Latest / Ops Cast / Practical AI for Marketing and Ops with Tracey Fudge
Transcript
- 0:24Michael Hartmann: Hello everyone, welcome to another episode of OpsCast, brought to you by MarketingOps.com and powered by all the MoPros out there.
- 0:31Michael Hartmann: I am your host, Michael Hartman.
- 0:33Michael Hartmann: Flying solo as a host this week because we are recording this during Mopsapalooza 2025.
- 0:41Michael Hartmann: So if you're there and listening to this later, we hope you had a good time there.
- 0:45Michael Hartmann: Uh, Mike and Yumi, I'm sure we'll be back soon.
- 0:48Michael Hartmann: In fact, we've got planned a recap, so watch for that when coming into your inbox.
- 0:52Michael Hartmann: So today I am joined by Tracy Fudge.
- 0:55Michael Hartmann: She is an AI operations architect and agentic workflow designer, and uh, she's doing that on her own with her consultancy AI by Thrive.
- 1:03Michael Hartmann: Tracy has spent the last few years deep in the AI trenches experimenting with language models, automation frameworks, and what she calls agentic workflows.
- 1:10Michael Hartmann: She helps marketing and operations teams not just understand technology, but actually put it to work.
- 1:15Michael Hartmann: So today we're going to be talking about how to move beyond the AI buzzwords, not that those are out there, to build real usable systems that save time, spark creativity, and drive better business outcomes.
- 1:26Michael Hartmann: So, Tracy, welcome to the show.
- 1:29Tracy Fudge: Thank you so much, Michael.
- 1:31Tracy Fudge: I'm really excited, and I'm I am, I'm I'm missing MAPSA, but uh I'm there virtually and in my heart, a lot of my friends are there.
- 1:39Michael Hartmann: Me too.
- 1:39Michael Hartmann: I have serious FOMO going on right now.
- 1:42Michael Hartmann: Well, I'm glad, but I am I'm grateful that we've been able to stitch this together.
- 1:46Michael Hartmann: I was going back to some of the conversations that you and I had to try to get this started.
- 1:50Michael Hartmann: It went all the way back to it is now late October.
- 1:54Michael Hartmann: Uh, and I think it's we started in February sometime.
- 1:57Michael Hartmann: So um good things come to those who wait, right?
- 2:02Tracy Fudge: Yes, exactly.
- 2:04Michael Hartmann: All right.
- 2:04Michael Hartmann: Well, why don't we let's start with this?
- 2:06Michael Hartmann: Like, let's start with maybe a little bit of like a short version of your journey.
- 2:09Michael Hartmann: Um in particular, like the last couple of years, like what led you from marketing and operations, uh, kind of the traditional one we were just chatting about this before we started recording about how so many people are still focused on platforms, um, and getting you into AI systems, agentic workflows, things like that.
- 2:29Tracy Fudge: Yeah, so it was it was an easy transition.
- 2:31Tracy Fudge: Well, one, I've been in tech my whole career.
- 2:33Tracy Fudge: Um, you know, I started in software sales uh before I really understood what software was.
- 2:39Tracy Fudge: You know, my explanation was, well, what's software?
- 2:41Tracy Fudge: And I was like, I don't know, I think it goes on hardware.
- 2:43Tracy Fudge: So that's how far back it goes.
- 2:46Michael Hartmann: You're not gonna start talking about floppy disk drives, are you?
- 2:49Tracy Fudge: You know, there was a day when we when software was a new word.
- 2:53Tracy Fudge: Um, and you know, so then fell into mops.
- 2:57Tracy Fudge: Um, you know, I was managing uh social media platform for somebody, and they're like, hey, can you go manage this email platform we have?
- 3:05Tracy Fudge: And that's sort of, and most people fall into mops by accident.
- 3:08Tracy Fudge: I'll start.
- 3:09Tracy Fudge: You know, there's no college courses or anything like that.
- 3:11Michael Hartmann: Not yet.
- 3:12Tracy Fudge: Not yet, yeah.
- 3:14Tracy Fudge: But the um the the AI part of it was just something that was just intriguing to me.
- 3:20Tracy Fudge: And you know, systems are connected via API.
- 3:23Tracy Fudge: So the agentic part of it was already being done.
- 3:26Tracy Fudge: We just weren't calling it that, right?
- 3:28Tracy Fudge: So when I um decided it to go deep and really learn, you know, on what agentic platforms were, you know, I had known Zapier and Zapier, you know, nobody really knows quite it.
- 3:41Michael Hartmann: They told us that we've had people on from there.
- 3:43Michael Hartmann: It is Zapier, like happier obviously fingers.
- 3:46Michael Hartmann: Not that we're like, we're not this is not a promotional thing, but I think I now have that that rhyme in my head.
- 3:54Tracy Fudge: And I don't know how far back you've been using it, but I was using it before people did correct me on what to call it.
- 4:01Tracy Fudge: Um, and uh so that's been gosh, and I mean well over 10 years.
- 4:05Tracy Fudge: But um anyway, the the whole AI part of it, the agentic part of it was sort of an easier transition to sort of understand what this all meant.
- 4:17Tracy Fudge: And obviously I was curious about well, what's an LLM?
- 4:21Tracy Fudge: And oh, there's other types of LLMs.
- 4:23Tracy Fudge: Oh, what do these frontier models mean?
- 4:26Tracy Fudge: And then putting them all together and making the intelligence layer over the connections.
- 4:33Tracy Fudge: Um, you know, and that's just that's much more complex than people realize because you go into the conversations around data.
- 4:41Tracy Fudge: And when you're inside of an organization, sometimes marketing doesn't have all the data or the systems.
- 4:47Tracy Fudge: You know, I it systems sit over there.
- 4:49Tracy Fudge: So that's a big uh gap that's still there.
- 4:52Tracy Fudge: And teams are starting to come together and realize that AI kind of goes over the whole thing.
- 4:57Tracy Fudge: Um, and AI needs to work on the same set of data, uh, not the same fields per se, but let's all talk about the same data.
- 5:07Tracy Fudge: Let's make sure that the pipeline reflects in the CRM, et cetera, et cetera.
- 5:12Tracy Fudge: Uh, so that's really where where I got into it.
- 5:15Tracy Fudge: And it's it's still a new, you know, people uh frankly don't understand it.
- 5:22Tracy Fudge: They think it's just workflows.
- 5:24Tracy Fudge: Oh, just flow build six workflows, and that makes it, you know, and that's not it either.
- 5:30Tracy Fudge: Um it's part of it, but certainly when you're looking at a business, you've got to connect it all together.
- 5:36Tracy Fudge: Uh and finance needs to have the same initiatives as RevOps, as Mops.
- 5:41Tracy Fudge: I mean, it it needs to all flow together.
- 5:42Michael Hartmann: Yeah, it's I think that's the that's the uh the goal, right?
- 5:45Michael Hartmann: The only thing you you said something that uh marketing sometimes doesn't have all the data.
- 5:50Michael Hartmann: And I I I would push back a bit on that and say that I think most marketing teams have more data than they know what to do with, um, and probably lack skills and knowledge to be able to do any much with it is is like to me that's the bigger gap.
- 6:05Michael Hartmann: It's not data itself, but the ability to understand it.
