70 | Data Scraping to Solid Decisions: Mastering AI for Unmatched Market Insight with Dennis Tröger

Whether you're a business leader, entrepreneur, or marketer, discover how to harness AI to scrape, review, analyze sentiment, extract key topics/themes, and identify potential product improvements from your data.

Join us with Dennis Tröger, an expert in the AI space and founder of an AI automation agency. Dennis brings a wealth of experience in applying AI to solve business challenges, offering a wealth of insights and proven strategies. With Dennis's expertise, you'll learn how to navigate the AI landscape to implement solutions that not only save time but also significantly enhance your business operations.

This webinar is more than just a presentation; it's an interactive experience. You'll have the opportunity to engage directly with Dennis and other participants, ask questions, and discuss your own business scenarios. It's a perfect blend of theory and practice, tailored to provide you with the knowledge and tools you need to succeed.

Learn the ins and outs of AI-driven data analysis through a detailed, step-by-step process that demystifies complex concepts into manageable actions.

Our focus will be on practical, real-world applications that directly impact your bottom line, from extracting meaningful insights from customer feedback to enhancing your product based on qualitative data.

Check the App Script 

About Leveraging AI

• The Ultimate AI Course for Business People: https://multiplai.ai/ai-course/
• YouTube Full Episodes: https://www.youtube.com/@Multiplai_AI/
• Connect with Isar Meitis: https://www.linkedin.com/in/isarmeitis/
• Free AI Consultation: https://multiplai.ai/book-a-call/

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

Transcript

Isar Meitis: 0:00

Welcome to a live episode of Leveraging AI, the podcast that shares practical, ethical ways to leverage AI to improve your efficiency, grow your business, and advance your career. This is Isar Meitis, your host, and I've got a really amazing show for you today. If you've been following me, this show, or even my previous podcast for a while, I am a huge believer in making data driven business decisions. Now, this is awesome, but there's three big problems with making data driven business decisions at scale. Problem number one is you need the data. You somehow need to find a way to collect relevant data that will allow you to make these decisions. That's problem number one problem. Now, by the way, that's why most of the companies who do this at scale are easily large companies who have a data team, or they hire a consultant to help them get the data for a one time thing. But it's very hard to do ongoing. Problem number two is okay. Let's say assume you have the data and you found a way to collect it. How do you analyze it? And analyzing quantitative data is relatively easy. there's multiple pieces of software from spreadsheets to More or less any platform you have that will allow you to build dashboards and seek quantitative data. But qualitative data is very hard to analyze because you have to either read or listen or whatever to a lot of information and then categorize it and then analyze the stuff based on its categorization and it's a lot of work. And so that's problem number two, problem number three is, let's say you've done all of that. Now you need to get to a point where you can actually create actionable insights that people in your business can actually take, because otherwise there's no point in doing this. So these are inherent problems to large scale, continuous data driven decision making. The good news is that AI can help us address all these problems with very little investment. And do this for any single company. So any company today has no excuse why not to do that unless you don't know how to do this. And that's why I'm really excited about today's show, because this is exactly what we're going to learn how to do. So our guest today, Dennis Troger. He's an AI automation expert, and his specialty is how to go and collect data through data scraping processes from relevant sources, how to put the data in a way that you can analyze it, and then how to analyze the data to make actual business decisions that can change the trajectory of your business. So this is obviously extremely valuable to any business out there. And hence, I'm really excited to welcome Dennis to the show. Dennis, welcome to Leveraging AI.

Dennis Trogger: 3:25

Perfect. Cool.

Isar Meitis: 3:27

Awesome. quick note before we get started. Today's episode is brought to you by the AI business transformation course. It's a course we have been teaching, since April of last year. A lot of people have been through that course. It's mainly for business leaders, but anybody in business can benefit from it. It's a really transformational course. It's four sessions of two hours each. So four weeks and every person that has taken it has completely changed their business around using different AI tools. And the course is available through our website. So if you're interested to know more about that course, you can find it over there. The course was completely sold out between January and. End of March, but we're opening another cohort in the beginning of April and there's still seats on that one. So anybody who wants to really learn how to use AI in the business, please. Check the details. Obviously, you don't have to sign up if you're not interested. But now, let's dive into how to make data driven decisions with AI. Dennis, what's the first step? Like, how do we actually get started?

