Leveraging AI

171 | The Ultimate Battle of Deep Research: (ChatGPT vs Gemini vs Perplexity vs Grok vs YOU)

• Isar Meitis • Season 1 • Episode 171

Share episode

Deep research tools are changing the game for business professionals, but which one truly delivers? ChatGPT, Gemini, Perplexity, Grok-3, and You.com each take a different approach—so how do they compare?

In this episode of Leveraging AI, we put these tools to the test! We analyzed real-world business use cases, compare their strengths and weaknesses, and reveal how to leverage AI research for smarter decisions and competitive advantage.

Expect live demos, real comparisons, and actionable insights—so you walk away knowing exactly which tool fits your business needs.

About Leveraging AI

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!

GMT20250306-163956_Recording_avo_1280x720:

Hello and welcome to another live episode of the Leveraging AI Podcast, a podcast that shows practical, ethical ways to leverage AI to improve efficiency, grow your business in advance your career. This Isar Metis, your host, and I am really excited to be here today. This is an episode I was planning on doing for a while, meaning since deep research on ChatGPT came out after it came out on Google and a few other tools, and I really wanted to do this, but we had guests every single week, and so I didn't have the bandwidth to actually do another episode in a week. I think two is enough. And so finally this week, we have an opening and I can do an episode just myself. So the topic of today's podcast is going to be deep research. So multiple deep research tools became available in the last few months. And it's a game changer across multiple aspects of people's day-to-day work and aspects of the business. And with that, I wanted to really dive in and see what the differences are. And as I was working on it, more tool came out so it make it even more exciting. So what we're gonna learn today is, first of all, what is deep research or deep search in some of the tools and why is it different than the traditional models that we've used so far? How to use them in the most efficient way. What are the differences between the deep research tools across the different platforms? And what are my recommendations on how to use those in the most effective way in the business? So we have a lot to talk about. So, with that in mind, let's get started and let's explain. First of all, I. Where did this all come from and why does it matter? And then we'll dive into the practical, tactical aspect of this. So in the beginning, when ChatGPT came out, which was the first model we had, there was no way to connect to the internet, meaning it was a standalone system. And all that system knew was what it knew from its training data. And that's it basically. You couldn't. No what's happening or research, anything that wasn't in the original training data. That was obviously a huge limitation that went away when the first connection between Chachi BT came initially through the connection with Microsoft Browser, Bing. And so that was step one. And then later on it became more of an integrated solution as part of chat GPT. Some of the other models followed suit with allowing you to actually browse the internet and get access to solutions in real time. And that evolved to all the other tools as well. Right now, as far as I know, the only tool that's still not connected to the internet and that is crazy to me is Claude. So I actually like Claude very, very much. But it's still offline. It's not connected in real time to any platform. But then. Online research tools started showing up. The first tool that I know that had serious quote unquote deep research is actually none of the very known tools. And it's u.com, YO u.com. u.com had a deep research functionality very early on. I've been using it for about a year. And so way before the recent deep research tools came to be known, and certainly shortly after that, we got perplexity. So perplexity was the first tool that really combined, if you want the search engine capability together with a large language model where you can have a conversation with it, but it also knows how to research the web. But then came the era of deep research. So what is deep research and why is it different than everything we talked about so far in the first three minutes? Deep research is more of an age agentic approach to research. What it actually does is it goes through a significantly larger volume of data and tries to distill and analyze the information in it and create a report. It works like a researcher would, researcher that either works in a company or at a academia or wherever else. It actually does a very thorough work and it approaches it in different ways, which we're going to dive into. And so the way it works is. It actually looks at the problem that you present to it. It dissects it to smaller researchable problems, elements, pieces of information that it thinks it needs to get in order to do the research properly. And then it goes ahead and researches a large amount of websites. the smallest I've seen is probably, I don't know, 30, 40 websites. The most that I've seen was 500 plus websites that it researched in order to get the answer. So it's very different than even the early days of perplexity or if you use perplexity or chate just with the regular search where we'll go and research six websites, eight websites, it's a much different level of research. So that's kinda like the general difference is that it's more of an agent that will decide on its own more things and more topics it needs to research in order to get a more deeper. Researched and more thorough response. And also the output is usually longer and more detailed. It comes out as a report with a lot of, with a lot of segments in it and headers and subheaders and bullet points. Just like a human would write a