What is Quin?

[00:00:16.17] - Speaker 1
Right. So first, welcome everyone and thank you for being here today. We have a lot of people, so I'm really happy that you guys are spending an hour or an hour and a half with us. I'm really excited about what we're going to be sharing with you today because we are launching something that we've been really been working on for a very, very long time. And I think what you're going to see today is going to fundamentally change how you approach your trading research, whether you're trading stocks, future options, crypto and so on.

[00:00:48.14] - Speaker 1
So today we are introducing Queen 2.0, which is Mentor Queue, new AI quant engine. And I want to be clear from the start, this is not another chatbot. Queen is a research system that is built specifically for traders and that combines everything that we've been doing for the past 20 years with live market data and real quant models and workflow. So by the end of today, you're going to see exactly what I mean and why we believe that this is really going to change the industry. And this is really going to be amazing for you guys, for you guys.

[00:01:22.29] - Speaker 1
And at the end of the day, at the end of the presentation, we're also going to have some really nice intro offer for you guys if you want to join, if you want to upgrade. So stay tuned and don't miss those. We're going to talk about that at the end.

[00:01:36.17] - Speaker 1
So here is really the uncomfortable truth for everyone, right? So retail traders have always been fighting with one hand tied behind the back. Not because you're not smart, not because you don't work hard, you don't study, but because the tools, the data and the frameworks that institutions are using are never or were never being accessible by, by traders. Right? About the Bloomberg terminal, how much it costs, retail traders cannot really afford that kind of setup.

[00:02:06.00] - Speaker 1
So think about your current research process. You probably have multiple tabs open, maybe multiple trading platforms. You have a chart here, news over there, maybe a screener somewhere else. So you're trying to really piece everything together from five different sources or more, none of which talk to each other. And you're trying to really get a picture of the market and define what to trade and why.

[00:02:32.00] - Speaker 1
So this is what is called fragmented research, right? That's data without the context, and that doesn't bring an institutional hedge because you are basically looking at all different places and all different tools might give you different answers, right? So all of this like, you know, think about what has changed in the future trading space, in the option space, large Option flow analysis, gamma positioning, quant screening, historically has been locked into platform like Bloomberg or software that really cost a six figure amount, right? So this 90% unfortunately is really the truth. It means that you're, you're not underperforming because you are not working hard, but it's really because you don't, you didn't have access to the tool set that institution have, right?

[00:03:23.26] - Speaker 1
But with AI and what we see in the past two years, everything changed. Retail traders finally have a chance to compete with large institutions. They can finally create a framework that can lead to a better consistency and a real edge. For example, like you know, we, we work with many traders and what we know about traders that consistently win is that they are not the ones consuming the most content, they're not the ones with the most indicator on their charts. And you know, Patrick is a clear example.

[00:03:54.24] - Speaker 1
They are the ones who have a clear process and they execute that process repeatedly. So every winning trade follows four steps, right? Whether you know it or not, whenever you trade you're following really four steps. The first is really the framework. So you need to understand what you're trading, you need to learn about the asset that you're trading, whether you're trading futures of option, you need to have at least a knowledge of what you're doing.

[00:04:22.11] - Speaker 1
The second is really understand the market condition. So in this environment today, is it good to go long future or is it better to maybe do some edging or, or trade options or trade, you know, spread all of this stuff, right? So understand in which market you're on and then basically define the condition. The, the third step is really screen the market, right? There's so much data out there.

[00:04:48.14] - Speaker 1
How can you effectively screen and find opportunities that can help you be successful? And the last step is really then once you find those opportunities, how can I make the trade, how can I manage my, my take profit, my, my risk and my stop losses and all of that, right. So those are kind of like the four steps that basically any trader would follow to be successful. The problem has always been that this four step always live in different places, right. And require different tools, take hours to complete.

[00:05:24.02] - Speaker 1
Until now AI obviously changed the equation and for this first time you can have all those four steps. So learn, read, screen and act in one integrated quant engine. So this is not really a small improvement. This is a massive improvement structural shift. And we are very, very excited to bring you Queen 2.0 today.

[00:05:49.25] - Speaker 1
So let's go over of what Queen 2.0 is right at its core is the combination of three things that have never existed together in one place. For retail traders. The first one is knowledge and we're going to go into details in a second. So not generic knowledge of course you can access generic knowledge in all the traditional AI tools. But what about mentor queue?

[00:06:11.26] - Speaker 1
Proprietary knowled. So our team is formed by traders, ex market makers. We've been in the market for over 20 years and we've developed a set of documentation articles, everything that you can find in our blogs, thousands of hours of video lessons in our academy. But we also have internal papers, research books that we've read, all of our notes from our previous experience. So I worked at Bloomberg for about 11 years, my partner has worked for various market makers.

[00:06:42.28] - Speaker 1
So we have a lot of information that we've consumed over the past 20 years and most importantly we have live trading journals and strategies. So all of this has been ingested, organized and accessed by Queen.

[00:07:07.14] - Speaker 1
The second is really data. So let's go in the second step. In order for an AI tool to be successful it needs to have access to data, right? So whether it's traditional market maker market data. But let's talk about why you're here today.