Dennis Trogger: 4:24

Perfect question, Isa. first of all, I'm going to share my screen. And, since not everybody's going to watch it, I try to explain everything, what I'm saying, as good as I can. So you can even follow through if you're not seeing my screen at this moment. Perfect. You should see right now, a Miro board from my side, and I started to call it how to scrape and analyze data from Amazon. so the first question we have to answer is the data we want to get. easy to get? Can we, are we allowed to use it? This is a question we should ask in the beginning. If it's our own data, this question doesn't arise because we are harvesting it from our customers and so on. But if we get the data from somewhere else, we always have to ask, are we allowed to get this data? this is why for this particular example, I've taken Amazon reviews. As an example for this today's webinar, because, this data is publicly available without logging in to Amazon and that this makes it, this allows me to use it without being scared that something's going to happen. So the first step we have to see is, or ask the question, what do we want to do with the data in the end? And, first of all, what I'm going to show today is we will start with a simple. Scraping of Amazon reviews. So we will have a look on one Amazon product out there and we are going to scrape the reviews from it and then try to make business decisions on what we learn from this. Product and the reviews we get, because this is what you already said and mentioned. If we make data driven decisions, it's much better. And this is the first time that we can do sentiment analysis and can do qualitative analysis pretty easily by asking AI. And this is what we're going to do. So the first step is we will scrape the data. We will put it into an easy to read format, and I will choose, for this because a lot of people are using it, Google sheets because it's a very easy tool to use. And most of businesses know it already. And, then at the end we will do analysis. Of the, okay. Sorry for my English spelling, not the perfect one. So this is what we are going to do today. and when it comes to scraping data from Amazon, I want to show you two paths you can choose to get this information. In this particular case, first of all, there is a platform and it's called appify. I hope you can see it. Appify is a platform where you can choose in a store different tools you want to use and different scrapers you want to make use of to get information out of different services. For example, what I just simply did, I typed Amazon reviews and what I get is A lot of different, scrapers who all offer pretty much the same. And sometimes it's just a question. How reliable are they or how much do they cost and do they offer a big product? packages for what you want to do for our little example today. I've decided for the Emerson review scraper from jungle B here. it has 1, 800 active user. That's actually quite good. And when I'm entering this review scraper, what I can see here now is. You can forget most of the information you're seeing here. Most relevant for us is, you can do here a trial period of 14 days. I already subscribed to it. And what I have to do now is I can add here in this search field, which product on Amazon I want to scrape.

Isar Meitis: 8:02

basically the URL of

Dennis Trogger: 8:03

the product. Exactly. This is exactly the point. You just go to Amazon, you're searching for any problem, a problem, product you want to search for. you're just going here to the upper URL bar. You copy this, here with copy. And all you have to do is you put a tier pair pasting inside. And that's pretty much it. This is like the easiest way how you can get information right from Amazon. And all you have to do is here to save and start. And now what's going to happen is this tool has now started in the back or will start in the background. And, in this case here in a few seconds, we will see that, the virtual machine in the background will do its work. and this might take, depending on how much you want to scrape. Maybe one minute to two minutes, and then the results will be there. I actually did this already. I, you can see now that it started, that we are now in queue and that the process starts here. And when I go here to runs, then it can already see here. how many results have already been scraped and how much it costs me. And the beauty of, epify is that you have 5 off. of usage per day. So I don't have to pay for it, even though it says it costs 5 cents now, roughly.

Isar Meitis: 9:19

If I go now, I want to pause you just for one second, just for people like, Oh, I don't sell products on Amazon and I don't care. The idea here is the concept, right? So you can scrape data from other sources. If you sell software, you can go to places like G2 and scrape that and see customer reviews for yourself and your competition. If you are in whatever, selling stuff on other platforms and you can go Shopify and see what's happening there. Or if you just want to scrape data from your competition, you can probably do that as well. So the idea here is not the particular. Fact that we are scraping data from Amazon. The idea here that there are tools out there that for free or almost free, we'll get you a huge amount of information in a format that now you can digest. And we got to talk about that in step two, to analyze whatever you want to analyze, either your own products, your competition, what's happening in the market. What's happening in the economy, like it doesn't really matter. if you find, if there's a reliable source of data, there are tools out there. And Appify probably has scrapers for most of those, where you can go and grab data for, Anything you want and bring it in a format that you'd be able to work with.