- 6:10Tracy Fudge: Yeah, um, and I think you I would say that you are correct in that aspect.
- 6:14Tracy Fudge: When I think of data, I mean the the ability to action on it, to add some predictive analytics, right?
- 6:20Tracy Fudge: Uh to be able to hold the data in a sandbox and just kind of play around with it, apply some machine learning, some prediction.
- 6:27Tracy Fudge: And that way your lead scoring's a little bit better.
- 6:30Tracy Fudge: But if you're still saying because person A watched Webinar X, let's give them five points.
- 6:37Tracy Fudge: And it doesn't take into account all the other things that said prospect or lead did along the way.
- 6:44Michael Hartmann: Sure.
- 6:45Michael Hartmann: Yeah.
- 6:45Michael Hartmann: Yeah.
- 6:46Michael Hartmann: That's interesting.
- 6:47Michael Hartmann: Yeah.
- 6:47Michael Hartmann: Um well, so you you kind of hinted at this when you were talking about this, but yeah, something you said to me, which I've been thinking about, is that you said AI isn't really new, that it's yeah, automation and data taken to another level, I think is the way you put it.
- 7:01Michael Hartmann: Like, what do you like?
- 7:02Michael Hartmann: What do you mean by that?
- 7:03Michael Hartmann: Break that down a little bit.
- 7:05Tracy Fudge: So hooking up, let's say HubSpot to Clay or HubSpot to Salesforce, that happens for the most part, out of the box, right?
- 7:14Tracy Fudge: API, API, field match, field match.
- 7:17Tracy Fudge: Um so that's already sort of an ingenic portion connecting APIs.
- 7:24Tracy Fudge: I think uh, you know, when you add in the intelligence layer, for instance, if you were to drop the data that's moving over to the marketing automation platform, drop that into a knowledge play, uh, an LLM node to do something with the data, make decisions, apply tags, do whatever.
- 7:44Tracy Fudge: And maybe that when you drop it into say N8M, and I'm just I'm making I'm making reference to things that we all know or to a Zapier.
- 7:52Tracy Fudge: But the point is that connection doesn't have to be direct anymore.
- 7:56Tracy Fudge: You pause it, you do things with it, and then you map it.
- 8:00Michael Hartmann: Right.
- 8:00Tracy Fudge: Um, and then you iterate, and that mapping can change.
- 8:04Tracy Fudge: So it's that part of it that is new, but the actual technical API stuff, even installing a platform like an N8M, things things are so easy, uh easier to understand once you've developed on one platform, you can do it on another.
- 8:24Tracy Fudge: One CRM largely looks like another, you know, minus some capabilities, but the concepts are the same.
- 8:33Michael Hartmann: Yeah.
- 8:33Michael Hartmann: It's it's interesting because you um it feels like well, one thing is like some of these terms get thrown around as if they're the same, right?
- 8:46Michael Hartmann: And I like in my head, I try I've started to try to break down like um AI does not necessarily mean automation, right?
- 8:56Michael Hartmann: Uh AI also I think generally gets conflated with LLMs, where it feels like there's a whole lot more that's under the AI umbrella.
- 9:03Michael Hartmann: LLM is sort of one type of AI um modeling kind of thing, right?
- 9:09Michael Hartmann: Where you've got you've mentioned machine learning.
- 9:11Michael Hartmann: I think predictive analytics could be a part of it, or it's a component.
- 9:15Michael Hartmann: But it feels like people kind of mix those up.
- 9:18Michael Hartmann: And to your point, I think some people are just still have maybe not blinders on, but like their their focus is on like small relatively like let's do the replace this small thing that we're doing with something that has AI as in quotes about it.
- 9:32Michael Hartmann: But um when they start to open up the the aperture a little bit, they start to get overwhelmed, right?
- 9:39Michael Hartmann: So for those people who are like, hey, do you feel free to disagree with my my assertion there about like the mixing of terminology, which is I think very common in a scenario like this, but also like any recommendations for those people out there in marketing, marketing ops who are maybe feeling a little overwhelmed about like where to even start with this AI journey, if you will?
- 11:17Tracy Fudge: Uh well, most people that I know that did it, let's say within the past three years, because that's really where when I went in.
- 11:25Michael Hartmann: We it's crazy that it's been three years for stuff, Rick.
- 11:28Michael Hartmann: It feels like it was just like the other day.
- 11:31Tracy Fudge: I um I actually started, there was somebody something kept coming in my feed, right?
- 11:36Tracy Fudge: It was this no code, low code.
- 11:38Tracy Fudge: And I was like, okay, this might be part of it.
- 11:41Tracy Fudge: And I think um that is easier to start because I'm not a software developer.
- 11:48Tracy Fudge: I can I've done Python, you know, I did a serious analytics course where I had to write Python code, but then there's stuff that does it for you.
- 11:57Tracy Fudge: So, you know, that sort of skill set goes away.
- 12:00Tracy Fudge: But the the whole idea of um AI just being connections, it could be um, you know, an LLM play.
- 12:11Tracy Fudge: But in terms of starting, I don't start with the start with the low-code, no-code platforms.
- 12:17Tracy Fudge: And I personally started on Maven and I stayed there for the whole time.
- 12:21Tracy Fudge: The the courses uh people then uh did more courses and more courses.
- 12:26Tracy Fudge: And plus you're with a cohort.
- 12:29Michael Hartmann: And I think um Maven is a like a training.
- 12:33Tracy Fudge: Yeah, uh not the platform.
- 12:36Tracy Fudge: Okay, uh I'm just saying Maven was where I started.
- 12:39Michael Hartmann: Sure.
- 12:40Tracy Fudge: Um and they do uh, or at the time were really the only ones giving true how to start with AI classes.
- 12:50Tracy Fudge: Okay.
- 12:51Tracy Fudge: Um I think that that's one way to start, just real basic.
- 12:56Tracy Fudge: What is AI?
- 12:57Tracy Fudge: And now, fast forward two and a half, three years, you could get the same thing on a YouTube video.
- 13:04Tracy Fudge: I mean, honestly, just break it down.
- 13:07Tracy Fudge: I think the hard part is this.
- 13:09Tracy Fudge: Our background is marketing and marketing apps.
- 13:13Tracy Fudge: And so we're flooded with platform.
- 13:15Tracy Fudge: Oh, Salesforce has AI.
- 13:17Tracy Fudge: Look at these Salesforce agents, right?
- 13:19Tracy Fudge: Spot has AI.
- 13:20Tracy Fudge: Oh, everything's got AI.
- 13:22Tracy Fudge: So I think there's a false sense of being AI when it's not AI.
- 13:28Tracy Fudge: It is just the platform's version of AI.
- 13:32Tracy Fudge: You have no control over the prompt, uh, little control over the knowledge base, um, and it's context, and you don't know what model is in there.
- 13:41Tracy Fudge: Um, a true AI person that wants to add the knowledge layer has all the levers to temperature and knowledge base and prompting and system instructions and prompt chaining, and that's the limitation.
- 13:55Tracy Fudge: So you might, and then another part of it is some of the AI in these things, it's just filling out fields, right?
- 14:03Tracy Fudge: It's um it's just doing, oh, that field needs this data or that field needs this data.