[00:07:25.08] - Speaker 1
You're here today because of course you find the mentor key data valuable. You find out what we do valuable for your trading. Queen has access to our indicators, our option chain data, our pricing data, open interest, gamma exposure, our Q score. We have access to real time news feed. Everything is connected in one place.

[00:07:46.11] - Speaker 1
And the third step is then once you have data and once you have knowledge, how can we then build intelligence? So the third step is really our intelligence layer with our quantitative models like our gamma exposure, our volatility models, our Q score, the actual really quantum infrastructure that we've been building for the past 20 years. So combine all those three together and you get Queen. You know, Queen is one AI that can research, screen, validate and help you decide all in one place. No dashboard, no manual workflow, no disconnected tools.

[00:08:27.02] - Speaker 1
So let's go over the first pillar which I think is a very, very important one, which is knowledge. So again as I said, Our team has 20 plus years of institutional experience. We've obviously built. If you guys have gone through our academy, our financial wiki page, we have a lot of documentation, right? A lot of documentation that we put together, we've selected it with hand picked that documentation and we created a really amazing knowledge base.

[00:08:59.26] - Speaker 1
So we are talking about all the documentation that we have in the guides, all the academy, but we also have internal documentation that we, you know, we've brought together over the past 20 years that is also being ingested by Queen. And on top of that, of course, our live trading accounts for the past two decades, where we took real decision, real market condition, everything is documented there. So our AI has really been trained on, on what we've done for the past 20 years, essentially. So what does this mean in practice to you? Right, so when you ask Quinn to explain a concept, you get an explanation grounded in our framework, not a generic textbook answer.

[00:09:41.11] - Speaker 1
Right, so you'll get the perspective coming from the Mentor queue framework about your question. So you can ask things like explain gamma levels, like, I'm a newbie, give me a roadmap for spx, how does your Q score work? Or show me the gamma exposure. But these are really simple questions. When we go into the demo, you're going to see the complexity and what are the things that you're going to be able to do with Quinn next is data.

[00:10:08.23] - Speaker 1
So the second pillar is really market intelligence. And this is where Queen goes beyond just knowing to understanding to what's happening right now. So Queen has access to the full suite of mentor queue data, and I mean the full suite, including Gamma delta positioning, volume open interest, our gamma levels, our blind spots, our swing model, our sku, our volatility models, our vrp. We also have access to news intraday data, sector positioning, and the data is just going to keep growing. So over the next few months, we're going to release our earnings models, our live data.

[00:10:45.28] - Speaker 1
So again, this is just going to be, this is just the beginning. So now the key difference is that most AI tools, even the most sophisticated ones, can talk about this data. In theory, they can explain what Gamma is, but they cannot tell you where Gamma is concentrated in spy today because they don't have access to the data. So you, yes, you can feed the data to these AI tools and they can do a great job, but they do not, they do not have access to the data Queen does. And most importantly, it can help you basically define and we have really a big intelligence layer that can help you understand the data.

[00:11:27.10] - Speaker 1
So instead of staring at a dashboard, looking at the net gamma exposure chart, trying to figure out what it means, you can just ask Queen questions like, what is the Gamma exposure profile for QQQ and how it has changed over the past week and how can you interpret that? So you can really have really intelligent conversation with Quinn to talk about data. But the third step is actually the most important one, which is research automation. And this is really the power move that we did. And I think this can be really game changing.

[00:11:59.14] - Speaker 1
This is really what separates Queen from every AI tool in the market. So first we have our intelligence screener. So instead of manually filtering through hundreds of ticker across multiple platform, you can describe what you're looking for in plain English and Queen finds it. You can screen for stocks, for example near the core resistance with an IQ score, you can filter by IV percentile, gamma positioning, momentum. And we have about 97 plus quant parameters that you can use in a single natural language query.

[00:12:34.11] - Speaker 1
Second is side by side comparison. So you can compare any tickers across the mentor universe and metrics. You can look at historical data, you can look at current positioning, you can look at volatility behavior all in one single query and response. This is the kind of analysis that would take hours or days, that can now take seconds. And third really is the complex multi factor queries.

[00:13:02.29] - Speaker 1
Right, so this is where it gets really interesting. You can run the kind of research that really only professionals and quant team are doing right now with massive python codes and data structure databases and so on. You don't need a spreadsheet, you can simply ask Quinn and we're gonna, and we're gonna show you, show you that in a second. So you can filter, you can rank, you can, you can surface across different stocks. You can for example screen around the universe.

[00:13:35.04] - Speaker 1
Like in this example, you know, find me all the stocks in the UI in the S P500 with the low IV rank and a Q score greater than 3. Right. So these are simple, but we're going to get into more complex queries once we go into the platform.

[00:13:53.16] - Speaker 1
So now let's have really an honest conversation about AI because I think there is a lot of hype. Of course everybody's talking about AI, but I really wanted to give you a grand perspective on where AI is really great and where it fundamentally breaks down. And then once we go into the demo, we can show you an example. So AI is really great at handling unstructured text. So summarizing documents, answering questions about the report, explaining concept, generating educational content.