research report about a specific topic. So that's on a high level introduction to what is it. Now, the different tools are taking different approaches to this across multiple aspects of how these tools work. So let's start with how you get to these tools, the way you get to these tools. And I'm going to share my screen. And those of you listening at home, don't worry about this. I'm going to, share with you exactly what's on the screen. But let's start with, I'll just start with whatever order, I'm in right now. So I will share my screen. So the very first one we're looking at is perplexity. perplexity, as I said, was the first tool that kind of went in that direction, but right now they have a deep research mode. The way you get to it is if you click on, in a regular conversation, there's a dropdown menu right in the middle of the search box that allows you to select the different options. There's auto raw search, deep research reasoning with R one and reasoning with O three mini, and if you pick deep research, that's how you get to it on perplexity on. So it's a dropdown menu in perplexity. The interesting thing in perplexity, if you'll see if I'll scroll down to a search of already done. What you can see is the next time you get the prompt line, basically after you've done deep research, you can select again, meaning in your new prompt line, you can select again, there's the dropdown menu shows up. Basically every time the prompt line shows up so you can switch. During the conversation from doing deep research to doing other stuff, which is actually very powerful because sometimes your follow up questions, you do not want it to do deep research. You just wanna follow up questions on the search. It's already done. And if you have deep research turned on, then it's gonna try to do deep research again, which is not exactly what you mean. And so most of the tools enable you to do that. If we go to, deep seek, you'll see the same thing. So if I'm in the deep seek solution, you can see that deep research. So they call it search instead of deep research. And you have like a toggle button within your search within, sorry, within your prompt line, there's a toggle button for the search option. It's a similar thing in in you.com, there's just buttons and you can see it says Research GPT-4 oh, smart genius, and so on. So you can turn it on and off during the conversation. in chat GPT, it's the same thing. Inside the actual front line, there's deep research button that you can turn on and off. Four different steps of your work. And the only place you cannot do it is in Gemini. In Gemini, if you to pick deep research is when you pick the model in the beginning. So now your entire universe that you're working in for that particular conversation is Gemini 1.5 pro with deep research, and you're stuck with that. And that I said, it's somewhat of a disadvantage, on grok. It's the same like all the other tools where it's a toggle button that you can turn on and off, and they call it deep search instead of deep research, but it's the same exact concept. So this is how you get into the deep research mode in all of these tools. Now let's talk a little bit about. Some other differences on how it works once you start doing it. So you prompted just telling it what you're trying to research. So you want to tell it what is the topic. You can go deep, you can go wide depending on exactly what you're looking for. But the more details you're going to provide on exactly what you want to get, you will get an answer. Now, most of these tools will just start the research and I'll explain in a minute what are the different processes that they take. But the first, the only two that are a little different are actually Gemini and ChatGPT. So in Gemini what it will do, it'll think about your problem, it will think about the research it needs to do. It will come up with a research plan and it will show you the research plan and it will ask you, do you wanna add or change anything So you can see what it's planning. As far as, I'm gonna research this, I'm gonna do that. I'm gonna summarize this, I'm gonna look at this. I think these are the right directions to go. And once you go. It goes and you don't really know what it's doing. Behind the scenes on ChatGPT, there's a slightly different approach that I actually like, even better. So in slight ChatGPT, deep research, if you give it any task, it will ask you two to five questions. It'll ask you two to five questions as a follow up to clarify what you wanna focus on, or if there's specific things you wanna know that you didn't mention, or are there specific sources that are more relevant or whatever it think will help it do the job better, which is actually pretty cool. So I actually really that approach. and so there's a question in the task. Which one does it? So Gemini shows you the plan and then you can go in and change the plan, and ChatGPT will ask you some follow up questions. I've seen it as little as one and as many as like six or seven, but that's about what it's going to ask you. The other tools just go, once you hit the go button, they will just do the research. Now, even in the research itself, there's varying levels of how it actually approaches it. So let's start with the one that I think is different than the other ones, and that's Gemini by Google. Gemini by Google doesn't show you the process as it's doing the process. Now, I don't know if it doesn't actually do a process that is similar to the other ones or not, because they're not exposing it. So from a transparency perspective, it's very hard to know what it's doing. But I think they're also taking a different approach, and I'll explain why. I think what Google does is they take the brute force of Google. Think about it. They indexed the entire internet. They know what's in every single website on the planet. And so their approach is, I. When