FREE DeepSeek V3.1 Course: Build & Automate ANYTHING

Deepseek 3. 1 the ultimate 1 and a halfhour course. Today I'm going to show you everything that you need to know. Now Deepseek have just released a brand new update. You can see that has just been rolled out this week. So Deep Seek V30324 is out. Now this is a huge boost

in reasoning performance, stronger front-end development skills, smarter tool use capabilities. I'll be showing you how to automate basically anything. Build anything that you want. Use AI agents if you want to. And you can do all of this for free with APIs or just directly in the chat. I'll show you exactly how to get access to it. This is one of the most powerful models in the world. Plus, it's completely free to access. Now, if you're wondering, okay, what are the benchmarks like? What's the difference here? So, you can see Deep Seek version 3 in light blue over here and Deep Seek B30324 in dark blue. You've also got this compared to Qu max GPT 4. 5 which their latest model claude 3. 7 which is also their latest model and one of my favorites previously. And you can see for many of the benchmarks for example like maths deep v324 is absolutely smashing it. The same for Amy you can see right here and the same for live code bench. So on a lot of benchmarks this free tool that you can also use on a free API. Bear in mind, you can't get a free API of GT4. 5 and from claw 3. 7. Sonet is available to use and it is super powerful and you can basically automate anything you want, build anything you want and even create like oneclick AI agents using this powerful

tool. Now, if you want to get access to it, you can get access to deepsek. com. Also show you many other ways to access it right here. The way that you want to use the newest version of Deepseek is to actually go right in the chat here. Then make sure you don't select anything else, right? the don't select deep think R1 cuz that's a totally different model. You're going to be using the main version inside the chat right here. Another way that you can get access to it and I'll come on to this later is you can go to open router and you can see the top trending model on open router is Deepseek V3324. The top apps being used with the API which is completely free to use as well are client and root code. I'll come

on to those later plus what that means and how it can be used. And if you just want to use it directly in the chat for free, you can see this is completely free to use. You can use it inside the chat and then start giving it prompts like you can see right here. So let's do

an example check. test right here. So for example, 9. 11 and 9. 9 which is larger. And it reasons it and it reasons out right here. As you can see, if you go back, you can also go to the compare section and then you can actually compare this side by side versus another model. So, if we for example pull up claw 3. 7 Sonet, we can compare these and you can see for example on the pricing is so different, right? So, for example, for output here, $15 per million tokens, $0 per million tokens, right? Absolutely gamechanging. Let's pull this up versus chat GPT. And you can see the difference in pricing here. Quite drastic. And the other thing to note here is that it will be released open source on Olama. I can imagine pretty soon because Deepseek version 3 is already on there. As you can see, Deep Seek R1 is on there. I think it's just a matter of time. Obviously, this is a brand new tool, so it's not available on there just yet, but you will be able to host it locally. All right. So, if we go inside here, we can also connect it to the search. So let's test this out. And we can also for example deselect that and we can upload images here. Right? So for example if we go onto so if we go to for example a random website like you see right here we'll copy that image and then we'll go back over to deepsek we'll plug that image in like you can see it can actually read images and then use that for it output. So for example if we upload that image and then say clone this and then hit enter we can get the magic back. All right. We can also for example connected search. So on that search that we did we said what happened today and then it gave us a bunch of ideas like you can see also gave us like weather events etc. All sorts of going on all sorts of stuff going on for March 27th. Although I will say some of these results probably not perfect. You definitely want to check this stuff before you start using and making decisions off it. So you can see here for example DeepC can actually code out four websites. So this is actually cloning the website from the image that we uploaded from our site. And if you want to code this into HTML code, just specify it inside the prompt and then it can start building out websites, apps or whatever you want for it. You can also run the HTML here. So if we click on run HTML, it's cloned the content from the site. It's pretty easy and simple. Maybe you want to take it to a whole different level, right? So, for example, here you

can see in the chat what we actually did with this was we said, "Make me a captivating endless runner game. Key instructions on the scene. screen. P5JS scene. No HTML. I like pixelated dinosaurs and interesting backgrounds. " It gave us the JavaScript like you see right here. You can basically code your own Flash tools, right? Let's take that content and then we're going to go over and preview it. We'll take the code. We'll plug it in here. We'll hit play. And boom. Look at that. The game is ready to be played, my friends, and actually works perfectly. So, it's wild what you can do with this. There's so much more I'm going to show you today, but that's just a little sneak peek, and we'll get straight into

