So What? Creating a Custom GPT model for restaurant marketing

Well, hey everyone. Happy Thursday. Welcome to So What the Marketing Analytics and Insights Live Show. I am Katie joined by Chris and John. Hello, fellows.

Howdy. It's been a minute since we've all been in the same place for a live stream, and I guess of course, next week that will not be the case again. Um, which I suppose is better than the alternative that nobody wants to talk to us, and we're all just sort of sitting around waiting and doing live stream after live stream, hoping that somebody takes attention. Too busy is better than not busy enough. Um, in this week's live stream, we are talking about creating a custom GPT model specifically for restaurant marketing.

And so we've been playing around. So OpenAI a few weeks ago rolled out the ability to create your own custom uh GPT model, which we'll get into the details of that. And so we've been playing with it. Chris has built a dozen or so custom models for various uh reasons. And today we wanted to focus specifically on restaurant marketing.

And so we'll cover how to extract review data for your custom GPT model, refining your custom GPT model to build personas, and how to maintain your custom GPT model for ongoing restaurant marketing. So Chris, where would you like to start? Well, let's start with refreshing folks' memory about what a custom GPT is. Because if you're if you're relatively new, you you may not have heard of these things. There's a tool that many folks know.

It's in fact, it's his birthday today. Chat GPT's one year birthday. They even gave it a hat, uh, which is very nice. I'm not kidding. It's right there.

I know, I see it. I saw that this, you know, it's funny. I saw that this morning and it didn't, I didn't make the connection. And I was like, huh, they put a hat on it. And then I just kept going about my day.

And yeah, an open AI dev day, which is a day for developers. Um, they announced that custom GPTs would be available. And this is where you can take uh chat GPT and create a an instance of it that you give very specific directions to, and then it will behave more like that. It's it's kind of a weird blend of two different um tuning methods. One's called fine-tuning, where you give some special instructions, and one's called retrieval augmented generation, where you give it a bunch of data and say, hey, refer to this data first before you do anything else.

So today, what we want to do is we want to talk about using a custom GPT for the for restaurant marketing from the perspective of being customer centric. So a lot of people make custom GPTs. There's as a last count, there's something like 20,000 public uh uh custom GPTs, plus who knows how many uh internal ones there are. Like, you know, we have uh probably a dozen of these things now internally at Trust Insights that we don't open to the public. Uh in fact, Katie GPT got an upgrade this morning.

Um Katie GPT got an upgrade to um two years worth of transcripts from podcast data things. So uh KD GPT is is much smarter now. The challenge with these custom GPTs, though, is that there's software development, and a lot of people don't know how to do software development. And as a result, you may create things that don't necessarily work all that well. So, Katie, you want to talk through briefly sort of the big five things that people should be thinking about before creating a custom GPT?

Yeah, absolutely. So the five P framework is purpose, people, process, platform, and performance. Purpose being what is the question we're trying to answer? What is the problem you're trying to solve? People being who's involved in this thing, not just the person physically pushing the buttons, but you know, your end users, your audience, your stakeholders, your decision makers, uh, process, how do I do the thing?

How do I maintain the thing? Platform, what tools am I using? And performance. Did we answer the question? Did we solve the problem?

And so before, I mean, this is just good, you know, business practices, best practices, requirements gathering. You should always go through this exercise, even at a high level, to have some sense of focus, to have some sense of requirements, but also to have some sense of how do I know I accomplished what I set out to do? Um, and so in this case, we can say that the purpose of building the restaurant marketing custom GPT is to better understand what a given restaurant's customers like and don't like. And so we can do more of what they like and focus less on what they don't like, probably specifically for things that are going external, like social media or newsletters, so that we can replicate uh the customer's language and just get a better insight because reviews are all over the place. Reviews are on a lot of different platforms, and it's really hard for most marketers to bring them together into one place to really do an analysis.