they build the plan, basically that phase where they're asked for your approval, they're reviewing lots and lots of websites, and they're building the plan based on that. And then they just go and execute the plan versus the all the other tools, literally all of them using more of a reasoning model to do that, where they go step by step evaluating and redirecting and making slightly different changes as the process goes on. So the reason I think Google doesn't do that, in addition to the fact it's not showing it, is when you use Google to do deep research, you're picking, as I said, from a dropdown menu, which model you're using and you're using 1.5 Pro, which is not a reasoning model. So I think this is, what's happening. And so this is, I. Google different than the other ones. The other ones have varying levels of how I would say active. The reasoning model is when it comes to making decisions and changing and manipulating the process as it's happening. So the, there's varying levels of activity in in these models as far as how active they are in the reasoning, the most active, and actually the coolest to watch because of that is grok. And you'll, let's look at a simple example in Grok and let's just look at it, and I'll show you a history of one of them. So what I did, I needed a benchmark. I wanted to compare all of them on a specific topic, and I needed a topic that I can verify the facts, right? So the whole point is to see if they're making information up, how detailed they are, how much information they can actually find. So I needed a topic that I knew everything about, and I started thinking about different ideas on what topic can I research that will know that I know everything about, that I can verify the information it comes back with. And I started this, like I said, as soon as ChatGPT came out. So that's, I don't know, like a month ago when it came out on pro and. Then it hit me that the one thing I know about everything is me. So I decided to do the research on myself. And so the prompt that I use, and I'm gonna read it to you, and then we're gonna look at what each and every one of the tools did and what it and so on. So the prompt I wrote is, what can you tell me about Isar Metis from Multiply ai? Find everything you can about him from the time he was born until today. I want to know everything, hobbies, education, professional, background, skills, online, commun communities, et cetera. So that was the prompt. I gave the same exact prompt to perplexity, deep seek you.com, Chachi, PT, Gemini, and Grok. So six different tools and I give them the task, the same exact task to see what they're doing. And I wanna start with Grok just to show you the reasoning aspect of it and see you how cool that is. And I'm gonna share my screen again, but again, don't worry, I'm gonna read everything that is in there. So here you see the prompt in grok and you see what it's doing and it's starting by thinking and it's thinking. And then it says, okay, researching isar, ais the request to gather comprehensive, detailed about Isar ais from multiply ai, covering it life, hobbies, education, and careers. I'm considering starting with a web search to find general info about him using his name and company. So that's what it's starting with. Then it's looking for, 10 results. Found it, found my LinkedIn profile. It found the badass page of my website, Multipli ai. It found my podcast, the Leveraging AI podcast. it find, it found a generative AI business transformation course, which is the course I've been teaching for two years, and it found Van Velo, which is a venture capital that I'm in, plus five more sources that I can see, that provide general information about me. Then it's browsing the results, and then it's starting to find information, and then it continues to think what to do next. Then under multiply it found my bio. So then it researched the bio and then it searched velo for that and then it found additional websites. And then from that it browses more results and it gets more and more ideas on what to look for. It found a different website about me called the E Tribe, which is my old website, and it find, found my biography, but it found out that website is not live anymore, which is true. so it didn't know what to do with that. And then it found Crunchbase and many more websites. So it's going through the process as if it's a human person, like it's going step by step. And as it's found another lead, it follows that lead and follows those steps. And then it keeps on going in all these different directions before it actually writes the report. So that's what I'm saying. It's very active when it's doing what it's doing. If you look at ChatGPT as a different example to see what ChatGPT is doing, I. You'll be able to see, first of all, in this case, it only asks me one question. So the question was, let me know which areas are most important to you. I would like to gather all, I'll gather all available information. And so in this particular case, I didn't tell it exactly what I want, but it researched the process for seven minutes. And you can see what it's doing here is I'm pulling together info on Star Mate is examining personal history, education, career, blah, blah, blah, blah, blah. And then it's searching and then it's collecting data and then again it's starting to find websites and it's tracing path to my, being an F 16 pilot and so on, and then rolling in college. But it's not as active as making decisions on more and more steps. It's kind of doing the same thing. The third one that is doing a similar thing and showing the work is. Perplexity. So if we go to perplexity, we'll be able to kinda see the same stuff. as far as Heart Perplexity is doing its work, it's gonna show you the sources, but it's showing you less of what it's doing. It's just showing you general high level steps. It might be doing