- 14:10Tracy Fudge: And you can do that now with a lot of platforms, you know, Airtable off is their uh AI component, Zapier's got one, they've all got one, but it's kind of filling out the architecture for you, which is part of the part of part of what AI is.
- 14:27Tracy Fudge: But once the scaffolding is built, where's the knowledge?
- 14:31Tracy Fudge: You still have to create that.
- 14:33Tracy Fudge: And that cannot be done yet without a human that knows what the hell they're doing.
- 14:41Tracy Fudge: Yeah.
- 14:41Tracy Fudge: I think unless you've you understand data, and I I always I've always said this is a data problem.
- 14:48Tracy Fudge: Um, understand not just where the data is, but what the data is, uh, what data matters, uh if the data changes what's the story it's telling.
- 14:58Michael Hartmann: Yeah.
- 14:59Tracy Fudge: Exactly.
- 14:59Tracy Fudge: And we're not having enough data conversations.
- 15:02Michael Hartmann: Um well, they this goes back to like one of my absolute strong beliefs right now is that we just lack in marketing in general, in ops in particular, um the skill set to really do much with data, right?
- 15:18Michael Hartmann: I think there's just not a deep understanding about how to do it.
- 15:21Michael Hartmann: Um I want to go like something that's just sort of clicked with me that I think maybe is part of the uh the challenge for some people in this, in that we're so used to having what I would call, I guess, deterministic kinds of solutions.
- 15:37Michael Hartmann: So, you know, I get a bunch of job titles, I'm gonna put something in there that I define the rules to say this is the job level, right?
- 15:45Michael Hartmann: So that which is sort of inferred from the titles.
- 15:48Michael Hartmann: And yeah, I think an a very obvious use case for probably LLM in this case, right, as part of a flow is to use that to categorize jobs, people with job titles into categories that make sense and use some intelligence on that, maybe with a little bit of human oversight.
- 16:07Michael Hartmann: But I think, yeah, what you described, right, in some of these other ones, there's a little bit of this trade-off, right?
- 16:12Michael Hartmann: You could either do that yourself and you have a little more control over what's happening inside the black box, or you take advantage of some of these tools that are being uh embedded within other platforms.
- 16:23Michael Hartmann: You mentioned a few, right?
- 16:25Michael Hartmann: But it becomes even less apparent, like what's happening within that black box.
- 16:30Michael Hartmann: And so there's this lack of, I think there's this like, do I can I trust it?
- 16:34Michael Hartmann: Can I not trust it?
- 16:35Michael Hartmann: Yeah, how can I tweak it?
- 16:36Michael Hartmann: Can I tweak it enough?
- 16:38Michael Hartmann: And it feels like maybe that's part of the like the resistance for people who are struggling with it, where they, yeah, you've got less like, oh, I want to take advantage of the stuff that's being provided in the platforms that I'm used to working in every day, but it doesn't really give me, like, I don't know enough about it.
- 16:52Michael Hartmann: So somebody starts questioning it, I can't answer it, which puts them in a position of not feeling comfortable about it.
- 16:58Michael Hartmann: And then at the other part is like the other struct struggle is like I still have to, like, how do I fit in time to go beyond that?
- 17:04Michael Hartmann: And that's I think it feels like that's maybe the rub that's the or the the the the things that are making it difficult for some people to go, like, how can I step in and take a step forward in this?
- 17:15Michael Hartmann: So does that sound right to you?
- 17:17Tracy Fudge: Yeah, it's a gap.
- 17:18Tracy Fudge: And I have friends at very large organizations, and um, they don't have time to go learn this.
- 17:26Tracy Fudge: And I think when you're a W-2, uh you don't have a lot of time.
- 17:32Tracy Fudge: We're all overworked.
- 17:33Tracy Fudge: I had, I chose to take time off.
- 17:38Tracy Fudge: Well, I have a side business, and that's what's been supporting me, to be honest.
- 17:42Tracy Fudge: Um, but I've taken uh a lot of time and taken very uh a few projects, but it's not, I'm not working 40 hours a week for someone else.
- 17:54Tracy Fudge: Uh, it's probably 20, and then I work the other, you know, even weekends to learn this stuff.
- 18:00Tracy Fudge: And I think it is it's a real um miss of an opportunity uh because you've got really smart people that are working really hard in these huge organizations that are not getting upskilled in this.
- 18:18Tracy Fudge: Because you and it's and here, here, here's the other element to this.
- 18:22Tracy Fudge: When you go in and design a workflow, it's not something you touch today for an hour, you come back next Tuesday and you finish it.
- 18:30Tracy Fudge: No, it's deep work, it's 12 hours sitting down, getting up just to go pee or eat and doing it end-to-end.
- 18:39Tracy Fudge: And there's no, it's heavy, deep can't outsource that part to AI, right?
- 18:44Tracy Fudge: You can't.
- 18:45Tracy Fudge: And it is you you've got to remember where you are and you're deep into that.
- 18:50Tracy Fudge: You're living inside the workflow.
- 18:52Tracy Fudge: I mean, I dream in spreadsheets and workflows because you know, and not everybody has that ability to say, okay, you wake up at seven and you realize that it's you're gonna work on this until seven at night, and you don't stop.
- 19:06Tracy Fudge: You don't answer the phone, you don't, you don't get on social, nothing.
- 19:09Tracy Fudge: You're just inside that workflow.
- 19:12Tracy Fudge: Um, and hopefully in that time you you have enough good data, good parameters to test it and it worked out.
- 19:19Tracy Fudge: But some of that can just be, you know, beating your head against the wall to try to make it work.
- 19:24Tracy Fudge: And um, you've still got to get it reviewed for the client, you know, for the client or for yourself or whoever to see your art because you're the one that designed it.
- 19:35Michael Hartmann: And here's the that's the main right, and that's hard to to test.
- 19:42Tracy Fudge: Nobody's done this before.
- 19:44Michael Hartmann: Well, and because if you're using so in my head, one of the distinctions I've started making is there's the AI comp AI can be uh there are AI components could be used in some sort of automation or workflow or agentic model, right?
- 20:00Michael Hartmann: So pick the tool.
- 20:01Michael Hartmann: But there are other like there are other more deterministic ones.
- 20:04Michael Hartmann: And I think what again I get back to like when you're trying to validate, right?
- 20:08Michael Hartmann: It's it becomes less of a um did it do what it was supposed to in in an exact way, or did it produce an output that I is expected even if I don't understand how it came to that?
- 20:19Michael Hartmann: And that's a very different validation.
- 20:21Michael Hartmann: And and then if you're not comfortable, if you're the kind of person who's not as comfortable with these sort of um what's wrong, right?
- 20:32Michael Hartmann: Like less, like unless like, oh, this is this directionally correct, right?
- 20:37Michael Hartmann: If you're comfortable with that as a quality assurance um level of quality or completeness, then you're gonna really struggle with this stuff, I think, right?
- 20:48Michael Hartmann: Because a lot of times what I've seen, even when I'm just using, say, uh an LLM, Chat GPT, Claude, whatever, right?
- 20:57Michael Hartmann: The output I get from my back and forth in terms of prompts, right?
- 21:01Michael Hartmann: Sometimes I go, I could I scratch my head, I go, like, where did it come up with that?
- 21:05Michael Hartmann: Right.
