Lance Hood (FranPro): 0:09

Hi everyone. Today I'd like you to meet Dominic Lamberzi, the co-founder of Text Cortex. Hi Dominik.

Dominik Lambersy (TextCortex): 0:17

Hey Lance, Thanks for having me. It's a pleasure to be here.

Lance Hood (FranPro): 0:20

Well you, I'm so glad that we're on this call today and enjoying this and helping out the franchise companies. Can you explain what does? Because it does AI writing, but you guys also are very different, I think.

Dominik Lambersy (TextCortex): 0:37

Yeah, thanks for the brief introduction. Actually, up until the end of last year, we were known as a writing assistant, ai writing assistant a little bit like Grammarly, but much more capable in doing things. Ever since we released our version of chat GBT we call it Xenochat People have started seeing us as a virtual assistant to their work. Yeah, what I am currently building on our narrative around is that we want to build personalized intelligences. Why personalized? Because a lot of solutions you currently see around they give you pretty generic outputs and results, and with , you don't. You do not only have a companion with is with you on over 4,000 websites and platforms, but it's also customizable on how you act as an individual or organization, plus also knowing what you know as an individual or organization, and therefore, yeah, ending up in a much more personalized experience for you. Think about your own little AI coworker.

Lance Hood (FranPro): 1:39

Right? Well, it sounds like you can load up a bunch of stuff that your company has written, so that then, when it does create copies so let's just say blog posts, emails, responses, whatever it's going to write it through the lens of all the stuff you've written before, so that it writes in your unique voice every time, not a general output, correct?

Dominik Lambersy (TextCortex): 2:04

Yeah, exactly, we did this whole feature built around two pillars. Yeah, first of all, customization how you act, what you give is basically sort of a background you as a person, where you're coming from, yeah, what is your history and, for example, the values you are acting after and what you then can do is also adding a few writing examples, such that our algorithm can map your digital twins, so to say, on over 60 variables. This is one pillar. The second pillar are knowledge connectors yeah, where you, for example, would can connect, upload any type of PDF files, connect your notion, connect your Google Drive. The knowledge connectors are still in beta for the for the time being, but will be also released very soon. And then it's just, like you said, basically building up on what you have learned in the past as an individual or organization.

Dominik Lambersy (TextCortex): 2:54

Again, because, if you think about the main disadvantage of many of these, many of these large language models, whether it be chat, gpt or any other AI tools, is that they are stuck in the past. They are mostly having information from 2021, from the European continent. Yeah, if you would ask for a famous soccer, famous, famous sports event, like the soccer World Cup here, who was the winner of the 2022 soccer World Cup. Most AI tools cannot answer it, so what we have done with Zeno is basically integrating a lot of different knowledge fields, also including search, including, in the future, own personalized files, whatever you want to share, certainly, we try our best to make it as secure as possible as well.

Lance Hood (FranPro): 3:42

And so, as we go through the functionality, we've gone through the personal AI assistant that does writing. We've talked about how Zeno chat I mean there is access to chat GPT, but we have the Zeno chat, which is its own model and then what are the other functionalities that people should be aware of?

Dominik Lambersy (TextCortex): 4:02

The other functionalities we have. We have over 200 use cases by now. We have plenty of different users from from plenty of different fields. Maybe let's roll up that question a little bit differently and talk about who are our top users. The top users are people from the creative space, oftentimes marketers or copywriters. That's by far the biggest group. Then we have yeah, we call them corporate professions. Oftentimes those are sales functions, those are customer support functions, but also management functions, because a lot of people deal with communication and prove their communication of our tools. And the third one is SMEs, and that's a combination of what I've what I've previously said. Yeah, we help them with marketing, with sales, general communication, a lot. And then we also have a lot of students, which I don't believe is so important right now for our call here, but yeah, they are getting some help with their homework, more or less, so also improve their communication, their writing.

Lance Hood (FranPro): 5:04

Well, did you want to do a brief demo today, dominic, or?

Dominik Lambersy (TextCortex): 5:10

Oh, I mean absolutely. I can show people briefly around. Let me just quickly share my screen and find where I already I think it's this one. Let me check. Yeah, I think that's the right. Can you see my screen now?

Lance Hood (FranPro): 5:28

I can yeah.