it. Big update from Deep Seek as we have a new Deep Seek version 3 update, also known as Deepseek 0324. Some people calling it Deepseek version 3. 1. and it is one of the best non reasoning models out there right now. So you can see the benchmarks here. This is a tweet from Zeon and I'm going to show you exactly how to get free access to it plus how it performs from my own test today. But you can see here that it is actually performing much better versus the previous version. So these are the benchmarks. This is the new version of Deep Seek, Deep Seek V30324 and this is the old version which is Deep Seek Chat. Now, some people are actually comparing it to Claude 3. 7 Sonic, which I'll be doing as well, and this was just announced a few hours ago. Now, if you actually go to the Deep Seek website, you can get access to this for free. And also, I'll be showing you how to get a free API key from Deepseek V3 0324. That is a bit of a mouthful to be honest with you, but we're going to go through this step by step, and I'll show you exactly how to use it, plus what it means, how, you know, how is this different. So essentially if you want to get started with this you can go to deepseat. com then start now and you get access right here. Also it's available inside LM arena. So for example if we go to lmarena. ai then we go to direct chat and from here we're going to select deepseek. All right. So just type deepsee here and you'll see deepseek v324 selectable in the dropown right there. Right. and then you can start chatting it with it and giving it prompts. The other way and this probably my preferred way right now you can

actually get a free API key and you can use the chat directly inside open router and this is free to use as you can see there is a paid version as well but if you want to use it completely for free then you can use it that way too and I'll show you some of the creations that we've made with it in a second. Now the other problem right here is that because the Deep Seek website is updating the server comes back busy quite often. So I've done a few problems with it today. I'll show you what I've created and what I think of it so far versus how it's performing. So, you can see here, for example, the server is busy. Please try again later. I think it's been flooded with people using it and also when these AIs are typically updated. Usually beta they're quite buggy. Anyway, so let's get straight into it and we'll start running through the new update. So, let me show you an example of what we actually built here.

I'm going to pull this up for you so you can have a cheeky gander. So, what I've said is build out an amazing keyword research tool in HTML with room to insert Google AI API keys to generate responses, make it modern and super useful, right? So, I wanted to try and create like a SAS tool on the fly. I will say it was quite slow when I was trying to test it out. Now, if we scroll down and we look, it's created the code, which is awesome. The other thing that I like about this is when you're using tools like Deep See, Claude is the same as well. It has this artifacts feature, so you don't have to run the HTML code externally or preview it. You can just click run HTML. This tool actually works pretty well. As an example of this, we're just going to pull this up and I'm going to grab an API key. a free one from AI Studio, Google AI Studio. And then we can plug this into our tool. Right. So, I'm going to go here. This is the AI powered keyword research tool. They've even named it keyword genius. Looks fairly nice to be fair, similar to what something that Claude would do. And then we'll click generate. And from here, it's generated the responses, right? And we can download this CSV Excel. We've got the generated keywords. It's got some ideas for keywords down here as well with the competition scores, the percentages, cost per click, etc. I wouldn't trust the data that much, but you get the idea. And you can switch between like question keywords, longtail keywords, or normal keywords as well, which is super useful. And yeah, it just created like a really easy SAS tool in one minute. Also, you can plug in an API key. So, I did this earlier inside the chat. You can just grab an API key, plug it in there, hit save settings, boom, shakalaka. We can start generating stuff using this, right? Really easy to do. And let's see if this works. I'm going to put dentist here as well, just to customize it and test like, okay, is this actually working. You see here, generates the keywords with AI. And then, yeah, we got a bunch of ideas for keywords right here. So, pretty simple, pretty easy to do. Created a SAS software basically perfectly first time round. Also, when I try and do this stuff with bolt new, it quite often breaks. That's why I don't really use those tools anymore. Whereas with Deepseek v324, it just did its magic straight off the bat. Pretty powerful stuff. And if we keep going through here, this is an article I wrote with Deepseek. So, basically use this prompt. Quite a detailed prompt on how to create content, etc. Put in some source context about me. And then if we have a look at the output here. So it's created an SEO optimized article with the keyword frontloaded inside the title. The article itself reads pretty nicely. It's also got a CTA with a link directly to my page. And bear in mind this is free, right? There doesn't seem to be a limit on this. If you were comparing it to something like CL 3. 7, Claw 3. 