How I Sold a $6000 AI Workflow to a Business (Live Sales Call)

In this video, you're about to watch me sell a $6,000 AI agent. This close took place over 3 separate calls back in December of 2024. So it was when I was pretty new to the space, but I still managed to close the call. So today I'm going to break down these calls and show you guys what I did well, what I could have improved on, and how you can go ahead and close a deal just like this one. So let's get into it.

All right.

So before we actually start watching these calls and I try not to cringe at myself as best as I can, I wanted to real quick tell you guys my mindset when I'm hopping into these discovery calls and I haven't met this person before. So it's a discovery discovery call, which means it's for you to discover as much information as you can about this client, their business, and what they want to do with AI automation. And in order to make sure that I'm not rambling on and letting the client talk the majority of the call, I use a framework that I call the LRP, which stands for listen, repeat, poke. It basically makes sure that I listen to what he or she is saying. I repeat it back to them to make sure that we're all completely aligned going through the call, and then I poke with a question and I prompt them for more information.

So I just wanted to throw that out there throughout the call.

I'll stop and I'll mention some times when I did LRP and I'll show you guys why that's beneficial, but let's get started.

Almost invited my note taker.

Uh, you, if you want to go for it, otherwise I'll send you a copy of this one.

Uh, no.

So it's funny actually. Um, when I said our own, I meant literally we, uh, this is different. This is a separate conversation, but my company, we actually are launching our own.

Uh, oh, okay.

Yeah.

So just wanted to show you guys real quick. That was like the first 20 seconds of the call. And it's important because I spent the first 2 minutes just kind of building rapport and realizing real quick that this client is very bullish on AI. You can see he's innovative.

You can see that they're doing things.

They have AI initiatives already in the company, which was a really great green flag for me of someone that we would want to work with because they have long-term goals with this and they have realistic expectations. A lot of times you have people on the two ends of the spectrum, which would be way too bullish and they think it's magic and they have unrealistic expectations and you know right away that throughout this discovery call you may have to try to manage those expectations or people on this left side where they're very skeptical, they need to still be convinced about AI automation, and then you know how to approach the rest of the call and sort of the questions that you ask.

So just want to throw that out there real quick. The next thing that I try to do here is basically just open the floor up to him and say, why did you book in a call today? How can I help you?

Yeah.

Well, uh, yeah, you want to just tell me about sort of what you were looking— I was reading your, your Calendly booking link a little bit, but, um, yeah, if you just want to sort of let me know, you know, what What prompted you to book a call and what you're, what you're looking to do here? So that's the way I wanted to open it up, just lay the agenda and get him talking right away about what it is he's looking to do.

You could see I wasn't very, like, I wasn't speaking very confidently there. So that was a tough watch. But now what I'm going to do is just listen until there's an opportunity for me to repeat and then poke with another question.

Yeah, I understand. I understand. So, you know, we're looking at, uh, you know, email integration, Slack. Um, what about sort of your calendar sync? Would that also be like a Google Calendar or do you use Outlook?

Uh, Google. Okay.

So what just happened there was I listened for a while and he started to break down his tech stack and what he was looking for this type of assistant. And I repeated back to make sure that we were fully aligned on the different tools. And then I threw out another question, which wasn't a great question, but just kind of like trying to get a better understanding of the tools and asked about Google and Outlook, stuff like that. But what I missed here was a big opportunity to highlight the value add that this system would bring because he basically just went through talking about the different tools he used. And what he does in those tools. And that would have been a great opportunity for me to bring light to that and say, how often are you doing this kind of stuff? And how much time do you think per week are you spending in each of these tools where this assistant would solve that? And just by me asking that would get him going more on about how much value this system will actually add. So something that you should try to do.

It's a great point you bring up because that's kind of the way that we like to work as a, you know, a very custom agency is we, we really like to understand the operations of the business, the goals of the business, and then not just help you solve one pain point. In this example, you come to me and say, hey, like, we're interested in this personal assistant, but we, you know, we've seen a lot of use cases, we've worked with a lot of businesses, so we'd like to be able to say, you know, this is the way that we think you should start to integrate because, you know, this is really just the beginning of AI as far as like getting integrated into businesses and really helping transform a business. So, you know, the earlier you start, the better. In 6 months, 12 months, like, where is this space going to be? Something that I think about every day. And just being able to start early and building up a foundation so that when these more powerful tools come out, we've already got, you know, a leg up on everyone else. So, um, yeah, we, we like to sort of, that's the way that, that I like to approach working with a client, make, seeing if it makes sense for both of us to sort of engage in like a partnership, I guess you could call it, as we're, we're sort of like a dedicated team for you and your projects. Um, so I guess that leads into my question of, you know, what are sort of some of your goals with AI integration and AI automation within your business? Is it kind of like you want this personal assistant and then that's kind of all you're looking for? Or Do you want to see like how we can continue to slowly chip away, chip away, save more time and help you grow at the end of the day?

