Transcription
And then we are now at 11 o'clock and I assume that you can all hear me well um and can all see me. If you have questions during the webinar, then you have the possibility to ask these questions in the chat here. You will find them down here in the Zoom bar, um yes, in the chat area. You can click on it and then you will um and then you can enter something there, enter a question and um I will see to it that I answer it either during the webinar. My experience from previous webinars shows, um that this usually doesn't happen. I have deliberately included a bit less content today, so that at the latest at the end I can then answer your questions accordingly. I will also open the chat for myself right away. Um, then I will see what might come in. Yes, and now it's one minute past 11. Um, one of the most popular questions right at the beginning. Um, you will receive the recording of this webinar afterwards. The recording will also be put online on YouTube. That means you have the opportunity at any time to watch the recording again. Um, but you also have the opportunity at any time to go to the YouTube website with various AI tools and then either copy the link, say, yes, what did Möenk say about this and that topic, give it to me exactly. Or you have the possibility to extract the content with an AI-based browser. Um, that's just by the way, maybe there will be a webinar again at some point where I will present such things in more detail. But today it's about other things, namely AI tools for the acquisition of um properties and plots of land. There are one or two very slight overlaps with the webinar we did before, so in this, yes, in this practical webinar series, I would say. Um, that means if you were at both webinars, then there are one or two small things that you have already seen, but I will of course make sure that we always have new variants, always new tools here, and that is then also really the main part of our webinar today. Um, a brief word about myself, just so you know who you are dealing with. I have been part of the real estate industry for 7 or 8 years. Before I came to Side, I was at BNP Parate as a project manager for digital strategy. or so startups Propex examined and checked um yes, which tools, which um which programs we can possibly use well within our company to work more efficiently, to work better. Um, I have been with Side since 2022, so in a week or two, a week and a half, I will be celebrating my third anniversary at Side, and for about 2 years now I have been um yes, a keynote speaker, lecturer, and I also give workshops at companies. Um, all on the topic of AI. in the real estate world. So these two are linked, which I do, among other things, at ADI, at CIA. There is another webinar for real estate agents tomorrow. Um, at BDB there is another webinar for architects. That is the day after tomorrow. At iWS I am represented as a speaker and lecturer. What I don't see here is um any techy developer or anything like that. I didn't study in that area or direction. I can't develop, I can't program. Um, but I have realized about two years ago that I don't need to, to make a lot of what I um what I want to do, to make my daily business here um yes, more efficient. Um, so I can do a lot of that with AI now, because AI enables all of us to program things, um to automate, or even to build websites, without us having the slightest idea how to actually do it. And that impressed me a lot, and that's how I actually got into this whole topic and can now show you very concretely, artificial intelligence in the real estate industry. What can we actually do? And um I have put together a very short agenda. Um, but we will only go through the um yes, the larger points of it. Um, we will deal with how we can search for properties and plots of land. Um, for that, we will look at on-market acquisition possibilities. Um, but we will also look at off-market acquisition possibilities, and of course, um also mention Side very briefly. Um, then it's about compiling data for property due diligence. Um, I have included an example here. um how can we actually, yes, check data and documents that we receive either from the owner, if I am an agent, or from an agent, if I am a potential investor, how can we compile them in such a way that we can quickly extract information? Then we will deal with data research with artificial intelligence and then um and that is honestly um the um I think the most exciting thing of today. Then it's about automating acquisition processes. Originally, I had another tool in here. But with this last one, I completely realized automation with Gen Spark, um why should I show you the other tool if it is much more complex to build and if it is um yes, also more complicated, takes longer, and doesn't do as much as building it via Jenspark. So, this is the very big, very big trick, I would say, that we will look at today. But um we will start first and I want to show you a tool right at the beginning, which um honestly is not an AI-based tool at all, but um a tool that is very, very relevant and if I had known it personally before, I would have saved myself a lot of time in my life and I think very few of you know this tool. And it's about the so-called Instant Data Scraper. I'll show you that once. Um, I'll show you that here. The Instant Data Scraper is a so-called extension for Google Chrome. That means, um I see in Google Chrome, if I click on this extension button here, I don't think you will see what I am opening here at this point. That's why I will also share my entire screen in a moment, and then you will see what I mean by that. I'll make the whole thing bigger here. Um, I have to stop sharing for a moment and then I will share my entire screen. That's always a risk. Um, possibly there is a slight mess here, but you should now see my screen. Yes, share desktop. So, that should be correct now. And this Instant Data Scraper, it's actually not fundamentally intended for the real estate industry, for the real estate sector specifically, but it is primarily intended to simply pull everything from a website in a structured form, in table form, that you actually want. But we can also use this in on-market um real estate acquisition, yes, you can also see it as on-market. Because if I now go to Google Maps, for example, and now I select a city. I'll go to Bonn um and I say I'm interested in properties in Bonn, then maybe the first thing I want to do is contact all real estate agents there and submit my acquisition profile, just as an example. And then I go to Bonn, enter real estate agents in the top left, click Enter, and what happens now? Of course, all real estate agents in Bonn will be displayed here. And if I now scroll down further on the left side of Google Maps, you will see this slight, this bar on the side, it gets smaller and smaller as I go down, because more and more real estate agents are displayed. And I'll tell you honestly, I believe if a real estate agent is not listed on Google Maps, yes, here, then this real estate agent doesn't exist. So, I claim that all real estate agents in Germany are listed on Google Maps in some form. And um now you see all these real estate agents. You could now go to their websites and then say, I'll contact them to submit my acquisition profile there. Um, but that's also much easier, and that's with the Instant Data Scraper. That means I click here at the top once on extensions. Um, after I have downloaded this free Google Chrome extension, I click on Instant Data Scraper and now this field opens here. So and you see, everything on the left side is now marked, and this field that opens has now automatically provided me with the company names of the agent agencies. It has provided me with the rating, the number of reviews we had for it. You can always recognize a bit from this whether it's a large player in the market or a new smaller one. Um, well, if we have an average rating of 2.5, then we should assume that maybe something is wrong there, I would say. Um, then we get the addresses out, we get the opening hours, the telephone numbers, and importantly, directly the websites. Now, of course, you can use the websites to then, for example, yes, with ChatGBT or with another artificial intelligence, enter some of these websites. We can do that once too. So, so and so. And say now, give me the email addresses of these companies. Companies. One can, if one speaks to the AI or enters something, of course always make as many spelling mistakes as one wants, I have the feeling. Um, but it looks a bit stupid when you do it in a webinar. Yes. Um, and