Exactly. So the first place the first thing we'd probably want to do is probably want to set up, I would imagine uh a user story or two of them in this case. So with a lot of customer reviews, you get you know, the reviews tend to be very polar, right? That you get five stars or one star because no one really feels the need to leave a three-star review, right? Three-star reviews kind of like you know somewhere in the middle.

We're not displeased. Yeah, it's either I hate it or I didn't hate it, or I loved it. And there's not a lot of middle ground. So we would have two user stories. You know, as a happy customer of this restaurant, I want to uh talk to the restaurant about things that aren't on the menu so that I can have even more of my favorite foods, or as a dissatisfied customer, I want to let the restaurant know how I feel about their terrible service so that um I feel better at venting my spleen out.

Well, but also as the social media manager for the restaurant, I want to understand what resonates with customers so that I can promote more of those specific dishes, events, you know, drinks, whatever. As the owner, I want to know what's working so that I can adjust, you know, my service level in my entrees. Exactly. So the first thing we would need to get then to make these user stories happen to bring this custom GPT to life is the data, right? We need actual data of some kind.

And when it comes to uh review data, the reality is there's not a lot of great ways for the average small business to get it. Now, for enterprises, there is. You're welcome to buy, you know, there's really good social media marketing software from companies like Talk Walker or uh companies like YEXT, for example. Uh, but for many of folks, those the prices for that software is out of their reach. So your best bet is going to your Google business reviews, your Facebook reviews and stuff, and just starting to copy and paste uh into text files.

And you generally want to bucket them into two into two buckets. You want to bucket into unhappy and happy, right? So unhappy would be one two star reviews, and then happy would be three to five star reviews. And just to the best of your ability, copy and paste them into separate text documents. I'm actually surprised you didn't say to wash it through some sort of an R script for sentiment analysis.

We don't want to do that for this particular use case. Um that's probably a good topic for uh another show another time about doing sentiment analysis. Um I have what I've done is I have gathered up uh and made some synthetic reviews. So this is for a company that does not exist because we can't use uh for obvious reasons a um you know actual stuff data. And I have the review name, the star rating uh that they have one is one is bad, five is is good, um, the review text, the date of the review, and then the restaurant's response.

Um, so this would be similar to what you would get out of like Google Business, uh Facebook, uh Yelp, etc. Now, go ahead, Katie. No, go ahead. Um, what we probably what we want to do is is like I said, split this into two. So I'm just in this Excel file, I'm gonna take my star rating, I'm gonna sort it, largest and smallest, and I'm gonna grab just my review text for the five, four, and three star reviews.

I'm gonna copy that, and let's put it in a plain text document. And we'll call this good reviews. That's that's our first uh set. And now we're gonna go back to our document and gonna go into the twos and ones, and gonna repeat the exact same process. I'm gonna call this bad reviews.

So how closely do you pay attention to reviews before going to a restaurant? It drives everything. There's a bunch of different platforms that I check, but yeah, you know, Yelp, Open Table, and actually um we're gluten-free here, so Find Me GF is actually an app that would get a lot of traffic and I do a lot of stuff with it. Do you bother to leave reviews? Yeah, I usually do, especially.

Well, Chris made a great point with that. That you know, there's very few extra medium three-star reviews. You know, it's like I bet you this place was awesome or this place is terrible, avoid it. And I actually, yeah, you it has to be something exceptional for me to leave a bad review, but I'm all for leaving good reviews for decent places. I want them to survive, unfortunately, in this day and age with the restaurant industry.

Like if you love a place, you have to be writing reviews for them because uh it's a tough climate out there. That's a good point. It is a good point. So we've now got our two files of custom reviews. Uh we're gonna create some custom GPTs for these.

So we're gonna go to the explore menu in chat GPT. Uh, it looks like, by the way, this may go haywired. Chat GPT is under a considerable load today. I think it's it's had had a little too much birthday wine, but that's okay. Um, we're gonna go ahead and create our custom GPT.