So what I did right there was within the first 10 minutes of the call, I wanted to make sure that he understood the way that we work, which is not just a one-off project. We want to work on a longer-term partnership where we're actually deeply integrated into the business. Like I said, understanding their goals, their operations so that we can help implement solutions where they make sense. If it wasn't clear, this client found me through my YouTube video about a personal assistant. Assistant, and that's kind of the first functionality he was looking for. And what I ended up asking as my poking question was, are you just looking for this? Are you looking to have to see how we can help you chip away and chip away and save time over the course of many months? And while that was a good question to ask, it shows two things about the bullishness and also shows some of our value. But I should have tied that a bit more to actual business outcomes by saying, after we nail this first phase with the personal assistant, where's the next area where you'd like to be able to buy back 5 to 10 hours a week?

At the William level. Uh, I'm, maybe I didn't mention I'm the founder and CEO. So, okay.

So if you didn't hear that, he basically just said that he's the founder and CEO of this company, which was great because I didn't even have to ask about that, but it's something I needed to figure out if he was actually in a position to make decisions within the organization and dedicate a budget towards something like this. So now I've validated that he's qualified. They're bullish about AI. I'm going to keep going on.

Um, but the idea that the operations bot would be able to, again, take the next steps. From our meeting notes and either populate them inside of our Notion space immediately, or would be able to recognize when that stuff is, you know, has, has been populated and can then, you know, our operations team can say, hey, tell me all the tasks for Bob. Give me all of Bob's tasks that are due this week, right? Whatever that is. So on one hand, there's workflow efficiency within operations. Um, there's again, bill recall, all of that, just what you would expect. But those are the main domains at the moment. I don't see us having it directly link into QuickBooks and send out invoices automatically or things like that. We've got other systems to do that stuff. Does that give you a good picture?

Yeah.

Yeah.

That was awesome. Um, I mean, you know, typically the first thing we do is we like to break down, because obviously there's multiple pieces. Um, And it seems like the first thing here would, you know, the most important aspect is always how can we get all the information that you have into the database so that the agent has context of everything that's going on? You know, data and context are the two most important things, especially with something like a personal assistant.

Yep.

So yeah, it would really just be diving into the different integrations you have, all the data, and then first aspect is can we get that into some sort of database for you so that it's in, you know, in an optimal way so that the agent's able to recall all that information whenever it's prompted to. Um, and then, you know, figuring out some sort of automated system so that whenever you change information, whenever you have new stuff you upload in there, that that process all takes place, um, you know, in the backend for you as well. So, yeah, um, another question I had was how big is the organization and like what does that operational piece look like when it comes to, you know, the next phase is where we're trying to help automate some of those, um, interactions as well.

I don't love what I just did there. What happened was he talked for a while about some of the operations or some of the different departments and what he would be looking for out of his assistant. So just dove more into the scope of this first phase. And he talked about a lot of things. He talked about a ton of different tasks that he would use the assistant for. And rather than me poking more at that pain point, I basically said, okay, I hear you. And then I tried to prove expertise. That's what I was doing there is I tried to throw out that stuff about the vector database and building that automated pipeline to convince him that I knew what I was talking about and that I was the right fit for him. That was not a bad thing to do. But what I should have done before that was say, okay, you just told me all of these processes that you want this personal assistant to be able to do for you. How valuable is that? How many hours is that going to save you? And what that's doing is it's making the ROI clearer. It's also quantifying his pain and bringing more light to it. And then it anchors the price and allows me to go even higher. Another good question would have been, since you're saving 2 to 3 hours a week with this new assistant, what can you dedicate those 2 or 3 hours to? And by putting the client in that position where they're thinking about that and they're imagining a world where they have 5 extra hours a week, indefinitely, it just opens up some cool ways to keep the conversation going.

So you're pretty eager to get this, get this out there.

Um, yeah, and it's just, it just comes down to the integrations I had in my video was like, it was Gmail and Calendar and that's pretty much it.

I mean, I had to send a Slack message, but there's so many more actions in Slack besides just sending a message. You want to be able to search through there. I'm sure you want to be able to recall certain information. Um, and the same thing with Gmail. You want to be able to not just send an email or get emails. You want to be able to Reply to drafts, or reply to threads, create drafts, label emails, delete emails, move them around, mark as spam, whatever it is. So we want to be able to make sure you have every single action. And every action in a, you know, every action we add is another layer of in the prompting we need to make sure that the agent understands what to do, when to do, when to do it, and how to do it.