Dennis Trogger: 10:32

Well said and thanks for, lifting this concept to a higher level and make sure, because what you said is actually pretty much true. the Amazon reviews is just an example. Everybody can grasp and it's, that's pretty tangible, but as you said, The important thing in business is that most platforms you're visiting daily, which are open to the public, they can be scraped. And as you said, there are so many, scrapers out there, which allow to scrape a G2 you mentioned, for example, we have a G2 product scaper. Then there is, product hunt. I'm pretty sure when I'm looking for this, we have Etsy scrapers and so much and so forth, and they pretty much all work with the same, mythology in the background. And if you really can't find something here, then there's always another tool you can use. and I won't show it because it's a little bit more technical and I don't want to deep dive too much. but there's another tool it's called Rapid API. It's pretty much a little bit more for developers so that you can do so called API calls. API calls is when you are having like, interfaces between machines and you can do very large amounts of requests. With coding, this is just, you don't have, if you don't want to have a look here, that's pretty much fine. I just want to show it because it's something I'm using very often. Often for our example here today, we will stay with epify because this is something everybody can use. and now after a few seconds, I see here that the Amazon review scraper already run through. and I see here that I have 100 results because that's the maximum I have now took here because that's what I needed. And now the beauty is I just can say in what format do I need it? Do I need it in CSV or in Excel? That's like the common thing we would do. And if I now download then a few seconds later, I have now the data here on my In the Mac book, you can't see it. I know that I'm just opening the file. So you see now that I have, what is the country code is empty. I don't know why, but it's, what's the, what we have right now. We see if the person is verified, what is the position of the comment? We see, the view URL. We get a lot of information of one of those comments. And what we will do now is we go into the webinar sheet here on Google sheets that are already prepared. And Za, please tell me if I'm zooming too much.

Isar Meitis: 13:02

no, you're perfect. So again, quick recap. We used Appify, one of the tools in appify, and there's hundreds if not thousands to scrape the data. We downloaded the data as a CSV, now we're uploading that CSV into Google Sheets so we can start analyzing the data.

Dennis Trogger: 13:18

So it's perfect. set. So in this case here, I'm going to use the same. She to say import data and what we now have now, what we have now is exactly what I showed you before in numbers from Mac. and I get now that I have a lot of rows, which are, could be interesting, but aren't that interesting for me. So I'm going to delete the obvious empty ones to get a little bit less. the product ASNI, that's an internal number of Amazon. I'm going to delete it because we know it's the review ID is not interesting for us. Images we don't need. So I'm going to remove them as well. The title, we will leave the URL category variant. and what we have left over after a little bit of, looking what kind of data we want to have, we see that we are left and use AS here repetitive. So we don't want to take this as well. And you see now that we are left with a few categories of content and we can start to work with it. I will remove this one as well. So now we have all the data. All those results and all those comments and all the titles in one Google sheet after a few seconds. now we talked a lot between, but this is something only took a few seconds and that depends of course, on the number of, re requests you do. But in this case, I will delete the, it's verified as well. the position we don't need and the rating score we are now left with. Our results will be biased because when I see now we have only got the five stars reviews, we know that most of those comments will be positive because otherwise you don't go to a five star review. But, sorry for this bias, something I haven't thought about before when I scraped the data, but it's all good.

Isar Meitis: 15:03

It's just to, for those of you who are not looking at the screen, we're looking at now only four different columns, the date, the rating. So how star rating the review description. So the detail review and the review title. that appears on top. So that's all we have. And because we scraped only 100 reviews, then they're the ones at the top of Amazon and they're mostly five and four star reviews. So most of them are obviously going to be positive reviews. That's what Dennis meant as far as the bias. I assume if we picked up a different product or if we scraped more than a hundred, we would have gotten a bigger variety. Yeah.