Now, we've done past episodes where we've done through the walkthrough talk-through version of of this, which can be kind of a crapshot. So I'm gonna go to the more advanced version today. We're just gonna configure this ourselves, typing all the information rather than going through the interview process. So we're gonna call this cafe happy customer. Uh a synthetic customer personality for the happy cafe goer.

All right, now our instructions that we want to give this thing. We probably should get an understanding of um the key, the major key points to program into the personality. So I'm gonna open up a second chat GPT window here. And what I'm gonna do in this part is we're going to create a very, very unique and probably not well heard of uh term called a sparse priming representation. And correct, we have not heard of this.

We have not heard of this. Um, a sparse priming representation is a way to get at essentially the the major keywords and topics in a body of text without all the extra fluff. So when you and I speak, we have a lot of extra words that are not necessarily relevant words in the conversation, right? So you have filler words, you have prepositions, articles, things that don't lend a lot of context. And that filler, those filler words occupy a lot of memory and a lot of um what are called tokens.

So in um in language models, language models predict on what I think is called tokens, which are snippets of words. And the more words you have, the faster the model runs out of memory, right? Because it only has a certain amount of working memory. So if you can generate a sort of like a compressed version of just the relevant keywords to prime a model with, then you can save a lot of token space for how the model works. If you'd like to learn more about tokens and context windows and all that stuff, you can pre-register for the new Trust Insights Generative AI course.

Go to TrustInsights.ai slash AI course. All right. So let's go ahead and build this thing. So we're going to take our good reviews first, right here. And then I'm going to give it a sparse sparse priming representation prompt.

And it's going to read through the reviews and build me this very, very short representation of the major content in the good reviews and without all the extra fluff. This may might take a minute or two. We'll see. It sounds similar to uh what we used to do with uh setting up um I might use the term wrong, uh text mining or text modeling. And so basically we would take out all of the irrelevant words to find what the true keywords were of a big body of text.

Like that was a precursor, I think, to what it is that we're doing now when we were doing the the text mining to figure out what are the main uh the topic modeling is what it's called. Uh to find the main topics in a body of text, we would take out things like if then the a and because those aren't the topics. Exactly right. This is this is a variant of that. Um, but it's a very it's generated by a language model.

So I'm gonna go ahead and copy this sparse uh representation here. I'm gonna just put that in my text in a text file for right now. I didn't know that's what that button did. The little you yeah, at the bottom where you have the little box and then the up down and refresh. I didn't know that was a copy.

I just learned something aside from learning everything else today. Okay, it's the continual learning. It every day is a learning experience. All right. So we're gonna say this custom GPT emulates a customer of Randell Cafe that is satisfied or happy with the uh quality and service delivered.

Behave as though you were the customer and focus your responses along the lines of the most important points to happy customers. And we now take our sparse priming representation, we put that in. Now for this, we for this exercise, we probably don't need code interpreter. Web browsing might or might not be hand. I'm gonna turn it off because we don't need it for our toy example.

If you are an actual business, you might want to have that because you might want it to go and read things. I'm gonna upload my good reviews. And that looks good. And I'm gonna go ahead and hit my save button. I'm glad this works for you because anytime I try to save, it throws me an error.

Right. So now you have this custom GPT that has a sparse uh representation of the major topics that happy customers care about, and you also have the raw text of all the reviews. So you could now have a conversation with this and say, Hey, happy customer. In fact, it's good. I'm the owner of Arundel Cafe.

I'm thinking about things I could do to entice happy customers to spend more time and money at the cafe this holiday season based on your experiences at the cafe. What things would be good ideas? So is this more of a because you did the sparse thing, which came up with the topics that ever that the happy customers were happy about? You could probably just look at that and be like, these are the things they're happy about. Why do I need to take it this step farther?