So, yeah, um, and the truth is, really quick, I don't actually need all of those. Um, like I've got a labeling system. I like kind of use it. I could probably use it better. And I know that there's a way to have the AI just kind of like automatically apply labels based off of what it thinks, but that could also be a little bit of danger. You know, I think I'm a big fan of artificial intelligence and we're, you know, we're in like, we're in day one of whatever this thing is going to be. But I also am not quite, I think that anything that it does needs to be vetted.

100%.

Like it's only the lowest stakes emails where I would say, just respond to so-and-so, right? Like the, it's always going to be drop it in drafts, right?

Yes, you're 100% correct. I agree. And, um, you know, I'm working through a project right now where, you know, we're doing automated research, which is great. Um, and then from there, taking that research and creating like LinkedIn posts and blogs. And I told the client, I was like, how about we drop all these into a spreadsheet for you? So you're able to go in there and, um, You know, basically just every week we'll have like those, those 3 automated posts, but we don't want to just post them on your LinkedIn. You know, you just never know.

Uh, I mean, you know, it's consistent.

It's been cool. And also one aspect that we're trying to add in is AI generated images, infographics for the LinkedIn posts. And especially with those, you want to make sure those are checked as well. Obviously we'll get to a space. I don't know if you played around with Sora at all, but, um, that's been really cool, but you know, it, it, it just gets smarter exponentially every day, which is cool.

Man, that's kind of cool to see because I remember thinking to myself, I can't wait till image generation gets good enough for being able to confidently make some graphics to post on LinkedIn and stuff. It wasn't there yet, but that's beside the point. What happened there was this also just validated to me that this person is very, very realistic about AI, and I really liked that because that helps me not have to worry about managing expectations. I have to set expectations and hold up to certain expectations, but we don't have to play that game of making sure that we're bringing them back down to earth.

I guess I had two questions. One is, um, your buckets of hours, I guess, how, what are, what are those tiers? Is it, I don't know, $20,000 for like $20,000? I get, yeah, I mean, I'm throwing numbers out there, but what is that? What does that break down to?

Yeah. So the first one is going to be $4,500 for the 20 hours and then, um, $8,000 for 40 hours.

Do you feel like that's something where you build out? A version of your personal assistant AI, provided we're able to get you, you know, everything you need in a timely manner, you know, login information, database API, I don't know, API links, whatever that is.

Yeah, I, like I said, it's impossible to estimate, but I really, I do think so.

Um, considering, like I said, the toughest part here is going to be understanding where your data is coming from and how to make that automated. Um, that usually is the biggest chunk is setting up that foundation because that's the most important part. And then from there, once we are able to connect all the systems, which in this case, um, the integrations don't seem like it'll be too challenging. It just seems more like the end 20 piece, 20% again will be the prompting and testing where that's the only, that's the only area where I could really see any spillover would be the, the, the basically refining to make sure that this thing's 100% ready to go for you.

Okay, so I don't love what just happened there, and let me explain why. Ultimately, when you get to the end of that first call, the question is going to start to come up in the client's mind of, you know, I wonder how much is it going to cost me, or how expensive it is to work with this person. And so the client asked me basically like how we work, and we talked about different models, and we ended up considering maybe just kind of working together for 20 hours. And so naturally the question is, well, do you think you can get this done for me in 20 hours? First of all, I think that maybe you should only use an hourly model if you're first starting out and you need to get experience, and that is a safer investment for the client. But like I've talked about many times before, you don't want to be tying yourself to an hourly rate because that's just— you're putting yourself in a box. But pricing aside, what I should have done here, I should have just not answered the question. I don't think there's anything wrong with saying, you know, the point of this call and the next discovery call is to scope out the build to a point where I feel comfortable with everything that we need to be able to do for it. Because at this point, I have no idea how much data he has that he's expecting this agent to have access to. And I've even said in this call probably 2 or 3 times, the data is the most important part. That's what takes the longest, is getting all of that right so that the agent has all the context it needs to actually perform. And without understanding what the data looks like, how much it is, the format, where it lives, I should not have been saying anything about how quickly I could get a POC spun up or if I could deliver in a month.

Like I said, anything that, that pops into mind before our next call too, we can bring there and Um, yeah, just dive into it and we'll, we'll, that way we'll be able to bring you like a very outlined build strategy, a very outlined wireframe of what we think the build will look like. That will also contain, um, our estimated timelines on that for each, each step of the build. And, uh, the main thing I want to talk about for the next one will be, um, you know, besides those integrations will be what your data looks like, where it's kept, and how we want to get it in there. So, um, yeah.

Yeah. Well, so let's quickly, what about, um, yeah, what's your Friday look like?

Okay.