now it searches the whole thing online, searches the websites online and will then give me the corresponding um or the corresponding um the corresponding email addresses for it. That means, from this list that I see here, with one click, we can do it again, so, I have extracted a list of all um real estate agents. Um, in this case, I don't know right now, I think about 60, 50, 60 of them. It can go even further or there's more. If I now, for example, if I click on Chart Crawling, then um no element with scrollbar found, then it doesn't work in this case, but um Start crawling. Okay, normally, honestly, this is the first time I've had this. Normally, it's like this, that it recognizes this scrollbar here and then automatically shows you everything that you can find there, if you were to scroll down yourself. In other words, it's one click and you have all real estate agents um yes, displayed directly. The webinar is for real estate agents and project developers, because acquisition is the same at first. Um, that's why another solution for this would be to enter real estate agents and project developers, to say, yes, show me all of them. Then again, use the Instant Data Scraper and now let's try it with Start Crawling. Shame, it didn't find it either. Then we go down here a bit and do it manually. But all real estate agents who are in this area here, so they should be displayed now. Yes, that's how it looks. And um with that, we now have the websites of all real estate agents. There are lists, champion sites and so on, where you can buy lists of project developers, property owners, etc. Honestly, you don't need any of that. um if you use this and then um with ChatGBT, we'll see how far it is, have the email addresses output, I wouldn't make the list too long here, because if you have like 100 properties, then um then it takes a while for it to finish. But this way, you have actually scraped everything directly from websites. Um, scraping is what it's called, and um with that you can then um work on it immediately and then you have a corresponding list and can then um use it and approach it, be it real estate agents with acquisition profiles or um you simply send the AI to the websites and tell the AI, please give me the acquisition profiles of the companies if available, then you have a quick, large customer list immediately. Yes, and um now I'm only sharing um now I'm only sharing Google Chrome again. So. and make it a bit smaller, because the screen is relatively wide here and then it can be that you may not have seen everything, because as a tool, um you can use it for everything. Yes, there are super super many possibilities on a website. Even if you want a list of listed buildings, they are sometimes on Wikipedia, click on the button and you have this list in a CSV file. I haven't shown you that at all right now. You can export the whole thing as CSV directly and work with it, right? And it's free. And if we want to take this to the next level, then there's a tool. Unfortunately, that's not AI yet either, sorry, but then there's a tool called Apify and um we'll open that now too, the Apify console. Apify is basically a website. I'll show you what it looks like. You log in, go to this console and Apify um offers you in the API store, as it's called, many different possibilities for so-called pre-runs and scrapers for the internet. That means, um it's always about you enter, you say what you want, and you get a lot of information output and downloaded in a list. And you can, of course, do this, as we just did, for example, for Google Maps. Yes, that means what I did here is use the Google Maps scraper. I then told it, um I'm looking, I'll show you what it looks like here. Um, you might have to look a bit here, how does it work? Honestly, it took me 15 minutes or 10 minutes. And I understood how to use it. I simply enter a location. In which area am I searching now? Now for Google Maps information, for example. In which area am I searching? Um, what am I searching for? Real Estate Agents in this case. Um, then I can specify further details, what else it should download and pull down. Um, what I find very, very exciting is Company Context Enrichment. Um, this basically means that um yes, it searches the internet and the website further, the website of the agent, and finds contact details that are on the website or are on the internet, for example, for the managing director with an email address, sometimes with a phone number and mobile number. Um, simply to approach them accordingly. Um, you can also use Business Lead Enrichment. It all costs something, not the world, honestly, um to simply download it. And then you get to um the last run I did here is Scraping Finish. And now you get the company names. You get the total score that it has on Google. Because we are simply searching for Google information, the website, category names, and the phone number. And you see here in the contact information um yes, further information. You see here further social media data is not available for all, but you have, for example, Instagram data and so on. And Lead enrichment is also available. Um, you see here Name, First Name, um yes, Sales at Spada in Hamburg. Um, here we have the CFO um also with departments and if I go a bit further here, you see it's extensive with phone numbers. Um, and and. Yes, with this you can get further information very, very quickly and what we have just done with the Instant Data Scraper, um for example, throughout Germany, and it takes you 6 minutes and 30 seconds. Um, and for, yes, 662 results, I paid just under $9 in this case. Yes, and um you can then download these lists as a table, of course. Um, as an Excel table, for example. I have already tidied them up a bit so that you can see a bit what you have and um you can then use them to initiate further steps and go to the corresponding websites um yes, or contact them or whatever. And this applies not only to agent contacts, if you want to enter your acquisition profile, but it also applies to um for project developers, it applies to property owners, it applies to actually anything you can think of, and now only for Google Maps. I would now like to show you another possibility. Um, because we also have the possibility to crawl on-market properties specifically with an API. Um, what does that mean? In this case, we use a crawler, a scraper that is available at API for ImmobilienScout24 listings, to give them to us in a structured table. Yes, there are tools like Immometrika. Um, but these tools have little AI included. And um what you can do with it, download it like this with an AI, I'll show you that now too. The first step is um for that, we go um to Apify again, look for this crawler that we have here. This is this one. Um, it costs $ for 1000 results you get out. That's negligible, and it works like this: you just enter a link, and I have this link as an example, and this is basically just the link to, yes, it's not the absolute best example right now, but this is a link to 163 rental apartments in Osnabrück as an example. How do you get this link? Well, it's simply the one that's at the top. That means you simply go to Immoscout, enter um yes, Osnabrück, and click on Buy Apartment. If you now want to scrape all apartments, for example, and then analyze them, you now have an overview. If you now say, new apartments are uninteresting to me, then remove them. Then you are at 99 results for condominiums, or copy this link, go with it again to um to to AP, click on enter a link type, click on Save and Start, and then this tool starts working. Here you will first see the logs while it is working. So what is happening now? What is it looking at? Um, and you will see the output. We'll wait a moment and you'll see a bit of what's happening here. But let's go to Board and I'll show you the finished result, of course. Um, the finished result in this case for these apartments is this. And you get an output. It looks like this at first. It's an incredibly long, incredibly large table with a lot of basic information for each individual apartment or for each individual apartment that you get. This doesn't help you much yet, but you can download the whole thing as a table. The table, then, has to be adjusted a bit. Actually ask ChatGBT or the AI how you would do it, or how you should do it, or if the AI can do it for you, and then you have here, this looks a bit unstructured now, a list of all condominiums that are currently online um on um on Imoscout. Um, and you can then use that and work with it. The point is, um if you are now looking for