7 is awesome for writing content. But the problem is it does have a limit, right? And if you want to upgrade, then you have to spend $20 a month, which is not affordable for everyone watching this. Whereas, for example, inside Deepseek, deepseat. com, you just go in. It's completely free. You don't need to worry about anything. You got all your chat history back here and then you can get straight into it, right? And it actually writes pretty nice content. Like you can see, pretty easy to read. And also like it customizes the content to us. It's fairly humanized and that sort of thing, but not bad at all. All right. Next up, what I did was I asked it to create an SEO cost calculator with a modern design as you can see right here. So, we got the HTML code back and let's open this up. So, run the HTML. This one was okay. Not bad. It's not as modern as I would like it to be honest with you, but let's check if it works. So, I'm going to click on the drop downs, select an option right there, and you can see it works perfectly. So, it's calculated the cost. Nice little tool to use. You can easily embed that onto your website, customize it to whatever industry you're in, and pretty simple and easy. Now, the other way that you can use this, like I was saying, is you can go over to the chat room inside open router, and then you can use the chat here. And I've actually got better outputs from this quite surprisingly, right? So, for example, if we go to liveweave and we test out the HTML. So, I said, create a beautiful landing page for SEO agency. Kept it really simple. There's nothing really fancy about that prompting style or anything like that. And that's one of the things I do like about this model is like you don't have to go overboard in terms of the prompting. And if we grab the HTML, so we'll copy that. And again, this is free. So you're using Deep Seat V3, the free version inside Open Rita. And if we go over here, we'll plug in the code. And we have that back. It's actually looking pretty nice. Look at that. Let's pull this up. Nice little design right there. gradiated gradiented background. Includes all the information about us. Added some testimonials here and did it really quickly as well. Pretty powerful stuff there. Pretty easy to use. Didn't take long at all and you can get access for free. And I would say it's at the similar level. The only problem that I'm finding is Deepseek server is going to get overloaded and then you can't use it. You can also go to hugging face. hugging face have an option to use deepseek and the new version of it as well. So that's another option and let me show you some of the other things and what people are saying about it. So let me pull this up. It's Deepseek. So someone actually created a app like you can see right here kind of interactive animation which is pretty nice. And then I did see a 3JS code game. Here we go. Yeah. So, this is the new Deepseek model and this actually compares all three models. So, this is a tweet from Depu who says 03 Mini looked good initially but didn't get the physics right but Deepseek with it new V3 update actually gives a better output. Right. So, if we open this up, let's see what we got here. So, Deepseek, Deepseek R1 and 03 Mini. You can see that Deep Seek's physics here in terms of the modeling are much smoother, much nicer in terms of the output. So really interesting to see that as well considering 03 Mini is a much more advanced model and it's an 03 and it's a reasonable model, right? That's the other thing to note about this. Here's another example. So this looks like an app someone's built for the weather which looks pretty cool. Someone built a 3JS game over here. Look at that. That's pretty crazy to be fair that you can build that. You can see it's just one big prompt. So you can see the prompt here. Let's have a look what we got. Make a cool 3GS game. That was all it gave it and it just went off and did its magic. That is wild. Yeah, it looks pretty nice. So, you know, you can code with it. You can create content with it. It's completely free to use. Here's another game that was built with it. So, this is some sort of like missile game. Look at that. 3D as well. Let's go on to open route and we'll just test this out. So I'm going to try the same prompt here. We'll say create a cool free js game. We'll see if deepseek is working directly as well. But before when I tested it, it was not working after a few tests. So you see how it takes so long to respond here. Actually looks like it's coming up with it now. But we'll see what it comes up with. And it's creating the JavaScript inside opener. It's just broken completely. Look at that 3GS game. I'm say, okay, code it in HTML. Ah, I see. So, it's thinking about it. I'm just going to go back and then we'll test that again. So, you can see here it's still not perfect, right? Nobody's going to show you this on YouTube. I just want to be 100% transparent. Like, it's cool. It can create some amazing stuff, but it does break. And you do have to go back and forth with it a little bit inside the chat here. See how slow it is as well. So, it keeps lagging a little bit, but that's to be expected with a brand new sort of feature and update that's coming out. So, let's get it to see create a 3JS game in HTML now. We'll see what we get back in a sec. Open router is still coding it. And also, if you want to use this inside, for example, like Visual Studio Code or something like that. So, you can use a free API. If you download Visual Studio Code, just Google it and you can download it. And then from here you can type in client and client have just updated this with the new API. So if you go into your settings here and then I believe let's just have a look here. Yeah. So if we go to open router and then inside open router we should be able to use deepseek 0324. So you see here it's got deepse chat v3 0324 and then it's completely free. So we can use it like so. We can hit done and then we'll just test this out. I might have to set up a new API key, but we're just going to test it out. So, I'm going to say, okay, create an SEO 3JS game. We'll see if that works. In the meantime, we'll switch back, see what we got back from the chat. Yeah. So, you can see it's coding out here in Deepseek and the new version. So, it's pretty awesome when you think about it. It's crazy that number one, you can get access to DeepSeek, but number two, it's completely free. Whether you're using the API, whether you're automating, whether you're building AI agents, etc., you can do this all for free with open router and the free API key. And then if you don't want to use the API key, you can just go straight back to Deepseek or into Open Routter chat room and just make sure you select the right API key here. What you can also do is like you can compare them side by side, right? So, for example, if we wanted to use claw 3. 