So at this point, I basically concluded by saying what I should have said earlier, which is we still need a lot of scoping around the data. So you can see I ended off the call that way. And now what we're doing is we spend that last minute coordinating our schedules and booking in a time. So that's a great thing you want to try to do is at the end of the first discovery call, just book in a call while you're both still on the call. And then at the end of the second call, try to book in the third call while you're both still on the call. But that's kind of how I wrap this one up. And now I have some information to head into the next one with, but I don't have enough yet to give a price or like I said, realistic timelines.

How are you?

I'm doing well.

Doing well, actually. Just, uh, just got into, um, I just drove like 3 hours in the snow. I was, I was, I was thinking I might have to, uh, email you guys and say, hey, um, I might be a few minutes late because I didn't expect the roads to be so, so bad. Especially I got up and, and left at like 6, but I made it just in time. So doing well. How about you guys?

Classic Nate trying to be charming, trying to build rapport. But now let's actually get into the meat and potatoes of the strategy call.

The process of still scoping out a build. It's about the questions you ask and about the, the way we talk about, um, just like the goals. So I'm glad that you have that, that sort of mindset here.

Um, also, and so as long as it goes to, I don't know. So I don't, I'm not a database guy. I don't know. I don't know how that works, period. Like I learned about a vector database from your videos. That tells you, uh, and don't get me wrong, your videos are great, but like I still don't know what the fuck a vector database is, in short.

It's, they're confusing. Yeah. And honestly, like, this is something that I tell people. Um, I feel like I've got a good grasp on it, but there's still so much, um, under the hood that I don't get yet. So much math that goes into it. Basically what I tell people is I understand maybe about 80% and that 80% allows me to get your agents to work, but I don't need to understand the formulas and the math and all of the deep, the deep down embeddings. Um, but I, I think I understand them well enough to be able to pull back metadata, filter through things, understand how to do it optimally. And like you were talking about, have a big social database, but maybe not having every agent have access to the entire thing, but pieces of it. And be able to filter and retrieve through certain sections, which is super cool. So that's, I've been pretty loyal to Pinecone with that right now, but I've been exploring some of the other vector databases like Supabase and Quadrant. Because yeah, you know, it's, it's those things where right now I've been loyal to OpenAI, N8N, Pinecone, but that could change. You know, VAPI has been also our voice, voice, uh, agent go-to.

Okay, so that was a bit of a good and bad mix. I was able to relate to the client and we kind of had a laugh about the technicalities of vector databases. But I don't love the rest of the piece of what I said because that could instill some doubt in the client. So what I should have done was taken a technical concept like the things that happen under the hood of a vector database and just transform that and communicated that into business value. So instead of saying, I understand 80%, which is enough to get your agents to work, I should have said, yeah, completely hear you there. Vector databases are pretty technical, but here's why it should matter to you. And here's like what we need to do with it. It's going to let your agents be able to accurately search through tons and tons of stuff quicker. It's going to be cheaper than if we basically made your agent read through all of your documents every single time. And so that would have probably clicked with the client a lot better on a personal basis, probably, because that's where I think reality is going.

Certainly in sci-fi dystopia, right? Each, each mega corporation has its own AI. Um, and I bet you where we're going in this reality is that the AI are just going to start talking to each other. We're already seeing that in social media anyway.

Completely agree.

And, um, one way that I talk to my partners about this kind of stuff is like, we're basically trying to create like interns where you can tell them like what to do sort of thing. They'll compile stuff. It's not always going to be perfect, but they, they get you started. You're able to give feedback and they'll kind of go back and do it again and talk to these other people about it. Um, and yeah, like you said, agents that can talk to each other and talk to each other hands off is the goal. And you know, that's the kind of stuff that happens in workflows already is like just agents pass data between each other and something that I've been doing a lot recently with my agents is I have them talk to each other and Like if, if it's not good enough, they'll send it back. So some, like this agent will send over like a newsletter article to this other guy. And then this agent will read it and send, um, like some information to a different one that will like check it. And then this agent, if it's not good enough, it'll send it back to start. And they'll just continue down that process until the final checking agent says it's good enough to go. And then that's when I get to see that output, which is really cool.

Let's bookmark that. That's fantastic. Um, so once one space where I'm a bottleneck is in our marketing space.

Okay.

That was pretty cool because what I did was I listened to him and I basically like threw in some insight from some other products that I've worked on with having agents kind of use like an LLM as a judge. And he loved it. You could see, he said, let's bookmark that. And he was very excited about that. But then I'd miss out on an opportunity here because he literally explicitly said to me one area where we we have a bottleneck, and then he starts talking about it. But I never go back and address that bottleneck by saying, how many hours a week are you losing because of that bottleneck? Or what would the value be if we could actually use AI and use automation to get rid of that bottleneck? And then once again, we're just poking the pain points and we're shedding more light on them. So it becomes very clear for the client.