condominiums, for example, that you want to acquire, then um many condominiums are also rented out, so that with the filter you have set, so that Imoscout always sends you the latest properties, so that they would not be displayed to you at all if you only search for unrented apartments. But now you have downloaded all the data from Imoscout for these apartments. And you see, it's extremely extensive. So, you also get the pictures, links to the pictures, and and you have to um a bit here um so it's confusing, of course, now as a human, right? You have to look a bit at how to manage it, I'll show you in a moment. Um, but you get all apartments out, and it could be that um that these apartments are actually also rented out, but um in the description, for example, it says, yes, the apartment will be available from 11.11., then that would be sufficient for you. Um, and it would be an um a property that not everyone finds directly and sees directly. Therefore, um it is very useful to download this data like this and run it through an AI. Tell the AI, please also pay attention to this and that in the description. Or for example, forward the pictures directly to the AI and say, what would the renovation of the whole thing probably cost me? That also works, and then work with that, and that's relatively fast. What I did and want to show you is um I took this data and uploaded it into Genspark, which is the tool we will look at at the end today, um into Jenspark, you can't see it anymore, these are older messages, and then communicated something with Jenspark. So, what you see here is always the answer from Jenspark, what it has just done, and and then I asked a question from time to time, um as one does when dealing with AI. I'll go down a bit, so. um I asked a question from time to time here. No, not here either. Here, for example, and said, now include this and that. Jens Park understands the table we just saw. It understands it, and you can then simply use this table. Yes, I have to do that again. No, luckily I saved it. Okay, give me the website again. So. Um, you can then simply tell Jenspark, this is the data. Please do this and that with it, or please calculate all um apartments according to my own um ideas or houses or whatever you upload here. Um, and please, please give me out the ones that are most relevant, most interesting to me. And what James Park does here, for example, is to create this mobile platform for me, which you see here, and all of this with the information that I have simply downloaded via APF, then uploaded here, and then spoken a bit with Jensberg. Um, this here is my personal um personal overview, which of course is not much different from what we um from what we see on Imoscout. Completely clear. But what I have done here is also to include current square meter prices, which I also had calculated by the AI, so that I can now see exactly which properties are below market, which properties are above market. Um, I also have an overview here, there is a need for renovation, here there is no need for renovation, this is fresh, this is not fresh. All this information and data, it comes from the texts, it comes from the further information that we have in this table, which Imoscout does not show you at all or with which Imcout cannot filter at all. And in the end, I have an overview of these corresponding properties. You can also build it so that you can click on it. Here, for example, it works. You see the pictures and you have your own overview, of course, with the normal description, but we are not interested in that. We want to have it read out automatically um automatically, yes, based on AI. And this this page and this overview, Genstike builds it for you as well. You can also enter how much agent commission you have. Honestly, that's already included in Emoscout, so that the total investment is calculated and and and it's very, very easy to build this up. These are a few prompts that you have to enter. You can experiment a bit and then you can search on-market for all properties that might be interesting and relevant to you. And that um works, so there are many different ways to do it. You can also simply send an AI to all the websites that we have previously extracted from the agents and say, give me an overview of all properties and then calculate them with my own data. Um, these are all step 2, step 3. But all of that is possible, and all of that is also possible, for example, via Gemspark. Yes. Um, we will now leave the area of on-market acquisition. Let's go into off-market acquisition, and for that I would like to show you Side briefly. Um, I think many of you have seen it before and know it. Side offers an overview of all development potentials, all existing data of all properties in Germany and can then make them searchable in reverse. That means, I click here once on plot search, then the simplest variant is to say, I am looking for residential properties or residential building plots. Um, I can either enter an area, a whole federal state, or I um yes, I simply select something where I say, that is interesting for me and search for plots um that have a development potential for residential use, so that they are already residential building land of at least, I'll take a bit more, 1500 square meters GFA, maximum 10,000 square meters GFA, and then um I also say that the plot should be at least 30 x 30 meters. Um, it's always very useful to do it like this. And I'll click through a bit faster here and now just say that the plot should be completely empty and then click on continue. Now you see, you have 80 results, and for off-market acquisition, so um I'm looking for plots and then I approach them independently to um yes, find out who the owner is and then um see if I can develop the whole plot or not. For off-market acquisition, this is perfectly suited. Here you see in the cadastral in these survey data, in these 3D points, that something stood there. In the cadastral data, there is nothing more. That means, this must have been demolished recently. I can imagine that something new is already happening here. You also have such examples, or such situations. Here it's different. Here, new construction has already taken place. Yes, so you have to look past it a bit, um that not all of these 80 plots shown are 100% correct. This one here seems to be free again. Yes, this plot allows you, it is already residential building land and it allows you to build with 4000 square meters. And um if you find these plots and buildings, like this, first plots in this case via Side, and then immediately go into acquisition, you will sometimes find plots, you might drive past them every day and not even know that it's residential building land. Yes. Um, well, that is also built up by now. Let's go back here, more into the inner part. Yes, here, for example, we have a plot um that is in the inner area, it is residential building land. Um, it probably looks like a garden area right now, but you actually have the driveway built through it, because it was planned to build on this plot at some point. So this plot is currently free. You could build on it with 1600 square meters and um to go into acquisition and ask who owns the whole plot. Um, should I or can I perhaps make an offer for it? That saves the agent's fee from a project developer's perspective, and um it allows you a completely different price negotiation for the plot, I believe. And you find these plots via, and what you can also do, this is something I actually do privately, is to search for plots where you make owner research somewhat scalable. What does that mean? Um, let's go into an area again, like this one, for example, and say, in this very large area, it must be said, I am not looking for free plots, but I am looking for plots where, in addition to the existing building, in addition to the GFA, I can build at least 500 square meters of GFA additionally. And um these plots should again have a certain, yes, I'll take only 15 meters, a certain length and width. And um here, however, the difference to the search we just had is that we are now looking for plots that already have main buildings in stock. That means we are looking for, yes, single-family houses. So for um we will also enter that. We are looking for single-family houses um from certain construction years. Yes, something like here. We hope that there is no monument protection on it. So, um from these construction years, we are looking for single-family houses that stand on a plot that currently has a very low floor area ratio. That means these 500 square meters of additional development potential, we can probably achieve by placing a second building on the plot. And since it is a single-family house, let's say the building has a footprint of 60 to 140 square meters, and the existing building has a GFA of 80 to 300 square meters, and it has a maximum of two full storeys, then we can be very sure it's a single-family house, and we are simultaneously looking for one with poor energy efficiency. Why? Yes, we now have 1200 results. But we have also let ourselves be shown a very, very large area. And these 1200 results are all plots, such as, yes, let's take this one, such as this plot. We have a single-family house on it, yes? We have a slight increase, you should know that, but we have a single-family house, but the plot would offer much more possibilities from a building law perspective. And specifically, from a building law perspective, it has the possibility of 918 square meters of GFA.
