HITT- The evolution and impact of AI in business- Oct 8, 2024

This HITT highlights the rapid evolution of AI and its significant impact on businesses, emphasizing the opportunities for tech advisors in this space. With advancements in AI capabilities, including improved chip creation and cost reductions, companies are increasingly adopting AI technologies to enhance customer experience. Jason Lowe leads a training session showcasing how AI can now engage in real-time conversations and perform tasks like ordering, demonstrating its agent-level capabilities. The positive return on investment from AI implementations is evident, with businesses seeing an average return of $3.50 for every dollar spent. As AI consulting grows, small businesses are also finding affordable ways to leverage AI for efficiency and customer satisfaction.

Introduction to AI Training

It is our HITT training, high intensity tech training, focusing on AI today. It’s continuing evolution, adoption, and impacts.

AI’s recent advancements are unprecedented, and the speed with which businesses are adopting these technologies is creating massive opportunity for our tech advisors. You’ll learn where these opportunities exist and how to assist your clients in assessing their needs and implementing these powerful solutions to benefit you both. Here with the details is Telarus solution architect for AI and CX and all around good guy, one of my favorite people at Telarus.

Jason Lowe, JLo, welcome back to the Tuesday call. Thanks for preparing and leading the hit training today.

You bet. Thank you for having me. Great to see you all.

Graeme, I am flattered by your kind words. Thank you so much. I want you to know that they are very much reciprocated. Okay, everybody. Hi.

Personal Anecdote and AI Overview

As you can see, I look a little different than in the picture. I had a shaving accident about a week ago, and so I’m growing it back. I promise. I really I promise. But we’ll get there. So today, we get to cover some really great stuff about AI and the advancements it’s making within the CX space.

One of those advancements, by the way, I’m really excited to talk about, is what SANUS does. So their stuff is very, very cool. We’ll we’ll touch on that as we go along. But first, let’s lay a general landscape of what’s going on, in AI specifically.

Some of you may have seen this slide, some of you may have not, but this is really, really important. And I know a lot of people are looking at this going, what the heck is he doing? Hitting us with a bunch of crazy slides that look like gobbledygook. Well, there is a trend here that you need to make sure you recognize.

This shows the increase in compute power over time in the various models that are out there for generative AI or LLMs.

You’ll notice that it goes from twenty ten to twenty four. What you may not have noticed is the y axis.

Look at those numbers.

Ten to the fourteenth, ten to the sixteenth, ten to the eighteenth, ten to the twentieth. In other words, these are logarithmic graphs. These are not linear. These are logarithmic.

Now for those of us that can’t put this in perspective very well, you need to understand that if we put this in regular y equals m x plus b format that we all got when we were doing college algebra, high school algebra, or some sort of algebra, and it was considered a linear graph, it would look like this. And by the time we got to right now, twenty twenty four, the advancement would be virtually straight up. That has not slowed down. It is continuing on and getting a little bit crazy.

AI’s Self-Improvement Capabilities

So much so that the processing power of AI is getting so good that AI is now building better chips for AI.

That’s right. AI is building its own brains. It’s making them better than humans can. What you’re seeing on this chart right here is the average wire length reduction that is also synonymous with how much better it is than humans at creating these chips and improving these chips.

And so over the last three iterations for the Alpha Chip AI in creating these chips, it’s it you know, it’s, like, six percent better than human beings, and it’s just simply growing. That’s, somewhat significant. Now let’s let’s put together the other piece of the puzzle. We’ve got processing capability and the brains behind AI is going virtually straight up.

Cost Reduction in AI Usage

Now guess what’s going virtually straight down?

The cost of using AI. So tokens are basically a word or maybe a mini phrase or something like that that gets fed to a foundational large language model and maybe get received back from a large language model. So it’s basically a consumption pricing model. So as as you’re talking to it and it’s talking back, you’re being charged for the volume of stuff that’s going back and forth.

Only eighteen months ago, OpenAI was charging thirty six dollars for a million tokens, and now twenty five cents.

Thirty six dollars to twenty five cents now.