- 21:06Michael Hartmann: It we've all heard about the hallucination thing, but also sometimes it just doesn't freaking follow the directions, right?
- 21:12Michael Hartmann: I remember working on something where I was like, I want you to draft a document.
- 21:16Michael Hartmann: I had we'd gone back and forth, I had a lot of stuff, dropped this document and came up with something.
- 21:20Michael Hartmann: I was like, I like that, but I don't like this one piece of it, right?
- 21:24Michael Hartmann: It was like I think I had done a header image or something.
- 21:26Michael Hartmann: I said, Yeah, just go fix that.
- 21:28Michael Hartmann: And it completely redid the whole fucking thing.
- 21:31Tracy Fudge: So yeah, and I was like, no, like that cost us down, right?
- 21:35Tracy Fudge: Like that that you can't put the whole prompt in one place.
- 21:40Michael Hartmann: Well, and I hadn't, like I had gone, but like I had produced something that was probably 80% of what I wanted.
- 21:46Michael Hartmann: It was in line.
- 21:47Michael Hartmann: I'd gone through like as many steps.
- 21:48Michael Hartmann: It was just like this last one, like the formatting, the layout of this document wasn't what I quite wanted.
- 21:55Michael Hartmann: And so I asked to make one simple change and it completely like it redid the whole thing.
- 22:00Michael Hartmann: And I was just couldn't understand why.
- 22:02Tracy Fudge: Yeah.
- 22:03Michael Hartmann: And that's the kind of stuff.
- 22:04Michael Hartmann: So if you take that, right, where I'm like going back and forth and it took me time to do it, and you say, like, I'm gonna do something like that, maybe not exactly, and I'm gonna be make that as a part of an overall flow, then like, how do you test that and evaluate it?
- 22:18Michael Hartmann: That's like that's where the uncomfortable like people get uncomfortable with how do I fit this into something where people need to trust the overall output of that, not just one piece of it.
- 22:31Tracy Fudge: Yeah.
- 22:32Tracy Fudge: I was introduced to a platform called Cassidy.
- 22:35Tracy Fudge: Um, it is it's a pretty cool platform.
- 22:40Tracy Fudge: I use it mainly for uh doc gen.
- 22:43Tracy Fudge: So creating um a workflow to create an RFP process or a workflow to create uh a presentation or talking point or or something like that.
- 22:57Tracy Fudge: It's to do one thing is eight different agents or assistants, right?
- 23:04Tracy Fudge: One of which is the JSON, and the JSON is gonna be how that document is formatted, and you tack that on to the end and you go, okay, I want the header to be this, da-da-da-da-da-da-da-da.
- 23:15Tracy Fudge: And then and then it goes through that node, which is a code node, um, and then it's formatting.
- 23:22Tracy Fudge: And that uh had I not gone through Cassidy workflow on a simple doc generation thing, yeah, I wouldn't have realized that no, no, we we first have to have a research agent.
- 23:36Tracy Fudge: Oh, and then we oh, first we need to have the brand voice agent, you know, or wherever you put that in, how do I sound?
- 23:42Tracy Fudge: So you've got eight different assistants to do one eight-page output.
- 23:49Tracy Fudge: And I know that sounds possibly gratuitous, but it's how you do it.
- 23:55Michael Hartmann: Yeah.
- 23:56Michael Hartmann: Well, I think so going back to my original question, to you, like, where should people start?
- 24:00Michael Hartmann: It feels like the way to start is because you can't do all this in one sitting.
- 24:06Michael Hartmann: If you're a kind of person who's busy with their day job and you can't do it all in one sitting, you could start to experiment with pieces of what might be a bigger process, right?
- 24:15Michael Hartmann: And you like figure that out.
- 24:17Michael Hartmann: And then because I it I I spent a lot of time trying to learn how to just use I have a bias towards ChatGPT, not for any good reason other than it's just the one like was one of the first ones.
- 24:29Michael Hartmann: I've spent more time with it, and I'm open to the other ones.
- 24:32Michael Hartmann: But I've done lots of individual things.
- 24:34Michael Hartmann: It wasn't until I'd been doing that for a while where I sort of lifted my head up and said, okay, I keep hearing about this agentic right in quote stuff, you know, what does that really mean?
- 24:43Michael Hartmann: And I played around with different tools.
- 24:46Michael Hartmann: And I don't think that if I I think if I'd started with the N8Ns of the world, or like I I I've had pretty good luck with relay.app, right?
- 24:56Michael Hartmann: There are others, I know there are plenty of others, but if I had started with those as opposed to learning how the LLMs work, I think I would have struggled even more because I would have tried to do what you said, like I would have tried to do like a whole bunch of stuff in one uh AI node of a process as opposed to breaking it down into smaller chunks, which does feel on the surface to be inefficient, but it feels like like now I understand that uh in order to maintain a level of quality or consistency, that's kind of what you have to do.
- 25:32Tracy Fudge: Yeah.
- 25:33Michael Hartmann: Which means then you have to understand like which it should be a strength of ops people, right?
- 25:37Michael Hartmann: What's the process that I go through?
- 25:39Michael Hartmann: That what's the well, how can I break down this overall process that I want to automate, have agents do into smaller steps so that I can trust the output at the end.
- 25:49Michael Hartmann: Yeah.
- 25:52Tracy Fudge: Yeah, it's it's and you evolve to that point.
- 25:55Tracy Fudge: We all start, we're all different learners.
- 25:57Tracy Fudge: And for me, I like being part of a cohort, a learning cohort.
- 26:01Tracy Fudge: And I didn't want to, I kind of paused in my mops world intentionally because I didn't, I felt like mops wasn't where I wanted to go.
- 26:11Tracy Fudge: So there were a few mops people in the community where I where I ended up, uh, and I still am, but not many.
- 26:20Tracy Fudge: It's CEOs are in there.
- 26:22Tracy Fudge: You know, it's just different people having different questions.
- 26:24Tracy Fudge: And I personally would be exposed to more use cases than just hooking up a CRM to a marketing automation plan.
- 26:32Tracy Fudge: You know what I mean?
- 26:33Tracy Fudge: Like I it and that's where that's where um so I went, you know, that's where the decision I made to get out of the mops mentality and the mops world because it's all mops.
- 26:48Tracy Fudge: And while mops is very relevant, take the blinders off, right?
- 26:52Tracy Fudge: Yeah, you just need to go and understand it.
- 26:55Tracy Fudge: And it is it's overwhelming.
- 26:58Tracy Fudge: It's overwhelming.
- 27:00Tracy Fudge: I cannot tell you the it's just it's it's it changes the way you see everything.
- 27:08Michael Hartmann: Yeah.
- 27:09Tracy Fudge: It's not just AI, it's it changes everything.
- 27:13Tracy Fudge: I mean, I look at things so differently now uh in the world, and um it it changes everything.
- 27:22Tracy Fudge: And I don't know where to tell people to start that.
- 27:24Tracy Fudge: I don't, I for okay, so fast forward today.
- 27:27Tracy Fudge: If I were somebody getting started, I would say go to N8N, do one of their starter templates, and just build it.
- 27:36Tracy Fudge: Just at least get the the click and the link and all that stuff, just understand it.