to grasp, so almost 767 m² more. We could therefore build a second uh house on it here. This could possibly also be a multi-family house at this location. I would be quite sure of that based on the data at least. This means we have a plot with a single-family house, um, with the possibility of building another multi-family house on it. And you now have a list of single-family houses. With single-family houses, it's usually the case that the resident is also the owner. And uh, if you now take this list here, perhaps look at each building again, um, and look at each plot again and say, yes, does this really fit here or not? The plot here is, for example, very well uh suited, if you disregard the slope, because we simply, although even with the slope, honestly, because we simply see, we already have two buildings here, there's a street here, there's a street there, here too, only not here yet. So we could definitely densify here. And now you get, now you have a list of many of these properties. And because it's a single-family house, I don't think an owner search is really necessary anymore. Because if you now send an individually designed letter, stating, uh, we know that on your property there are so and so many square meters. We would like a part of that, would like to build a new single-family house here and offer you, while we are building the single-family house, we will renovate your house thoroughly, because that will probably be necessary at some point with energy class H. Then you have created a win-win situation for both parties. For you, you get the plot, uh, and for the, um, for the owner and resident, because he gets a free, almost free, one would have to discuss, renovation of the building. This win-win situation, you create it for all these, uh, addresses and properties here. And you can, of course, then contact them all one by one with a letter, for example, uh, and find out if there is corresponding interest. And this is one way to acquire plots completely, um, completely off-market first and, uh, to see, yes, what, uh, what comes out of it. And I can tell you, it works. As I said, I do it myself privately in this way or in a comparable way. Um, and, uh, very, very good, uh, results come out of it. At the same time, you also have the opportunity over time to search for plots. Uh, for example, industrial and commercial plots located in a residential area for redevelopment. Um, you can do this search for all asset classes. For now, we are very much in the residential area here, but this naturally works for all asset classes. Uh, you can then directly take over a renovation plan over time, and a residual value calculation. So, um, all of this happens very, very quickly, and, uh, with that, you can scale this off-market acquisition, I misspelled, sorry, uh, in the end. Yes, um, that is possible with it. So, and now we go into, um, into the next area, into data extraction. Um, data extraction, that's something when I, as a broker, or when I, as a project developer, existing investor, uh, receive an object sent to me with either just an exposé or, uh, many, many more, uh, further documents, many, many more, um, topics that need to be included, then I have to read them all first. And AI is extremely good at this. AI is very, very good at saying, um, these are the, these are the documents, and I will now give you exactly what you want from me, what you need, for example, to check it. Um, example, I took this, uh, Immoscout exposé. This is an offered multi-family house, uh, in Düsseldorf. Yes, it's basically just saved once from Immoscout, uh, and, uh, given out as a printable version. And, uh, I have also created further, uh, documents for myself. These are all completely fictional for now, I must say. But, um, I wanted to show you that you can read in many documents at once and thus extract data. This means I have created a document here with craftsman and modernization invoices. As I said, fictional, but it states exactly, uh, what has been done in recent years and when. Yes, uh, then we also have the transcript of a conversation with the owner, where he tells a few more things about it. So, so also unstructured data that we might need in the end. Then we have a rent statement, uh, that we have received here, with corresponding invoices. So these are just the example properties, or these are the example documents in the end. And, um, now we want to have the really relevant data for us from this. And for that, we can simply go to ChatGPT and provide ChatGPT with a corresponding prompt, i.e., with what we, um, what we enter, what ChatGPT should do in the end. And this prompt, you see, it's a bit more extensive. By the way, I create all prompts directly via ChatGPT. This means I say, "ChatGPT, create the perfect prompt for this use case," then the perfect prompt comes out. Um, you don't have to write all of this yourself here. I haven't written it all myself here, of course, but, uh, this prompt says, first of all, you are an experienced real estate analyst and investment expert for multi-family houses. You have a deep understanding of project development, portfolio management, and real estate valuation, and analyze a series of documents for an existing property, uh, to be checked as a capital investment. Extract all relevant economic, technical, and legal data from the texts that are important for an existing investor or project developer to make a prioritized purchasing decision. And with such a prompt, you then only need to upload the corresponding data and documents, uh, that we have here. And, uh, let's upload this one here. Um, these are not all of the documents we saw earlier right now. I'll just quickly go back to all documents and take them. Sorry, it's somehow, uh, not open. Yes, but that's relatively quick now. So, and now I have it. So, I drag all these fictional documents in here, and it's possible that, uh, there are too many. Sorry. So, all these documents that we saw earlier, I drag them in here now, and, um, wait a moment until it has uploaded them, and now I just click on Let's go, on Start. And what ChatGPT now does is it reads the documents, and that was very fast. Uh, it now gives me all the data that I actually need from it in a well-founded, structured way. Year of construction, construction method, floors, and so on. And that, I think, is the first step for, uh, a project developer, an existing owner, to extract and analyze an exposé and all the data available with it from a data room, for example. Simply upload it, say, I need this information, please output it to me, and let's go. And this data extraction is extremely easy and fast, and you can, of course, also have the whole thing automated by AI if you build, um, for example, a custom GPT. Uh, how the whole thing works, you can also see in the recording of the webinar that we provided here, for example, um, you build this, you drag the documents in every time and then get this overview. You can also work further with the overview, everything is possible, but be very, very sure that the data that is in here is all exactly correct and exactly represents what you saw in the data, or what the AI saw in the data that you entered. This means it's very fast. You no longer have to read it and have everything you need for your purchasing decision at a glance. Yes, and this also works with the free ChatGPT version. Just saying, yes, and then the next step would be to say, well, uh, now I have all the data about the property, right? And now I also want to know, um, what other information is available that is publicly accessible. And for that, uh, we use ChatGPT again, but we use this so-called Deep Research variant, and I'll show