Dominik Lambersy (TextCortex): 5:29

Beautiful. So first of all, yeah, what I will, what I will show you today, is the workings of the Chrome extension. I can see it here in the top right. The Chrome extension is active. You can change it. I mean, I haven't changed in English. You can change it in different languages. That's one of the major problems we had recently, because we have global impact on many different language speakers and they want to see it in German, spanish, french. But let's get down to the use cases here. For example this is a call summary when I talked with you, for example in the past, or with any type of potential customer, I always note down things in the most uncanny ways, with really weird abbreviations, for example, just like quickly shutting it down and trying to just retain knowledge. What I can do now sorry, that's now being German basically says press a shortcut for Zeno. Why is it German now Interesting.

Lance Hood (FranPro): 6:32

Yeah, I like it. I like it there, I've used it and what I like is, as long as you see that pink and blue circular icon there, you know that you can just click on that and access it right away.

Dominik Lambersy (TextCortex): 6:46

Yes, exactly, I want to show you now first the Zeno assist feature, for example, and what I can do now is I can say, hey, please summarize me the above. It works. It says the demo call was with Ben Tobito's restaurant chain, owner of TechSavvy. It makes the whole thing a little bit more understandable. This is one of the one things. The same thing you can do with our toolbar, for example. It's very easily happening just by highlighting anything and then clicking rewrite, expanding creative writing, email writing as well. So this toolbar is usually our most popular features fixed spelling and grammar completion, for example. I could also, if I now say grammar fix, it should fix that really weird. Yeah, look, with the code and my weird abbreviation here we could bring revenue potential 5X, but it didn't really summarize it. For summarization, we would click this year and we would arrive at a very similar example, like we had with Zeno assist here.

Dominik Lambersy (TextCortex): 7:54

What you mentioned with the little bubble, that's our access to wait. I need to move you a little bit to the over here. This is where our Xenoy chat comes into effect, yeah, where we can say, hey, write me the outline of blog post on increasing franchise opportunities via follow up emails. Let's see what it will write usually takes around 10 seconds up here In no time. We already have our outline. Then we can start as a human being. Then we can go back into the divide and conquer approach where you can now say, hey, let's expand on each chapter and build it step by, step by step.

Dominik Lambersy (TextCortex): 9:04

The whole thing works on yeah, I mentioned someone before 4,000 different platforms. We have here this content brief, which is part of one of our YouTube sessions, for example, as well, where you can hear now also say, hey, we have the local SEO topic here, please expand on that Can make it a little bit longer, takes a little while, and it also starts writing here. You see again, it started creating an outline, basically filling that with a little bit more of life. I click on the format thing is a little bit broken now and then you can already go step by step down the whole the whole road, also working on Gmail, for example. Here's again the bento Beatles example. In Gmail, I can just say, hey, I take these bullet points as I already have made up my thoughts. Just highlight it, press on the email button and it basically formulates out an email for you. Maybe we need to have it a little bit longer.

Dominik Lambersy (TextCortex): 10:12

That's also when I still do our customer support. A lot of times I just copy paste the original email from our customers into one of our templates, just drop it in here. I give some directions, as I had it here with the bento example, because you always have. If you read an email, you always have these three, four, five next steps you want to do up on top of your head. You can write them down here. Basically let the AI create. I won't create it now because I don't have an original email here, but then I already have my email formulated out. That comes at much higher response time, certainly, but also at less psychological burden. I mean, this is what usually customer support users use text cortex for exactly this view, and I know it also. Sometimes you have customers which are plainly not nice, which is a psychological strain for many users, customers as well. There's so much about the text cortex plug-in. I don't want to go deep, I just want to show it briefly. In the customization suite you need to go to our web app for that and then you have the Knowledge Connectors Customize your AI and this is basically where you can start Persona name, persona block background.

Dominik Lambersy (TextCortex): 11:37

I think we talked two or three times in here. We just type down here's the example from my co-founder, jehun some values, a description, and then you would enter different types of writing examples. I can show you with my little digital twin how I did it. This is then the result. After analysis, it tells me that apparently I'm a very enthusiastic, motivational, inspirational person. I think I should be, as a founder, that reading is. I really try to sound as easy as possible such that everybody can understand that sentence length, medium, active voice. You can see the background of myself. I hear values, I like to work after examples, and then you can basically use this Persona right within the note chat.