Having agents check at every step before it passes through, uh, it really opened my eyes. And then I saw just the power of— I think that's where agents are able to get smarter too, because they have that memory and they can see what didn't work and what did pass. And just continue to get smarter and smarter as we sort of adjust the prompts and all that. So yeah, definitely cool stuff that we, we could work on in the future as this kind of stuff gets, gets smarter. It's just so exciting. But yeah, well, I wanted to, one thing I wanted to dive into today would be specifically the inputs that you're looking to have into the big overall database. What those inputs look like, specifically the integrations, and then like how often do we need to be able to feed in, you know, dynamically? Is it every day? Will we have new stuff to feed in every week, every month? What does that sort of look like?

So what I did right there is I tried to bring the conversation from kind of a fun use case, which actually is the bottleneck that I maybe should have been poking at a little more, but I tried to bring it back to the initial conversation where I needed to really scope out how much data that he has. And the frequency of updates and deletions and stuff like that. So now I let him talk for a while, I listen, and then I follow up about that.

For the most part, it's Dropbox, Notion, Slack, Gmail, and yeah, otherwise AWS. So, you know, at some point I think it'd be great to have Ari's output, just like a web scraping, you know, if we can have it listen to a YouTube video and pull a transcript and summarize it, for example, or if it can, you know, scrape a website or, and say like, oh, hey, this is, this is what Deloitte says about themselves, right? And we can figure out, because then obviously we can do something with that information. So some capability to interact with the website. This isn't a tool, but it is the last thing that's on my mind is like citations that link to where it found that stuff. That would be really, just really helpful from—

Yeah. Yeah, 100%. That's, uh, definitely possible. One of the products I'm actually working on right now.

Don't love that. He just spent 10 minutes talking about the data sources and transformation that they're looking to automate. He ends his kind of breakdown with literally saying, that would be really helpful for me. And I say, oh, okay, gotcha. This is something else I'm working on. I don't know what I'm thinking there. That is one of the times where he says, it's helpful for me. I say, how helpful? If we can automate this for you, we could save your ops team 5 hours a quarter. Uh, that's probably low, but more than that. What could we actually save you if all of that process is taken care of now? So learn from that lesson. After a big breakdown like that, relay it back, poke with another question, but also try to make the value clear as you're going through the scoping. I consider that a win because I just got tons of information about where the data sources are and what we need to do. But once again, I should have just relayed it back to business value.

Because the first phase will be data ingestion, and that is what I imagine taking the longest, is basically just optimizing all of your data in an automated pipeline to get it into your vector database. And that's, yeah, like I said, that's what's going to take the bulk of the work. So if we were able to maybe just start with one of those sources, get you something up and running in Slack that you can see and test out, and then it's like, okay, yeah, let's start to add our Notion now. And then now let's add Dropbox, that sort of thing. So, okay. Yeah. I think that that makes sense and we'll, we'll align in early January and just, uh, just sort of have a conversation about it.

Sounds good. Um, so really quick, when you say ingesting our data, how, what would that process look like? Um, and how would that work? And how is that different from just like connecting the bot to Notion through one of 8n8n's, um, triggers or something like that? Uh, and then again, I'm always saying that because I have that baseline from the videos that I've watched, but I don't say that from a space of knowledge. I'm genuinely curious.

Yeah, basically, um, we want to get everything in that source into a vector database. And it's not just as simple as plugging in Notion to Pinecone. We have to optimize the data, create some sort of pipeline that we can just basically pull everything. It'll run through this logic to optimize it with metadata, um, with the right tags. The right embeddings and then put it into vector database. We have to basically load it in correctly, embed it correctly, or not embed it correctly, split it up, chunk it correctly, get it in there. A lot of testing to make sure that it's actually coming back accurately because sometimes with the vector database, it can start to hallucinate a little bit if you don't sort of split it up right. And after we get everything in there, we want to set up that automated pipeline so that if you do add new tasks, new pages, they'll also go through and it will, you know, it'll be a robust system. Um, and so that's basically that process of getting it into vector database because that's going to, ultimately it's going to be able to run quicker. It's going to be run, run more efficiently. It's going to, um, help pull you more accurate results back when you're asking like, hey, what was, uh, Bob's task on the 26th? And, um, like, what were the action items and that sort of thing? So, um, it's all about the data and that's the big chunk is how do we get that in there and how do we get that in a robust system so that you can manipulate things on Notion and not have to see it happen in Pinecone, but it is happening for you.