you what the whole thing looks like. Um, for that, we go back to ChatGPT, open a new chat, and enter a prompt. I have also pre-prepared this one again. Unfortunately, it doesn't look as nicely structured as before right now. Uh, this prompt essentially says, um, I want for a plot of land, so now a different example, I want for a plot of land in Cologne, Deutsch Kalerstraße, or 3 Optimus plot, we have already dealt with it in another webinar, um, I want all information for this plot that could be relevant for me if I want to convert the plot for residential development. I want the tool to research completely, to know everything, or to output everything it knows. Uh, and then, um, I want a complete report on it. And Deep Research is designed for this. So you click on plus, select Deep Research, and then click Start. Then you will be asked one or two more questions. Deep Research is designed to really search the entire, um, the entire internet for all information available, to output it to you in a structured way, so that while the internet is being searched, sometimes 7 minutes, sometimes 25 minutes, you can do something else, and in the end you get an eleven-page, fourteen-page report, uh, that outputs everything that is relevant for your examination of the property, of the plot of land, in the first place. You would have to answer a few more questions here. I won't do that now. I have, of course, pre-prepared the whole thing. Um, and have used this prompt so that you can also see a result. You see, this is already the result, and it's very, very extensive. It's even more than I, uh, uh, thought. The tool took 28 minutes, looked at 19 sources, performed 112 searches, and, um, current use and structural condition are indicated, even with a picture, history of use. Uh, so everything that is found online here for this gas station, it was built on behalf of Deutsche Shell AG according to plans by architect Herbert Baumann. Um, it's super, super extensive. Overall legal situation with development plan, monument protection, we have here, uh, planning feasibility and so on, and, uh, usability of building rights. It outputs everything that is available. Yes, and I would recommend doing this for every plot of land and every property that you look at more closely, because sometimes you find information, uh, about it that you wouldn't have searched for otherwise, because you wouldn't have known that this information could actually be relevant. And this ChatGPT Deep Research, I would now expand it, for example, with the use of agent mode. The agent mode, for example, finds development plans for you, and, uh, I'll show you that in the finished result now. Uh, this is, this is the prompt. You are a professional research assistant for urban planning and building regulations. Your task is to find the valid development plans for the street Am Pickenhof in Neuss. And the agent mode is essentially also something like ChatGPT Deep Research, but the agent mode clicks, you see it here, that's how it works, it clicks through the web activity, through the websites, then searches further with it. And what the agent mode can do, what Deep Research cannot do, is it can navigate completely freely on websites and click on things, understands the websites. This means that while Deep Research only outputs text information and therefore reaches its limits with websites where, for example, development plans are shown on a map, the agent mode can understand this website, clicks on the corresponding things on the website, enters, uh, the addresses, in this case, and then outputs to you, okay, this and this development plan should apply here, because I saw that on the website where I clicked. And this clicking is what makes the difference between agent mode and Deep Research. And now we have here, I haven't entered a specific address here, but now we have different development plans, uh, for this area in Neuss, yes, um, which I could now all check. You can also enter a specific address. It doesn't work in all cases, not in 100% of cases. That's why I would recommend it like this. It's a bit more manual work, but it works very, very well. Um, but it also saves you a lot of time searching for a development plan, and the tool also looks at further information. Should there perhaps be a new development plan or something else? All of this is also checked automatically. And the agent mode is not only relevant for this, but also for your micro-macro analyses. Uh, while you are examining these properties. These micro-macro analyses are essentially something very, very similar. Here too, we go directly to ChatGPT, because even with micro-macro analyses, it can happen that, uh, that a tool has to click through Google Maps, or on some other maps, in order to see exactly what kind of area we are in. How is it here, for example, yes, noise maps. Yes, these are usually not texts, but maps. And, uh, that should, uh, also be taken into account and found by the AI. And you achieve that when you, for example, here, I'll go further up, when you enter a prompt for this location analysis with the micro-macro location for residential at, in this example, this address here. And then we get here, uh, so in the prompt, we have specified the working method, uh, exactly. We say we want absolute data. Um, we can also enter a scorecard, let's say, we'll come back to that later, so that you say, it's particularly important to me that it's very quiet, because what I want to build, or the properties I want to invest in, are residential properties in a quiet location. You could enter all of that, as you wish. And then, uh, we have it here, for example, like this, ne? Micro-location accounts for 60% of the total score, and so on, and then, uh, the agent mode goes on the search, on the journey, gives you an executive summary. Uh, with our scorecard, we get, uh, 78 out of 100 points in this case, um, and get a profile, and get a micro-location analysis. So it has now checked exactly, yes, the next place, the Hoffmeierplatz, is 200 to 300 meters, um, away. So, and through that, there is the possibility to carry out this micro-macro analysis here. And you can use this well as a broker to present it in an exposé at the end. And you can, of course, also use it well as a, uh, project developer, to simply see if it fits with what you have in mind. This works really, really well. Of course, I would always look at the location myself on Google Maps for a moment, but simply to have these numerical facts, it is perfectly suited. Yes. So, and now, now we come to the, to the exciting, very exciting, very, very exciting area. Um, namely, uh, yes, developing the scorecard, which I've already talked about, um, to then fully automate the property acquisition, to some extent, or at least fully automate all checks. Um, if you invest yourself, then you have a purchase profile. I also had a purchase profile generated by AI from Möllenkamp GmbH, Königsallee in Düsseldorf, with Managing Director Dipl.-Ing. Martin Möllenkamp, which could be used. I have a buy-and-hold strategy, but I also have a value-add approach. Um, I want to, uh, minimize risk, and have the following property criteria, such as residential and multi-family houses, residential multi-family houses with at least four units, that I actually look for, in which locations, uh, I search, what purchase prices I have, occupancy rates, and so on. This is already a very, very, uh, yes, very extensive, uh, very extensive purchase profile. Um, if you give this purchase profile, or if you give a purchase profile to a broker, then the broker understands very, very well, um, what you are actually looking for. And the broker can then also give you exactly the properties you are looking for, but only because he knows the properties exactly, because he has all the data and information about them, and because he can match them with his own, his own intelligence, not with artificial intelligence, to what you are actually looking for, and then certain things fit, yes, 28th annual net cold rent or annual, uh, cold rent, etc., then these things fit, but in principle, you always have certain things that are, uh, a dealbreaker for you or not a dealbreaker. And these things, you might have them in mind. Perhaps the broker also knows them gradually. Perhaps it becomes clearer through the purchase profile, because you can imagine it. But if you want to check properties using artificial intelligence, then you must, you must always think when working with AI, you are now giving the AI something, and it has absolutely no idea who you are, what language you speak, um, and