Lance Hood (FranPro): 12:29

So you've taken the time to fill out all that information and set it up, and now you're writing in the Persona of this AI Persona, which is look, that's my comment pitch Born and raised on German fun fair selling sausages and fries.

Dominik Lambersy (TextCortex): 12:57

Customer service. Yeah, that's my first pocket money in gaming in the early 2010s, before NFTs were a thing, and suddenly I have my virtual twin, who replies a lot like me and can give advice not fully like me because it doesn't have all the knowledge I have, but that will soon come here as well with our Knowledge Connectors where you can integrate all sorts of different things and, before overloading your viewers more, if somebody's interested, we have a lot of blog posts around how you can use all features videos around them as well to best educate you.

Lance Hood (FranPro): 13:41

Yeah. So I think that this custom AI is really a great way to get around the general generic responses people would get. But also, not only are they generic, but they're not going to really follow along with your core values or anything like that and your more humanistic personality driven writing styles. This is kind of the shortcut or hack, for that is to set up your persona. They would also let people know that the people who are writing stuff for the company, or if you're a marketer that's doing work for a company, you can upload stuff on that specific company in here and then, oh, today I'm writing for franchise A, so I use this persona to that. You know, now I'm writing for franchise B, I'll use this persona.

Dominik Lambersy (TextCortex): 14:27

Absolutely, absolutely.

Lance Hood (FranPro): 14:29

Yeah, so it helps you produce stuff much better. So Well, this is excellent. You know, one of the things that I like about the usability of this is that you have the browser extension, so wherever you're working, the XenoChat can start writing things for you. You know, it's very handy.

Dominik Lambersy (TextCortex): 14:50

Yeah, it's very handy for 100,000 of people who use it actively on 4,000 platforms now, and I can see our competitors and they can see how people use it in Google Docs. They use it on Outlook, gmail, even chat, gpt, for example. So when our belief and our vision was back in the days, nobody wants another web app to tap in between all the time. We just want to be next to our user, right where they need us.

Lance Hood (FranPro): 15:21

Right. Well, you know as I think about using and implementing this stuff, because I've always loved copywriting, done copywriting and this tool when I first found it was just absolutely amazing because it overcomes the whole. I don't know where to start. If you just give me a white sheet of paper and say write this, it's like there's too much creativity there. I don't know where to start without having you know some sort of preexisting tests or templates or baseline of some kind. I can improve very easily, but improving on nothing is hard. So this is a great way to get started, but you know to talk about how to talk to it and improve it. I think, first of all, it's good to understand what is AI, because I think people have some misconceptions or non-understandings on what it is, and you have to know what it is and how it works so that you can talk to it the best and get the best results. So what is AI? Is it this big computer system that's going to take over the world?

Dominik Lambersy (TextCortex): 16:21

It's a great question. I've also, last week, have been part of a finance summit as a keynote speaker for Generative AI and there was similar misconceptions. I mean, ai is nothing so new. Generative AI is now new. What is Generative AI basically doing? It tries to create something.

Dominik Lambersy (TextCortex): 16:40

I like to call it also creative AI because from what it has learned from all the tens of thousands of texts or, in terms of mid-journey tens of millions of pictures it has seen, it can draw and learn patterns which we usually combine with some sort of textual structure and can recreate on top of it. What happens under the hood is more or less an auto completion. So if you would ask an AI, hey, please write me the blog outline for a blog around the topic of how I can improve my marketing ops for my franchise. The AI basically takes this as input and improves. Or hello, Siri, I'm talking about AIs why? Why does it come up now? It tries to auto complete your prompt. That's why it's also so important that that's what I've seen with many users. One or two years ago from our product, they talked to Zeno, to text cortex, like it was a machine.

Dominik Lambersy (TextCortex): 17:44

But ultimately, what you need to really think about is how you communicate and I believe this whole thing, the soft skill of communication, will be much more important now in the upcoming future in the collaboration with AI systems.

Dominik Lambersy (TextCortex): 17:57

Because, in comparison to if we talk with our team, for example, and I tell one of my team members, hey, it would be great if I have a result to topic XYZ in one to two days, I get a response in one to two days with an AI, have instant feedback. So if I ask it to write an outline for a blog post, I will have a result within 10 seconds. If I don't like the output, maybe it was more or less about me, because write a blog outline for a topic X is not very defined. So, for example, expand on the prompt. Hey, the topic is generative AI in the franchise ecosystem. I want to talk about the marketing operations and how to decrease costs, for example, or how can I scale up for more opportunities if I add some sources, some real time data, that really helps the AI to understand where you want to arrive at. And these basic instructions are incredibly important and that's why I say communication as a soft skill will be much more important in our collaborative ways around AI in the future.