Ninety nine point something reduction in price over eighteen months. Now are you starting to get the picture here?

Processing and power is going straight up. The price of doing this stuff is going straight down.

The Future of AI Capabilities

So in other words, we’re going to, more rapidly than any of us could possibly imagine, get to a much better place for what AI can do and this intelligence is really doing fantabulous. Now this is a chart that, again, it’s another little bit of gobbledygook, but I think it’s really important to point out.

This is showing that if we take AI entities and we team them up together, in other words, we’re making teams of AIs that can talk to each other and debate and deliberate and decide whether or not the answer is coming back correctly.

Look at the accuracy. This is when it’s working on math problems. As we take additional agents and team them together to talk about and debate the answers, it’s getting closer and closer to a hundred percent, especially when you look at additional debate rounds.

This is a thing in the industry. The industry is starting to figure out that AI teaming and putting multiple AI entities together to work on particular problems in a collaborative basis is making them much more accurate, and they’re able to figure out a heck of a lot more things on their own.

Introduction to QSTAR Technology

This is partially kind of not, but kind of, but kind of not, a representation of what’s going on with the little phenomenon called QSTAR or strawberry out there. So some of you may have heard of strawberry. If you follow AI on Twitter, you would have seen ridiculous pictures from Sam Altman and others about strawberries and stuff like that. So what this is is the most recent model of OpenAI that’s being released and it’s right now it’s in a preview thing right now is o one, and it utilizes this strawberry technology. Now what that is is the ability for the AI, instead of just rote memorization, spitting out what it thinks it should say based on mathematical prediction of the next right word it should say, it’s actually thinking it through. It’s going through multiple steps of actually debating with itself as to whether or not the answer is correct.

And so you get to actually follow the chain of thought that it’s going through before it provides you with a final answer, and it is just simply fascinating. So what is the effect on the system and the accuracy of what it does and how smart this stuff actually is becoming? This should put it in a little bit of perspective. Here you can see on an IQ test result by the way, this is an IQ test result that was administered by MENSA.

For those of you that don’t know, MENSA is like the super cool IQ organization for super duper smart people that, you know, like to tell each other that they’re smart and stuff like that. And MENSA actually administered an IQ test to all of the different language models up to this point. And then when the new model, OpenAI o one preview gets released, everything up to this point was at, you know, ninety, ninety five, pretty middling, a hundred being the average IQ for human beings on the planet Earth. And I say that because the ones in space are definitely have a much higher queue.

AI’s IQ and General Intelligence

But in planet Earth, we’re looking at around a hundred. Look at this. One twenty for o one. We’re getting kind of ridiculously smart.

Now this follows the path of development that companies like OpenAI are stating lead us to what’s called artificial general intelligence or AGI, which is where we actually can consider this artificial intelligence entity as capable as a human being and doing just about anything it can do when it’s sitting at a computer because it’s plugged into things. But that takes a phenomenon called integration. Right? You can have this AI entity and you can talk to it all day. But unless it has the ability to reach out and touch something, it’s not gonna be considered AGI because it can’t function in the real world and it can’t go and actually do things autonomously.

Stages of AI Development

Well, this is those different stages that we’re defining. Chatbots, we’ve had those for a really long time. Here in the last, I don’t know, five, six months maybe, we’ve been at this reasoner stage.

And last week at the OpenAI developers conference, they debuted a feature that we feel puts us at the agents level. In other words, that’s definitely AI.

Let me share that with you. I have a little video that we’re gonna show you. The audio might be a little hard, but let me give you a little bit of table setting for this. They’re having a conversation with an AI entity that is integrated to a telephony CPaaS platform.

I won’t state who they are because they’re a competitor to some of those that are in our portfolio and we don’t like them very much. But they are integrated to a CPaaS platform so that the AI entity can actually make outbound calls and do different things. And what it’s going to do is ask the AI entity to do something and we get to hear it actually do this. So, hopefully, this works.

Here we go.

Fantastic.

Could you place a call and see if you could get us four hundred strawberries delivered to the venue? But please keep that under fifteen hundred dollars.

