The argument in one line.
Claude Code breaks out of the chat sandbox to connect files, APIs, and databases, making it a production orchestration layer for outbound sales that chatbots fundamentally cannot replicate.
Read if. Skip if.
READ IF YOU ARE…
- You run a cold email agency or in-house outbound team and want to automate list building, enrichment, and ICP filtering.
- You currently pay for separate OpenAI or other API calls to do lead scoring or personalization.
- You spend time manually clicking filters in Prospeo, Apollo, or Clay to build lists.
- You want campaign experiments to run and log themselves overnight without human intervention.
SKIP IF…
- You are looking for general AI productivity tips not connected to outbound sales.
- You do not currently run cold email campaigns and have no plans to.
The full version, fast.
Claude Code operates outside the chat sandbox, connecting to files, APIs, and sub-agents, making it a true orchestration layer for outbound sales. Four production workflows: skill files that encode SOPs any team member can invoke; voice-controlled list building against Prospeo that outputs a filtered CSV without touching a UI; Sonnet sub-agents that classify leads for ICP fit at no additional token cost on the $200/month plan; and an Auto Research loop derived from Andrej Karpathy that pulls campaign results, mutates list filter and copy, relaunches the send, and writes the experiment to a database, fully autonomously. Two enterprise customers are running it and one is outperforming human-written campaigns.
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 →Where the time goes.
00:00 – 00:55
01 · Hook and four use cases
Promise of four ways Claude Code changes lead gen; preview of the four-point agenda on screen.
00:55 – 02:16
02 · Why Claude Code beats a chatbot
The sandbox analogy: chatbots answer questions; Claude Code connects to files, makes API calls, and stores data.
02:16 – 02:25
03 · Setup
Install via one copy-paste command in the terminal; choose terminal over VS Code for beginners.
02:25 – 03:58
04 · Feature 1: Skill files
What a skill file is, two use cases (build your own vs use others), and the Cold Outbound Skills GitHub repo with four production skills.
03:58 – 04:29
05 · Cold Outbound Skills repo demo
Shows the GitHub repo: Cold Email Copy Grader, Domain Setup, Google Maps Scraper, Prospeo Full Export skills, plus common outbound lists.
04:29 – 06:33
06 · Feature 2: Voice-controlled list building
Live demo: voice command to build 1,000 marketing leaders via Prospeo search skill, filters proposed and confirmed, CSV opened automatically.
06:33 – 08:19
07 · Feature 3: Sonnet sub-agents for ICP filtering
Spawn Sonnet sub-agents inside Claude Code to classify leads as SaaS or not at zero extra API cost, running inside the $200/month plan.
08:19 – 09:21
08 · Auto Research intro
Introduces Auto Research from Karpathy repo: give context, set an optimization target, let it run experiments autonomously.
09:21 – 10:31
09 · What Auto Research optimizes for
Set reply rate as the target; the loop changes list filters and copy, runs experiments without any human involvement.
10:31 – 11:53
10 · Single-Offer Campaign Loop and results
Walkthrough of the four-step loop diagram; 10 percent volume slice for two enterprise clients; one is outperforming human campaigns.
Lines worth screenshotting.
- Claude Code breaks the chat sandbox: it connects to files, APIs, and two different softwares simultaneously, which a web-based chatbot literally cannot do.
- A Claude Code skill file is a plain text file that encodes a multi-step SOP so any team member can run a complex workflow without knowing the steps.
- You can train a cold email copy grader by feeding Claude past campaigns and having it guess success, then check reality and improve over 1,000 iterations.
- Voice dictation into Claude Code lets you build a filtered list of 1,000 contacts and open the CSV without clicking a single UI filter.
- Spawning Sonnet sub-agents inside Claude Code for ICP classification costs zero extra tokens, running against your existing $200/month usage not a separate API key.
- The Auto Research loop changes one variable at a time so results are readable and the winning change is attributable.
- Pointing Claude Code at a shared GitHub repository of skill files lets an entire agency share SOPs the same way developers share libraries.
