. I could buy Bright Tradewind. I could buy Click Tradewind.
16:19I could also come back in here and throw in the word automations, and it's gonna give me even more options. I can even buy Tradewind automations, but then I've got a ton of other ones to buy, and it doesn't really matter that they're not the exact domain as long as they're similar to your business name.
16:31So let's say I wanted to buy this one. You can buy five accounts per domain, and then you can set up the first and last name on those accounts. So it's super nice that once you have all this data, Clay can basically handle the rest for you.
16:43And then from there, you can come into campaigns, and you can just manage everything from here. You can even set up a follow-up message. So three days later, if no one responds, and then you can even do another third follow-up after that.
16:52And once again, Clog could generate those messages for you, or you could set that up here in Clay. Clay's MCP server cannot yet manage all of this. I'm assuming maybe by the time you're watching this, that's already out there.
17:02I'm assuming it will be coming very soon, but that is where we're gonna end the video today. Hopefully, one was helpful and it was able to open your eyes as to what is possible when you connect Cloud Code to something like Clay. I think it's going to make lead generation and outreach so much easier for a lot of you guys.
17:16So anyways, if you guys haven't yet started to set up, like, your own second brain and your AI operating system in Cloud Code, then definitely do so. Join my free school community. The link for that is down in the description.
17:25You can see that we've got a full course in here around, you know, building your AIOS as well as a bunch of other resources. What else I'm gonna do is I know that you guys are probably curious around this exact demo project. I will compile all of this into a single markdown file that explains exactly how I set everything up, how we have the outputs, how we have the context, how we have basically everything in here so that you could import this into your project and say, hey.
17:46I want you to be able to use clay just like Nate did in this video, and it should be pretty simple for you. So all of those resources will be in my free school community. The link for that is down in the description.
17:54Anyways, if you guys enjoyed the video or you learned something new, please give it a like. It helps me out a ton. And as always, I appreciate you guys making it to the end of the video.
18:00I'll see you on the next one. Thanks, ever
The Hook

The bait, then the rug-pull.

In one prompt, Nate Herk has Claude Code find, verify, and personalize cold outreach for fifty leads, turning what's usually a multi-tool grind into a single natural-language workflow.

Frameworks

Named ideas worth stealing.

00:58list

The three blockers to cold outreach

  1. Finding the right business
  2. Getting real contact info
  3. Writing outreach that isn't AI-generated and spammy

Cold email fails on three distinct points, not one — a useful checklist for diagnosing why an outreach effort isn't working.

Steal fordiagnosing a stalled cold-outreach or lead-gen effort
01:30model

Data problem / tool problem split

  1. Data problem: sourcing and enriching accurate leads
  2. Tool problem: switching between too many disconnected platforms

The video's core structure: a data platform (Clay) fixes the data problem, an AI agent (Claude Code) fixes the tool problem by replacing UI-hopping with natural language.

Steal fordesigning any two-vendor workflow where one tool holds data and another holds orchestration/context
03:40concept

The waterfall enrichment model

Instead of relying on one data vendor, the platform checks a top provider for a match and falls through to the next provider on a miss, repeating down the list until it gets a hit — raising match rate from ~30% to 80-90%.

Steal forany B2B contact-enrichment or data-lookup workflow
07:26concept

The goal prompt

A single upfront prompt states the target criteria, required output fields, and an explicit end condition ('don't stop until every lead has an email, subject line, and body'), letting the agent plan sub-agents and verification passes on its own.

Steal forany multi-step agent task where you want a stated bar of done instead of babysitting each step
CTA Breakdown

How they asked for the click.

VERBAL ASK
18:00newsletter
Join my free school community. The link for that is down in the description.

Soft close after the demo, not a hard pitch — frames the free community as where the full project write-up (context files, prompts, outputs) will be shared.

MENTIONED ON CAMERA
FROM THE DESCRIPTION
Storyboard

Visual structure at a glance.

cold open / result preview
hookcold open / result preview00:00
data problem vs tool problem framing
promisedata problem vs tool problem framing01:30
waterfall enrichment explained
valuewaterfall enrichment explained03:40
clay.com signup + plugin install
valueclay.com signup + plugin install04:40
writing the goal prompt
valuewriting the goal prompt07:30
sub-agents running across six cities
valuesub-agents running across six cities10:50
50 enriched leads + cost breakdown
value50 enriched leads + cost breakdown11:40
importing the CSV into a Clay campaign
valueimporting the CSV into a Clay campaign13:32
wrap-up + community CTA
ctawrap-up + community CTA18:00
Frame Gallery

Visual moments.

Chat about this