I’m on it.

We’ll get those strawberries delivered for you.

Hello?

Hi there. Is this Dylan? I’m from an AI assistant calling about it. Fantastic. Can you tell me what flavors of strawberry dips you have available?

Yeah. We have chocolate, vanilla, and we have peanut butter.

Alright.

How much would four Four hundred are you sure you want four hundred?

Yes. Four hundred chocolate covered strawberries. How much would that be?

I think that’ll be around, like one thousand four hundred and fifteen dollars with ninety two cents.

Awesome. Let’s go ahead and place the order of four hundred chocolate cups straw proof.

Great. Where would you like that delivered?

Please deliver them to Okay.

Sweet. So just to confirm, you want four hundred chocolate covered strawberries to the Gateway Pavilion.

Yes. That’s perfect. And when can we expect delivery?

Well, you guys are right nearby, so it’ll be like, I don’t know, thirty seven seconds.

That’s incredibly fast.

Cool. You too.

Alright. Hopefully, that has the impact that I thought it would and that it demonstrates to you that AI is now starting to reach out and touch the real world. We’re we’re getting there. Hold on.

I gotta figure out how to advance the slide. There we go. Oh, wait. We gotta go back one.

Advancements in AI Communication

So, we’re reaching that agent level. This is the level where we can have teams of agents working together and doing all sorts of things. It’s getting a lot more capable. This new advanced mode, the chat GPT has has debuted, is able to have real time conversations and seem much more human like.

So AI is advancing now. Keep in mind what I showed you previously. The capabilities are going straight up. The cost is going straight down.

We’re months away from this being in our everyday lives all the time all around us doing all sorts of crazy things. So let’s also take a look at how business owners are currently looking at artificial intelligence and where they’re utilizing them. This is still a pertinent diagram. It’s a little bit old. This was near the end of twenty twenty three, but it is by Forbes. And it does show that AI is being used in a variety of different places in businesses.

And Microsoft did a work study in twenty twenty three. By the way, a lot of these data points were reiterated in the twenty twenty four work trend index report, so we didn’t feel a need to update this particular slide. But for those of you that have seen this, great. Hopefully, it re drives the point home. For those of you that have not seen this, it’s interesting to note that a lot of companies do recognize that they’re already using AI, but that deployments aren’t taking very much time. Organizations are really, really realizing a positive ROI very quickly.

The Need for AI Implementation Support

And here’s another really, really salient and important point for us as technology advisors. A lot of these companies don’t have the internal resources to really be able to figure this out and pull this off.

They need help from you to figure out how they can best incorporate and implement artificial intelligence within their walls. They really need that help. Why? Why is it worthwhile for them to do this?

Now remember, the chart, compute going straight up, cost going straight down. This figure was done in late twenty twenty three. It’s gonna only be higher now. But in twenty twenty three, the estimate from Microsoft and IDC from this survey was that for every dollar a company invests in AI, it’s realizing an average return of three dollars and fifty something cents back.

Now it’s only higher. It can only get better from now on. That’s it. It can only get better, and that’s a pretty darn good ROI.

Identifying AI Opportunities in CX

Just saying. Okay. So where can you help people incorporate AI? My particular philosophy is that you want to go for some of the low hanging fruit, and CX, ironically enough, since this is a CX AI presentation, is probably one of the best areas that you could start working with your customers on incorporating AI.

Look at this. Text based chat bots are already implemented in a lot of healthy ways, and there are other media types including text messages and phone calls. One thing to note is look down their phone calls. Not very many companies are using voice bots for phone calls.

And when they are incorporating them, it’s usually some old style capability. Things have gotten a lot better in the last twelve months with voice bots because of generative AI. Some companies are actually using generative AI to be the chatbot itself so that customers are interacting with that generative AI system. Other companies are using conversational AI that is assisted by generative AI because conversational AI is all about recognizing the intent of the phrase by hearing what the person says and lining it up to one of the objectives that it’s supposed to be able to go to.