- 27:40Tracy Fudge: Yeah, and mops people will understand that because most mops people, I mean, actually, I wouldn't say most mops people.
- 27:47Tracy Fudge: There's a set of mops people that don't hook systems up.
- 27:50Tracy Fudge: You know, they're not on the API side and they're not on the data side.
- 27:54Tracy Fudge: But the ones that are will get that part.
- 27:57Tracy Fudge: Um and I would start there.
- 28:00Tracy Fudge: N8N's gotten a lot better.
- 28:03Tracy Fudge: I was an NADN, I left.
- 28:06Tracy Fudge: I didn't, I was not a fan of the community.
- 28:08Tracy Fudge: Um, I didn't feel like there was a lot of help there.
- 28:11Tracy Fudge: I thought it was a lot of bravado and not things that were true.
- 28:15Tracy Fudge: Uh, and it turned out that was the case.
- 28:17Tracy Fudge: A lot of people were saying, well, we'll come in and do all this magic, and and they couldn't, they could just build the thing inside of NADN and it was visually appealing, but it didn't do anything.
- 28:26Tracy Fudge: So anyway, um, but now I think it's a lot better, and they do have things for people to go learn quickly.
- 28:32Tracy Fudge: And I don't, and I think you just do these P these bytes of things, maybe an hour each, and just build and then and then move into the data layer.
- 28:42Tracy Fudge: And that's where Airtable and Super Base uh or Superbase, you know, that's another one.
- 28:49Michael Hartmann: Do you know how to say I have no idea?
- 28:52Tracy Fudge: But they're very good.
- 28:53Tracy Fudge: Uh and when I started to step into data and believe it or not, uh into knowledge graphs.
- 29:00Tracy Fudge: So, and we could go into this, but AI has to know context and it has to know how things are tagged so that it can go and retreat it.
- 29:13Tracy Fudge: Um, this is different than Google's algorithm looking for keywords.
- 29:17Tracy Fudge: So AI has to have context.
- 29:20Tracy Fudge: So you've got to have a defined ontology.
- 29:23Tracy Fudge: And that means, you know, this is a rotter word for saying tagging, you know, you've got to know what things mean and then how they're related.
- 29:29Tracy Fudge: Uh, and that's where triples come in.
- 29:32Tracy Fudge: So AI can't move beyond that layer.
- 29:36Tracy Fudge: So if you don't have the knowledge graph and the nodes and ontology, it can't work.
- 29:42Tracy Fudge: So when that light bulb went off in my head, I was like, damn.
- 29:48Michael Hartmann: Yeah.
- 29:49Michael Hartmann: So that's like con that's like con providing context to a whole nother level, right?
- 29:55Tracy Fudge: Yeah, but it's getting it right.
- 29:57Tracy Fudge: It's so it doesn't hallucinate, right?
- 29:59Tracy Fudge: Right.
- 29:59Tracy Fudge: So you'll see, and they may not be called knowledge graphs, but it is.
- 30:05Michael Hartmann: It's gonna No, I it it's a good, I think like me, it's a good mental model, like in my I I can already kind of envision it what you mean, but ontology is a big word that I think most people listening or watching may not really fully understand.
- 30:18Tracy Fudge: Um it's getting it is giving the relation of how things are related.
- 30:24Michael Hartmann: Yeah, yeah.
- 30:25Michael Hartmann: Um it's like librarian, right?
- 30:28Michael Hartmann: Virtual librarian.
- 30:29Michael Hartmann: Um not that anybody goes actually goes to libraries anymore, but um that's a whole other topic.
- 30:36Michael Hartmann: Uh so I'm curious, like what are what are some of the like can you give us some examples?
- 30:42Michael Hartmann: Maybe uh going back to early on, like things that you've done where you've kind of that were helpful in your learning and still were maybe productive, maybe weren't productive in terms of an actual thing you can apply in the work, but it was like a good learning experience.
- 30:59Michael Hartmann: And maybe something more recent that you've done as you've kind of learned and evolved and and what you've seen as possible.
- 31:07Tracy Fudge: Well, I was lucky enough to have my own business to sort of act as a playground, right?
- 31:11Michael Hartmann: Sure.
- 31:12Tracy Fudge: So I automated um a lot of the front office, a lot of the back office.
- 31:18Michael Hartmann: Um for your business, you mean?
- 31:22Tracy Fudge: That's where I practiced a lot of it, um, where I learned um real life things that that were impactful.
- 31:30Tracy Fudge: So um that's how I was able to.
- 31:34Tracy Fudge: To do things live and play around with it.
- 31:36Tracy Fudge: Not everybody does that.
- 31:38Tracy Fudge: They're still so if you're in an organization, you've got their platforms, you know, you've got their stuff, and it may not, they may not have NADN, you know, they may not want you playing on an agentic platform to understand it all.
- 31:50Tracy Fudge: But those the so the efficiency, so that's how I learned a lot of it.
- 31:55Tracy Fudge: I just threw my own business, my own use case, I built my own knowledge graph.
- 31:59Tracy Fudge: Um, I built my second brain, and that's all knowledge graph work.
- 32:03Tracy Fudge: Um, and I'm actually building the second brain for someone as a client right now.
- 32:07Tracy Fudge: And that's actually all encompassing because uh a person's second brain that's an evolved person, say a diplomat, um, does a lot of different things.
- 32:19Tracy Fudge: So you have to connect a lot of different dots for that person.
- 32:22Tracy Fudge: Um, but from a workflow standpoint, I've done lead routing, uh, which was honestly, it was easy.
- 32:31Tracy Fudge: It was an easy problem for when they started talking, I knew right away, okay, that's the problem.
- 32:37Tracy Fudge: We need the lead routing to be fixed.
- 32:40Tracy Fudge: And all it was on the sales side.
- 32:42Tracy Fudge: They couldn't keep their territories and their data and Salesforce up to date.
- 32:48Tracy Fudge: And it was honestly, I created an SOP, uh, I created an ideal framework for it.
- 32:53Tracy Fudge: This is how we want it.
- 32:54Tracy Fudge: And they built it.
- 32:55Tracy Fudge: And then we cut lead routing down from 48 hours to four minutes.
- 33:02Tracy Fudge: Um, and then I did some predictive lead scoring uh for somebody, but that's on the mop side.
- 33:08Tracy Fudge: And I've other done other boring things um that people might find are boring, but it is um just workflows and filing.
- 33:17Tracy Fudge: Uh, you can build an ontology with a workflow now.
- 33:21Tracy Fudge: Like to do it right, you'd have to look go say you had a thousand documents.
- 33:26Tracy Fudge: Well, someone would have to physically go through all thousand and apply an ontology, relate it, build the triples and stuff like that.
- 33:33Tracy Fudge: So there's workflows.
- 33:34Michael Hartmann: So sorry, you've used the word triples now multiple times, and I I was just gonna assume that it's a no I don't know what you mean.
- 33:41Michael Hartmann: What does that mean?
- 33:42Tracy Fudge: So it is meaning that um Johnny kicked the ball in the street.
- 33:48Tracy Fudge: You got Johnny ball street.
- 33:51Michael Hartmann: Okay.
- 33:51Tracy Fudge: Well, someone else could have kicked the same ball into the ocean.
- 33:55Tracy Fudge: So it's it's the it's how it's related in triples, three things.
