282 | How to Turn Claude Into Your Automation Engineer and Ship n8n Workflows with Jeremy Grandillon

0:00Hello, and welcome to another live episode of 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 building workflow automations is an extremely powerful skill. It allows you to take manual work across multiple tools and tech stack and whatever, and automate them perfectly. Now, many people think that AI or AI agents are required in order to build such automations. But the reality, that's not the case. I started using Zapier in 2015. That's 11 years ago. That's way before we had access to AI as normal people.

0:43I mean, Google had it, but we didn't. But now with the introduction of AI tools, these automation capabilities became 100x more powerful. And the reason they're so much more powerful is because now you can benefit from the rigid step-by-step nature of the automation and combine it with the AI's ability to analyze, create, process, et cetera, do all the things that AI knows how to do. And then you get the best of both worlds. You get the rigid, solid, consistent output of an automation, plus the smart capabilities of AI, plus the AI's ability to, if you want direct different channels of the automation based on what he has analyzed and the exact situation.

1:29Now developing sophisticated workflow automations was until not too long ago, a highly sought after skill and people charged a lot of money to either build it for you or teach courses on how to do this. And in tools, you know, like NA10 and make and Zapier and all these kind of tools. The reality is right now, Claude knows how to build extremely powerful N8N automations on its own. And in order to be able to do that, like it's, and it's doing this in order to be able to complete tasks that it doesn't know how to do on its own, or I should say, it doesn't know how to do on its own yet. So all the universe that N8N has of connectivities and automations and things like that still do not exist in the cloud world.

2:17And cloud knows how to build these processes for itself so it can connect and do things that it just can't do out of the box. Now, in today's episode, we're going to show you exactly how you can use cloud to develop really complex automations without knowing anything about NA10 or code or anything else. Our guest today, Jeremy Grandilon, he is the CEO of TC9, which is an agency that designs and builds AI automation powered go-to-market engines for B2B companies. He's been doing this for a living for about three years now. So he's built probably hundreds of these automations. And for a very long way, he had to actually build it himself.

2:59And now he uses Claude to build it and he builds it for companies for live production solutions. So he's not just toying around. He's going to share with us exactly how to build an automation like this. And to be more specific, he's going to show us how to build a lead nurturing process beginning to end using this methodology. So knowing how to build lead nurturing processes is important by itself. Knowing how to build any automation you want using Cloud of N810 is obviously a lot more powerful because you can then automate anything in your business. And hence, I'm really, really excited and honored to have Jeremy at the show again for the second time.

3:37Jeremy, welcome back to Leveraging AI.

3:42Jérémy Grandillon:Thank you very much. Thank you. I'm very excited. That's a great intro. That's exactly what we are going to break down today. So I'm very excited to share that with you guys. Yeah, I'm really excited. You know, you and I exchange ideas on LinkedIn a lot, and I love following the stuff that you're doing. And we're in the same space of building really cool stuff. And I think the world right now is really crazy. Like, if you want to build something, you can. It's really just that. Exactly. And it's going very very fast. We were talking about that a few days ago. Talking about Cloud, Entropic released like I think every day last month.

4:21Jérémy Grandillon:They released 74 things in 52 days. It's like nuts. And not small things like obviously some are small but most of them are quite impactful features. So yeah, it's going very very fast. that's a that's a exciting period of time right now yeah with that uh let's get started jeremy it's it's it's your show so show us the magic okay let's go um so before before diving into the the the technical things uh maybe let's put the stage and uh and and give some context so as you mentioned i'm working in in a automation for for a few years now um for gtm purposes so basically Basically, the goal is to automate the processes that are generating revenue.

5:07Jérémy Grandillon:So mostly marketing, sales, and rev-ups processes. So that's our expertise at TC9. And with that, I have an example today to share with you. You mentioned the lead nurturing. So the scenario is you create a lead magnet. So that's more a marketing scenario in that case. You create a lead magnet, so a good piece of content that you want to gate. to collect contacts. But in the marketing world, the more questions you ask, the more friction you add, the less chances you have for people to give the contacts. If you're asking too many questions about them, they might just keep it and say that was a good resource but next time.

5:54Jérémy Grandillon:So we want to remove this friction as much as possible so we only ask for an email. But the problem with that is that one, you have to find who is this person and two, you have to qualify and enrich those contacts and make sure that you're not using the personal email because of regulations like GTPR, especially in Europe. If you want to use those contacts for sales purposes, you have to find a business email. So that's all those constraints that I just described that we are going to solve with this automation to not only talk only to the right people but make sure that we are doing this within the regulation and the rules.