similar stuff in the background. We just don't know that. So for each and every one of the steps, you can see I found some initial information about I Sar Metis, including his, professional role at multiply ai. And a few details regarding educational background, blah, blah, blah, blah, blah. So significantly less active as far as what the agent part of it is doing. So you can see different approaches to the problem, but the reality is we don't really care about the approach as long as it gives us the best output, right? So which one gives you the best output? So even in the output, they have very different approaches. The most unique one that again, I find really cool is actually grok. So what Grok does is if you go down to the report, it always starts. All of them, by the way, tell you how many websites they researched. So if we look right now, we can see that grok researched 92 webpages. Think about how long it will take you to research 92 webpages to reach a conclusion. Gemini Research, it's gonna be on the bottom on Gemini search, and everyone is a little different. Only 21 websites. but by the way, the largest number of websites I've ever seen was Gemini. It was, like I said, over 500 on ChatGPT, 20 resources on new.com. I don't know if they say, I don't think they say new.com, how many websites? they do not. So, but you get the point. It's gonna research many different websites and it's gonna give us an answer. which one actually gave the best results? So let's go on a few of them and see what they've done. Let's start with the worst one, and I've tried this across multiple things. the worst one consistently performed was deep seek, which I was actually surprised. So sometimes it works okay. Sometimes, like in my case, it worked very poorly. It basically gave me one fact and then said something like, due to technical issues, the search service is temporarily unavailable. And then he gave me a little more information and that's it. So I didn't found much. I try this, sometimes it does work, but in all the cases it's not as good as the other deep research tools. Perplexity actually did a very good job. So it did a comprehensive report, ISAR Metis from military pilots to innovator and entrepreneurs. So it gives it a header as if it's providing this as something people would want to consume. Isar Metis, a seasoned entrepreneur and CEO of multiple AI has cultivated a multifaceted career spanning from military service, tech startups and innovation. Born in 1973 in Israel and so on and so forth. Go through my F 16 pilot and being at the Air Force Academy. And then there are different businesses and the exits that I have, and it gives this executive summary that is relatively short, but really great. Like if you just read that, you kind of know who I am. Grok does the same thing. It starts with key points, and it does this for every single search. It does this quick executive summary in bullet point format, which I absolutely love. And so if you're looking for a quick executive summary at the beginning and then more details, the best play to go is gonna be grok, and then grok gives you more of a breakdown. The weird thing about Grok is after it gives you the breakdown at the bottom, every single time, it gives survey notes, which is basically giving you more details. And it's almost one-to-one repeating what was in the more detailed research. So I don't understand why it's repeating it twice. And again, it's doing it every single time. But the fact that there is three different levels of depth you can go into is relatively cool. And I find this for my usage, very helpful. Again, in 99% of cases, I don't research myself. I actually research stuff that I wanna find information about. So let's look at perplexity again. So it started with his opening and then it goes to early life in education. He talks about my childhood and early education, talks about Milan, military training and leadership development, academic pursuits. And then it goes to my professional career, early ventures and tech startups. Each and every one of them has between a paragraph to two paragraphs of information, e-commerce leadership and scaling success, multiply AI and consulting. And then he dives deep into what I'm doing right now, including, outcome centric thinking, valuation shift, professional as scales, and so different things that I teach, infinite scalability, different things that I refer to in my courses. So we do deeper into the content that I'm generating right now, mentorship and community building. So he talks about my Friday AI Hangouts and other communities that I'm a partner of. And then he goes to contribution to AI and thought leadership. He talks about my podcast and educational initiatives and many other things. And then he talks about my personal life. Stuff like that and online presence. So a very detailed, great report. I would say two things about perplexity. One positive, one negative, the positive. It's the fastest out of all these tools. So we got used from these tools, being able to say something and then in five seconds get an answer. These tools will take anything between three minutes to 20 minutes to give you the final summary. the longest I always see is Gemini taking the longest amount of time to get you the results. so that's the one thing. The downside is that I see it hallucinating every now and then. And I run this research on me with perplexity, more than once, and at least once it made stuff up. The other one that made stuff up, which actually surprised me because it's been around the longest, is u.com. So u.com. If you go to that to just see its format, you can see similar format, early life and education with significantly less information than perplexity. Educational background, professional background with. Bullet point breakdown, which is actually easier to follow. But they have me as the head of AI at Play