- 34:01Tracy Fudge: And so long as you can match the three things, then everything you can see how everything is related.
- 34:07Tracy Fudge: Uh and I'm not doing a great job of explaining it, but you'd have to see it.
- 34:11Tracy Fudge: It's just applying relationships by three.
- 34:15Michael Hartmann: Okay.
- 34:15Michael Hartmann: Interesting.
- 34:16Michael Hartmann: Okay.
- 34:17Michael Hartmann: I mean, that makes sense.
- 34:18Michael Hartmann: I mean, triangulation on stuff kind of makes sense.
- 34:22Michael Hartmann: Okay.
- 34:22Michael Hartmann: I'm gonna be uh you're gonna see my heads like you're gonna see my eyes going back and forth because I'm still thinking about this.
- 34:28Michael Hartmann: Keep going.
- 34:29Michael Hartmann: I'm sorry.
- 34:30Tracy Fudge: No, that was it.
- 34:31Tracy Fudge: It is, and I'm not an ontologist, so there are people, you know, as I stepped into this world, I'm in the other cohorts and taking more classes.
- 34:39Tracy Fudge: Um, you know, I am I'm I'm kind of addicted to taking classes, um, to be honest, because I don't want to do it myself.
- 34:46Tracy Fudge: I want to sign up for a class that I've invested in and it's got beginning and an end date, and it keeps me accountable.
- 34:52Tracy Fudge: Plus, you meet people along the way, right?
- 34:55Tracy Fudge: Um, which is a great way.
- 34:56Tracy Fudge: And and community and networking is gonna matter now more than ever.
- 35:00Tracy Fudge: Um it's gonna matter now more than ever because it's gonna be who you know.
- 35:04Michael Hartmann: Sure.
- 35:05Michael Hartmann: Yeah.
- 35:06Tracy Fudge: And at my point you are how many degrees you have.
- 35:09Tracy Fudge: Um, so I don't know if I answered that question.
- 35:13Michael Hartmann: No, I think I think I think if you did, I think I'm trying to think about like if I was someone listening, watching whatever, and um I didn't have my own side business, what could I do?
- 35:22Michael Hartmann: And I think about some of the things that I've done, because most of mine has been uh more on a personal level.
- 35:28Michael Hartmann: So interesting.
- 35:30Michael Hartmann: So I've done automation actually related to the podcast, where um I have now a link for people to schedule this recording, right?
- 35:37Michael Hartmann: And part of what I have done, this doesn't involve AI at all, which is interesting.
- 35:41Michael Hartmann: But I did play with an automation platform that goes this looks for when uh that new thing is added to my calendar, it goes looks for new ones and it does a couple of things with it, right?
- 35:51Michael Hartmann: Adds a couple of people to it.
- 35:53Michael Hartmann: Um I've been thinking about like how could I take that even a step further?
- 35:57Michael Hartmann: So I still do a manual effort of prepping.
- 35:59Michael Hartmann: So I've taught uh in this case GPT, uh how I like to do the preparation document.
- 36:07Michael Hartmann: So for people listening, right, we actually do a fair amount of preparation for this.
- 36:10Michael Hartmann: It's not a total wing-it thing as much as we try to make it feel organic.
- 36:15Michael Hartmann: But you know, that's still a fairly manual process based on some.
- 36:20Michael Hartmann: You've everybody knows we we have initial discussions about these things, and and uh you know, I've got recordings.
- 36:26Michael Hartmann: So I would love to get the process if I could set set it up where like it can go back and go find my notes and transcripts from our planning discussions to generate the document, right?
- 36:35Michael Hartmann: That would be an automation that would would benefit for me.
- 36:38Michael Hartmann: This still doesn't have taken me as much that much time manually, so it hasn't been a top of mind.
- 36:44Michael Hartmann: But I have done other things um that are more focused on still manual but recurring things that I'm doing, or you kind of hinted at this, like doing research now.
- 36:56Michael Hartmann: Um, I find it really, really valuable in doing research on stuff.
- 37:01Michael Hartmann: Um to put like I literally had today, had people here, service repair people.
- 37:06Michael Hartmann: We have an old uh cooktop having problems with it.
- 37:10Michael Hartmann: And so I did a bunch of research on is this stuff I could fix myself, right?
- 37:15Michael Hartmann: Did it I did it with uh we had a deep freezer that went bad over the summer.
- 37:20Michael Hartmann: Um, and I did a bunch of research like what are the possible causes and is other things that as someone who's not super handy could could fix.
- 37:27Michael Hartmann: And it's a it it made gave me a solution that was a $20 solution as opposed to a replace it for a few hundred dollars, right?
- 37:35Michael Hartmann: Which is beneficial.
- 37:36Michael Hartmann: And I probably could have done that research on my own, but having the LLM do a bunch of that for me, come back with stuff, and then I could refine it.
- 37:48Michael Hartmann: Um I've even done stuff if you're a kind of person who likes to cook at home.
- 37:52Michael Hartmann: We took photos of all the stuff from the pantry and said, come up with some recipes.
- 37:58Michael Hartmann: Take a picture.
- 38:00Michael Hartmann: That's what we did.
- 38:01Michael Hartmann: Yeah, it's really actually quite good at that.
- 38:03Michael Hartmann: I found it's not so good at generating photos, but it's or pictures, but it's really good at deciphering what's in photos.
- 38:10Michael Hartmann: I I've been sort of blown away.
- 38:12Michael Hartmann: I didn't believe it would work well, and it's been really good.
- 38:14Michael Hartmann: Yeah, so we actually did that and it generated a number of recipes, and we tried one and it was terrific, right?
- 38:21Michael Hartmann: No, no, will everything be that way?
- 38:22Michael Hartmann: Right?
- 38:23Tracy Fudge: I doubt it, but um so I think walking into your kitchen and all you have to do is talk to your kitchen, yeah.
- 38:33Michael Hartmann: So I think I think I wouldn't yeah, go ahead.
- 38:36Michael Hartmann: I think if people think about like how could I try to learn some of the stuff even if I don't have a site, like it doesn't have to be a business context.
- 38:42Michael Hartmann: I think you can learn a lot from doing things, and there are like I've played with connecting like my email to one of these automation platforms using an AI kind of engine to automate drafting replies and things like that, or categorizing things as important or not important.
- 39:01Michael Hartmann: Um honestly, I'm a little bit of a like I'm paranoid and like just like the amount of access that those tools currently have to have to things like your inbox, not comfortable with personally.
- 39:15Michael Hartmann: So, but I know it's possible.
- 39:19Michael Hartmann: Like, and it's definitely uh like that's a very common use case that most of these automation platforms will give you as a starting point.
- 39:25Michael Hartmann: Like open up your email, classify the emails, draft the reply to those ones that you think are important, and then you can go in and and then send you a summary on a daily basis.
- 39:33Michael Hartmann: Pretty common thing you could do.
- 39:36Michael Hartmann: And um, like I think there are things that people, if they thought about it, even if they're not doing a work-related one, because there are concerns about you know uh security and proprietary, you know, confidential information, things like that, that would probably make it harder.
- 39:54Michael Hartmann: Um, but there are ways you can learn.
- 39:56Michael Hartmann: So I think that would be high encouragement is to do that kind of thing.