Dennis Trogger: 15:39

Well said. in this particular case, I want to show you something that really can help us because now we have the data and now the most important part begins. I have the data now. Now I have to ask myself, what do I want to learn from that data? what I've seen when I've done my AI hackathons in the past, what people did, I'm just doing an example. They, Went here, marked a lot of comments, switched to chat GPT, and just ask, tell me what we can learn here. So I just copied all of those comments and now I will drop them into chat GPT. And what we will get out of it is like pretty much nothing because when we are unclear of what we want. AI can't help us to determine a good result. And to make this even a little bit more clear, for this particular case, what I will do is, Google Sheets allows us to have something what is called add an app script. Appscript is, something where you can define your own functions in Google, for example. And I can show how easy it is to get ChatGPT to write a function like this. And so I will go to ChatGPT here, and I will say, please write a Appscript function that shows a pop up and says, It will, if I do this, jet GPT will give us all that's needed to copy and paste this. And I have now here function, it's called show popup. And when I copy this and post this into my file, I can save it. And now when I run it, the popup will show here. So this is nice, but nothing special, nothing fancy is happening here, but I just want to show the, the, the theory behind it and what we are going to do now is what is also possible to do is, we can write functions, for example, if I had five numbers or two numbers here. For five and three, I could say, sum up those in Google Sheets, and then I get a result back here, like an eight, and we can write custom functions. Why is this interesting for us, I'm going to show you, what we can do with Apps Script is that we can call the API of JGPT in the background. for our example, and because it's a little bit cheaper and for you, it's, it doesn't make any difference. I will now copy and paste my, my code, and this is fully generated by JetCPT. This, I haven't done anything here by myself. I've now created a function called call Mistral, what is an alternative tool to JetCPT, and as you can see here, in this particular case, This function X can be used to give it something to work with. So what I can do now is say, call Mistral, who was the second president. Of the United States, I should say, but, I haven't saved it and if it isn't saved, then it won't run. in a few seconds, the second president of the United States was John Adams. He served, as president from 1979 97 to 1801. So we get an answer from Mistral in this case for something that we asked it here. And now what we can do is we can have like several columns up here and say, for example, does this, comment include information, how to improve our product? Simply answer with yes or no, only one word. It could be that it sometimes answers with more, but what we can do now is we can say that we want to call the Mistral API. We will use what is set in this first, this first cell up here, and we add simply the comment here at the beginning. And what's happening now is Mistral is going to, analyze it. And we see now that Mistral thinks that in this that in this review is something how to improve our product. So we can have a closer look now on if it doesn't work well, and we see now, yes, this comment includes information on how to improve for the product. It mentioned specific concerns such as limited internal storage and joy contrived. I don't know what Joycon Drift is, but if it's your product, you hopefully know what the people are writing about. So what I can do now is I can simply, it may be from Google Sheets, drop this down. And now I do a lot of API calls. and hopefully, I know I made a mistake because I haven't said that the first.

Isar Meitis: 21:02

So I want a quick, recap for people who are just listening to what we're doing. So we took the data from the scraper, dropped it into a CSV. And what we've done now is we've taken a app script, which you can create on your own. And would you be able to share it so we can put it in the show notes, the actual script? Yes. Yeah. Okay. So Dennis will share it with us. We'll put it in the show notes. So all you have to do is in Excel is go and create a new, script, which is in the dropdown menu on the top, paste that script. And then you can basically communicate with a, any API of a large language model, which means you can now create, talk to the large language model from within the data ranges Particular, off this particular set of data. So what you can do, and that's what we're doing. So in the top of the columns, we're asking a question, which is basically the prompt that we're sending to the large language model and then copying that down to look at every single row separately. So every single row has. A different review of a product or a service or a software again, depending what data you brought in. So now what you're getting is you're getting the ability to analyze, ask questions about qualitative data, written text off all this information. Across as many rows as you want. And literally every single one of them just goes and calls in the back end to the API to actually ask the large language model in this particular case mistrial. But you can do the same thing with Gemini. You can do the same thing with. Claude, you can do the same thing with OpenAI chat GPT. All you have to do is go and grab, and there's a multiple, YouTube videos that will show you how to go and grab the API key. But all you have to do is sign up. It's nothing. It sounds really scary if you haven't done this. It's as simple as following a one minute YouTube video, and you'll see how to get your API key. You put it in that script. And that's it. And you're up and running, and you can even do that with several of them, right? You can ask the same question to each HAPT and to Mistral and see what's happening in each and every one. But that's what we're doing. So we can now ask questions about hundreds or thousands of rows of data with one drag down of that one cell that basically calls the API. And you will ask the same question for every single row and will give us a very specific result for each and every one of the pieces of data that we brought in. You

Dennis Trogger: 23:39

have summed it up very good. Wow. That was on point. Listen,

Isar Meitis: 23:43

I, I love this process. I use it a lot myself. So I find it extremely powerful.

Dennis Trogger: 23:50

and what you said, I just want to underscore it. all you see here is. No rocket science at all. Everything, what you've seen here, you can easily find. And if you're a businessman or woman, you can ask a colleague or someone who is a little bit fond to do stuff like that, and he or she will pretty much easily can redo this. This is nothing special, nothing fancy. And you will find thousands of videos explaining it very good and very easily. The most important thing you have to take with you is that. As you can see here in this particular case, and for this particular questions, we have a lot of yeses here. We have one, yes, two, yes, and we have one question, one comment that actually says no, but otherwise, oh, we have here, yes, no. So you see that if we take care of this, we could now create a filter in our Google sheets. And for example, only let us show which of those actually were really yes or no. And then we don't have to scrape through 10 of thousands of product comments. We'd only have to scrape through, through, through you.