Okay, so that was interesting. I didn't really love the answer at first, but then it ended up being a little bit better. And the reason I say that is because he asked, what does ingesting mean? And what's the difference between doing that and just connecting the agent to something like Notion? He didn't care really technically what that means. I didn't have to talk about embedding, splitting, chunking, all that kind of stuff. What I should have said is it's just a different strategy to provide context to your agent. Going through a vector database is going to let it be cheaper, faster, more accurate compared to if we just have the agents searching through Notion, which could be slower, more expensive, and all this kind of stuff, because that's what he wants to hear is cost and efficiency.

Well, really quick, looking at the calendar, are you thinking— so the 1st is a Wednesday. Are you thinking like that Friday, like, you know, Thursday, Friday, 2nd or 3rd, or are you—

kind of breaking for Christmas and all that kind of stuff. And we decided we're going to meet up after the new year. So we find a date that works and now I'm going to head into that final call with this client.

Um, I will go ahead and share screen over this build strategy unless you guys have anything you wanted to talk about real quick before we sort of dive in here and go over some of the details.

Uh, nope, just excited. Okay, well, we'll get forward, whatever.

Okay. We have a more detailed doc that we would go over sort of, um, once, once we're actually really launching this, uh, this project. But obviously for now, it's, it's, it's just going to be focused on that sort of personal assistant that we had talked about. Um, we talked about some of your data sources like Notion, Dropbox, um, Slack, Gmail, um, managing information, being a personal assistant for you and with the long-term goal of potentially pushing this solution out to more employees within Connexus. Um, but the initial focus here is quick and easy access to your data, um, being able to interact via Slack. And, um, obviously having a, a good knowledge infrastructure of different tasks that is going to update automatically, um, and just that sort of, uh, capability. So that's sort of like the general overview, of course. And this is what we looked at doing for the actual build strategy. Like we talked about, the first phase would be the data ingestion, getting everything into a vector database. Um, we talked about your different data sources. So far we've been able to work with all these sources. There's nothing too complicated. There's nothing that, you know, doesn't have any endpoints we could connect to. So we don't see any major complications there. Um, it, we would obviously have to get into the details, like what the data really looks like. I don't assume it's going to be too complicated, but, um, that's obviously how we're going to start off. And then we will do a lot of testing before we really push into integrating with the tools like, um, you know, Slack and your email. Obviously a lot of testing is important to see how the metadata is going to work, what type of embedding and what type of chunking and splitting we should do to make sure that everything coming back is accurate. And then that way we're also going to explore sort of doing some namespaces up front. That way when you do have wanting to push this solution to other employees, we'll already have like a separated sort of system for information specific to each person or, you know, if you guys want to have access to all the data, but not all the agents should, that sort of thing.

Okay. So now we're at the point of the call where I have a proposal and I'm talking about, this is what we've talked about, are we aligned? Honestly, I would recommend that you bring something like this earlier than the final call. It ended up being that we were able to close on this call. And if you notice what I did here was I have all of the tech stack listed out, I have all of the functionality, and I'm reading it off to make sure that he agrees with everything that I'm saying so that we can ultimately use this as the functionality requirements and the definition of done for the system. And the whole point of scoping is that you can get to a place like this where you confidently understand exactly how you're going to build it and what the connections are going to look like. And if you haven't scoped it out enough to be able to say that, then you're not ready to close a sale because you're not ready to talk about timelines and integrations or put a price tag on it.

For the most part, what this agent will be doing is waiting for commands. It's not going to really be taking action on itself, right? So, um, you know, there's other integrations that we've done with basically like an inbox manager that takes emails and can sort of send them around, label them, respond to certain ones. But we're looking for more of like a, you will be specifically prompting this when you want it to do something.

So I think one tool integration to add to this is search, you know, like being able to search Google or something like that. Uh, I, that is going to be a thing that would be very useful for us to have upfront. Uh, and partly, for instance, whether we're collecting blog post information or something like that, we'll want to be able to just you know, have it, have it search and support our efforts, uh, which also leads to the automated element that like one thing that could be really useful is does a search and collects information into a giant summary and sends it off and, and shoots it off internally to some database or something like that. So I do think there are certain unprompted automations that we would want to add. Um, but in terms of like proper autonomous agents. Not yet.

Okay. And so when you say like searching, do you mean you would be able to prompt on like certain keywords that it would go look for recent articles about?

Exactly. Like, hey, go search Google for, or hey, pull this from Wikipedia or not even, right? Rather that it has the ability to do whatever, you know, collect some information and give me a document or, you know, whatever. Right. Um, and it does, you know, it knows that Wikipedia is a pretty reliable source. It knows that like New York Times or whatever else are like reliable sources, but then it's not afraid to search for other things. But at the end of the day, that, you know, maybe it's got a preference list for sources. Um, and it knows to, or at the very least it has the ability to go retrieve information from those sources online as part of the request. Okay, cool.