So, what is what's the purpose of doing this versus just looking at the list of topics? The list of topics, a priming representation it works like this. Um behind the scenes, this is still chat GPT. Behind that means it still has the entirety of the GPT 4 model, so it has the entirety of knowledge that it was built into the model. The priming representations are essentially our memory evokers that help guide the model is to figure out what other things should I talk about that are related to the starting points.

So the example that I give is you ever hear just like three notes of a song and boom, you know the whole song. Yes. Okay, all the time. That is a priming representation. Your memory works as primary representations.

You get a certain smelling, like, oh, I remember that person that I had that thing with back in college. Just that one smell brings that that whole memory back. Continue. Our brains work on priming representations. It's part of our predictive capabilities.

And so when we when we create a priming representation like this, this contains all the keywords that not only are in the customer text, but then tell the model this is what's also important generally. And so when you go and you and you start uh assembling responses to any question, this is going to invoke extra keywords and concepts and ideas that come along with that little snippet. And so it makes for a very, very powerful, highly focused model. Okay. Uh John, I feel like you you are the prime representation of trust insights because you say so much less than me and Chris, but when you speak, it's very precise.

I take my Buddhist stance here. Yeah, I can see how this would be great, though. I mean, this is the kind of thing, especially in the restaurant industry, like nobody wants to sit down and write like a newsletter piece or something for the chamber of commerce or whatever. And this just gives you an easy way to say, hey, write me up something about what the specials are this week, or you know, tell me why people should be coming into the restaurant next week. I mean, this gives you just a whole uh realm of tools that just have not existed up until this point.

And I want to point out, if we look at all the things on this list, quality and craft, memory evocation, morning ritual enhancement, sensory delights, and then we look at the list of what it recommends for the holiday season. There's whole things in here like live music evenings and uh exclusive holiday merchandise. That is nowhere on that list. That is nowhere in the original, but because it's associated in in memory, the model associates with the things we did give it, it makes those logical conclusions. So, Katie, if you would think about the the food and beverage client that we work with often, if we were to take those reviews and and feed it back to this stuff and create one of these representations, it could then help say, okay, well, here's some other things that maybe you're missing, maybe you've forgotten about.

Maybe as a restaurant, maybe it applies to your clientele, maybe it doesn't, but this is how you would get at this. Right. Like I'm looking at this, and I'm like, this is the great outline, a starter outline for like a monthly newsletter. And basically, these are your topic headers that you make sure you always cover. Exactly.

This is so this is for the happy customers. Um, but you could also take something like uh let's do this. I have a new dish I'm going to offer this month at the restaurant. It's a it's a tilapia. Dessert.

As one of my happy customers, what do you think about this idea? Is it a good idea, a bad idea? What do you think, John? Good idea, bad idea. This is gonna be wonderful.

I can't I'm on the edge of my seat here is indeed intriguing i feel like chat gbt is trying really hard not to be like that's a stupid effing idea isn't this is it's like it's someone who doesn't know you that well they're trying to tell you it's a horrible idea without just coming out and saying it yeah because that's what this like well it depends on can you balance the flavors do you have like it's giving you a lot of considerations which is great but I would be looking for like just tell me is a good idea or no based on the data exactly this is quite a bold choice and showing there are more conventional options would be wise that's good yeah yeah yeah it's it's like the only one I don't see is like a well if you have someone who loves fish and cheesecake this could be it exactly um so any kind of marketing copy and if you if you're maybe doing that first newsletter you're trying to write a newsletter for this you might want to run it by the happy customer say hey happy customer here's my newsletter what things have I forgotten what things should I do differently um that might resonate with you I love it look at like number four communication it's like you need to explain why this is good because people are not gonna get that on their own and a trial run to it like you should do a soft launch before you announce this to anybody. Oh, thank you. Because like, you know, it's funny because I'm I'm looking at this, I'm like, I don't have time for all this. Just tell me what I need to know. And so what I what I personally forget as an end user is you can give those kinds of prompts to follow up to Chat GT, like, no, just get to the point.