- 40:00Michael Hartmann: So I oh I get so one of the things you have I think encouraged me, um, and I have yet to to really do that, and I've already mentioned right that I have a bias towards Chat PT, GPT because I'm most familiar with that, and then I particularly like um Grok because you can put on the uh what do they call it, a persona, I think?
- 40:22Michael Hartmann: You can do the unhinged comedian one, and it's like I just that's more of an entertainment thing than anything else, just to see what it comes up with.
- 40:30Michael Hartmann: But um how do you like what what could you share about what you know about some of the let's keep into the LLMs with this, I guess at this point, like what like what do you see from them?
- 40:41Michael Hartmann: What do you think that they're like what are their strengths and weaknesses?
- 40:44Michael Hartmann: Because it feels like they all have sort of various things, and I know it's evolving, so like by the time this gets out, it's probably gonna change a little bit.
- 40:50Michael Hartmann: But in general, what's your take on those?
- 40:54Tracy Fudge: I um so I I don't really use grok.
- 40:56Tracy Fudge: I have in the past, but not to the extent.
- 40:58Tracy Fudge: So my main ones are ChatGPT.
- 41:01Tracy Fudge: I just pay the 20, and then Claude.
- 41:03Tracy Fudge: I I think I did bump it up to the higher one because Claude um has some memory and context issues, and I hate having to start over in the middle.
- 41:12Michael Hartmann: Uh yeah, yeah.
- 41:14Tracy Fudge: So, which is very irritating.
- 41:15Tracy Fudge: Um, and then Claude's limitation was not being able to hold the context inside of folders or projects.
- 41:21Tracy Fudge: You know, you can create folders.
- 41:22Tracy Fudge: So I have a I have a huge folder structure, and I was actually arguing with ChatGPT.
- 41:28Tracy Fudge: Because it used to be able to drop into the folder and ask a question and uh about anything in that folder.
- 41:37Tracy Fudge: Well, today I found uh that it didn't it didn't have the context of a conversation that I had just had in that same project.
- 41:46Michael Hartmann: Yeah, I've found that I've I've had to give it explicit direction, go to this other chat that's in the same folder.
- 41:52Tracy Fudge: Yeah, and that was not the case.
- 41:54Tracy Fudge: So I don't know what's going on.
- 41:56Tracy Fudge: Maybe they realize that they let too much out with chat GPT that this is a lot of power requirement to make your, you know, the return of your request happen.
- 42:08Tracy Fudge: Um but I use both.
- 42:10Tracy Fudge: I actually um I intentionally did not do Claude Desktop until a month ago or two months ago because I didn't want to get too advanced because I knew that that would then uh I would build MCP servers.
- 42:25Tracy Fudge: So I've evolved into Claude Desktop, MCP servers on my on my desktop to go into these systems uh for me.
- 42:35Tracy Fudge: But that's not for everybody.
- 42:38Tracy Fudge: You still have to know what the hell you're doing.
- 42:40Tracy Fudge: Or what it's doing, you know.
- 42:43Michael Hartmann: Yeah.
- 42:43Tracy Fudge: Build, you know, build the JSON to be, you know, uploaded into, you know, uh N8N.
- 42:48Tracy Fudge: I mean, you've still got to know uh a few things about that.
- 42:52Tracy Fudge: But that that's what uh and I use Claude for that.
- 42:55Tracy Fudge: So but I still go back to chat GVT for creative.
- 43:00Tracy Fudge: I've I've started to write more often.
- 43:03Tracy Fudge: Um I love to write and I've started to write more often on LinkedIn and I've done it.
- 43:08Michael Hartmann: Do you find it do you find it better at drafting initial stuff with a lot of context or you drafting stuff and now asking it to um give you feedback on it?
- 43:18Tracy Fudge: I've been training it for a while.
- 43:20Tracy Fudge: Um, and assuming it's still got the same project context.
- 43:24Tracy Fudge: That was one of my things I was frustrated with uh because it has my brand voice, it has my last post, it knows sort of where I left off last week.
- 43:32Tracy Fudge: Right because I get one loud.
- 43:34Tracy Fudge: I don't, I I I took last week off and I was like, I'm not going on LinkedIn.
- 43:38Tracy Fudge: So I took a break.
- 43:40Tracy Fudge: Um, but it's still so that for that I use it.
- 43:43Tracy Fudge: Um uh I use Chat GPT for that.
- 43:47Tracy Fudge: But Claude, I use for the technical stuff.
- 43:49Tracy Fudge: But Claude's gotten better uh with the creative and the writing um as well.
- 43:55Tracy Fudge: And my you know, there's so much noise, and I know everyone says this, there's so much AI noise, and now with all these layoffs and things, and I just I want to post something that matters.
- 44:09Tracy Fudge: It's just not more of an echo of what's already and sometimes that's hard.
- 44:13Michael Hartmann: Yeah.
- 44:14Tracy Fudge: Because you want to call out the noise for what it is, right or wrong, and then you know, have your point of view.
- 44:21Tracy Fudge: And it's it's hard to get a point of view sometimes when when it's so noisy out there, you know.
- 44:26Tracy Fudge: You don't want to, you know, it's hard to not be afraid, you know, these types of things.
- 44:31Michael Hartmann: So yeah.
- 44:31Michael Hartmann: It's interesting because like my biggest, my latest challenge, even though I've got some folder structures inside ChatGPT, because I'm also at a paid level, I think that's a you have to have at least the basic level folders.
- 44:43Michael Hartmann: Yeah.
- 44:44Michael Hartmann: Um is that even within that, I've got like I'll I I I actually did something with my wife too, for some she does in her work, which there's ongoing doing a lot of the same things, and so having context is really good.
- 44:58Michael Hartmann: What I found is when I it goes on for a long time, it um chat PT GPT tends to lock up, right?
- 45:07Michael Hartmann: If I if it's if the chat thread gets too long, and so that's my latest one is like how do I retain what is like I did a lot of work training it to voice and stuff like that.
- 45:19Michael Hartmann: Um but the performance on new asks is still there, and that that's my latest challenge.
- 45:25Michael Hartmann: But um it's what's a screened this week.
- 45:29Tracy Fudge: I don't know what it is.
- 45:30Michael Hartmann: Well, I've been noticing it for a few weeks, so I don't think it's anything specific to this week um for me, but um and and I think it's just just that, right?
- 45:37Michael Hartmann: The the threads are just so long now that uh it may just be browser, right?
- 45:43Michael Hartmann: The browser rendering it takes too long and it's just locking up.
- 45:47Michael Hartmann: So uh but again, like this is like part of the learning process that we go through, and it it would help me knowing like, hey, if I'm building some sort of automation for a work context and um I wanted the context to be there and available over time, right?
- 46:02Michael Hartmann: I need to think about how to structure it so that I don't run into the same thing, an automation step where I'm like, hey, asking a whole bunch of stuff to a say uh uh LLM engine, and uh because it's like if it's building it out over time, is that gonna cause that to slow down and not run correctly?
- 46:22Michael Hartmann: So things like that, right?
- 46:24Michael Hartmann: So I've kind of tied tying that together.
- 46:27Michael Hartmann: Um let's let's let's wrap up here because you kind of alluded to this.