Tika, which I'm not, or I wasn't co-founder of CEO at people, which I'm not founder of Prospero Technologies, which I'm not. And so out of some of the skills that the professional history that it has my current role as CEO at multiply, and then it made up three other roles. Not good. If you're doing research now, the reason I wanted to research myself is because I can verify this very quickly, but if this was me researching something else, then it will be very hard for me to go and verify. That being said, it'll always give you links to the sources so you can go back and check where the information came from in each and every one of these tools. But it's still gonna be a lot of work. My suggestion, always go and check the resources, but I will show you in a few minutes how you can. Do something even cooler and more impactful when it comes to finding what is actually accurate and what is not. So what am I referring to here? And I just see a lot of stuff happening in the chat, so I'm gonna open to see if you guys have any questions. what model is used by you.com? They don't tell you. So I think what they're doing is they're writing on other models behind the scenes. I know that for a fact, but they've developed their own age agentic approach to the deep research part of it. So a lot of it is their own proprietary secret sauce. One huge benefit of you.com, and by the way, you can do the same thing in perplexity if you have a, the enterprise account, is you can mix existing information that you have in your company, large documents, in a high volume of them, and have them be a part of your deep research. So you can combine the research on proprietary data that you own together with information in the outside world. And you can do it in the paid version of you.com and you can do it. And then they also have a parole version of the search that may not hallucinate as much, I don't know. And you can do it in perplexity if you have the enterprise version as well. Enterprise said, perplexity said in this past week or so that they're gonna. Provide this functionality to what they call personal files and they didn't exactly explain what that is. So maybe in the next few weeks or days or tomorrow or once we're done with this live, I don't know, they will actually release a version that allows you to do it for anyone and you don't have to have the enterprise license sense. So there's another question from Denny on when answers are not cut and dry, where does it differ? As far as opinions, I haven't tried that thoroughly enough, like I've tried it, but I don't have a conclusive opinion on which one actually does better in thinking. But I will take that back to what I said in the beginning. Most of these tools allow you to go back and forth from the deep research model to their thinking models. And I will show you in a minute how that can be highly beneficial. But you can start the research to get the dry facts with a deep research kind of model, and then in the same chat switch to a reasoning model and then ask it for opinions. And that will be my recommendation for this kind of use case. So let's continue. Let's look at chat g PT for a minute. ChatGPT. An overall, I think that's the best job right now. So it's not the fastest, it doesn't have the largest number of sources. it doesn't think as much as grok, but I think as far as the output from all the searches that I've done, and again, right now, every time I do deep research, I go to all the tools just to learn which one is doing what better. The other thing that will help, and I'm opening a parenthesis for a second, is it be most of these tools show you how they think. That helps you know what you may want to use in your prompt to push them in a specific direction to think about specific things. So it might be, I will probably give more thought and more depth when I prompt Gemini that is not gonna have that thinking process. Then I'm, if I'm gonna give it to Grok or ChatGPT as an example that I know do a lot of thinking. So just food for thought on that. But let's look at the report on. On, ChatGPT for a minute. You will see that it's the longest, the most detailed, lots of, formatting options that help you see what it's doing. So there's bold sections inside the text on important sections. It's broken down into clear segment. Every segment is significantly longer than in any of the other reports. I haven't found it hallucinating yet, and I've done different researchers on different topics. Again, in some of the topics. I don't know if it's hallucinating or not, but the other cool thing here is that it gives you the links inside the text itself. So if we looked, if we look at current roles, one of the things that it's mentioning right now is that I am in, a member of a. Of a venture capital here in central Florida called Velo, and it gives you a link to the Velo website. It's telling you that I spoke on different conferences and it gives you a link to the conferences that I spoke at to see that I was actually a speaker there. So in every paragraph, there's several of these links directly to the information, allowing you to verify that information, which I find very helpful as a way to verify the information that you're getting. So all of them have the links, but this is the one that actually makes it the easiest to see where this sentence came from versus you have to find it out on your own. It also has a sidebar that you can see in the menu. If you're listening, just believe me, on the side, you can open the sidebar and see how it was searching and see all the links. It was searching as it was thinking, which is also very helpful. So overall, as far as the general results. I get the best results as of right now with ChatGPT. Now let's talk about the disadvantage of ChatGPT. The ChatGPT Deep research is available at a high volume only to the$200 a month licensing level, their pro