And, or, Um, where we'll also obviously be able to come back with like, okay, here's a quick summary of like what I found. Here are the links that I used. That sort of thing. Okay.

Exactly.

So you can see what kind of happened there was even though we had talked about this stuff on the first two calls, we saw that we weren't aligned on something already, which was the ability to have some autonomous web search, which is fine to add in. But the reason why you want to list all of this stuff down as clearly as you can and avoid as much ambiguity as possible is to avoid scope creep because you don't want to be two weeks into the build, three weeks in the build, and then The client wants to add more things. So that's the kind of the whole point of getting all this stuff written down as clearly as possible. That's why in-depth scoping is required to understand every little nuance of this build that could potentially pop up. And then you can bring it like a proposal like this to align on during the call.

But where I'm at right now is as far as next steps, um, I know we've had a lot of calls, which has been good. We've gotten, um, to know each other a little bit. We've gotten to understand sort of the way we work. Um, and so. Recommendation here would next call, we would want to, um, it would be like the project kickoff call. Um, we'd really get started from there. We would have, um, one of my, one of my devs would hop on the call too, just to make sure that we're, we're both aligned so that we could pretty much kick off, um, right away after that call. So yeah.

Um, any questions that you guys have about moving forward with this?

Um, one thing that I'd want to throw out is I would love to hear, I know we talked a little bit about, you know, end of January, we'd love to see something, but Um, with the more calls, things have been delayed a little bit. I would like to know what you guys are looking at here as far as the urgency. Um, ideally, what is it? What does a good timeline for this project look like for you? Um, and then any final thoughts or questions that you've got?

Honestly, as soon as possible, um, is the— that's the timeline. Um, there is no urgency from a business perspective. Um, we're not promising this to anybody. This is totally internal. Uh, but it's, it's all directly related, right? The sooner we get this, the faster we can begin to do other things. One, to test, you know, two, to figure out like our own processes will be augmented by this. So I'm looking forward to having increased automation in our own systems. But in terms of, you know, we've got no client recommendations or anything like that. Like this is purely an internal effort. So as soon as possible is ideal. And I recognize that that's a balance. So yeah, so I guess I would say, you know, you let me know what you think is possible. If end of January still for some reason becomes possible because it's actually pretty straightforward, great. You know, like to not have this go into March, right? So if we could say like, you know, by end of February, but if we get into February and you're like, hey, actually we need to add write capabilities to Dropbox because Notion's a dead end and we need to be able to update the RAG database, uh, in, you know, the, the Google spreadsheet in Dropbox, for example, right? Like, I get that too. So, yeah. Yeah.

Okay.

Awesome.

I think that that aligns really well with what we were thinking. Um, I don't see this pushing into March. Um, just as a ballpark at the moment, definitely don't see this pushing into March. Um, especially, especially since you, if, if we sort of agree on that, then You know, we'll, we'll pretty much, we'll make it a priority to make sure that it doesn't push into March, um, unless any unforeseen things pop up and it's just like really complicated for some reason, which I don't think it will be. But, um, yeah, okay. So that sounds good to me. Um, that would give us sort of, you know, 4 or 5 check-ins, um, throughout the process, um, just to make sure that we're moving forward as, as planned. Based on estimations, I don't really see this taking anywhere upwards of I would say 40 hours max would be my estimate right now. And so what I was thinking is ballpark, I think that maybe doing $3,000 upfront and then maybe a $3,000 upon completion, which would put it at a $6,000 total project. That's sort of what we were thinking based on, you know, like I said, just scoping out all of the integrations and, uh, the data ingestion piece up front. I think that that makes sense as far as, um, the timeline and sort of the resources that we would dedicate to this.