Isar Meitis: 24:54

to explain why this is important. So what Dennis is saying is you can filter. So you've done your first question should be a very high level question to let you know which of these pieces of data are relevant to what you're actually trying to find out. Now, since you scraped, you're scraping 100 percent of it. It might not all include the stuff you're looking for. So in this particular case, he asked one question, but again, going back to our examples, let's say you're taking, I'll take a different example that you can use without scraping. You can take all your recorded sales calls. Transcribe them with any tool that transcribes bring the data in here and I can do the same thing in which calls are there specific objections raised by the client and or the prospect. And it's going to tell you yes, or no. And then you only care about the ones that actually had objections if you're trying to analyze what are the biggest objections you're getting. So now, instead of running the next question on every single row, which doesn't cost a lot of money, it's like fractions of cents for every single one of those API calls. But if you have 10, 000 of them, it starts adding up. And Being able to filter before you do the next step based on the first question is very helpful because now instead of running this. Next question on 10, 000 comments, you're going to run it on 600, which is obviously going to save you a lot of money and time. So how do we do the filter? That's the next

Dennis Trogger: 26:18

question. That's a very good question. We have now the option, we can do two things. As you said, we could either say, we do another question, which is very high level, because there might be a lot of questions we want to have answered on a high level thing. And, What we could do now is, we could write a simple, we can do two things. there's the, a little bit, I'd say the easy way would be, I'll just ask chat GPT to do the following. We'd copy this output. And that in this output, there's already a yes inside. And for some, there's only a no. And what we can do is we go to chat GPT and tell us, please. Write a Google sheet formula that checks if. A text contains the word, yes. and we, what we do now get is that it simply says here. in this case, we should use the search function used by his number function. And now what we can do is pretty easily here. we can copy and paste this here. And in this case I get back a yes. So instead of the yes, what I could also have done is that I now start here to do another call. And now I can say, listen, does this comment include, something about the product itself? Is that a good question? I don't know, but let's take this for the sake of itself or, yes or no? No. if the, review only says something about. Other things. I don't know if this is a very good question, but yeah, I will use it, right? So now, because there's a yes in this, in the answer we get, yes, this code includes something about the product itself. in this case, the Joy Con drift, and I think has something to do with the controllers that can be used. And if I now do the same thing. I simply, run the same prompt now for all of them. Then I get no answers only for those comments, for those reviews, which have yes before. So I can save a lot of, of data and it can pinpoint certain things I want to learn. deeper and deeper. And this I can do, as you said, on the sales call, for example, I wouldn't start, with, you could say maybe the person has, we can ask, is there an objection in the sales call? Yes. What are, please name now all the objections in the sales call. And then suddenly we can go deeper and deeper and deeper. And then you could ask, okay, please now show me what were all the answers that the salespeople had for this objection around this. And then you can ask several questions regarding what is your goal. And this is something I just want to add, because you see, if you do it right, you can ask any question and you can get lost pretty easily. And if you're some nerd, like I am, you can get lost to the tiniest of details and you won't learn anything new. You won't, we will learn something. But the main question is what I said before, but Answer. Do you want to solve with the data? What is the problem? What is the, what do you try to find? What does the KPI? You can do this explorative. you can explore the data and just. Play around a little bit with it, but at a certain point you have to ask yourself the question. what is the point? What do I really want to learn? And this is why I picked the amazon example because if you for example are in product design You can see what can what do I have to improve to increase my rating? during a sales call you can see hey does my Sales script what I teach new sales people already include them The most objections that come so you suddenly without relying on the salesperson, you can analyze all your sales calls and can get the biggest objections. The customer has, you can find, you can also find all The competitors that person is mentioning, you can analyze on a very high level for sales calls. And, but always with the question in mind, what do you want to answer in the