version. If you just have the plus, which is most people have, you're limited to 10 searches a month, which is not a lot. if you have the free version, you're limited to two a month. Perplexity gives it to you for free. Now you gotta remember it hallucinates more, and it's not as detailed as this one, so you gotta. Choose your battles, and decide how much you need this tool. If you need to do a lot of research, it's worth every penny paying the$200 a month because this report is by far the most detailed, the most thought after and best research, and with the best formatting to actually follow what it's doing. So there's again, goods and bads in each and every one of them, and you will have to pick, the ones that you want. you.com is also free. gr is currently free, but it's gonna stop being free. And Gemini is only available to the paid personal version of it, which drives me crazy. So I have an account through my company, which is a Google based company. So all my universe is in Google. If I go to through my business account to Gemini, I cannot pick deep research. So I have to pay separately for the paid version of Gemini in order to get deep research, which I don't understand how that makes any sense, but that's just the way it is as of right now. so there's a recommendation in the comments, in the chat for those you've not seen for the chat g PT to help you chat g pt itself to write the prompt for the deep research in order to maximize the queries since you only have 10. And that's always a great idea. thank you for that, Deb. and then there's a question with chat. GPT. Do you know if there is a way to find out how many out of the 10 queries you've used? I don't think it's showing you, I haven't seen that anywhere. you gotta put a, like a board next to your thing and run lines on it as if you're in prison. like connecting every five of them together. But I don't think you can know right now how many of you actually used. So let's go back to. What next? So now you have, let's say you do what I did and you run it across six different tools. Why would I do that? So I did that, first of all. So I can help you and I can help me and I can help my clients and I can know which one does better in specific types of searches. But the other reason is it allows me to do something very cool. It allows me to find what is most likely true versus not true. So what I did after that, and I do it a lot right now, is I went back to ChatGPT and I took each and every one of the outputs from the six different inputs. So now I have perplexity you.com, deep seek, Gemini, grok, and ChatGPT. All of them provided me with an output on a topic. I saved each and every one of them as a separate file, and I've uploaded all of them to GPT oh three Mini High, which is their best. Thinking model right now, and I told it the following. You're an expert in market research analysis. I will provide you with several files, all files generated by deep research in different tools. The name of the tool is in the name of each document, so it's telling it what's in the documents. The research was on a person called Isar Metis. Your task is to do the following thoroughly. Review all documents, create a table that has the following columns. Fact Gemini, Chachi, pt perplexity u.com, deep seek, grok and verification. Each row should include one fact that was found by at least one of the deep research tools, each of the tools. columns will include a checkbox or an a, a check or an X in the tool that found the fact. For the facts that are mentioned by only one or two tools, I would like you to search the web and try to verify or reject the facts. So my assumption is if three tools out of the six or more find a specific fact, it is probably true. If it was found by one or less, it might be made up, one very likely made up, two less likely made up, but still could happen. and so what you can see, and again, for those of you who are just listening, I have a table with many different facts. And next to each one, there's columns for each and every one of the research that I've done. And in there's either a checkbox or an x. And then in the final column it says, verification. In this particular case, Chachi, Pete even went the further step of actually explaining what the check boxes are showing, which from my perspective is irrelevant. But in, in the first thing it says, born in 1973 in Israel and the only one model that found it was perplexity. And it says, only perplexity reports a 1973 birth year. Web sources eeg, LinkedIn profiles are inconclusive. So it says, okay, I'm not sure, but now you know, and you can go research that further. F 16 pilot, all of them found that I was an F 16 pilot earned an executive MBA from Rollings College Commerce School of Business, 2007 2009. Three out of the six found out fact ChatGPT Perplexity, and GR confirms this external records support the MBA. So this additional step that is done as a. And as a reasoning model that can go and check what it thinks makes sense and doesn't make sense. By reading all the four sources that I give it, and it has access to the internet, it can go and check the internet, allows me to verify or reject stuff that the search may or may not be conclusive about. Now that being said, that requires to do the search six times and so on. But that being said, you can always build automations with tools like, Tools, like basically any automation tools you want, whether it's NA 10 or Zapier or make or any one of those to actually do all of that process for you or hunch. So you drop in your prompt once and then it will send it to all the tools. It will collect the outputs and it will send it to a reasoning model to do this work for you so you don't have to manually go and do all these little things if your work requires a lot of real research. This is an exceptional way to A, do all the research. B, collect facts that not