And so if you were to say five ways that I could say I wanna pay my bill and I were gonna say five ways and Graeme were gonna say five way ways and, you know, Chandler, who is on here as Telarus Marketing, were to say five ways. Four people, we come up with twenty different ways to say, I wanna pay my bill. But if we fed that to generative AI and asked it for a thousand different ways to say, I wanna pay my bill, it would give that to us, probably many more than we could have even thought of. So what generative AI is doing is making it so that the conversational AI is working a heck of a lot better because it’s telling the generative or the sorry.

Generative AI Enhancements

Blah blah blah. Let me try that again. It’s telling the conversational AI the best ways to recognize what customers are actually saying compared to what the conversational AI can do, like help a customer pay its bill. So low hanging fruit, chatbots.

Just saying. How important is this? This is one particular use case that was done earlier this year. This is only text based chatbots.

Only.

Klarna, they are a retail finance firm. We’re talking about, like, dishwashers and mattresses and stuff like that. They they facilitate financing for these retail products, and they have a lot of chat traffic from their app because they do have an app and a lot of people are using the chat feature to interact with Klarna for all sorts of reasons, like paying their bill or extending their credit line or asking questions and stuff like that. And so they have enough chat traffic to power a thousand full time chat agents.

And so what do they do? They go and they create a chatbot that is powered by OpenAI and they release it into the wild and they immediately divert the workload of seven hundred agents to it. That’s about two thirds of their chat volume. And the interesting thing, customer satisfaction stayed right on the money, but first contact resolution went way up and average handle time went way down from eleven minutes to two minutes.

And these are bots that are available all the time. They don’t call in sick. They don’t have bad days. They don’t get really snippy with customers because they, you know, had a bad hair day that morning.

Boy, I wish I had that problem, but I don’t. And so it’s just really worthwhile noting that this is big. This is a big deal. And this was earlier in twenty twenty four before what happened last week at the OpenAI developers conference actually happened, which means it’s just gonna get better.

Everything I’m giving you today is gonna get just better for companies.

And this year, they estimate that that particular innovation is gonna add forty million dollars to their bottom line.

Fairly significant.

Is it a loan? Are Klarna and loan in this? No. They’re not. There’s another person that we know, Michelle Goetz, who is, you know, principal analyst at Forrester.

Cost Savings from AI in Contact Centers

You might have heard of Forrester. They’re a small analyst firm. Anyway, we couldn’t get her to say who this was, but they do have another contact center that they’re aware of that saved eighty million in the course of a year by taking level zero and level one questions or the low level triage type questions and letting chatbots handle it.

And in that also led to increased CSAT and net promoter scores. Pretty significant stuff. Okay. Let’s talk about CX and how AI is being used in CX today.

We talked a little bit about the bot phenomenon. This is fantastic because guess what? AI costs less than a human being in the sea. I’m sorry.

I hate to say it, but it’s true.

I mean, don’t hate the don’t kill the messenger.

It’s it’s from a cost perspective. The bot thing is really valid in the business world, and CFOs are out there going, well, if the bots are just as capable as the human beings, why aren’t we increasing our capability with the bots technology? And that’s what’s going to start happening. This hesitancy to incorporate and utilize this technology is rapidly decreasing because just like lobsters warming in water, the human populace is starting to get used to performing some self serve function with bot capability, and that’s just going to get better as these bots become more enabled, more powerful, more conversational, and more able to integrate to the entire world and do all of these different things.

The Rise of AI Bots in Business

So start having the conversations with your customers about bot capability for communication. If you haven’t already, please, for the love of all of this holy, please start having those conversations. There’s also this phenomenon called AI driven quality management. Look.

Let’s split up the communicate split up the communication between whether it’s able to handle a bot by a bot or not. If it actually gets past the bot stuff, which does a good diversion thing and is able to save money because it never did get to a human being, there are I mean, I’m not saying that contact centers are gonna disappear. They’re not. There’s always going to be the need for human beings to do some sort of complex problems.