7 Sonic and just compare them side by side, you can do it like that, right? Pretty simple and easy. So, let's run this HTML now and see if it actually works. Here we go. That's the game that we just created in one prompt. I'm not even sure what you're meant to do here, but it looks pretty cool to be fair to create that in Oh, yeah. You're meant to collect the rings. There you go. All right. So, collect the pink rings here. 3D game works perfectly in one shot. You can't argue with that. And that's just not even testing the boundaries of it, right? Deep Seat just mocked that up in one go. Here you go, mate. You want your game? Here you go. It's probably better than most Mega Drive games back in the day. So, really simple and easy to do. Pretty powerful for coding. It can write games. It can create beautifully designed websites. If the server is not working inside deepc. com directly, then just go to open router chat room or you can go inside client and use the API key directly here. But either way, you're good to go. And that's exactly how you can use it. I honestly from what I can see, especially with that last 3JS game, like that's looking better than claw 3. 7 Sonic or probably about the same, right? usually as well. 3. 7 Sonic like it runs out of tokens and then you have to regenerate the code or it doesn't work properly, etc. But this has just gone off and done it perfectly, right? See, it even works when it says game over. Pretty cool. So, thanks so much for watching. If you want to get

access to all of my best prompts, tips, workflows, AI agents, automations for email content, social media, AI agents, and you want to make more money with AI as well as save hundreds of hours of AI, then feel free to get that AI profit boardroom community link in the comments in description. If you go to the SAP section, you'll see all of my best latest SAPs. This is all the stuff we've added this month. Prices are actually going up this month, so make sure you sign up now and lock in your legacy price. Also, it comes with weekly Q& A calls. So, you can jump on the weekly Q& A and ask us any questions. And then also inside the community, if you have any questions or you get stuck between the Q& A calls, you can post inside the community and get help from 530 people who are all focused on making more money and saving time with AI. So, it's an awesome community, constantly getting updated, loads of cool stuff in there, and you can sign up link in the comments and the description. Also, if you want to get a free one-to-one SEO strategy session, feel free to get that link in the comments in description. We'll show you how we take websites from zero to 145,000 vis and generate hundreds of thousands of dollars in sales on autopilot. On this free link building acceleration session, you'll get a free custom tailored link building game plan so you can generate more leads, sales, and profits to your website. You'll discover the secrets SEO link building. You can ask us any questions you have and you'll learn how to 10x SEO traffic based on what's working for us and our happy clients like you can see right here. Feel free to get that link in the comments description. Deepseek have just released a brand new model called Deepseek V324. And the beautiful thing about this is number one, it's better at coding. Number two, it's better reasoning. Number three, it's better at logic. These are the main differences. And also you can basically automate anything for free if you use the strategies I'm about to show you. Right. So what you can actually do is if you go to open router. ai then you can open up a free API key for open router and you can plug that into many different tools right so for example you can see here you can actually use it inside root code you can use it inside clone. You can also use deepsee version 3 the new update inside open route to chat room. And today I'm going to show you exactly how you can basically automate anything using this process. Right? So what you're going to do inside open router is you're going to sign up for a free account. Then you're going to go over to keys and inside keys select create key. Now once you've created a key you can then plug that into your settings inside Visual Studio Code. Now if you've never set this up before let me show you exactly how to do it. So you're going to go to code. visisualstudio. com. Sorry code. visisualstudio. visualstudio. com. Then you're going to download this for whatever you know whether you're on Mac or Windows. Once you've done that, then I would recommend you go to extensions. So click on extensions on the left. Type in client and you can install this. You can also install R code. Root code is super powerful as well. And these are both awesome ways to basically automate anything that you want using this process. Now once you've done that, you can then go to your settings. For example, inside client, we can go to settings over here. Select open router. Plug in the API key that you got previously. And then in the settings here, you're going to make sure that you use deepsek chat v324 for free. Right? That's how you can automate stuff for free, right? And then you can also add like custom instructions, what you want, etc. And then if we go inside the chat here and we'll say now okay create just as a very simple example and say create a basic sleek modern SEO tool. All right. And basically we can automate the creation of