- Auto Research stores every experiment in a database so the loop reads its own history on the next run, building compounding knowledge with no human curation.
- Marketing is just a fancy word for testing, and Auto Research removes the human bottleneck from that testing loop entirely.
- A 10 percent volume slice dedicated to Auto Research is enough to generate meaningful experiments without disrupting existing campaigns.
Four ways Claude Code redefines lead generation.
WHAT TO LEARN
When an AI system can reach outside the chat window to call APIs, read files, and spawn sub-agents, the entire cold outreach workflow collapses into a single operator.
- A skill file is a plain text SOP that any team member can invoke, removing the dependency on tribal knowledge for complex multi-step data workflows.
- Pointing Claude at a shared GitHub repository of skills gives a team the equivalent of a shared library: one update propagates to everyone without retraining.
- Voice-controlled list building against a data enrichment API removes the manual filter-clicking bottleneck; the model proposes filters, confirms edge cases, and saves the CSV.
- Spawning a sub-agent to classify leads as SaaS or not costs nothing extra when run inside Claude Code, replacing a separate paid API call for every classification.
- Encoding guardrails in a context file is what makes autonomous campaign optimization safe enough to run on live sends.
- Running experiments on 10 percent of total volume creates a dedicated learning track without disrupting the main campaigns.
- The Auto Research loop changes one variable at a time so results are readable and the winning change is attributable.
- Storing every experiment result in a database that the next loop reads turns a one-time test into compounding institutional knowledge.
Terms worth knowing.
- Skill file
- A plain text file loaded into Claude Code that encodes the rules, steps, and boundaries for a specific workflow so the model can repeat that process reliably without re-instruction.
- ICP (Ideal Customer Profile)
- The firmographic and behavioral characteristics that define whether a lead is a good fit for an offer, used to filter lists before sending outbound emails.
- Sub-agent
- A secondary Claude model instance spun up by Claude Code to handle a discrete task such as classifying whether a company is SaaS, in parallel, without requiring a separate API key.
- Prospeo
- A B2B data enrichment platform with a search and enrich API that returns contact details, company descriptions, and email addresses for prospect lists.
- Auto Research
- A framework originally built by Andrej Karpathy for running autonomous optimization experiments, adapted here to mutate cold email list filters and copy and log results for the next iteration.
- Enrichment
- The process of appending additional data such as email, phone, company description, and funding status to a raw list of contacts via a third-party API.
- Smartlead.ai
- A cold email sending platform that manages inbox rotation, sequence scheduling, and reply tracking for outbound campaigns at scale.
Things they pointed at.
04:29toolWhisper Flow
Lines you could clip.
00:55
“Claude code breaks, let's call that sandbox of the chat window.”
06:55
“We are basically circumventing making direct API calls, and just using Sonnet sub agents inside of Cloud Code to do all of our ICP filtering.”
10:25
“Marketing is just a fancy word for testing.”
11:14
“For one of the customers, it is starting to outperform the human written campaigns.”
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.
metaphoranalogy
00:00There's an AI tool that can build your entire cold email lead generation system. You might have heard of Claude Code, but it is radically changing everything that we do inside of our business. From coming up with campaign ideas, pulling lists, enriching the leads, even setting up the campaigns completely end to end.
00:15In this video, I'm gonna show you how we use Cloud Code to, one, share SOPs throughout the entire team through things called skills. Two, how we use it to plug into databases to build lists and enrich things very quickly. Three, a secret hack that we use for sub agents to filter for ICP and write personalized lines.
00:33And then four is a new kind of lead generation research category that when we say Claude code is changing cold email lead generation forever, that last fourth thing is gonna be the most important thing, so you wanna stick around for it a 100%. Let's first talk about why Claude code is such an absolute game changer. So for starters, if you all you've ever used is just a chatbot, ChatGPT, Claude, on their web browser, up until this point, you ask a question, it gives you an answer back.