all of them found, and I just showed you that even chat, GPT, that did the best work, missed a few things and the other tools did find it. So I have a way to aggregate all that information and then all I had to do is ask it to write a new report summarizing all the stuff that is accurate based on all the information from all the other reports. Again, you build on automation around it. You don't have to worry about doing this entire process now. I will say one more thing. I tried the verification process on Chachi piti and I tried it on perplexity, and both of them didn't catch all the stuff that was wrong. So there were the things that I told you that you.com found, like me being the co-founder of Prospero, which I don't know, it says, reported solely by you.com, external business directory support, his founding of this venture. Now, I couldn't find where that was found when I asked it for the resource. It told me that the resources out there exist in companies, blah, blah, blah, blah, blah. But I couldn't find it. So there might be a website out there that puts me as the co-founder of Prospero or the head of AI at play, Tika. I personally couldn't find them, but again, it's a very serious red flag. Not only one out of six research tools found that piece of information. So out of out, don't know, 40, 50 facts. There are here, there are three. Not only one tool found. Two out of the three are made up. One is that I'm born in 1973, which is correct. And so it still gives me a very good starting point of knowing what's most likely accurate versus what's not accurate. there's a question from Deb. How do you use hunch, off topic? So hunch is an incredible to do exactly these kind of things, meaning stringing together multiple steps of various AI tools into a solid outcome. I use Hunch for a lot of things. This is a great use case for hunch, but if you don't know hunch, you can again use Zapier or make or any of those, as well. That's it. Quick recap of everything we talked about, today, and I'm gonna stop sharing my screen. So deep research can be used for literally any research that you want in your company. You can research things such as a. Market status in your market competitors and how they're doing right now. How is your industry doing as a whole specific supply chain? Things that you want to know, specific tip research that you wanna do, or you can go and say, tell me everything I need to know about deep research tools and how to compare between them and create a table comparing the different functionality that they have. And they will do everything I've done for you. Now in 45 minutes, you'll get in a very well organized report and detailed output, including which one are free, which one costs money, and how much money, and so on if you ask the right questions. And so it's an extremely powerful tool for anybody in business, especially people who deal with. External information. So you need to know what's happening in your market. You need to know what's happening with competitors. You need to know what's happening with clients. Supply chain, cost of things, the markets, anything you want. you can do, you can get very detailed report and if you go back and you run on some of them and combine them together through the process I just showed you, you can get a very high level of confidence of what they're doing. I think in the long run, these tools will be good enough that we'll do self verification. So basically the process I just did, it will do on its own to verify. Right now we're not there yet. As I mentioned right now, the tool that I found to be the most helpful to me in the, I don't know, 20 searches that are run on it, in the past few weeks has been ChatGPT with probably grok and. Perplexity coming as close second. but the disadvantages, as I mentioned with chat GPT, is that you're limited unless you're paying the$200 a month. So that's it on deep search, deep research, whatever you wanna call the tool. Highly powerful capability that did not exist for us unless you used you.com a couple of months ago and now we have it accessible through all the different tools. My suggestion, start using it. Try different things. Try the different tools. Most of them are free or some of them are free. If you're having the$20 a month tool in Chacha pt, you can use that as well and do your own research like I did, because for your world, your universe, the things you're researching, you may get different results because these tools, as we mentioned earlier, work differently. Thank you so much for joining us. live on LinkedIn and live on Zoom. I know this was. Very condensed and with a lot of information, but hopefully very useful to all of you. We do this every single Thursday. So if you're listening in your car right now, oh my God, I wanted to ask a question as well, or participate in the chat, then you're missing like, there's a lot of conversation in the chat going on that I can't relate to all the time because I'm also trying to teach you stuff about things. but you're missing all of that if you're not here. So we do this every Thursday at noon Eastern. come and join us. The link is on my website and the link is also on my LinkedIn profile, so it's very easy to find. You can also join us on LinkedIn. We stream this to LinkedIn, and we do Friday AI Hangouts, which is open to the public. It's usually 12 to 20 people who join and we just talk about. AI issues, implementation issues that people have when we all together try to resolve it. So it's our community getting together, talking about what's happening, new tools, things we find, things we try and it's a lot of fun. Very unscripted and we just learned a lot from one another and things that we're learning with ai. So you're all welcome to join that as well. With that. Thanks everyone. Have an awesome rest of your week.

People on this episode

Head Shot

Isar Meitis

Host