Isar Meitis: 30:49

end? Fantastic. I want to do a quick recap before I have some follow up questions. So we have data that was put into a CSV that data in this particular case is sourced from a scraper that there's multiple tools out there that will do it for you for. Almost free, like getting all that data that we just did probably cost us 70 cents. And so it's in, in a scale of running a business, it's, and even if you've got to cost us 20, it's still free compared to hiring an analyst or buying a report from a third party company that will do it. So we got the data, we put it on a CSV. We have several different columns of data. Again, in our case, it's date and rating and description and review, but it could be any kind of data you have there. Then in the next columns. We start asking questions, making calls to an API over large language model. So in our case, the first question is, does this comment include information? How to improve our product answer? Yes or no. So we get a list and we drag this all the way down to all the pieces of data that we have every single row and we get an answer. And the thing is, it doesn't just answer yes or no. We could have probably made. The question more accurate to make it answer just yes or no, but in our case, it answers. Yes, this is a comment that includes a comment and then it gives us a lot of information about what it says. So then in the next column, we basically said, okay, let's only look at the yeses and let's ask a follow up question about these yeses and you can keep on doing this. But what Dennis said that is really critical is. You want to know what you're looking for, but I will say something even more than that, which I really like doing. And it's a slightly different approach that then would lead to this. So it's like a middle step and what you can do is that middle step. is you can let the large language model look at the entire data. So instead of picking one cell, pick rows one through 100 in our particular case, but it could be 10, 000 and say, what interesting, tell it what it is, right? So think about it. This is, even though it's in Excel, it's like writing a prompt. You are an expert in data analysis with 10 years of experience doing this and that. I'm going to give you a list of 150 transcriptions of sales calls. What I want you to do as a first step is tell me what interesting insights and commonalities you find in the data. Because sometimes you don't know what you're looking for. You just have the data. And then it will tell you. It will probably give you 20 different things if you have enough data. Now, you have a good starting point to say, Oh. I want to dive into three, six, and eight out of the list of 20 things that he gave me, because this will have the most amount of business impact. So going back to, okay, now, what are the things you want to focus on? Because you have a lot of ideas of what this data actually contains. So what I love doing is in many cases, starting with just asking GPT, a broader question, have it give me ideas, even if I have an idea. Sometimes this will give me three more ideas and didn't think of, and they're like, Oh my God, this is awesome. And then start following the process that Dennis described. You're like, okay, now I can go sale by sale, ask these questions and dive deeper and deeper until you get the insights. The other cool thing, and I'll add, sorry, I'm jumping here, but there's a lot of things I want to say because your process is amazing. there are tools out there today. If you're from some reason, afraid from putting a script on your computer, which is not a big deal. Again, there's a million places where you can get this that are credible. Including, we're going to put one in the chat of like in the comments of this, of this podcast and in the YouTube channel, but if you're not, there are off the shelf tools that will do it, right? So there are other tools that you can buy that are extensions. I used to use, GPT for sheets and docs. It's a commonly used one. It costs money. This one is free, but it's a little bit of money. So if you're. Feel more comfortable getting an off the shelf tool. You can do that. The benefit of these tools is that it will also do the formula thing that, Dennis showed us how to do. So instead of going to chat GPT, which again, it's not a big deal is opening another tab, but it will do it right in there. Like you can say, okay, I need a formula that does this and that, and it will do it for you. And the next evolution of that we're on the verge of it. And it started to happen, but it's not great yet is Microsoft themselves. Now has copilot for 365 in Excel, which has some of this functionality within Excel and Gemini for Google Workspace is already available, which has some of the functionality that this can do within workspace natively in those applications there is. Zero dot in my mind that the full capability will be there within two to three months. But if you want to do this right now, the easiest thing is to do exactly what Dennis did, which is to Get a script from somewhere put it in your thing and you can start using it tomorrow and I would

Dennis Trogger: 35:35

add the point is as you said there are for a lot of things. we showed here today You can most for amazon reviews pretty sure you can and there are as you said done for you software which already what I would just add here, for example, if you want to do the path of testing it by yourself, I just want to show one tool I'm using and love to use. And I only recently discovered it. it's for the nerds a little bit, but, I love it so much. So I want to share it. it's called open router. and open router is, A platform where you can very simply, you can call different large language models, which are out there, which with one API call, for example, if you want to see, if you want to save money, because the point is some of those, big language models are free to use. And sometimes you want to start with a very, depending on what you do, you want to start with a very costly language model and work your way down to become cheaper and cheaper, the better your prompts get. And what is also right, quite interesting here is that, for example, if I have a prompt like this here, I will take, Just an example here, one second. I'm just copying the question here into the chat and I'm copying the review here into the chat. So doing pretty much by foot what I did before in Excel. And now the interesting part is I get here from different language models. I get the results so I can see which of the language models does actually the best job. And maybe having prices in mind. So if you're doing this as a company, as you said, yes, it's actually cheap, but, it's a certain point from some scrapings we do, we are dealing with 10 to 100, 000 entries. And even if every entry costs only 10 cents, then it starts to point. It starts adding up and this is why at some point it can be interesting to have a look at this, but this is like next level. If you're starting out, you don't have to do this, but this is just for fooling around a little bit, having fun. and just wanted to share it because I'm loving this so much to test different models and see what the results are.