what you actually want from the AI. And therefore, it is necessary to build a scorecard when working with AI, and you could also call it a knowledge database, um, where it is stated exactly how you evaluate certain locations, when we are talking about locations now, how do you evaluate a micro-location for you? Yes, you can, of course, simply say, I'm looking for A-location, and the micro-location should also be very good, and that must fit. And that is then something that the broker who sends it to you describes very individually, or individually, uh, yes, decides for himself. And what you also decide for yourself individually. But if you want to do the whole thing with AI, then that's no longer possible. Then there is this, this emotional perspective, or these perspectives, they are no longer there, but you have to say exactly what you mean by that. And that's why I have, um, now developed a sample scorecard, and a scorecard means that an investment is relevant for you if it reaches a certain score. You could build it like this, you can also do it differently. This is just an example. The scorecard was also generated by AI, of course. I simply told it what is particularly important to me and what is less important to me. And then, uh, the scorecard, or the AI, uh, built this scorecard in such a way that I have different categories here. Uh, return and cash flow gives, uh, a maximum of 300 points, but requires at least 180 points for the object to be relevant to me. Location and market, uh, yes, for 250 points, requires at least 125. Uh, building substance and technology, and rental and tenants. Um, this is all something that is output in points here. And then we also need the exact statement, uh, yes, how much, uh, gross return leads to 100 points, in this case, over 5.5%. Um, and 60 points are given at 4 to 4.4%. And then the AI can use this basis, this point allocation, to match it very well with what is in all the data. It can also calculate the data itself if the return, for example, is not included, and can then make this point distribution. And if you have such a scorecard, and as I said, you can create it with AI, it all looks very extensive here. You can simply upload your purchase profile, then add a lot more information with language, what does all this mean, and then this scorecard will be output to you. If you have this scorecard, then it is practically the knowledge database, knowledge base is what it's called, um, to completely draw the purchasing conditions with AI and, um, and, uh, yes, to build it up for the AI so that the AI truly evaluates and thinks about the properties exactly in your sense, and that is, I think, the best time you can invest in building this score workout first for yourself, for brokers, but especially for the AI. And you should do that now, because now is the point, um, yes, now, um, um, now more and more people will use AI for such an examination, and, uh, just do it, spend half an hour with your own purchase profile and build it together, whether for existing properties, whether for residential properties, for plots of land, or for anything else. What exactly are you looking for? How exactly would you evaluate certain things in the purchase process? What is a dealbreaker, what isn't, what can be compensated by what? Put all of that into a document. That's the first step. And the second step is then to, uh, to optimize this purchase process completely, concretely, completely, uh, to, um, to optimize and have it done by AI. And for that, there is now, um, a tool, even from ChatGPT. I'll show you that. You can find it via, um, so it's called ChatGPT Agent Builder. Google, uh, Agent Builder, um, from ChatGPT, from OpenAI, then you'll get to this, uh, this page of the platform. It's essentially something that looks sensible right now, um, but is currently still in the, uh, developer platform, but even as a non-developer, you will quickly understand how it works and can build it yourself. Um, if you don't understand something, just ask ChatGPT, just ask the AI, take screenshots of it, and it will give you the answer, and then you can build it yourself accordingly. And the point is, these automations that you already see built here, you can of course also build them yourself with Zapier, with Make, with N8N, these are tools for building automations. Yes, this is, um, for someone who has never built anything with these tools, significantly faster and much easier. You also have to learn a bit at the beginning. Yes, what does that mean, actually? Do it with AI or watch videos on YouTube about it. Uh, that's very, very quick. Yes, and if I now have the start button, the start point, then it works in principle like this. I enter the prompt that I would otherwise enter in ChatGPT here in these instructions. And in these, uh, in these instructions, you can of course also have the prompt generated by AI again. In these instructions, there is essentially the statement, um, I upload, I upload objects, or documents, analyze the documents for me first, and extract the data for you first. Yes, what we essentially did once before via ChatGPT is contained here. And then, um, it goes to the next step. And in this next step, uh, is stored here, um, is our purchase profile and the scorecard. And then it says, look, you take the data that you extracted before and overlay it with this scorecard and, uh, consider with the help of the scorecard, how many points the whole object gets, and, um, is it suitable for me or not? In this case, it wanted over 650 points, uh, and then you can tell me exactly, is the object suitable or not. That's what's contained here in the end. And then we go into this area here, if the word "Suitable" comes out here, so it's built like that, or the prompt is built like that, that this word is included here. If it is suitable, if it has over 650 points, then it goes into this area, and in this area, the task for ChatGPT is then to look at the object very carefully again and to consider, with which measures, um, what optimization levers do I have here? With which measures can I possibly make the object fit my purchase profile? Can I adjust the rents? So, to adjust the rents, ChatGPT would research how high the rents are in the area. If it hasn't already done so, of course, but can I adjust the rents? Uh, if yes, um, how is it, or could I carry out a vacancy? For example, uh, if yes, how much will it cost me, so that I can agree with the tenants a bit? Could I build an attic conversion? Uh, can I densify here, can I rezone, and so on, and then a solution for it will be output to you. And I have already done the whole thing in advance. Yes, and, uh, it looks like this. Uh, here you can't see right now what the whole, what ChatGPT thought or did, but here we have the short diagnosis first. Why is this object not suitable for, uh, for the scorecard we had? Well, we have a cash flow gap, uh, we want gross, or we have gross 2.8 to 3%, which is less than we want. Uh, and the energy efficiency is extremely weak. We didn't want that according to the scorecard either. And now it gives these corresponding optimization levers. We can adjust the rents. Uh, potential added value of 3 to 6% on the current rent. Uh, main risks, formal errors, contradictions, energy class can reduce possible tensions, political environment. Uh, then we could include index-linked rents for new contracts. We would have a modernization package, um, where, uh, which apparently, uh, yes, corresponds to a subsidy here, a subsidy here. Uh, we can renew the windows, light, light version, add balconies, and so on, yes, very, very many possibilities to simply see if this object is interesting for us after all. And all these topics, um, are output to me by the AI accordingly. Um, and I could, therefore, build them myself. And now I have already announced, we are coming to a so-called super agent, and, uh, yes, we have, I will slightly exceed the time, I apologize, but, um, this is very, very relevant and super exciting, my, uh, AI Jens Spark, this is a so-called super agent. A super agent. Um, the word sounds a bit silly, but a super agent is essentially, uh, a mixture of many, many different tools. You can, at Jenspark, just like at Manus, for example, simply say, uh, I want you to, uh, research these things, then output them to me as a table, and when you have output them as a table, then expand this table with the and the displays and statements, and then also output the whole thing as a website and create a podcast and a video for it, and you can say all of that in one prompt here, and it will know by itself