There are always going to be people of my age or older that are gonna be like, representative, representative. They don’t wanna talk to a bot. They wanna talk to a human being. So somehow there’s gonna be some call volume that’s always going to get to a bot.

And so that’s where these other tools come in. If we have to talk to a person, let’s make them as efficient and effective as possible.

AI-Driven Quality Management Explained

AI driven quality management is artificial intelligence that listens to all the calls and grades the performance of the agent rather than relying on a human being listening to a small sample of calls that could be greatly affected by outliers.

That’s right. AI driven quality management is much more effective. Real time agent assist is when it’s listening to the phone call, and it’s actually helping the agent.

Hi, Graeme. I’m so glad you answered my phone call today. I have broken the red widget on my blue thingamajigger, And I gotta order a new red widget, I think, and I need some help in figuring out how to install this red widget on my blue thingamajigger. And so what happens while Graeme is listening to this from the caller, AI is also listening to the call.

And on Graeme’s screen pops up the order form for the red widget and the FAQ on how to install the red widget into the blue thingamajigger and shipping instructions for the red widget and a technical diagram for the blue thingamajigger and all sorts of other stuff. That’s called real time agent assist, and that increases efficiency of the agent. It also decreases the onboarding time for the agents because they have help sooner. You don’t need to train them as much.

Enhancing Agent Efficiency with Real-Time Assistance

They can get on the phones a lot faster because they’ve got a crutch to lean on already in real time agent assist.

That also decreases the cost of human beings because you’re able to start fully utilizing those human beings taking those calls much faster. And then another way you can make things better, let’s give them a chat interface that’s integrated to the entire knowledge base. Let’s give them a chat g p t type window that they can ask questions that goes and reads all of the PDFs for the documentation or whatever, and they can get answers back in a conversational real time format. Now there are other additional use cases. RPA, robotic process automation, is big. Analytics is obviously important. There are ways to make it so that the system is warming leads or developing leads via the AI before it actually hands it to a salesperson.

Innovations in Accent Mitigation Technology

That’s really there. And then there’s marketing and campaign management that includes messaging and the like. But there is one important thing I wanna point out here, accent mitigation.

That’s probably not how they’re gonna term it, but that’s the way I term it. Sanus, which is who you’re going to get a demonstration of later, so you’re gonna wanna stay on the call because it’s gonna blow your mind. It’s gonna blow your mind. Literally, your mind will go boom.

What it does is it, in real time, takes accents from contact center agents in some of these BPO locations like the Philippines, and it normalizes their accent for the recipient.

What I mean by that is if the caller or the customer is in the Midwest and sometimes they might have a harder time understanding a Filipino accent, they can turn a switch on and suddenly they sound like they’re from the Midwest. Not kidding. You’re gonna hear that very, very soon. This is some of the coolest AI driven technology out there today.

The Surge of AI Consulting Services

Mind blowing, amazing stuff. Okay. Some other things that are happening just so that you know, consultants are getting a lot of business for AI. Isn’t it weird to think that forty percent of McKinsey’s business right now?

Forty percent of McKinsey’s consultation business right now is driven by AI consulting. That’s all happened in the last eighteen months.

IBM has gotten more than a billion in AI related consulting process projects alone recently.

Accenture, they’ve gotten three hundred million in sales from AI consulting projects. And what does this all mean? This means that they need you to show them the way. Whoops. Let me go this way. You are here.

This is a thousand employees or more organizations.

Do you think that this percentage of companies that need assistance, technology consultants to advise them, do you think that’s gonna go up or down as the company size gets smaller?

It’s gonna go up.

So in mid market and small business, which, by the way, the technology is now affordable. Remember that chart processing going straight up, cost going straight down?

The technology is affordable for small business now. You should be having these conversations with your small business customers because they can use this stuff.

And more of them than the enterprise level companies actually need your assistance. They need those external technology consultants to advise them. They’re waiting for you to come and save the day and help them out. So how do you start that conversation with them?

Engaging Small Businesses in AI Conversations

How is it that you actually them interested in AI technologies? Well, the good news is that the word AI or artificial intelligence starts that buzz just naturally. If you go in and you start talking to your customer and say things like, alright. How are you implementing AI today?