That is so tough to watch. First of all, I'm not speaking confidently at all. And that kind of stuff is important when you're trying to sell this stuff. Because I don't have a sales background. So I don't have these sales tactics and I'm not a pushy salesman. So speaking like that, and then you've also got the aspect of just being transparent, so telling straight up if I think something will work or if I don't think something will work, just trying to build goodwill. And then the final thing is being able to back stuff with facts, because ultimately most decisions in life come down to a math problem where if you have data, you can make a strategic data-driven decision. And what you just saw me do there is I threw out a price. I was probably sitting there with my feet shaking and just waiting to see what he would say back. But what I should have done is been able to justify it by saying, We're charging you this much. This is why. We've done the math and we're saving you this much time over these different departments, which basically translates to this much dollar savings. And you're going to make your money back in 2, 3 months, if not quicker. And then over the course of a year or 2 years, you're netting tens of thousands of dollars. And then you just stand on that because that's objectively true. But what I did is I said, I think that this makes sense based on timeline and resources. And that's just horrible. If you think about the way the client now perceives me in the future, if we want to work on more and more, which is the goal, it's hard to break out of that barrier of now being perceived as an hourly worker, even though I tried to set that foundation upfront in the first and second discovery calls about the way that we want to ingest in their business as a long-term partner. So really, really don't like the way that I kind of approached the pricing in this conversation. Cut me some slack. This was in December, but the reason why this worked here is a couple things. What I still did well throughout this process was I used LRP. I listened to everything he was saying, I repeated everything back, and then I asked more questions. And because I was able to scope out the build so well, we now have a full build strategy that completely aligns with what exactly he was thinking. And through the other calls where we had kind of bonded and we talked about kind of passion projects and other use cases of AI, we got to this place where trust had been established. So a lot of stuff happened in those 3 calls, and I obviously couldn't show you guys everything, but What I wanted to do is now kind of just recap with 6 key lessons from what we just looked at. So the first one is something that I didn't do great in these 3 calls, which is to prove the value with ROI. Collect your data before and after. Without this baseline data, you cannot actually prove ROI. Keep it simple. Focus on 3 to 5 key metrics that align with business goals like hours saved, lead conversion, or error reduction. Translate your technical improvements into financial outcomes because clients can actually understand that. So like with that example earlier about the vector database, rather than me talking about the metadata or the Euclidean distance or whatever technical jargon I was throwing around, I should have just translated that to the agent being able to respond cheaper, quicker, and more accurately. And hopping right off of that ROI stuff, you want to price based on the outcomes, not the effort. Value is based on result. Value is not based on time. Never sell hours or number of nodes or the complexity of the build. Sell business transformation. More leads, less churn, reduced cost, whatever it is. And that's how you can actually pitch out a number and confidently justify it rather than what you just saw me do where I said, I think maybe $6,000 makes sense. I think that sounds good. That was just hard to watch. And once you start understanding how to actually price based on value, it makes it clearer for you and you're not going to undervalue or underprice your services, which is a big issue that we had for a long, long time was severely underpricing tons of our builds. Master consultative selling, not technical selling. Position yourself as a problem solver, not a tool pusher. Ask deep questions in discovery like, what business problems are we solving here? What result must this deliver? It's important to be technical enough to understand how to scope out a build, but speak not technical when you need to so that the person can actually understand what you're saying and not get confused or overwhelmed. Use analogies and visual aids instead of overwhelming the client. You can see in the call when I used that intern analogy, he loved it. Use a structured framework, and that doesn't mean to enter the call with a script on your right or a set list of questions that you're going to ask in order no matter what, because you have to be fluid and you have to be a human. But if you have a framework like LRP where you listen, as soon as you listen and it's your turn to speak, you recap, and then you just poke another question, that's going to help the conversation flow in a way where they're speaking the most of the time, which they should be in a discovery call, and where you're getting a ton of information that later you can revisit the call read the transcripts and have it all there in front of you. Turn every win into a growth engine. After showing that ROI, that's when you can start to ask for video testimonials, case studies, referrals, stuff like that. And that's going to help you in your discovery and your sales if you're facing any objections or like you could see in these calls, I was able to talk about other products I'm working on or other things I've done, which helped build trust for this client in me and prove that I could do what he was looking for. And then finally, just to maintain your sales rhythm, make sure you're researching and you're prepping before a call, not just hopping into it a minute late with no idea who the person is. Listen for 70% of the time, speak for 30% of the time. Focus conversation on business value, not technical details unless you're specifically asked, cuz sometimes the clients do like to nerd out a little bit as well. And then follow up with low pressure, high value touchpoints, insights, quick wins, or relevant examples. So that's gonna do it for this one. What I'm gonna do is drop this document as well as a resource that pretty much broke down everything that I just broke down in those 3 steps. Calls, and I'll drop that in my free school community. All you got to do if you want to download that is hop in using the link in the description. Like I said, it's completely free. And once you get in here, just search for the title of this video or go to YouTube resources and find the post associated with this YouTube video. And in there, there'll be a PDF just like this where you'll have all of the resources that we just talked about. And if you're looking to take your skills further and connect with people who are running businesses using any, then, then definitely check out my Plus community. The link for that that's also down in the description. Not only is this a great community of people who are passionate about end-to-end and monetizing their skills, but by the time you're seeing this, we would've just dropped this new course called Automation to Monetization, where you learn how to actually launch your AI freelancing or consulting business. So if you like this type of content that you've been seeing from me on YouTube, this full course covers a lot more. Anyways, that's going to do it for this one. If you learned something new or you enjoyed the video, please give it a like. It definitely helps me out a ton. And as always, I appreciate you guys made it to the end of the video. I'll see you on the next one.

Thanks guys.