which individual tools it should use and must use to do all of that for you. This means that this tool is also a deep research tool, deep research, like we had with ChatGPT earlier, um, and can do many, many things at once for you. And now, this is new, um, I honestly only used it for the first time last weekend, and then immediately incorporated it into this presentation, um, there is the possibility to build such a super agent yourself. This is something like a custom GPT in ChatGPT, as I said, we had that in the, uh, in the previous presentation. Feel free to take a look at what a custom GPT can do there. Uh, this can do that too. And the point is, it can then simply, um, with this scorecard that I have, and with the information, build a, um, custom GPT as a super agent. I click on it once. Loads briefly. So, and now I'm building a new agent, click on create new, and now I just have to tell it what to do when something happens. So, I'm essentially just telling it, um, if you receive, uh, information from an exposé, um, or anything I upload, then please match it with my purchase profile and my scorecard, uh, which I give you either individually or which is already stored. You can do all of that, as you wish. And then I want you to immediately fill out the entire scorecard, that you immediately, um, check what levers I actually have left, um, to, uh, to get even more out of it. And I can also tell it, then create an executive summary that you send to yourself directly by email and send it to yourself. Jenspark can access various tools. I have, of course, already prepared this super agent here, I can also show it to you. You see, it's very, very extensive. First, the answer. Yes, I have only uploaded these, um, yes, data in this super agent, which concern the object, which we have already seen for the object in Düsseldorf, and then it says, I have received these documents. Before I begin the professional purchase examination, I need the purchase profile and the scorecard. Then I uploaded that too. I can upload all of that to Jenspark in such a way that I don't have to upload it individually anymore. Yes, easy, no problem at all. And then, um, it looks at these six phases of purchase examination with the scoring system and now comes up with an executive summary with the key statements, yes, one purchase criterion was violated, the purchase price is below the minimum requirement of 2 million euros. The object does not fit the purchase strategy. And then you can see here how it used this scorecard. So the object is not relevant for now. Although it is just above the minimum score, it has violated the, uh, purchase criterion. Yes. Uh, but now you see here how the AI actually checked this. The KO criteria must, we have one that is not fulfilled. Otherwise, all are fulfilled. Then we have here in category A returns and cash flows, um, which have been checked very precisely here. So this is always the area from our scorecard. Legal consequences, where we then say, here we want a return of XY. Then it says, uh, how many points can be given here maximum? 50 pieces. But we are in the range of a return of 2.5 to 2.9%, which is below 4%. So we give a maximum of 20 points for this.
The cash flow would even be negative here. That means there are zero points, and so it goes through every single area of the scorecard. Here, also warehouse and market. He has checked everything, so everything that the agent mode also did for us beforehand, that was all checked again accordingly. Um, and this was all here, so in Jamspark this agent mode is practically already included, and this public transport connection and everything you see here was checked automatically here. Then we go into category C, how is the building substance? For this, he checks the invoices, uh, the craftsman invoices and things like that, everything that was in there. The overall result is now, uh, we have not met the criteria in one area. We had a NOG exclusion criterion beforehand anyway. Um, now we go into external research again. What other data, uh, is relevant for us in the macroeconomic situation? This is now phase 4. Uh, then he looks, he goes into the research of the rental prices for the apartments, uh, the purchase prices for the houses. So, are we here in an area, uh, that is, uh, relevant? The average industrial is much, much higher than what we have here, for example. Um, so on this basis, it would now be attractive at first. Uh, then he searches for all the financial capital, the modeling. In principle, I could go through all of this individually. Uh, in principle, um, he takes the scorecard and can research everything automatically for you. Everything. In the cash flow analysis, it now turns out that this doesn't fit here. And then he automatically does a sensitivity analysis again. So, in scenario 1, if we could increase the rents to market level, the cash flow would still be negative. If we increase the rents optimistically, the cash flow would still be negative. And if we reduce the purchase price by 10%, the cash flow would still be negative. He does all of this independently. So all these, um, possibilities that you would have to, uh, then perhaps convert the property into something that is relevant to you. All these possibilities are first checked automatically here. So, fillers, gap protocol, and risks. So, what do we not yet have statements about? Um, no, that could also be asked of the broker again. That comes in here. Then we automatically get a risk heatmap issued. Here are, uh, things very critical. Some things are significant, and some are, yes, are moderate risk. Uh, and we get a market situation report again, have a decision template, yes, with which we can continue to work. And all of this, all of this you get out, just because you uploaded your scorecard, your acquisition profile, and the data about the property. It is also checked with sources, by the way, everything, everything. Yes, and it goes incredibly fast. Jamber is incredibly good at this. He researches everything and only stops when he is really at the end and has a good, good result for you, a good result for you. And you can, of course, also continue to work with this and say, yes, you haven't considered one thing, uh, uh. Um, think about it, we can still do this and that, or you can upload further data and then say, now do the whole thing again. This is a perfect data room for this, uh, to check this property. And you see, I also briefly hinted at this earlier. Um, we have, uh, I mean, I also did this once before, yes, exactly, I asked him to do it again, which solutions could lead to me generating a positive cash flow, um, for example, eviction or something like that. He says purchase price reduction or optimized financing. Uh, for that, one would have to do all of this here. Um, then he says regarding eviction, uh, value turnaround eviction calculated over 12 to 24 months, uh, with termination agreement and and, um, it is very fast, very easy, and with this you can automate everything. I then built a second agent again. Uh, I would like to show you that very briefly again, uh, because, uh, with, um, with Jenspark, you can store certain, uh, certain, yes, um, tools, such as, uh, your email, your email tool, such as, um, a Notion page, for example, where where further information is, how you actually acquire. You could also have your scorecard on your Notion page. Um, you can connect very, very many documents with Jenspark in principle. And I have now told him here, please, uh, do the following, uh, do this whole analysis that we have just seen, and then build an executive summary and send it to me automatically as an email. And I said that in the first prompt. In other words, if I have that in the first prompt, then I just upload all the, um, all the data. So, I have this tool, this system, I upload all the data, and then what we saw before happens. It is completely calculated once, and then, uh, I also automatically receive an email with this executive summary. Why is the building interesting and why is it not interesting? We have, uh, status is KO, category A missed. Yes, unfortunately, it doesn't fit. Critical gaps, solution approaches, price reductions, uh, and next steps, which are indicated to me here. This means you get a property, get all the documents, just put them in here, get an email as an example with the perfect calculation of the whole property, with the executive summary, and you know, is it interesting for me or is it not. Very simple, and that is enabled in Jens Spark. And this is now an example of many. Everything that goes in this area, everything