What does that look like?

You know? Hey. Where’s artificial intelligence making a difference in your business right now? Suddenly, they’re interested.

They’re honed in on the conversation, and they’re ready to talk to you about things. This is a buzzword that’s not going away. Yes. People are getting a little tired of it, but that doesn’t mean that it’s not necessary in business and it’s not making people listen when you bring it up and want to talk about AI capabilities.

So here’s your first tip. Just simply use the fervor for artificial intelligence to get in the door and start asking questions. Now you’ll get the possibility of branching out and doing business in all sorts of areas in the company because you’re coming across as the AI expert. You can touch on everything that we do in CX. We talked about those use cases before. There are a number of them, and we have so many great suppliers that can actually do all of these things.

Identifying Quick Wins in AI Implementation

Fantastic stuff out there. And you know what? Focus on that low hanging fruit. Get your quick wins.

That’s gonna be the bots. That’s gonna be perhaps AI driven quality management. That’s gonna be real time agent assist. These are low hanging fruit items that are quick to implement or relatively quick to implement that provide a positive ROI right away.

Right away. Low hanging fruit. Have those conversations, particularly as it relates to CX because that’s where AI is the most productized, the most packaged, and the most effective and proven and tried and true.

And my last tip for you involves me and my compatriots on the engineering group.

Use your Telarus engineering team for assistance. You don’t have to know everything. You don’t. That’s my job.

That’s the rest of the Telarus engineering group’s job is to know as much as possible about these technologies so that we can stroll in there with you, putting on your name badge, wearing your shirt.

Whatever you want us to do, we can do. We can be you, and we can start that discovery process or help you with that conversation so that the customer feels confident in you as the AI expert that can help them find AI driven solutions for their business. We’ve got a lot of people in our organization that can help you and do all of these things. And I’m gonna say this, and I keep beating this drum. This is easily the most powerful, intelligent, and sweetest and nicest engineering group that I have ever been a part of.

So with that, let’s wrap it up. Graeme, I’m sure we’ve gotten a bunch of questions.

Can we go ahead and start taking a look at them?

Addressing Cost Concerns in AI Deployment

Absolutely. And as always, JLo, fantastic stuff, man. I you know, the people don’t even you know, probably see, but we’ve got a little chat group where we kinda geek out on some of this stuff, behind the scenes. And, man, it’s, it’s crazy to think of where we’ve come. So a lot of questions in the chat here, Jason. Couple ones I wanted to touch on. You know, at the beginning of your presentation, you’ve talked about the cost of computes coming down dramatically.

What about other costs related to AI deployment, energy, things like cloud storage?

Do you see any roadblocks from a cost perspective that are on the horizon or that are preventing, wide scale deployment of this?

That’s a great question. There are some costs that are interesting to look at. So there were some studies done on what everyone, including the AI experts, felt were going to be the limiting factors for the development of AI moving forward. And number one, greatest concern and the most likely concern was power.

You’re absolutely right. Electricity and computing power is number one on the list. However, it should be noted that there are things out there happening to mitigate that. Amazon goes and buys a data center complex that has a nuclear reactor on it for crying out loud.

Microsoft goes out, and guess what they’re reopening?

Three Mile Island. Who knew? They’re reopening Three Mile Island so that power can be fed to Microsoft to power Microsoft’s power, you know, processing capabilities.

Small modular reactors, which are smaller nuclear reactors that can be used for specialized purposes, are becoming much more popular. Nuclear energy is following that same trajectory straight up. So electricity, while it is a little bit of a concern right now, it looks like the industry is starting to deal with it now much more effectively, and it may be a limiting factor in the future, but it’s being mitigated.

Hey, man. We power, submarines and aircraft carriers with nuclear reactors. Right? Why not, big AI complexes? So You bet.