[00:14:26.22] - Speaker 1
If the information exists in a written form, the modern AI can really work with it brilliantly. That's the left side of the slide. But here is where it breaks down. The moment you need to handle structured numerical quantitative data, the kind of data that you need for your trading decision, that's when generic AI starts to fail. For example, if you are looking at option chains, jax table tick data screeners, you know, AI frequently miscalculates it hallucinates number, it presents a confident sounding output, but the data is completely wrong.

[00:15:03.28] - Speaker 1
So if you are making a trading decision and you're trading with the wrong data, then of course you, you, you're basically risking of losing your capital. So and, and the fundamental problem really is that if you're here today, you believe that we're doing something great. ChatGPT Copilot or all the other general, General AI, they have zero access to our data, zero access to our model, zero access to our trading intelligence. So, so you can ask ChatGPT where Gamma is concentrated in Spy right now. It doesn't, it wouldn't reply to you with the right data because it doesn't know they don't have access to the data.

[00:15:43.04] - Speaker 1
So unless you build a data structure and feed the data to the AI, AI will not understand and will not be able to answer. Most likely it's going to make it up and you're going to trade with the wrong data. So this is really not a criticism of this tool. They're actually extraordinary for what they're designed to do. But for quantitative trading research they're currently brilliant at the wrong things unless you can feed them with a data structure and with the data.

[00:16:16.26] - Speaker 1
So what we've done, we've solved the structured data problem, right? So obviously this is a very bold statement, but I will show you what we've done once we go into, into the demo. So Queen is not just a chat wrapper on top of an LLM. Let me say this again because it really matters. Queen is not chatgpt with a trading skin on top.

[00:16:39.08] - Speaker 1
It's a purpose built quant engine. So here is really a simple example on how the architecture works and we are, we've built and we operate through three interconnected layer. The first one is the data layer, right? This is really the quant engine. This is specifically engineered to handle large volumes of structure financial data with quantitative precision.

[00:17:05.29] - Speaker 1
So anything from option chain, open interest, gamma exposure, Q score levels, a lot of tickets, we cover thousands of assets. So everything is, has been engineered for precision, not for guessing. So that's the most important, the first step, the second step is really the unstructured knowledge layer, which is our knowledge engine. So we've already talked about this, but obviously we've trained our AI with our proprietary knowledge, with our guides, with our video lessons, our research paper, our training journals. So here is where the AI gets the knowledge from.

[00:17:50.05] - Speaker 1
This is very important step and in selecting knowledge is knowledge that we've been building for the past 20 years. The third step is really the where it gets interesting which is the intelligence layer. So this is really what makes Queen unique. It cross references the structured data with the unstructured knowledge and produces grounded explainable outputs. This is not gasses like most of AI might do when they hallucinate.

[00:18:15.24] - Speaker 1
This is not hallucinating numbers. This is actual reasoning that you can follow and verify through the platform. So the results is really a low hallucination by design because the way we built the framework, so really this is really the key difference here is really why Queen can win. This is really a comparison to generic AI other fintech AI tool. So the really the first differentiation here and the first things that we want to see is really the hallucination, right?

[00:18:52.26] - Speaker 1
So we want to stress that basically the way we build the tool is law by design. So we're trying to give you access to accurate data. So we built it in a way where AI is not going to be able to guess or give you the wrong data. The second is really our proprietary knowledge. So our proprietary engine and data.

[00:19:14.25] - Speaker 1
None of these tools have access to our data. So Queen has full access to our models. Right. And then of course our experience, our 20 plus years in the market experience that has been used to train our AI. Right.

[00:19:29.02] - Speaker 1
So those are some of the of the things and this slide really can help you understand why Queen can be your go to tool using AI for training.

[00:19:46.11] - Speaker 1
All right, so now let's, let's go over something really how can you guys start using and how can you get actionable with Queen as soon as you get access to. So we're going to show you some example in a second. But let's go over some really three simple use case. The first is really learn, right? Let's say that you come across a concept like Gamma squeeze or Gamma exposure.

[00:20:13.25] - Speaker 1
Maybe you're new to Jax, you don't know what Gamma is. You can simply, you can simply ask Quinn what is Gamma or show me the mentor key models that can help you understand Gamma exposure. And Quinn can give you really an answer very, very fast. You can also build a learning path. So you can actually start Lear directly through our academy, through our, through our data.

[00:20:38.23] - Speaker 1
The second use case is screen, right? Find opportunities, right? So how can I, how can I find stocks that are matching certain criteria? How can I find ETFs or indices or how can I see things that match my criteria? So no more guessing.

[00:20:59.29] - Speaker 1
Now you can use Queen to build the process and then the, the third step is really validate and decide. So before you enter a trade you can actually talk to Queen and understand what the data is telling you. So you can do a really deep down analysis on a ticker. So let's say that you find a stock that you're interested in. Let's go over and see what the data is telling me.

[00:21:22.25] - Speaker 1
And maybe if your setup is actually matching what market is telling us on that specific ticker. Right. So very, very simple.