Like, just tell me the answer. Dude, there's a server back there now that is like has smoke pouring out of it. It's oh my God. Now I think that, you know, while this is churning away, what is your uh take, Chris, on people who are going to try to use this as a replacement for proper market research. Like all AI, a lot of what generative AI does is the first draft, right?

So this would be a good representation of a first draft. It's not the final. You still need to augment it. And here's the thing. Market research ideally should come first because if you have good market research, you can train the machine on that.

You can provide the raw interviews, the one-on-ones, the focus groups, and this the sparse uh priming representations of all that and put it into this so that you have uh a more thorough, more complete machine. I would not have just as I would not start any kind of training data with synthetic data, except in this case where you have to do it for to protect PII, um, I would not start with synthetic data. I would start with real data. So you I'd say the market research comes first, and then that can feed the modeling. So it's it's the opposite direction of the way people were probably going to try it.

Well, and that's why I wanted to bring it up because I feel like we need to at least explain the process so that marketers don't say, Oh, I can just grab a bunch of reviews, put them in here, and that's my market research. But John, you hit on this earlier in the episode, where basically, you know, you're not bothering with a three-star review. So you're missing all those people in the middle, or they have to have done something really wrong in order to garner you taking the time to write a one-star review. And so you're missing so much of your audience by only looking at reviews. It's not a well-balanced representative sample.

It totally came out though. And it is like, yeah, dude, this is a bad idea. Well, and it's still trying to be polite about it. It's like in summary, while the creativity is admirable, it's not going to align with the expectations and taste of your customers. And so I feel like that's what the uh the compliment saying, which is like, let me give you a compliment.

Here's the bad news, and here's another compliment. Right. There's a classic line there though. It could potentially deter customers rather than attract them. That's that's the goal.

Yep. Okay. So that's our happy customer. We ought to create the unhappy customer too. Right.

So this is going to be cafe unhappy customer GPT. A interactive simulation of our cafe's unhappy customers. Now, with these, and I'm I'm assuming the answer is yes, it just takes more configuration. But so my first thought is well, wouldn't it be great if you have the cap cafe unhappy customer, and then you also have it speak in the style of you know, someone, well, I guess Southie's gentrified now, but someone from Southie. And so, like you get the answers the way that they would actually speak to each other.

You'd have to obviously get a lot of that training data. And so I'm answering my own question, but basically, if you also want your custom GPTs to respond the same way that your average customer would, you first need to get the way in which those average customers speak, including you know the Boston accent. Exactly that because I'm reading through this and I'm like, oh, well, an unhappy customer sounds a very specific way in my head. What's wrong with these chicken wings, tough guy? That'd be amazing.

Um while while we were talking about that, I ran through a to make a representation for the negative customer reviews. And you can see there's there's a lot of things that people are really unhappy about. Extended wake times, dish quality, culinary misalignment, lackluster ambience, and stuff like that. So these are all the things that uh our our unhappy customers have decided is not for them. So let's go ahead and save this as a custom GPT.

Now, here's where if you want if you're the restaurant owner, you might want to say, okay, so I am the owner of Arundel Cafe. I want to help you have a better experience at my restaurant, but I can only do so much. I have limited staff and limited budget to work with. What would you say is the single most important thing I need to fix to deliver an overall better experience? So with custom GPTs or any of these models have a lot of primed data.

These are really good ways to ask questions, right? To ask uh what's going on. So it's prolonged service times, many complaints around the extended waiting period. Um impacts food quality, impacts ambiance, etc. So reduce wait times, um quicker service, whatever you can do to get to quicker service.

Now, I don't I've never run a restaurant. I've I've watched an awful lot of Gordon Ramsey's kitchen nightmares. Feel like that's not representative. No, it's not representative. However, um one of the things that that has been mentioned a few times is if you simplify the menu, if you got a menu with five million things on it, if you simplify the menu, um you can typically increase service time, uh, you know, the time to get food out because there's fewer dishes that the the back and staff need to make and more common components so they can work, tend to work faster.