6:39Jérémy Grandillon:So with that said I've prepared three things to share with you. The first thing is I will break down the entire workflow and show how important actually the idea, the process in your mind is the value now because all the rest I'm going to share with you has been done with AI. So the very starting point is, okay, I have a clear idea. And of course, you will iterate with code code and you will find new ideas and improve it. But if your process in the beginning is not clear for you, you will probably struggle. So that's the very first thing. So I've created a visual so you can see. For those who are just listening, I will describe.

7:19Jérémy Grandillon:Then I will show you the final output, which is the big NA10 workflow that has been created with me, not by me. And then I will show you how I did it in at least a piece of it, how I did it in code code. 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. three. 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, basically solid fundamentals across the board for AI usage in the business world.

8:18This 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.

8:51The 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.

9:34so 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. Fantastic I'll say two things about what you said, because I think they're very, very important. One is the idea side of it.

10:10And the other is how to develop an idea in a better way. So the idea side of it, I think, and I'm a really big believer, and I said that on the podcast several times in the past few weeks. I think the limiting factor of businesses used to be resources, how many people, how many, how much money in the bank, how many computes, how much whatever. And right now it's three things. It's having good ideas, having good judgment, and having good requirements, documents, and definitions, which connects exactly to what you said. And what I've done, like the very first multi-agent thing that I built together with Claude is a tool that interviews me about the idea to really understand the essence and push me to, instead of idea, like, okay, if you want to productize this, you need to know the target audience.

10:59You need to know which technology you're using. You need to know how frequently you're going to use it. Are you going to use it yourself? Are you going to sell it to other people? Like, it's going to ask me about 30 to 45 minutes worth of questions that I need to answer. and then he writes a PRD. He writes up 30 to 50 page product requirements documents that then Claude knows how to build, which is really, really awesome. And so knowing your idea, coming up with good ideas and knowing how to define the requirements for them are the new superpower.

11:31Jérémy Grandillon:100%, 100%. And in our business, we are building those automation. Now Claude Code builds the automation. So we could think like, That's the end of our business. But actually, we are very confident because Cloud Code won't replace what you described, like our expertise, our experience. I have almost nine years experience in sales and marketing. That's the thing. And also adding to our offer some consulting advice, where to start, how to do it right, all the steps that you described. I think our business is going to be safe for a few more years. So that's the very important point. All right, cool.

12:14Jérémy Grandillon:Let's let's dive into it. Let me share my screen. Yeah. OK, cool. So this is the idea. So that's the workflow I describe. I would go through this quite, quite fast. But the very first step, and I would describe everything for those who are just listening, as I mentioned, the first step, the intake is the visitor download the lead magnet. So they gave us an email and they have received the the resource that's very classic for for marketing workflows and that's the trigger so when we collect this by the way i created the the gated tool so we basically grab this from our website and created all those those uh those steps through cloud but that's for another another episode then i really i saved this this uh this email in a database and that triggers our workflow So then the second step is the identity resolution.

13:09So as I mentioned, the first thing we want to know

13:13Jérémy Grandillon:is is this a personal email or a professional email. We are not going to do the same steps. If it's a personal email, we want to find the professional email attached to this personal email and if it's a professional email then we continue and go to the next step. Note on that, also one value, because if we zoom out a little, we could imagine, we could say, okay, why I'm not automating everything with cloud code? Why am I using NA10? But as you said, for maintenance, not all the steps are requiring AI, so you can save in resources, you can be more consistent. So all those reasons are why we are using workflows and tools like NA10.

13:59And in that scenario... I will say two things just to add to this. I think the two places where the three decisions, whether you want to build on automation or just do it inside of cloud code, one is, is it a rigid step-by-step process? If it's a rigid step-by-step process, A, NA10 will do it cheaper. B, NA10 will do it consistently. You build an agent, an agent will do it the same way, 90 % of the time, but that might not be enough. You may want it to run 100 % of the time and NA10 will run the process 100 % of the time, exactly the same. And then the last component is really the access to other tools, right?

14:45So the one thing that Claude still doesn't do great is built in connectivity to any tool you want. And there's MCP, but it's just not as efficient. And so having access to the entire universe that NA10 has access to just gives cloud code through NA10 access to all that stuff. So it's very useful from all these reasons.

15:05Jérémy Grandillon:Yeah, and it is also safer because if you are building everything into cloud, you are not necessarily a developer and you might make mistakes in terms of security relying on NA10, they have handled those topics already. So that's also safer. So yeah, good reasons to continue using N8N. And when you think of a workflow and you choose a tool to support it, for me now, the MCP connectivity, the API, or how open the API is, is a new criteria. So N8N is very open, so you can connect it and do a lot of things into N8N. Some other tools won't be that open. So that's also a criteria for you in the future, if you want to think about it.