websites, tools, apps, etc. inside here. Now if you're struggling you can switch between the providers. So right now this is probably overloaded but you can see the API request is now working. So just be prepared that if it's in beta or it's just been released within the last few hours which has then you might have to go back and forth it a little bit but it seems to be working beautifully right here. Whilst that's loading I'm actually going to show you something else as well. So another way that you can automate stuff is if you go to chat. So find deepseek on open router then click on chat inside the chat room here. You can use it for free as well. So we can give it the exact same prompt and we can automate tools directly here. All right. So if we say create a basics modern SEO tool that will come back to us with the code and we can automate the creation of tools, apps, websites. You can even create SAS software using this process. Right? And now you can see it's coding out the project that we want. So really simple and easy to set this up inside R code inside client etc. Some people were probably asking like okay does it include browser control. So if you're using the free API key it doesn't support computer use right which means that you can't use this for browser control directly inside ru code. But the easiest way to set this up if you want like a deepseeek API to control your laptop then you can go to web browser UI set up the GitHub and you can run AI agents in your browser that way. Right? I actually have a few videos on YouTube if you type in Julian Goldie browser use web UI and you can install DeepSseek APIs directly into that. Right? So if you want it to control your laptop if you want the AI to basically start using your browser etc. then you can automate that using this process right here. So you can basically control your browser like you can see and then you can get Deepseek version 3 to just start googling stuff and doing research for you. Even has a deep research option here. You can see how it works step by step. So just get the browser use web UI option inside there. All right. Now if we come back to the project, you can see it's coding away and doing its magic. If we go back to the chat room, it's still coding away. All right. So we can just automate stuff and then do other things in the background. The other option that we have, I just want to test this out first of all before we do it, is we're going to sign in to my N8 workspace and I want to see if N8 have actually updated with the new APIs from Deepseek. All right, so let's wait for the sign in here. I'm going to go to the admin panel. I might need to update this. So I'm just going to go to settings and make sure I have the latest version installed. Looks like we should be good to go on that. All right, if we're going to open this up, we'll see if we can set up AI agents with NA10 as well using the new version of Deepseek. So, let's create a new workflow. Add an AI agent. And then inside the chat model section, we'll type in open router. So, we got that set up. It doesn't look like Deepseek is available free directly inside there. So, if you want the free version of it, it doesn't seem to be available. Let me just check. Oh, there we go. Look at that. So, just don't type in deepseek, right? If you type in deepseek, it didn't seem to come up. But if I type in v3, it comes up. You got the newest version right there, right? And then if we go back here and we're going to go inside the AI agent, we can just automate whatever we want using this process, right? So, I'm going to call this deepseek 33. 1 AI agent. That's saved. And then if we open up the chat in the bottom here, we can basically automate our AI agents using the newest version of DeepSeek. All right. So if we go inside the chat here, we'll say write an SEO article about DeepSeek. You can see it's using the AI agent and it's using the open router model right here. We'll just wait for that to load and that should work. Now, in the meantime, if we go back to the chat room and we go back to Visual Studio Code, that is coding out right there as well. The other thing to be careful of here, of course, is like when you're using this, it may be a little bit slow, right? Cuz it's everyone's going to be rinsing this at the same time. So, just for the sake of making things easy. We can go back to the chat here and yeah, you've got the output. All right. So, it says, "What is a deepseek? " Then it comes up with the details. It's written the content, etc. The article is ready to go. And we just automated that in a few seconds using this AI agent setup right here. Obviously, what you want to do inside the AI agent is really give it like a good system message in terms of what you want it to do. And then when you add the AI model chat model over here, just make sure you select open router and then deepsee chatb324. Right? If you want the free version, then make sure you select colon free at the end right there. Right? And that's how you can get access to this. So, pretty powerful stuff. Like, I've shown you in the space of a few minutes how to automate stuff directly inside the chat, which you've got inside open router. ai. I've shown you how to set up free AI agents using this process. The other thing to note here as well is if you host NA10 yourself or if you host it locally, then this is completely free, right? Then you don't even pay for NA10 if you're hosting it locally or yourself. And also you can use this for free inside client or ru code using visual studio code. Now if we run this. So we're just going to run the command. We've got the page ready to go. We just automated the website. And that was incredibly easy. Right now if you want better results like for me I didn't really like the design there then you can just go back and forth in the chat and ask it to improve the UI, make it look more modern, etc. But between