that, uh, yes, everything that requires a lot of data and a lot of research and a lot of extraction, you can do with such a Jenspark user-defined super agent that you can build. And we started building it earlier, it is very, very easy. I could now display the super agent. I could also create it further by simply entering what I want. Very easy. And then you have created it, pull all the information into it, and at the end you get, for example, this email. But you can also say, please access this and that table, enter all of this into the table, uh, so that you simply have an overview of all the properties that have been sent to you. Also super easy and super fast. Yes, I definitely wanted to show you this because I used it in this form for the first time this weekend, and it impressed me very much. Um, and I know a lot about AI. I am no longer easily impressed, but this is really very, very, very, very, very, very good. Um, I can only recommend it to you. And, um, yes, in this sense, we have reached the end of the webinar with a slight, slight overrun, I apologize, um. I would like to point out to you, we have, uh, on 13.11. You can register directly via this, yes, via this QR code. We have the next practical webinar where we will look at, uh, AI tools from the German real estate industry. So, there it will be less about large language models, so about Chat GPT or about Jenspark or about Manus, um, which we have covered a lot today, but it will be mainly about, um, yes, that we, uh, for example, look at Alpha Prompt, that we look at Quirepad, and indeed tools that really use AI from the ground up, from the basis, to, uh, improve something in the German real estate industry, and to get an overview of what is actually out there. Yes, scan the QR code, then you are, um, then you are at the registration page for it. Um, and if you still need or want my contact details, then I would actually have to, uh, show you the corresponding page for that. I'll look that up again very briefly. I seem to have overwritten one page. That was not the goal of the whole thing. Um, I'll look that up again in parallel and include it again. But otherwise, we have reached the end of this webinar, and, uh, should you have any questions about it, I really enjoy this topic. So, this whole thing was also created with an AI, by the way, with Gamma, that's what it's called. Uh, yes, well, now I've overwritten it. That also seems to have happened before. So, you can find my contact details here. You can find my contact details here. If you have questions about anything, if you have an idea how you would like to build the whole thing, uh, if you want to build an automation for it or something like that. Um, yes, add me, so the easiest thing is, add me on LinkedIn. Uh, I really have super, super fun with it. Nilas Möllenk is the name, actually. Nilas Niklas Niklas without a K. I have super fun with the whole topic. Uh, I am very happy about questions. I am very happy, uh, to think along and, uh, and to consider how one can build the whole thing. Um, and, um, I publish on LinkedIn more regularly, sometimes less regularly, but I have, uh, I have built something with which I now publish more regularly, also, uh, articles on how to, uh, yes, how to, uh, uh, use AI for us. So, where things that I have shown today, uh, are then broken down again very concretely with very concrete steps, so that one can, um, so, uh, replicate it oneself. I do that too. I am completely caught up in this whole topic, I must honestly admit. And, um, therefore, feel free to ask me, feel free to write to me, feel free to contact me, um, and of course, above all, also contact me if there is, uh, interest on your side in, in Zeit. Uh, then I will show you that again and we will see, uh, how you can use the whole thing. Zeit also has an interface, a so-called API. An API can be used very well to, uh, yes, uh, connect it, for example, also with Jenspark and with other tools, which means that pulling data from Zeit directly into another tool and then working with AI further is comparatively easy. Um, coincidentally, I know, I know how it works. So, we can also talk about that. Uh, yes, and now I have said a lot more here at the end, and I think everyone has now had the opportunity to, uh, scan this code accordingly. You will receive, um, a recording of this webinar quite soon, and, uh, yes, then I would say at this point, thank you very much, uh, for your, uh, for your participation. I have, uh, now once again, okay, I have opened the questions again. Yes, there are two or three things briefly. Um, owner data via Site is not obtained. Was a question. There is, uh, currently no student version of Site. That was also a question. Uh, we do not offer that at the moment. and a question for the topic Apify. Um, uh, and there is another question for the topic Apify, uh, whether there is a, uh, subscription or whether it is per. Uh, it is different. I think you need a standard subscription, which costs something like $10 a month. Uh, and with this standard subscription, you get, uh, access to almost all tools. Sometimes you need a monthly subscription for the tools again, uh, which can then cost $ sometimes or more or less. Uh, and then you pay for the data or for the query per se, but you pay very little money for a lot of data. I was just told that the, uh, that the registration page for the next webinar is also, sorry, for the next webinar, the link to Jenspark. That is of course also not necessarily intended. Uh, I will have to change that again briefly, uh, or I will send you the registration with the registration link with the, uh, with the recording that you will receive at the end. Um, and we still have, uh, two questions. Is it possible to receive the displayed prompts? Um, I can do that. But it will also take some time for you to receive the recording. That, uh, will come together. Um, I still have to transfer something. That is not yet automated for us. But I will do it. Uh, you spoke earlier about being able to contact property owners. Uh, for that, I need the data. Exactly. I spoke about the fact that you can contact property owners if you are looking for single-family homes, because then you are not contacting people, but the house on the property. That's why this search that I showed from Mide for single-family homes with a lot of space on the property where you can build something else, that's something, uh, there you could theoretically, honestly, I'm not 100% up to speed on data protection, but theoretically, you could then write a letter to the house and through the house you would inevitably reach the owner, because I think, I estimate that 85-90% of single-family homes are actually inhabited by the owner. Um, you could do that through that. Uh, what is the data basis of Zeit? And how is it ensured that it corresponds to reality? The data basis of Zeit are cadastral data, so 2D accurate building and property outlines, and 3D LOD models are placed on top of that. And these LOD models come from the state surveying offices, um, and, yes, describe the buildings with an accuracy of 10 to 15 cm in length, width, height, depth, whatever. And, uh, that placed on top of the, um, cadastral data leads to you having very precise information and very precise data for each individual, uh, property, because we take these 3D models, which are very precise information as, yes, or a very precise 3D model for each individual property in all of Germany. And this information is then, um, translated, yes, so that we measure the facade, so that we measure the walls, the exterior walls, and we also know how many full floors or stories each building has. And that, combined, means that we can calculate how much GFA the buildings have, and from that, GRZ, GFZ, GFA of the properties or existing buildings can be calculated, and from that, with an AI, it can be calculated how the maximum possible buildability of a property is. But we can, please feel free to contact me, then we can have a call, uh, specifically about Zeit. I will show you how it all works, and then we will see, uh, if it might also make sense for you to integrate it into your acquisition basis. Uh, there are super many possibilities and super many solutions, and I think I am relatively creative in that. So, we actually still have many who are still in the call, even with a 16-minute overrun, um, thank you. Uh, I hope, uh, you enjoyed it as much as I did. Um, and I would say, until the next webinar. As I said, I will send you the link, and if you have any questions, please contact me. Um, thank you very much and until then, bye. Oops.