15:52Jérémy Grandillon:okay, is it agent ready more or less? So yeah, to continue with the workflow, so we call in that case in NA10 APIs to other tools. So that goes with your point you just mentioned. In that case, full enrich, which is a great tool to find professional contacts from a personal contact. And based on what it returns, then we go in the direction of another. we have all the errors you know pass but if it goes well then we find the person and then we start enriching so in that step we find the name full name so from just an email we find the name title LinkedIn profile company so that's all we need to continue and enrich the rest and then we continue with our criteria.

16:46Jérémy Grandillon:So that's step one, is it personal or professional? Step two, who is this person? And once we have find them. Step three, okay let's test them against our criteria. So the first one is the CRM check. Is this contact already in our CRM based on the email and the LinkedIn profile? If yes, just update me. I just want you to know, okay, this contact has been done downloading your your resource so maybe they are you know looking for extending you know renewing whatever so that's that's a good signal you want to capture anyway so we update our hubspot in our case and trigger a slight notification so we can see it in a in a channel if it's a new contact then even better we continue and we push them to more filters and that's the enrichment filter so that's where we collect everything we can you know contacts and everything and we qualify the person so that's where the ai enter the game in an a10 so we have a first qualification step which is on the person is this person matching our icp um you know is this person in the right uh location geographic location for example is this person, does this person have enough experience in its role, etc.

18:10Jérémy Grandillon:Those type of criteria, that's an AI agent at this stage. If no, we save everything we have done so far in our theorem, but we disqualify it. That's a person that was interested in what we do, but it's not a potential client. Maybe in the future, that's why we save them, but not now. Then we continue and we qualify on the company level. So now that we have identified, okay, this person is potentially a decision maker, is the company interesting for us? Is it big enough? Is it in the right location? Is it in the right industry? Your criteria. Same logic, if you disqualify here, we save them. Maybe in the future, this person will change job and we monitor our contacts.

18:54Jérémy Grandillon:So that's always good information to keep. We have many of those workflows working in the backend. But in that scenario here, if no, we just save it. If yes, we continue. And we go to the next step, which is the routing. So that's basically updating the CRM. But most importantly, once it's updated with a new contact, who is interested, who is qualified in our CRM, the next step for us is to add them into a sequence to send them a message. And of course send the Slack notification for the little dopamine hit for us in the team. But then that means that from one person downloading a lead magnet on our website or whatever on socials, we automatically qualify them, enrich them, save them in our CRM and start conversation with them and that's works behind the scenes fantastic i two quick questions one what was the tool that you started with in the beginning to get their information like the very first information you're getting about them yes uh full enrich this full enrich that's the name of the yes yes it's an api and you pay per usage or something like that yeah you can have a subscription and it will consume your subscription or you can use directly with the per cost, I think.

20:20Jérémy Grandillon:Yeah. Cool. Awesome. Yeah. So very straightforward, right? That's exactly what a human would have done. Like you check if that's a relevant person, do we already have him in the CRM? If we don't have it in the CRM, okay. How, what other information can I find about that person? Then does that, now that I have the information, does, is it aligned with my ICP or not if it is awesome if it's not okay i'll save him maybe later and and then you send them a message the last question that i have do you personalize the message in the sequence based on what you learned or is the sequence the same sequence every time yeah so it is personalized on a low level for now because i'm preparing a new one which is way more advanced but it's taking a bit of time but right now it's just uh i'm sending a voice note on linkedin that this person and just asking you know how did you find this resource was it helpful for you should we should we talk about doing more something like that and the voice note is is the same voice note or is it like a 11 labs voice with you saying the name and stuff like that no so right now it's a it's a generic one so i'm just saying, hey, how was the resource?

21:33Jérémy Grandillon:You downloaded it. But that's the thing I have on my to-do list to use the Eleven Lab to do the dynamic one. That's exciting. Okay, awesome. So let's look at the final outcome. How does this thing work? Yes. So from those steps that are looking pretty simple, let's say, we go to something like this. so for those who are not seeing the screen that's an N810 workflow I will zoom in but that's 59 nodes so you can imagine how long it would have taken me to create and set up those 99 nodes manually create and test I think that's usually the and test that's even a bigger point I agree. So if I zoom in a little, that will reflect what we just talked about.