01:00Maybe it will search the web to find live information, but that's really it. Claude code is so amazing because it breaks, let's call that . When you enter something into a chat and you say, hey, look at files on my computer, it's not connected to the files on your computer.
01:15It has no shot of being able to do that. Claude code though is connected to the files on your computer. It can make tool calls and make API connection requests between two softwares.
01:23It can store data so that if you write an SOP once, you're always using that SOP going forward. Just a completely paradigm shift in comparison to a regular chatbot. And you might think that this is really complicated to set up, but that's not the case.
01:37I've never coded a day in my life and it is so easy. All you have to do to set up this platform is go to code.claud.com and then you can click on the terminal, you click on desktop.
01:49If you've never set it up before, you probably don't wanna use Versus Code or JetBrains. I personally use the terminal. All you have to do is just copy and paste this into your terminal, and you're ready to go.
01:57Anytime you have a problem with the setup of any of these AI tools, I just take a screenshot of it and then go to the chat version on the web and just say how do I fix this? And it always comes out to be the right case. So now that you have Cloud Code setup, let's talk about the first game changing feature, which is called Skills.
02:12Previously before Skills, people would train an AI in order to make its own custom use cases. You might remember custom GPTs or being able to fine tune models.
02:22All of these things, they worked okay, but they weren't fantastic. And so all a skill file is is literally a text file that you can plug into Claude code and it will remember everything that if you worked on this long workflow and you were to say, hey, first we do step number one, and then we do step number two, and then we do step number three.
02:40Instead of telling it that every single time, you can set the rules, the boundaries, and the guidelines inside of skills. And so I think for lead generation, there's two things that Claude Code does so amazingly with skills. One is you can make a process yourself and work on it back and forth with Claude Code, and then eventually just get to the point where you say, great.
02:57This is exactly every time we wanna run a report to see which domains are most likely landing in spam. We wanna run this process every single time. The other thing is you can use other people's skills, and instead of putting in all the time to become a great front end designer, putting in all the time to figure out exactly how an API works and all the edge cases, you can just download somebody else's skill.
03:19We even have this repository I'm building up for ourselves called Cold Outbound Skills that right now it's got four main skills in it, where we already have a skill that grades your cold email copy. This cold email copy grader is based off of every campaign we've run-in the last year, and the way I trained it is I said, hey, Claude, guess how successful this campaign would be based on the job titles that are in the campaign data and what the copywriting is.
03:40And then check how successful it actually was and improve your guessing. And it did that over definitely more than a thousand. And so it literally is just guessing back and forth, and it knows what makes the campaign successful.
03:51Successful. This domain setup, if you're using Dynadot and Zapmail, there's little edge cases that have literally just vocabulary in the Zapmail API that Claude is gonna get confused with on how to set up the inboxes.
04:03That's all taken away. You can just plug in this skill right away here. And then if you wanted to scrape Google Maps or you wanted to scrape Prospio searches, we have a skill straight up for that.
04:11As well as some common outbound lists, like I have 12,000,000 US businesses that you could just have here. I have a SaaS company list here. I have every zip code in The United States.
04:19And you can just point Claude code literally at this repository and get access to all of it. So I'm just gonna use Whisper Flow and I can just talk to it and I can just say, hey Claude, using the prospio.io search skill, can you help me build a list of 1,000 marketing leaders in The United States with a employee headcount between ten and one hundred, and they had recently raised money.
04:41Can you help me build that list? And so now, we're just gonna shoot that off to Claude Code. It's gonna read our skill document, and then it's gonna put that together.
04:49So you'll see it's even proposing the filters for me. CMO, chief marketing officer, everything that I wanted, location, funding, raised money in the last six months, all stages, email verified only.
05:00And so it's even asking me questions, which is great. Let's make the funding recency a hundred and eighty days. I don't care about the stage, and verified emails are required.
05:08We can keep that, and there's no industry filter. Thank you so much. And when you finish this, open the CSV file on my computer so I could show everybody.