these AI agents really simple and easy to do. Now, the other thing that I think you should be able to do if we go to maid. com is we can automate anything using DeepSeek and the method right here. So, I'm just going to grab this. We'll plug this in right here. We'll sign in. And now inside mate. com as well, we should be able to automate things for free as well. So, what I'm going to do is I'll run over to this DeepSeek R1 content creator. And what you can see with this workflow is that we're taking keywords from a Google sheet. We're plugging that through open router and then we're sending that to WordPress. Right? So what I'm going to do here is I'm going to clone this and we'll set it up with the new version of DeepSeek. All right. By the way, if you want all my best templates, workflows, etc., you can get that inside the AI profit boardroom link in the comments description. And it comes with all my best make. com automations that you can just import along with all my best MA10 AI agents as well if you want to just one click set up this stuff. And so what we're going to do from here is take the keyword then inside open routters module we're going to select my open router connection. Right. And then inside the model section let's see if we can get the new version of DeepSeek. Yeah look at that. Deepseek v324 free ready to go. Boom shakalaka. We're ready to go. We're living the dream here, sunshine. And then we're going to right click this and we'll click choose where star. We'll click choose manually. And we should be able to select our keyword and then run that through the new version of DeepSeek to create the content. So let's scroll down here. We'll select El Dorado Hills SEO and hopefully this should work. So I'm just going to run once, plug it through open router. And you can see Open Router is using the new version of Deep See V3. 1 to create the content. and then it should automatically post that to WordPress. So, in the background here, I'm just going to log into WordPress, we'll wait for this to load. Again, I think because it is the first day of this release, like the APIs are going to be a little bit slow, but if you're patient with it, if you're doing different things in the background, that doesn't matter at all. Now, also, what you can do whilst we're waiting for that to load is we can go back to our NA10 workflow and we can also, for example, select a tool. So we could link our Gmail to this or we could for example create an AI agent that actually plugs content directly to WordPress. Right? So let me show you an example of how this works. So we're going to click on Gmail tool over here. We're going to let the AI figure out who to send to the subject line and also the message to send. And then additionally, yeah, I think that should be all good to go now. I'm just going to double check, see where that sends to. Yeah, I think we should be good there. All right. Now, so what I'm going to do from here is I'm going to say write an email to John@julongi. com. Let me just make sure this is draft, not send. All right. Yeah. So, we'll put write an email to me at julianggoldie. com inviting him to the new Deepseek V3 party this weekend. All right. And we'll see if that works. Now again, the API is going to take a little bit of time to complete, but we should have the outputs back from the first WordPress draft. So you can see here it's already created the first draft from WordPress. And then if we open this up inside WordPress here, we've got the article from Deepseek. And there we go. Look at that. Deepseek V3 automated an article. Really simple. It's got our internal links automatically inserted right here. Boom. And that was just with this one simple workflow, right? So, you can automate anything using mate. com. You could also, for example, use n and that was incredibly simple. All right. Now, you can see it's using the Gmail feature to write the email. So, we'll see where that comes back in a minute. But for the make. com automation, that was super simple. We just automate two blogs from our spreadsheet, went through open router using the new API from DeepSeek, and then plugged that through to WordPress. Now, it might be a bit confusing seeing me switch between nat. com. If that's the case, don't worry because inside the AI profit boardroom, I have separate trainings for each. Right? So, if you go to the classroom over here, we have a whole course on NA10 templates and workflows. So, you can see all our different courses and templates you can just insert if you want to use NA10. And then if you type in make. com at the top here, you'll see all my best automations form make. com, including 12 automations between DeepSeek and Make AI, right? Also got GPT4. 5 AI agents and all sorts of crazy stuff inside there. Right? So if you're a little bit confused right now, don't worry because you know the APIs are so slow that I have to switch between them if it's a YouTube video. Otherwise, it's going to take absolutely ages. Right now, let's just check has this actually sent the message or not. But look at that. Boom. Shakalaka. All right. I love it when it works first time around. I'm not going to lie to you. So, I'm going to stop that right now cuz it doesn't need to go on forever. But basically, what we've done here is we asked Deepseek inside N and the AI agent to just write an email to me at julian. And inside the subject line, the two email address, and also the message, we said, "Figure it out, mate. use the AI to figure that out. It did it. It did its magic. And you can see here it says, "Hey, Julian. " So, it even figured out my name from the email address and it said, "Hey, hope this email finds you well. We're thrilled to invite you to the exclusive launch deep party for Deep Sea V3 this weekend. It's going to be an exciting event filled with innovation, networking, and fun. Here's the details. There you go. And you