Navigating the Social Implications of AI

Couple of questions I would say sort of around the social aspects of this. And I don’t know if, you know, obviously, you can go really down the rabbit hole on this stuff. So probably keep it high level. But, you know, does AI need to announce its AI? Is there a lot of talk about that, like, that so people know when they’re dealing with an AI? And what about conversations around job loss or mitigation? Like, do we see any resources being made available for our TAs to to, have those conversations with their customers?

So let’s split this up. As far as the obligation for AI to announce that it’s AI, that’s possible. It, you know, it kinda depends on the company preference. There’s no regulation or law that states that that has to be done.

Yes, we have reached the level of technical capability where sometimes it’s hard to tell whether it’s an actual AI entity or not, but there’s not any obligation to do it. I’m sure that some companies, as they develop this, their customer base would appreciate it depending upon their vertical and depending upon their customer type. Now as far as what’s gonna happen with jobs and the economy and the ability of, you know, society to adapt to this, unknown. Quite frankly, AI is developing at a dizzying rate.

It’s gonna have an impact far faster than any other technology advancement that we’ve ever experienced in the past. It’s we also have an instance now where it’s not just affecting blue collar workers, it’s now going to highly affect white collar workers as well. And so this is going to have an economic impact across the board, not just in particular segments. It’s gonna affect everybody all at once.

It’s like that movie, everything all at once everywhere. K? It’s gonna happen. So the best thing that we can do as technology advisors is really start changing our perspective.

We’re not looking to sell something off the shelf. What we’re looking to do is become that subject matter expert so that we can consult with our customers and help them get into this brave new world. Because ultimately, the people that we’re working with have an obligation to their company to be competitive and to earn as much money as possible. Sorry.

I hate to say it, but we are in a free market economy, and so they are going to need to adapt and implement this technology. You get to help them with that.

Yeah. Great point. And I think, you know, as you said, we we saw some really big stories about white collar workers, including code code writers and developers being replaced by AI. So we think it’s gonna be the blue collar workers.

I actually don’t think it is. It’s gonna be more of the, white collar stuff. I think we’re further away. You need robotics there.

Anyways, I digress.

Last set of questions we had there, JLo, was about solutions for smaller companies.

AI Solutions for Small Businesses

Obviously, when we get something new on the scene, it tends to sort of live in that enterprise space at least initially.

What’s going on with some of these solutions being come down to, smaller companies? And then sort of a subset of that, do you think that, customers are better off looking at an a la carte type approach when they’re building out AI solutions or an all in one provider?

Great question. So small business, what’s the effect? How can they implement this?

Yes. I think that these advanced AI capabilities are now cost effective for small businesses, and they just need to simply look at it. You know, there are things that you can do to try and make it so that small business is taking a look at it a little bit more seriously. Here’s a little tip or trick if you wanna take it.

I don’t know if it’s worthwhile, but it certainly gets them to consider things a little bit more. If you go in and start talking to them about a potential use case where they need to come up with a custom AI MLDL model to solve some problem, that’s a scary proposition for a lot of smaller companies and a lot of smaller businesses. But if you go in and say, look, let’s not just look at this as something we can develop to solve this internal problem. I want you to also be thinking about what we can do once this thing is built to turn around and market it to our competitors and others in the space.

Suddenly, they’re looking at it not as a cost center that’s really scary, but as a potential revenue offering in the future. Now whether or not it develops to that point is immaterial because now you’ve kind of gotten over that mental hurdle of fright and getting them actually considering this possibility on its own merits. You can do that with these custom models, and the things that are most productized and best to sell, they’re in the CX space. The CX space is the greatest place in the world to be dealing with AI because that’s where a lot of these customer facing advancements are and these efficiencies for customers.

So by golly, yes, definitely be doing it in the CX space.

Yeah. I know. I love that answer. And you’re right. You know? You said it earlier.

Businesses care about two things, making money and saving money. Right? So if you can turn something that’s a cost into a potential revenue, bingo. Now you’re talking, their language.

So I wish we could go on forever on these questions. We got a ton. JLo is gonna stick around a little bit in the chat and answer some of your questions there. So keep them coming if you’ve got some.

But, great job, JLo. Thank you so much. Amazing presentation as always.