05:16And now we're just gonna let that run and get kicked off. So now we got our CSV file from the Prospio search. And without clicking around, without doing anything, just using my voice and that Prospio export skill, I now have a list of marketing leaders in The United States at all kinds of different companies, really just in a flash, just like that.
05:34My favorite part about using my voice is then also cleaning up the data. Prospio inherently does not give us the email when we're using the search endpoint. We need to use the enrich endpoint.
05:44So we're gonna get everybody's email addresses right now. But then what we're also gonna do is we're gonna confirm that these companies are software companies, and I'm gonna show you a secret about how we're gonna be able to do that. We're gonna switch back over to Cloud Code, and I'm just gonna tell it, hey, thanks so much for pulling this list for me.
05:58Can you also use the Prospio Enrich endpoint to find all of the email addresses of the contacts in this? And I also know that the Enrich endpoint usually comes with the company description as well too. Can we confirm using a Sonnet sub agent that these companies are actually software or software as a service companies, and then filter this list for only marketing leaders that fit this initial criteria, that have a valid email, and that we can confirm that they run a SaaS or a software company.
06:28And again, use a Sonnet agent to be able to figure that out. While that's thinking, the secret sauce that we've been using inside of our agency is normally what we would have to do if we ever wanted to look at a company description and say, is this a good fit company or is this a bad fit company? Do they mention this keyword?
06:44Are they a good fit contact? And we wanted to use AI to be able to look at this. We would then say, hey, use our OpenAI key.
06:50Here's the prompt. Make this call. But ClaudeCode gives you so much extra usage on the $200 a month plan.
06:57We are basically circumventing, making direct API calls, and just using Sonnet sub agents inside of Cloud Code to do all of our ICP filtering, to write our personalized lines, and that's exactly how we do it. I literally just say prove to me that they're a SaaS company and use a Sonnet sub agent to do it.
07:14They will also probably check with me to make sure that what it thinks is a SaaS company is actually SaaS company before that runs. But that's the awesome power of using this through Plug Code is this is gonna be included in my usage to be able to run it like this and I don't have to pay anything So now, let's jump back into our terminal screen and see how it's enriching all of the email addresses and all these things.
07:32What I was talking about, classifying batch one as SaaS, classifying batch two as SaaS, this is where it's spinning up those Sonnet agents so that we don't have to pay extra. We don't have any extra token costs. It is not charging me in any other way.
07:44I'm using my Claude code usage here to get all of this done. And so it's not done yet. We still need to wait.
07:49But this is what I'm talking about where it can do the scoring and the filtering for you straight in here, so then you don't have to pay extra. You could just use your usage, a part of your plan to be able to do this. Alright.
08:00Now we just gotta wait, I guess. And we're back. Everything ran.
08:04Again, I didn't have to touch a single thing. Just with my voice, we enriched all of the contacts for their email addresses. Their phone numbers stayed masked because we didn't pay extra for them.
08:14And then what we could see the most interesting thing is we have the company description, but then we have the output of is it a SaaS company, is it not a SaaS company. And we have all the reasoning in here as well too.
08:26And so I didn't pay any extra for this. Like I said, we use Sonnet sub agents to be able to get this done. You could review it, you could then go back and forth with it, and you could say, oh, I actually prefer that this is considered a SaaS company or this isn't considered a SaaS company.
08:39But that's one of my favorite hacks that we do for our ICP filtering is this Sonnet sub agent thing. The last thing, in my opinion, is the biggest game changing thing and the thing that we're working on the most right now for our customers. And it is something that is called Auto Research.
08:55And I think this is by far the most game changing part about Cloud Code. Auto Research is a repository made by Andre Karpathy, who many people regard as one of the best AI researchers in the world. And this is actually a really simple idea when you think about it, but when you give it to Claude Code, its ability to run this process over and over again autonomously is game changing, and we'll talk about that in a second.
09:18All this does is it basically is a repository that you can say, I am gonna give you a bunch of context on how my business works or an experiment that I wanna run, and I want you to optimize for positive response rate or reply rate.