can just create email assistants, fire off emails for you, or answer emails, whatever you want inside NA10. Super simple and easy, right? You get the point. Like between make. com, between n10, between root code and also the open router chat room, like you can automate pretty much anything you want and you can automate it for free with AI agents and they literally take seconds to build like you can see today that we've done. Yeah, super simple and easy, right? You can build websites, tools, apps, games. You can create email assistants. You can automate content from spreadsheets through open router for free and then send those over to WordPress. Like your only limit here is your imagination. And with the power of Deep Seek and these new updates, this technology is just getting better and better, right? Like you should be looking at, okay, what's one thing that I can automate each week that would save me hundreds of hours? And then you just do that again and again. And you can do it all for free like I've shown you today. And it's really simple once you get your head around it. Right now, if you want to figure out, okay, how do you set up a workflow like this? Let me show you how to build something like this inside make. com. I've already covered how to do this inside NA10 today. So, I'm going to go back inside scenarios over here. All right. And make. com is really good for linear scenarios, right? So, when you're going from point A to point B, right, in a straight line. Whereas, for example, NA10 is better for more complex stuff. If you want to see some of this was a super simple agent that we built today. If you want to see something that's a bit more technical. Let me open up this temp this one for Telegram. So you can see how we've set up Telegram here to basically fire off emails via Gmail. You can also see for another example. Let me pull up another example right here. Want to find another example for you. All right. This one is super complicated. Look at this bad boy. All right. If you want something really technical and complicated that has many different steps, NA10 is the best. But if you want something that's super linear and simple to set up, then make. com is pretty decent. And also, it's free for the first thousand operations per month. Right? Now, if you want to set up a workflow like I did a second ago, then you would just go inside make. com. You're going to set up like, for example, watch new rows. Then from here, you're going to link this to open router. Create a chat completion. Make sure you have your credential set up, right? So you want to set up your credentials like you see right here and then you're going to choose the model that you want to use. Right? So if we type in DeepSeek, we can use latest version of DeepSeek over here. You would add a message. So this is essentially your prompt. And then from here you can just link this to WordPress or whatever you want. Right? So if we wanted to create like a SEO content automation tool, we can do that. Click create a post. Fill out all the details once this loads. So, you fill out all this stuff and then in the space of seconds, you've built out an AI SEO tool, right? Something that you probably would have paid $200 a month for a couple of years ago, right? So, that's how easy it is to set up automations to do this stuff. You can do it with NA10, with made. com, root code, you can do it with client, open router. I also think that very soon, probably give it a week or two, Deep Seek V3 in the new update will be available inside O Lama as well. So there's many different options from here. All right. Now, like I said, if you want to get all of my best automations for mate. com or NA10 or AI agents, etc., you can get that inside the AI profit boardroom. Prices are going up this month. So, make sure you sign up before the end of the month. Otherwise, you're going to lose out on the legacy price. And this community is just focused on one thing, which is making more money and saving time with AI. So, if you want that, feel free to get it inside the AI profit boardroom. All my best automations are in here, including AI agents. There's a crash course to save you hundreds of hours. And this is all the stuff we've automated inside our business. And then also inside the SAP se collection here, you can see all this different stuff we're adding. Like pretty much every single day, we update all of this stuff. I'm going to add a new SAP for Deep Seek and all the automations you can do with the new version of Deep Seek version 3. But you get the point. And then also inside the community here, if you have a question, just post it inside the community and we can help you. So, for example, you can see all of these people posting yesterday and they all got their questions answered. We stepped in, we helped them out, etc. Look at all the updates we've done as well. Right? So, this was an update from 5 days ago. We added tons of new stuff right here, including like MCP agents, NA10 MCP agents, Google trend extractors, etc. So, we're constantly updating this because it's a new technology that's adapting every single day. And yeah, feel free to get that link in the comments description. If you want to get a free onetoone SEO strategy session, you can get that right now. Feel free to learn and book it in. It's a free SEO strategy session. So, it's going to show you how we take websites from 0 to 145,000 visits month and generate hundreds of thousands of dollars in sales on autopilot. And on this free link building acceleration session, you'll get a free SEO domination plan. Right? So you're going to get a custom tailored link building plan to generate more leads, sales, and profits from your website. You will be able to ask us any questions you have. So if you're confused about anything related to SEO, you can ask directly on the call. And you'll learn how to 10x the SEO traffic based on what's working for us. So feel free to put that in link in the comments in description. Deep Seek version 3