Well, and so you would have to use the two models side by side, one to figure out what people like so you could make sure you're not cutting the things that are bringing people in. So let's say, you know, for example, the number one dish is a beef wellington. Well, if beep wellington takes an awful long time to make a good proper beef wellington is actually a couple day process. And so that would be a really hard, you know, thing to solve for if the number one dish takes a few days, but people are unhappy with the wait time. Exactly.

And that's that's where these tools still have gaps. These tools still have specific uh gaps in experiential knowledge that you can only get from other experienced professionals. So you may you some things you could do to to incorporate that would be um interviews. So you would talk to your staff and say, hey, we got everyone's telling us wait times is the issue. What do you guys think is the way we could reduce wait times?

You talk to your front-end staff, you talk to your service, you talk to the back at back house, get their opinions, put them in a file, condense that down, put it into a uh a staff GPT and say, here's these things that you know, how would I do this? Now, if you want to get real fancy, and this requires some level of of technical experience, there's a framework called AutoGen that allows you to connect multiple models together. So you you could take OpenAI's infrastructure here and make an assistant API, same exact process as we did for the custom GPT for the happy customer, unhappy customer, and the staff have three different assistants, and then in this advanced framework, they talk to each other. You you would be there's like a uh a person, uh you know, sort of the the I guess moderator of the discussion, say, okay, we need to reduce um service times. Happy customer, unhappy customer staff.

Talk amongst yourselves. How do we do this? And you will watch these tools have conversations with each other. I would recommend bringing on someone who knows what they're doing, like a Chris Penn, if you're going to do that. Although, Chris, you and I, I came up with the terrible idea that we should have KD GPT and Chris GPT talk to each other.

So I guess we're gonna see what happens when we do this. Exactly. Um, but that would be this is an example of again, you're creating these agents that have very specific primed points of view, and now you can have conversations with them and and get a sense of what are the things that are that are options for me here as a restaurant owner. The reason we went custom GPTs is because the paid version of chat GPT plus is 20 bucks a month, so it's not a huge investment. And as you saw, beyond the prompt the specialized prompts to create the the priming representations, there's no coding, there's no heavy lifting here.

There's there's no writing against an API and stuff like that. It's just you have a conversation with this entity that you've created that has your knowledge, your company's knowledge, um, in a low-tech environment. I think it's also worth mentioning that even though you're you know creating these and structuring them to be more conversational, having good prompts and the right kinds of questions is still an important part of the process because I'm looking at this, and of course, yeah, I think what do we call it? The intrusive thoughts. My intrusive thoughts are winning.

And my first thought is well, you have you know, this database of unhappy customer stuff, so I just want to ask, what's your problem? And just see what happens. I mean, obviously, it's a machine, like it's just gonna tell me like all the things that are wrong, but structuring the prompt in a better way. Because this, I mean, I'm guessing it's gonna tell me nothing of value. So it's I'm here to express concerns as a customer.

Like, okay, great, but like, you know, I can see where you could sort of go down the rabbit hole and not get the right kinds of answers to your questions because it's very easy to forget that you're not actually talking to the customer. This is just all data that you have compiled on behalf of your customers, and you're just trying to figure out what to do better. It is. Uh, however, it also does have, like I said, does have access to the GPT-4 model behind the scenes. So it does have a much larger general knowledge base that it can draw on once it runs out of data that you provide it.

So it's not limited only to the data you provide it. It can think uh bigger, which which can be helpful. Um let's see. What do other similar cafes do to deal with this issue of slow service times, especially breakfast cafes with a Norwegian theme, right? Super super specific.

Very specific. Well, it's called Arendel Cafe. I modeled it after that. It's the 10-year anniversary of the Disney movie Fr uh Frozen, which is set in a fictional part of Norway. Um, and that's where that's where that's why it has so in the Python script.