09:33Or if you're using this outside of cold email, you wanna optimize it for a Google ad bidding strategy. Whatever the number is, you tell it, I wanna optimize for this outcome to happen. So then what you could do is you could use this repository framework to then keep running experiments without you touching anything that improves over time your Google ad budget, your cold email campaigns, whatever it might be.
09:55Without touching anything, you can have an AI optimizing your cold email campaigns, running experiments, and then learning from what works and what doesn't work so that you don't have to keep running those experiments. Right? Because marketing is just a fancy word for testing.
10:07And with this auto research repository, you would be able to just plug this in and without you having to think about anything, other than giving it context upfront to basically say, hey, don't give our services away for free and here's some other rules of experiments that you can run. It can plug into SmartLead instantly.
10:22Whatever tool you're using for sending, change the copy, change the lead list, and run all these experiments for you on your behalf. And so this is actually a visualization of a offer campaign loop that we've created as well too.
10:34What this version on our repository does is it first pulls the recent results of the campaigns that we have auto research pointed to. We usually give it context and we say, hey, for our customer, this is the boundaries of the experiments that you're allowed to run and what kind of offers you're allowed to make and who we're targeting and all those kind of So first, it pulls the recent results, and it says, okay, what happened yesterday?
10:56What was the most recent experiment? Did it work better than baseline, or was it worse than baseline? And then it rereads the context file to then think about, okay, what are new experiments that we're allowed to run?
11:05And then it changes the list filter, it changes the copy, and then it relaunches the campaigns all completely autonomously and it stores the new experiment that it's gonna be doing so that we learn what's the best list filtering for us to use, what's the best copywriting for us to use, and it recursively learns all of this knowledge knowledge over and over and over again.
11:23And so we've already installed two of these auto research repositories for some of our enterprise customers. We've taken 10% of their overall volume, and we're just dedicating it to this auto research thing. For one of the customers, it's starting to outperform the human written campaigns as well too.
11:37But I really think that this is the most game changing thing to happen to lead generation in a really long time. And so if this hasn't convinced you to start using Claude Code for your outbound campaign strategies, I don't know what will. Hopefully, we'll have another video coming out that will convince you, and I'll see you on that one.
11:52Thanks everybody.
The Hook
The bait, then the rug-pull.
Cold email agencies have been waiting for a tool that can reach past the chat window. Claude Code does exactly that, connecting directly to files, APIs, and databases to run end-to-end outbound workflows that a chatbot simply cannot replicate.
Named ideas worth stealing.
03:58list
Cold Outbound Skills (4-skill repo)
- Cold Email Copy Grader
- Domain Setup (Dynadot + Zapmail)
- Google Maps Scraper
- Prospeo Full Export
A GitHub repo of Claude Code skill files for cold outbound. Each skill encodes a specific workflow so Claude can run it without re-instruction.
Steal forAny agency that wants to standardize AI-assisted workflows across team members without retraining each time
10:31model
Single-Offer Campaign Loop
- 1. Pull recent results (last 3 days)
- 2. Re-read context file (offer, guardrails, targeting)
- 3a. Change list filter (one lever)
- 3b. Rewrite copy
- 3c. Launch experiment
- 4. Write to database
An autonomous four-step loop adapted from Karpathy autoresearch that runs cold email experiments, mutates variables, and logs results without human intervention.
Steal forAny outbound team that wants to run continuous experiments on list filters and copy without babysitting each test
How they asked for the click.
VERBAL ASK
11:31next-video
“If this has not convinced you to start using Claude Code for your outbound campaign strategies, I do not know what will. Hopefully we will have another video coming out that will convince you.”
Soft tease of a follow-up video. No hard subscribe ask. Description carries lead gen CTAs: free campaign offer and Clay affiliate link.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
AFFILIATECommission earned if you click.
OTHER LINKSAlso linked in the description.
Visual structure at a glance.