Lance Hood (FranPro): 19:10

So you need to talk to it like you talk to people and just like you're having a conversation with another person. That's how you talk to AI. But also one thing I've learned from talking with you in the past is that AI is creative. It's made to be creative and so it can go off all over the place because it's just designed to be creative. So the more you give it more information and you type in more stuff or to give it direction, it's going to be more of what you want. So if you just say, write this and you get a general response, that's because what you're saying is too general and so it's just going okay and it answers it. But if the more precise you get, you'll get it. And that's why you also said that if AI is doing, if you were using AI to do some sort of research, you'd want to just double check it, because it's very creative and it can try to autocomplete and not necessarily have autocomplete. Be 100% accurate with facts.

Dominik Lambersy (TextCortex): 20:12

Correct. Yeah, exactly, that's a really good point from our former conversations Always validate what the AI is creating for you. I mean, six months ago, everybody believed what AI has written, which is extremely dangerous. It's just like how you interact with other human beings. Take everything with a grain of salt and do your own critical thinking around it. There are plenty of people who try to sell you something and lie to you. Similar things can also happen with any type of AI generation. So always double check facts. There was another point which I wanted to add to that, but sincerely it flew out of my mind now. Maybe it comes in a little bit later down the road, but validation of information is extremely important by an AI model and it's kind of the reason why AI's generally have a limited output, because you'll, you'll, uh, you can.

Lance Hood (FranPro): 21:08

it can go out too far off in the wrong direction if you don't Oversee it, and I've always kind of looked at. After I started using it, I Started looking at AI as more of like a race car, but it needs a really good human driver, you know like it's a little course. What's that?

Dominik Lambersy (TextCortex): 21:26

a really good pilot to it, huh.

Lance Hood (FranPro): 21:28

Yeah, yeah, exactly. Somebody's got to be in control of it, Otherwise it's not gonna have as much value. So if you're not getting the value out of your AI and it's not producing what you want, you just have to learn how to talk to it and you have to learn how to drive it and direct it, and then you have to oversee the output. So it's not necessarily Eliminating a lot of humans. What it's doing is, is it just it produces way more, so you can get more, way more output per person.

Dominik Lambersy (TextCortex): 21:55

Yeah, that's what I also said in that in that speech recently last week. We basically go now from an age from Unlimited access to information to an unlimited, to the age of unlimited, unlimited creation. Basically, what happens is that we do not need to think about all these information which comes to us at the moment and then need to produce something. The production is already Happening, also on the AI level, but still it's our job to validate whether it's right and proper, fitting Our use case and generally true, and I also just got my point break which I just lost a minute ago.

Dominik Lambersy (TextCortex): 22:31

One concept which we're also praising to our users is called divide and conquer. It's nothing new. Yeah, with many big problems you have in life, you should divide and conquer them into smaller ones, and we have this beautiful YouTube video as well when we basically show people through how they can collaborate with AI to create blog posts. Now, if your goal is a 2000 word blog post, your expectations shouldn't be that the AI is Just snapping the finger and you have a 2000 word blog post in front of you, which is perfectly fitting your case. That's the.

Dominik Lambersy (TextCortex): 23:00

The short-term memory of an AI is not enough to keep that concise and to keep, keep and keep the truthfulness behind it. So what you do? You divide and conquer the problem. For example, instead of 2000 words, I say, okay, let me first write the outline of, let me first write the outline with Zino chat about the blog post. And then for each of the chapters, yeah, if we divide the problem into 10 chapters, we suddenly have 200 words per chapter and we have arrived at our 2000 word blog post.

Dominik Lambersy (TextCortex): 23:34

And that's how you should approach it. And this also gives a much more time for you to personalize everything, to validate whether the facts are right and also to put in your own research. Still, because ultimately, these, these contents, needs to be, needs to have some, some form of originality, and we also, with, with that age of unlimited creation, we've been already living in in the flood of information before. It will be even more information now and a lot of more Generic information, so it will be even more important to find these few little pieces which Still touch a human's heart more than you do that by proper research, by creating proper value for somebody with. Yeah, beyond that, beyond the play, thinking, more or less, we would say Right.