- 46:31Michael Hartmann: Like, how how how can people think about what's the right way to start to incorporate AI, LLM, you know, automation slash agentic stuff into their, let's keep it to Mops, RevOps, whatever, uh, into their world where it's it's a complement uh or a um I like the term I heard somebody use, like it provides a time dividend, right?
- 46:58Michael Hartmann: To like into their their day-to-day um work effort, right?
- 47:03Michael Hartmann: How did like what are some ways they can do think about doing that?
- 47:07Tracy Fudge: So are you asking from the perspective of the mops individual or mops?
- 47:14Michael Hartmann: I think I think mops people as individuals, right, but as part of a team, even if it's a team of one or two people.
- 47:21Tracy Fudge: Mm-hmm.
- 47:22Tracy Fudge: Content is a big thing.
- 47:25Tracy Fudge: Um, and I think content's really relevant.
- 47:27Tracy Fudge: Uh, but you can't just put it into Chat GPT and say, write an article on this topic.
- 47:34Tracy Fudge: I mean, you've got to iterate it, you've got to give it examples, you have to understand.
- 47:39Tracy Fudge: But I think getting content out for the team um for um, you know, email is another one.
- 47:47Tracy Fudge: I have not ventured into email for exactly what you said.
- 47:50Tracy Fudge: I want to go in and read my emails and things like that.
- 47:53Tracy Fudge: And I'm scared to, and I I use uh Google Workspace and I'm scared to turn on Gemini and my email.
- 48:00Tracy Fudge: I don't know what it's gonna do.
- 48:03Tracy Fudge: Right.
- 48:03Tracy Fudge: Um, but I do think that, you know, find a few workflows that are for you and build those out.
- 48:10Tracy Fudge: Uh for the business, if it's if it's easy to show a return, then do it.
- 48:18Tracy Fudge: And you know you could show it because you want to show ROI.
- 48:21Tracy Fudge: And that's gonna elevate you to leadership as well.
- 48:24Tracy Fudge: Look, I I shortened your lead routing.
- 48:26Tracy Fudge: We could do this.
- 48:28Tracy Fudge: Look, let's um, and do some predictive analytics, pull some data out of sales if you can, you know, the last four campaigns.
- 48:37Tracy Fudge: Uh, what else did those people do that converted to a sale?
- 48:41Tracy Fudge: Did they visit uh a certain and besides the webinar, did they do these other things?
- 48:49Michael Hartmann: Um looking for pattern, like looking for patterns tied to exactly uh the desired outcomes.
- 48:55Tracy Fudge: Most companies aren't capturing those events, right?
- 48:58Tracy Fudge: So you've got to figure out, okay, can I pull in data on the white paper they read, not just the webinar they signed on?
- 49:04Tracy Fudge: Can I pull uh and we already know what emails are opened?
- 49:09Michael Hartmann: Um those you could provide it, you could provide it not only the data, but also the content, right?
- 49:14Michael Hartmann: The examples of the content.
- 49:15Michael Hartmann: This here's this content, it's tied to this data point or this kind of activity that's in the data versus this other piece of content.
- 49:23Michael Hartmann: And um you could then tell it to look for what are patterns in the content that uh are tied to um better conversions, more pipeline, like whatever that is that you're trying to optimize for.
- 49:42Tracy Fudge: Possibly look at the last thing they did, like they looked at an ROI white paper or something.
- 49:48Tracy Fudge: Let's just make that up.
- 49:49Tracy Fudge: So then you have the AI note that, right?
- 49:53Tracy Fudge: But then craft a draft email around RLI.
- 49:57Tracy Fudge: And it's something they just did, so it's fresh in their brain.
- 50:00Tracy Fudge: It may not be the thing that pushes them over the to be a uh cli uh a paying client, but it's something that's relevant.
- 50:08Tracy Fudge: Um, that's something that a lot of people uh could easily do.
- 50:13Michael Hartmann: Yeah.
- 50:13Michael Hartmann: I mean, I think I think what I would do, like if I was in an organization that had like product marketing and or just content marketing teams, and um we had a sales team that had some sort of call recording platform, I would be like, that sounds like such great context if you could capture the transcripts from those sales conversations, then tie it back to which of those and ended up turning into deals.
- 50:41Michael Hartmann: Mm-hmm.
- 50:42Michael Hartmann: And capture the language that's in there, both client side and sales side, to feed back into how are you thinking about the content you're publishing and the material you're providing to the sales teams, right?
- 50:54Michael Hartmann: Because you because like I think there's so much crap out there on B2B websites in particular that is like just gobbledygook nonsense that doesn't really tell anybody anything about what you actually do.
- 51:05Michael Hartmann: Like if you could drive, like if you could do that, take that back, feed that back into your content engine, um, which then hopefully is gonna drive more traffic and awareness, right?
- 51:14Michael Hartmann: Like you could build a pretty strong flywheel, um, I think in terms of that that's just simply based on what are the actual terms and uh things that uh customers, prospects actually care about, and make sure that you've got that really well honed on your public-facing website and the content that goes with it.
- 51:35Michael Hartmann: Like to me, that's like it's it's not trivial, I get it, but like it talks about like uh an ROI over the long run, both short term and long term.
- 51:44Michael Hartmann: I think that that one to me is a use case that I would love to see more people trying out.
- 51:50Tracy Fudge: And then you could retarget people to go to that new dynamically created blog post that was created, you know.
- 51:56Tracy Fudge: So these things are dynamically um done because there's APIs in there that are doing it.
- 52:02Tracy Fudge: Yeah.
- 52:02Tracy Fudge: So there's the API work, but absolutely.
- 52:05Michael Hartmann: Yeah, so anyway, well, hey, I it feels like as so many of these are that we could go on and on and on.
- 52:11Michael Hartmann: Uh, but unfortunately, we do have to we do need to wrap up.
- 52:14Michael Hartmann: So, Tracy, first off, thank you for sharing.
- 52:17Michael Hartmann: It's been a lot of fun.
- 52:17Michael Hartmann: I enjoyed the conversation.
- 52:18Michael Hartmann: I'm so glad we were able to make this work uh while everyone else is out there having a fun time at Mopspalooza.
- 52:25Michael Hartmann: But if uh if if folks want to connect with you or learn more about what you're doing or go deeper on this topic with you, what's the best way for them to do that?
- 52:36Tracy Fudge: Uh find me on LinkedIn.
- 52:37Tracy Fudge: Um, my website's AI by Thrive, and I'm Tracy with an EY at AI by Thrive, if they won't email me.
- 52:44Michael Hartmann: Perfect.
- 52:45Michael Hartmann: Well, thank you again, Tracy.
- 52:46Michael Hartmann: Appreciate it.
- 52:47Michael Hartmann: Thanks always to our listeners and now watchers now that we're uh going live with videos.
- 52:54Michael Hartmann: Well, we appreciate your support.
- 52:55Michael Hartmann: And as always, if you have ideas for topics or guests or want to be a guest, you can reach out to Mike, Naomi, or me.
- 53:02Michael Hartmann: We'd be happy to talk to you about it.
- 53:03Michael Hartmann: Until next time.
- 53:04Michael Hartmann: Bye, everybody.
- 53:05Tracy Fudge: Thank you, bye bye.