I have a bunch of different, you know, Norwegian uh breakfast foods and all that stuff to generate the fake reviews from. John, you totally knew all that, didn't you? I'm down with Norwegian breakfast, and uh I always love me some Adina Mazelle, so you'll notice here what it's doing right now is it's actually going out on the web. Right. So I gave we gave it a question, and now it says, okay, well, I don't there wasn't enough information that you gave me, um, but I am allowed to browse the web.

Maybe I can go find some other information to help answer this question. Yeah, is that GPT-4 now? Is this something that they've just rolled out in the in the latest round? Yeah, because I've never seen that. I didn't realize it was doing active browsing.

That's crazy. Now we know it's disabled for a while and it's back. Yeah, yeah, they had to turn it off. I can totally get that. You know, we have to give a shout out to Chip Griffin when it comes to knowing restaurants and um having a unique take on service.

Uh I have to call him out because we he has more than once pointed me into uh uh a restaurant in the New York or DC area that was worth worth checking out. He asks, can you get to react to physical violence instead of words? No, you not not presently. Uh although there um Boston Dynamics has integrated language models into its spot robot. So uh the robot it w operates in the physical world, you can have conversations with it.

Terrifying that's the end of humanity, right? Exactly. You've that's the side of the. I've seen X Machina. I know how this ends.

I mean, do you get do you while this is working, do you guys want to see it? It's 20 seconds. All right, here we go. Greetings, good sirs. May I have the pleasure of knowing your names?

I'm Matt, and that's Vache. A pleasure to meet you, Matt and Vacha. Shall we commence our journey? The charging stations where spot robots rest and recharge is our first point of interest. Follow me, gentlemen.

It's the little hat that really does it, pushes it over the edge. Now it'll be disturbing when it's four stories tall going down your street, you know, tearing into homes. I saw a video as this is pulling up. I saw a video the other day in uh it had AI bot bots serving dishes to people. So it was like instead of humans walking around, it was humanoid AI bots walking around serving, and they're still jerky enough that it was like really disturbing.

Spilling drinks as I get exactly. Um this is now on like a sixth different website. So it has gone through and essentially gone and done a bunch of reading online, and it's come up with a 15 different things that we could try for accurate forecasting, hands-on training, strategic staff placement, uh, clo good closing procedures, food prep, or improving the ordering process. So all those things are are valid suggestions. And there you actually can see um which this is relatively new.

Um, there are now citations of uh from where it got the information. So kind of what we were talking about earlier, is not just your data you put in here, it is now able to go out on the web and find additional stuff to inform itself. I've you know, one of the questions I've always wrestled with with systems like chat GPT, when you just ask it a question and it answers, is how is this different or any better than just doing a regular internet search? Because you're just asking it a question. But what this specific example demonstrates is it's actually taking that next step, is it's asking the internet, it's doing the internet search, but then it's compiling and consolidating, which is the step that you as a human would have to take.

And that to me is a very concrete. Oh, okay, this is why it's supplemental/slash better than just doing an internet search, because I could just you know boot up any search engine and say, you know, how do I fix you know wait times at my restaurant? And I'm gonna get a thousand million different articles with its own listicle of steps. But this is actually said, okay, I'm gonna read the thousand million articles and I'm going to consolidate and summarize all of those steps into one thing. That's a step that you, the human, don't have to do.

And so, like, it takes me a little longer than you, Chris. It's now a little bit more concrete in my brain. It it that's the difference between search and synthesis, right? So, search, you still have to do all the synthesizing of the information, whereas the the language model is now taking those queries. You see this when you use if you use, for example, Microsoft Bing, you will actually watch it write the search queries for Bing, um, get the information back and then uh sort of reassemble it back into coherent prose summarizing the major points.