Lance Hood (FranPro): 24:24

And so if you're gonna do something more complex, let's just say you're writing in a follow-up sequence for your email autoresponder of following up with customers, and you're you're trying to generate Like a, you know, like a one month or a one year sequence or whatever.

Lance Hood (FranPro): 24:40

You're gonna, instead of just telling it to create that, because you know who knows what would happen by the end. You're gonna start with write the framework, write the outline, and then, within each Component, you're gonna look at what needs to happen in that specific unit. So if it's a book, you'd you'd write the, the premise and everything else, and then you'd maybe write the chap, you'd list out the chapters and then you start writing the chapters. But if you're doing a follow-up sequence, you might say what's you know how many days is is ideal, how many Emails is ideal for this amount of time for a follow-up, what are the things that we should discuss? And then you pick each one of those and start writing each one of those, and so you're producing it Kind of in that organized way, but not all at once, so it can do a good job.

Dominik Lambersy (TextCortex): 25:31

Yeah, exactly, there's a great customer case study as well. We have on the web page from faith. She herself has dyslexia and she was struggling with writing such a. You know, I think it was a three month long follow-up sequence for anybody who Subscribed for a newsletter. As she was struggling with that for seven months, she found our extension, started working around it exactly how you described it and within two hours she had nine emails over three months. The problem was gone Now. But this divide and conquer approach is so important and that's why you still always will need a human. No, because for this original thought or for the basic validation, you still need some human creativity, while you know everything else building the narrative out of your strategy can be done with an AI, for example, and filling, filling, filling, filling a chapter with more meaning for, for example, can be done by an AI.

Lance Hood (FranPro): 26:26

Right, because if you just do it it's just gonna fill it up. It'll be more general and that's why I love the things about you know, having having the AI assistant that has a baseline of information to keep it, you know, in line so that it writes like you or writes more like a human, because you do get that general Kind of emotionalist writing. So can you talk about how to, maybe how people can tweak their writing to make it write more like an individual, make it like write more like? Some of the things that I have tested is you know and write this like a copywriter with ten years experience and blah, blah, blah blah. Can you give us an idea on how prompts work and how to make them better?

Dominik Lambersy (TextCortex): 27:11

I mean, we take quite a quite a bit away from it with our customers, where I feature already More. You basically define once the background, the values, for example, and some writing style Examples where the algorithm then can build up upon it such that you know whatever Later collaboration you have. You basically chat with your virtual twin there. But what does it mean? I oftentimes take an example from how organizations put brand scripts. Yeah, you have the background of the company, you define which type of writing style. You want to have a text context.

Dominik Lambersy (TextCortex): 27:46

We clearly say we are an informed, more informal company. Yeah, we are not a formal cooperation where everybody needs to speak very professionally. No, we are informal, we want to be educated and we simply want to create value without having any expectations from whoever consumes our content. And Basically, what you try to do is building those prompts step by step by step, adding that information to the model or into our customized very I feature ultimately and Then work around that and this will always think about it. It is sort to say the short-term memory of the AI. By giving that into the short-term memory you can deal with a lot of the limitations, large language models or, sort to say, the crystalline knowledge base that has, which is from 2021, more or less, or depending on the models. Yet it takes quite a while to retrain, retrain those models, but to keep them in line, you use the prompt, the short-term memory, to insert more information.

Lance Hood (FranPro): 28:45

And and about how far? Because if you're talking with the chat, right it? It looks at the previous chat and applies it to what you're doing too. So how many characters back does it typically go?

Dominik Lambersy (TextCortex): 29:00

And it really depends on the models. The issue is now there's there's now there's a new model around which says we have a hundred thousand, a hundred thousand tokens of Window, of short-term memory window. I'm not quite sure. I haven't tested it out that fully, because a hundred thousand tokens are seventy five thousand words, which is quite a long text, and to fully validate whether the AI has not hallucinated anywhere within so much information Is is a longer task. No, I think there's a lot of research happening around that model. Now I wouldn't trust it at the moment.