Isar Meitis: 38:02

So I'll add another tool that does something similar. And before that, I'll explain why again, just summarizing what Dennis said, different. Large language models do different tasks better than others. And I'm even putting the money aside for a second, just knowing which of the large language models does better in whatever specific task, whether it's analyzing qualitative data, analyzing quantitative data, creating, reviews for something, writing blog posts, like every one of them, we'll have. pros and cons, and we'll do different things better. And sometimes it's better for you, right? Maybe it's not an absolute better, but for the way you're using it, for the use case that you're using on daily, weekly basis, it actually works better. So knowing which model to use for which use case, and now. Layering on top of that, okay, how much does this thing is going to cost me if I do it times 10, 000 is very helpful. So Dennis showed one tool, the tool that I love using is called, chat hub and it's a Chrome extension. And what chat hub allows you to do is exactly that, but it looks like a regular chat. So there's a chat on the bottom, but then you can open several of these in parlance and actually run a complete chat and you can see them side by side. And so it's an extremely powerful tool that I use regularly to evaluate different use cases. And it's amazing because you literally have the four windows open or six windows open as many as you want. I never opened more than four because it starts getting crazy, but in each of the four, you can pick whichever model you want. So if you want to compare GPT four to Gemini. 1. 5 Pro to Mistral to Lama 2, you can run all four of them and continue having the chat like you're having a regular chat, but you just see four variations of the outcomes, which is very obvious to see which steps work better in different tools. The other thing that it helps a lot is sometimes you just make a mix of the answers to for the use that you need. So you ask it to all four of them at the same time, Oh, I like this point from here, but 0. 2 and three from here. And I like 0. 7 from here. And now for you, you now have the five or four points, four or five points that are the best combination of all of them. So that's another way to do, the same thing. The only thing he doesn't have is pricing. So the tool that you mentioned that it has the benefit of showing you how much it's going to cost you if to run that model, which is obviously very beneficial. If you're then going to. Connected to Google Sheets and copied 10, 000 times. Yes,

Dennis Trogger: 40:37

well said. first of all, thank you. I didn't know Chathub. We'll have a look at it later. Thanks for recommending it. and. What I just wanted to say here regarding the data scraping, this is like a very rough data scraping process I just showed here. When you're doing it, it's, it would be beneficial if you first ask yourself, how is the information you want to harvest structured? What questions do you want to ask? Because. it might be beneficial to have several sheets open and stuff like that. it might be good to, to scribble down first what you want to analyze and how, and what you said before is copy and pasting a lot of information into chat GPT and ask, Hey, what can you see here? you can use it to, to ask it, which questions would you ask when you see those data? As an executive C level, C suite person, if you were critical, for example. And then it starts to give you critical questions and then you can start to, to dig deeper. yes, this is an awesome approach.

Isar Meitis: 41:40

A hundred percent. there's a question from the audience. Michael Hoffman is asking, is there a VBA script for Microsoft Excel? Can you do the same trick we've done here with Apps Script? Can you do the same thing with Excel?

Dennis Trogger: 41:53

I don't know, but the beauty is we can just go into chat GPT and say, can you rewrite the following script for VBA in Excel? And let's see what's going to happen from what I see so far. This looks solid.

Isar Meitis: 42:16

So for those of you not watching what we've done, it was taking this, we took the script that was created for as an app script for Google Sheets. Copied it back into chat GPT and say, Hey, can you rewrite this for VBA, which is visual basic, which is the scripting language that Microsoft uses and then paste the old script, hit enter and it gave us a new script that we don't know if it works or not, but it looks like a proper script.