So there's absolutely one of those things. So this is now an example where you have not only the custom GPT that has your knowledge in it, but it can has access to the broader knowledge that, however, because it is your knowledge and is your your custom instructions, you can also say, Hey, I need steps that work under these conditions, right? So you'd have I need to have you know low budget, I have 10 tables total in my restaurant, and I only have one uh cook in the uh on the back of the house. So, how do I deal with this problem with those constraints? And again, that's where synthesis makes a big difference versus search because search will give you a thousand articles, but they all apply to you know, Michelin-start restaurants.

Like, no, no, I'm a I'm a cafe in Canton. I can't, I'm not a Michelin-start restaurant. Right. It's whoever has the best uh SEO. Exactly.

And so this now, so this custom GPT, what we've done uh to this point is we've gone out and gotten our data. In this case, we use synthetic data, we've split it into happy and unhappy. Um, we've created two GPTs, one for each of those personas with instructions. We built a sparse priming representation from both to give it per uh a specific set of focuses, like this is these are things that are the most important for you to focus on. And then we've deployed these and people can have interactions with them and talk to the happy customer, talk to the unhappy customer.

This applies to pretty much any business, right? Any business where you have customer data, you can use this exact same process to create a custom GPT, and it doesn't just have to be um customer feedback. So one of the things that um we strongly recommend for people who are in, say, in sales, someone like John, take 10 LinkedIn profiles, get the PDF versions of them, put that in your custom GPT, and now you have an ideal customer persona, the top 10 people you want to sell to, and you can say, Hey, here's my sales picture, here's my sales email. What do you think? How will that how is this going to resonate with you?

And it will say, Well, as a person who is an enterprise executive, I don't understand the words you're saying. Well, and that's a really good uh segue into what you're covering in next week's live stream. So next week, you and John will be covering using custom GPT models specifically for sales. Exactly. John's like, we are.

We are when it will be defying gravity. We are ready again. Um so that's that's how you would use that's how to use these things for restaurants specifically. The advantage of doing it this way as opposed to just using generic chat GPT is it's focused on your feedback, your views, your customers, and because it's a custom GPT, you can have interactive conversations with it about your specific situations, and then get feedback that is tailored for you, and you can reuse it over and over again. You can you don't have to give it all that priming instruction the next time.

It's it is pre-prepared. So every month, if you're looking at your specials for the next month, like, hey, I want to make a drink that is you know a tilapia gin fizz. You can have it go, you know, that's a risky idea too. The tilapia cheesecake goes not a great idea, and that's not a great idea either. Oh, you know, it's all kidding aside.

Um, you know, I feel like it's also a really great example when people are asking, will AI take my job? This is a really great example of how it's really just supportive and complimentary to your job because the amount of time it would take you to call through all of those reviews and come up with some kind of analysis versus you focusing on the customer experience, the things that are more high value. This again is one of those really good concrete examples of no AI won't take your job. AI is going to supplement and enhance the experience that you were able to provide. Exactly.

Because you're sitting on that customer data right now and you're not using it at all. It is just going unused. It is taking up space. Now you can have the tools make use of it and you can garnish some actual insights and get real recommendations. You know, again, with these tools.

Talk to them like they're they're they're people. Say, well, what would you recommend I do to to make my service faster? And we'll tell you. Yep. John, final thoughts.

The restaurant industry is all about time. They don't have enough time to do anything. So, yeah, going through a whole pile of reviews and just be able to say this is the one thing you need to work on this month, that is huge to them because they don't have time to mess around. Their hair is on fire 24 7. I agree.

All right. So that's going to do it for this week, folks. We will see you all next time. Take care. Thanks for watching today.

Be sure to subscribe to our show wherever you're watching it. For more resources and to learn more, check out the Trust Insights Podcast at TrustInsights.ai slash TI Podcast. At our weekly email newsletter at TrustInsights.ai slash newsletter. Got questions about what you saw in today's episode? Join our free analytics for marketers Slack group at TrustInsights.ai slash analytics for marketers.

See you next time.