Dominik Lambersy (TextCortex): 29:37

I know what works rather well is if you have somewhere between Two, three thousand words. Yeah, that's where I know that also our users are very happy. I tested it out myself as well. There's research which which can basically say, hey, yeah, it keeps information. Well, you can see with models like GPT for the biggest one is what thirty, two thousand tokens, I believe, and that's around what?

Dominik Lambersy (TextCortex): 29:59

Twenty six to twenty eight thousand words, maybe what twenty five thousand words, and not quite sure about the exact math now takes a, takes a lot more time, certainly to compute as well, but also currently I'm not quite sure how, how much information is still retained in the short-term memory. But yet again, I would keep it concise. Yeah, ultimately, it's just like if you overload a human with information, they get confused. Now I'm getting confused if you ask me too many questions. If you ask me more than 10 questions, I'm just like hey, wait, before we go deeper down the rabbit hole of questions, let's first answer the first five questions and then we can move on, because otherwise the quality of communication will suffer. It's same. It's the same thing with a ice mm-hmm.

Lance Hood (FranPro): 30:51

And what do you? I Know that you guys have all the Templates where if whatever you're trying to do, you just click on it and it's already pre kind of designed for you and ready to go, making it easy. This is really kind of a great way for people to just free up their day and start using these tasks to just get things going. I like how we discuss that. You have to keep an eye on it. I think people didn't maybe realize that there's a reason that you do Words at a certain length because you know you work at a certain length because otherwise it's unlimited.

Lance Hood (FranPro): 31:27

Creativity can take it down a rabbit hole versus focus on what you want, and then we have to be more specific when we use it. What is the? I was just gonna say what sort of market research can we do that would be effective? You know, asking about, you know competitor analysis or To help develop a? You know an avatar, a customer avatar or anything like that Is there? How reliable would it be to ask it to do some stuff like that to give us a baseline to start from?

Dominik Lambersy (TextCortex): 32:03

I Mean from our last conversation. We actually made great progress on our knowledge connectors. So one of our engineers he's originally from Turkey, he's immigrating to Germany now and as a special project and beta Piloting project, he put in the whole German law into Guess what's their knowledge base, uploaded via via PDF, and now he uses text, cortex and Zeno basically as a Communication layer to talk to that knowledge. This is a feature which will be rolled out in the next month and I'm very excited to see what happens there, because basically, what we have developed there is Sort of a knowledge search through a lot, and I'm talking about German law. Well, german laws, one of the most complex law systems on this planet. Yeah, that's also why we know for an exporter of bureaucracy and regulation was more or less. But yeah, he asked questions like hey, how long do I have to be in Germany before I can apply for working permit, how long for residency, and it basically took the legal information and made it human understandable. Yeah, not German legal speak, which is a nightmare I mean, english legal speak is also a nightmare but makes it much more understanding for for the common, for the common person, these type of new developments. I mean, we are also not the only one who work on on that.

Dominik Lambersy (TextCortex): 33:32

To be fully transparent, this could make a very, very great research Retainer tool as well. So, basically, what you put together is maybe one word. It could be a word document, it could be a notion page, it could be just a PDF document which you upload to text cortex and then Our system is searching through your knowledge, integrating this into your generation. That's still heavily better. Yeah, I hope that this Comes out to the point how we envision it now, and it certainly will be in one year from now. Currently, what your best, best with us do your research on a separate paper you would need to do it anyways and then you start dividing, conquering a big problem and basically writing down whatever you want to achieve if it's a blog post around how to Improve profitability in your marketing operations for franchise, and you have three key facts you want to talk about.

Lance Hood (FranPro): 34:27

At those three key facts, to your prompt you talked about Five reoccurring problems around marketing, sales and communications that most people are using this for, and I just wanted Check with you what. What are those five things that are really being used the most?

Dominik Lambersy (TextCortex): 34:44

Hmm, yeah, first pillar text modification. Yeah, rewrite text. I think you you know what. You start writing an email, you start writing a blog post you already mentioned and you don't Fully feel fulfilled with what you've written. Yeah, you can use our rewrite function to rewrite it. You can use the tone changer to make it sound informal, formal, more enthusiastic that's one of my favorite features because, as a German, I'm not usually the most enthusiastic writer, so that can help me to make it a little bit more friendly. But also summarization, for example, boiling down heavy corpus of texts where we already have this, this. That's where the whole knowledge connector Feature has started, with us summarizing a lot of information down such that you know it's truthful and you can work with it.