Dennis Trogger: 42:48

Yes. summarized and I would say it could work. I have some doubts from what I see, but you could test it. from my perspective, I've worked with Excel quite a long time in the past. And I've at some point switched when I did a lot of, let's say, internet related things like API calls and stuff like that. And what, from my perspective, Google sheets. excels, pun intended, excels when it comes to doing API things and working with data like this. So if you do like the extraction with Google Sheets and this analysis and later put it into the environment you like most, that might be most beneficial and easiest for you to do. But that's just a suggestion. That's all I can say here, but maybe there's a tool or plug in already because I'm pretty

Isar Meitis: 43:36

sure there are. I'm sure there is. And like I said, if, even if there isn't a copilot, we'll sometime in the near future, have it built in right now, copilot is very good at doing Excel stuff. Meaning it can create formulas. It can create new tabs with new formulas. It can create charts and bars and calculate and pivot tables and all these things without knowing how to do them. Like you literally just ask for it. It still doesn't know how to make API calls back to Open AI to answer qualitative data questions like we did, but I'll be again, extremely surprised if that's not the next step that's coming. Yeah, absolutely. anything you want to add? At this

Dennis Trogger: 44:17

point, I think one of the most important things I wanted to show today, and I'm very thankful that you invited me to the webinar is that if you take one thing today out of this webinar is that this is the first time in history that we can do. Reliable sentiment analysis, quantitative analysis of data the first time. It costs nearly nothing. I don't know if you ever have done a survey in your life. And there is a type of survey questions called free text. They were like the most horrible things to have whenever you did a survey because you knew it will be hell of work to work through it. Now, if you do like free text, maybe you do customer surveys, you can use now free text and do the same questions. You can use the same mythology. don't look too much. And as Isa said, don't look too much about the Amazon reviews. Just ask yourself, what is quantitative data and qualitative data that you want to have analyzed? And this is now the first time it's really cheap and easy possible. And if you only take one thing with you. That's it actually.

Isar Meitis: 45:31

Fantastic. I'll add one more thing, which is, could be the next step after this, which I really like doing. So we now have an Excel with a lot of really good insights that we filter down to, to the last two columns that have the gold, right? We kept digging and digging, and then we found gold. And that has from 10, 000 rows. It's 50 rows of like really good stuff. What you can do is then you can take that column, save it as a new file, upload it to chat GPT itself, or Claude or Bart or Gemini or whatever. It doesn't matter, Mistral, and then ask it to help you write the report. Because at the end of the day, you need to deliver this as actionable items to a team, your marketing team, your sales team, your product development team, your whoever, like it doesn't matter. So you can then ask and say, Okay, here's what we found. I wanted to create a table that shows this information. I wanted to create a graph that shows this information. I wanted to create a executive summary that summarizes it all up. And then I want you to save it as a PDF and it will do it for you. So it's not even saving the steps off the data scraping and the data analysis and getting into conclusions. It also, the next step will actually create the report for you in whatever format you define and will allow you to, then you want to take it to the next step after you have the PDF file, ask it, okay, write the email where I introduced this to my leadership team or do my marketing team or to whatever, and then you have the email, you have the attachment, you open your, Email platform, whatever it is, copy the email, make whatever changes you want to make, add the people on top, connect the, the PDF file, hit send and you're done. So the process that Dennis and I done with a lot of talking, in 45 minutes, but that practically takes. 10, 15 minutes to do. If you know the process and you know what you want to ask, would have taken you days, if not weeks previously to analyze the data and come up with the data and create the reports and put it in the right format and so on. And now we're talking about minutes. And if it needs to be really detailed, really fancy, and you want to create several reports with different people, two hours instead of two weeks, several people instead of one person. So it's a complete game changer. I. Really like the way you summarize it, Dennis, as far as it's the first time we can do this. Like previously, this was kept to the Googles, the Amazons, the, the big players of the world could do this. And now anybody can do this for almost free. There's no excuse why not to do this in your business. And everybody has qualitative data. Take all your proposals, load them up and say, this one, this lost, categorize this one and ask it to compare them. there's so many ideas on how you can use this. So if people want to follow you, connect with you, learn from you, et cetera, what are the best ways to do that?

Dennis Trogger: 48:28

I'd say the best way to connect with me is still LinkedIn. I love LinkedIn because the community is so friendly compared to other networks. I share most of my stuff for free on LinkedIn. If I find something new and I'm very happy for everyone who connects and has questions because I'm sharing my knowledge completely for free. I'm not holding anything back. So if there's something up your mind in a few days or hours and you think, Hey, I just simply have a question. Don't hesitate. Just connect with me at me and ask me questions.

Isar Meitis: 48:55

Phenomenal. Dennis, this was really awesome. Thank you so much. Thank you Israel.