22:30Jérémy Grandillon:Like this is the webhook. I also have some manual for the testing, some manual entry, some bulk entries for the ones that I missed before I created this workflow. Then normalization, classified email, full and rich research. I will go quite fast on those things because it's not the sexiest, those nodes conditions you know passing the results etc slack notification as you can see here some timers like that this this thing was interesting when i was creating this with my agent because i was like yeah let's just do the you know check the check the database in full and ritual emlist in that case and then move to the next step but i didn't count that it has to call the API, that takes time, and then the result has to come back to the workflow, that also takes time.

23:22Jérémy Grandillon:And it said, oh, you should add a wait step here for like 30 seconds, otherwise you won't receive anything. I was like, hmm, good point, good point. Thank you, agent. I'll say something about this. Like when back in the day, in December of 2025, when we used to create these values. When we were doing this. We were, we would save, like there was a whole process on handling issues and mistakes in the process so you can document it and learn from it. And now it just does it. It just, you don't even have to track anything. It just knows what to do and how to fix things and things like that, which is, which is really, really amazing.

24:05Jérémy Grandillon:No, exactly. Exactly. And I will show you the, one of the conversations I had with this agent, activity is the first one, which I could say. That's impressive. I will show you that right after. But anyway, that's the workflow. That's how the agents qualify the person to qualify the company. It's also documented little comments on the thing, in case I don't remember what's what. One pause on this. So all these tools, whether you're using Make or N10 or Relevance or whatever, all of these tools have built-in agents. and the trick is to know when to use them, and you want to use them when you need to, in this case, qualify or analyze information, right?

24:48Everything else runs rigid step by step by step, and then the agent says, but Claude also knows how to build the agents, and so you don't really need to know even what that means, but an agent is basically just a set of instructions connected to an AI brain behind the scenes where it can go and do something, and in some cases, it's connected to tools to actually take some actions as well,

25:09Jérémy Grandillon:but in this case it's purely an analysis step yes yes exactly good good point here uh yeah we feed it with the information that comes from the previous step and say okay this is the prompt we need this right here is this person doing this this and this they use the information of the on the person and they and they qualify and yeah hubspot steps slack steps so as you can see it's 59 nodes, pretty big stuff. I did in a few, I would say, days. I would say days, like two, three days, something like that. And I will show you right now, which for a couple reason would have probably taken me a few weeks to do it properly with testing and all of that.

25:56Jérémy Grandillon:So yeah, it's a great saving time. Let me show you. And I will say something about what I said before. knowing how n8n works helps a lot but it's not mandatory anymore like the fact that jeremy has all that experience of building n8n processes before helps a lot because you understand the logic you understand how it works when it gets stuck i didn't get to a point where it got stuck and he didn't know how to solve a problem i did get to a point that it got stuck and spent two hours on something that I can solve in six seconds because I know what's broken. And when it's close, when it's like, okay, it's going to take it eight minutes and I can do it in six seconds.

26:34Okay. I will let it run the eight minutes because I'm doing something else. But it's when it's stopping me two hours from completing the process. I'm like, okay, this is ridiculous. I know what to fix. And so knowing how N810 works and knowing how these tools work really helps, but it's really not necessary anymore because it will solve the problems that you run into sometimes in the right way and sometimes in not the optimal way but it will still solve the problem yeah 100 and uh

27:02Jérémy Grandillon:yeah i think the the cliche that says like uh you know inputs quality of the input equals quality of the output is still true the the the ai llm will be as good as the context you give it and if you add your own expertise you will be in control more of what's going on and you will you you know, say probably some tokens. That's another conversation. And some time, 100%. That's actually a good transition before I show you the conversation. That's how to build an agent. So very, very short and summarized version. You want to create files, MD files, and those MD files have rules. Pause you just for one second.

27:45MD files are markdown files, which is basically think about Microsoft Word without the fancy design, right? It's just pure text. And this is how most of this universe of agents works. So it's just the most efficient way for it to read and write stuff is just reading and writing markdown files, but it's just text. Like it's nothing fancy. You can open it and read it yourself. It's written in English or in whatever other language you want, but most of them are in English. And that's it. It's just a set of instructions in English.

28:21Jérémy Grandillon:100%. And that's actually great to add this. And the value of those MD files is, as you said, that there is no fluff and fancy visual things. So it's very light. So you can have your... Because basically an agent lives into a folder where you put those files to guide it and say, okay, this is your identity, this is your mission, and this is your basically skills and tools. and that's all described in those files and from there every time you start a session it will go through those files in a specific order and be ready to you know use those tools use those skills and etc so that's how you create an agent and that comes with what you said if you can prepare your agent in advance let's say okay this agent i will use for n8n only then a good practice would be okay let's give it a purpose.