Dominik Lambersy (TextCortex): 35:34

That's the second point. Front point improving your productivity with an AI agent. We talked a lot about it today. Yeah, you can use it for For improving your communication in emails. We can see how people love to use it in the Communication with colleagues on slack, on discord, even. You can use it to align, for example, to different writing styles as well. If you know that your customer is more of an analytical communicator, you can basically also work together with Zino and saying hey, please. My receiver of that message is a very analytical person. How can I improve my writing of my email now such that it fully resonates with that person impersonates somebody else?

Dominik Lambersy (TextCortex): 36:21

Translation is also a huge issue. I mean, we are a German company or European company, the continent of any type of language. It's very difficult. You just go around 100 to 100 kilometers. You're in a completely different country speaking a completely different language. I know from my visits to the US you don't have that problem. Everybody speaks English, maybe a different accent, but somehow it's somewhere similar. But that translation is definitely something where we're helping a lot the dyslexia and help for neurodiversity. I told you I'm very proud of the problem we are solving there. A lot of people use the text-to-speech feature there. There will be sooner voice command features where you can basically just talk out your prompt and whatever you want to do. You don't need to write it down. That comes from your voice. What else am I very proud of in terms of the features we are offering?

Dominik Lambersy (TextCortex): 37:16

Yeah, also the templates. Currently we offer, I believe, around 80 default templates. We're currently in the making of increasing that to over 1,000 templates. It takes a little bit more time, also for the user. There will be a full editor where you can save whatever template you constantly work around, because it gets very tedious at one point. If you always ask a chat, gpt or a ZenoChat, hey, please take the following, rewrite it in a more academic way and then you copy-paste everything in there. If you do that five times, always using the same prompt, you want to have a template for it.

Dominik Lambersy (TextCortex): 37:53

Similar things also around the customization. I have my virtual twin called Dominik Lamperse on text-to-speech. I feed it with my background born and raised on German funfairs, venture capital, always tech businesses, the eight values I'm following after my writing style. Then I also use that persona to basically answer customer support emails, also sales emails, ultimately write some content for us around the company, around our narrative or whatever type of value I want to provide, or LinkedIn posts, for example. That's also a thing, right. The last point I want to finish on is to make a customizable experience out of the very generic AI world you currently have.

Lance Hood (FranPro): 38:44

Are there any last insights that you want to share with everyone today about AI or using ZenoChat?

Dominik Lambersy (TextCortex): 38:53

What I can see in a lot of people currently is a lot of doubt, a lot of conspiracy as well. Ultimately, I had a beautiful slide, said that I don't have the slide that can now prepare somewhere around, but we kept on talking that machines can only be as smart and as useful as the human who use it. That's pretty much also the case. Even with as creative systems we are getting now, they're only as good as the user who's behind it, who thinks about what they want to create. I really hope that also our educational system is picking up and educating the new generation how to work with it. You can see already now younger generations who work with Zeri to solve their math issues. In the next five years, we will all need to adapt to AI collaborators, like we did adopt to the personal computer, for example, to all the information we have of our smartphones. This will be common now, and the earlier we adopt to it, the more we can flourish. I think that's a good word to end.

Lance Hood (FranPro): 40:02

Instead of just searching with AI, we can now use it to create. We have unlimited creativity, so now it's going to be it's also going to have to help us sift through all this new creativity that's being thrown out into the world to find what we're looking for.

Dominik Lambersy (TextCortex): 40:16

Absolutely.

Lance Hood (FranPro): 40:18

Well, I just tell everybody that right here next to the video, is a link to Text Cortex. I think that if you apply what you've learned here today, you use those personas, set those up and use those and then go in and you'll have that browser extension. You can start using this information to chunk it. Make sure that you're clear in your writing style and take advantage of all the training, the blog posts and the knowledge bases here, because if you just pause for a second and go through the training and understand it, you'll get an even better result. I mean, I've found that results are great from the beginning, but if I keep tweaking with how I talk to it, I actually get what I really want, and then once I know that I can use it forever, so I would take advantage of it. Thank you, Dominik, I really appreciate it. Thanks, lance, talk to you soon. https://Franpro. vip/GoTextCortex.

Dominik Lambersy (TextCortex): 41:11

It was a pleasure.