versus Claude 3. 7 Sonic. Who wins today? We're going to test this out and see who's the winner. Which one is the best? Now, if you're not familiar with this already, just a few hours ago, Deepseek released V3324. Now, this is available inside the chat. So, you can go inside deepseeek. com, chat. deseek. com, and get free access right there. Or you can go to LM Arena, go to the direct chat, and you can select Deepseek version 3024 there as well. And additionally, if you prefer, you can also grab the API key for free on openrooter. ai or just go to the chat room. So it's openrooout. ai/hat. And then you can compare two different models. So you can see here we've got 3. 7 Sonnet versus DeepSeek version 3. So what we're going to do here is we're going to test them side by side. See, okay, who's the best? Who's performing the best? Which one creates the best prompts? Now the first thing that I'm going to test is its writing ability. One thing to note here is the 3. 7 Sonic is a reasoning model. It has thinking abilities. Whereas, for example, Deepseek version 30324 is a base model, right? So, it's not a reasoning model. It doesn't have thinking capabilities. It should be quite smart, but at the same time, I don't think it's going to be as good at reasoning. All right, but we're going to test this prompt out now. So, I'm going to say create an SEO optimized article for this. We'll put in the keyword and then we'll plug this into both. Right? So you can see Deep Sea working its magic here and Claw 3. 7 working its magic as well. Now if we actually compare these side by side, what's interesting about this is actually it looks like Deep Seek version 3 is totally given up on the response set. I'm just going to refresh that. So it seems to be stuck on processing. That is super buggy. And what I might have to do is just open up a separate tab. So Deep Seek version 3 is now writing as well. We open up both of these. So this is the output from Claude 3. 7 Sonnet. One of the first things you're going to notice here is you see how it says 2023 inside the response here. That is not ideal, my friends. We don't want that. So Claw 3. 7 Sonet seems to be a little bit confused there already. Deepseek version 3 has come back to us. It's frontloaded the keyword. It's included in the first line etc. which is great. Let's have a look at the content from Claude. Also look at this right. So Claude 3. 7 said looking for top-notch SEO training in Manchester. Now the key word here is top hyphen notch. So if you actually look at the outputs here, number one claw 3. 7 is put 2023 for some reason. And number two is using AI fluff words like topnotch. Whereas if you compare that side by side versus deepseeek, this feels a lot more humanized, right? So if you look at the first line, looking for SEO training in Manchester that actually works like no AI fluff feels quite humanized. Get straight to the point. It's linked to our funnel after the first paragraph. All right. So if we pull these up side by side, it looks like Deepseek is actually doing a better job than Claw 3. 7 Sonic when it comes to writing the content. I'm just going to check how long this is. So the content from Deep Seek V3 is 485 words and the content from Claude is 1087 words. All right, so let's just pull these up. What I'm going to do is run them through zero GPT and AI detection tool and we could see which one creates the most humanized content as well. Honestly, if I had to pick both blogs, I'm going to go with Deepseeks because it just feels a lot more humanized. It feels a lot more natural, etc. So, let's take this content and we'll run it through zero GPT and just see how it performs in terms of humanization. So, Deep Sea, this is pretty amazing actually. Deep Seat's content comes out at 0% AI detectable, right? So, the AI cannot detect whether this is human written or not. It thinks it is actually human written, right? So, Deepseek has done pretty well there. Now, let's compare 3. 7 Sonet. So, we're going to take this content and just compare it side by side. Bearing in mind, Deep Seat scored 0% which is perfect. Claude 3. 7 Sonet has come out

at 0%. Human sector as well. So, they've done they've both done really well in terms of random content. I would just say that Deep Seeks doesn't read quite as nicely as using Sorry, I wouldn't say Claude's content reads as nicely as Deep Seeks. All right, next up, what I'm going to do is I actually prefer using these directly in the chat. I think it'll be easier to compare as well. So, I'm going to get rid of Claude right there or XL that. And we're just going to use Deep Seek inside Open Router and then we'll use Claude over here. All right. So, we'll run the next prompt.

We're going to use a reasoning challenge to compare them. So, I'm going to use this prompt here, which says, "There's a tree on the other side of a river in winter. How can I pick it out? " Basically, what we're looking for is like solutions. We're looking for the AI to recognize that obviously apples don't grow in winter as well and that you could be wasting your time, etc. So, let's see how it performs and whether it can actually figure that out. All right. Now, you see claw 3. 7 is actually a lot faster. So, this is still loading with Deep Seek over here, but with claw 3. 7, it's already given us the answer and gotten straight to it. So, in terms of speed, claw 3. 7 is winning. However, this model has just been released, so it is going to be a little bit slower than normal. I'm waiting for this to load, and you can see it's taking quite a long time. I might switch to the paid model if this doesn't work. But so far, I've let this down. Let's just go back onto Deep Seek V3 and we'll use it directly inside the chat. See if that works instead. So, we're going to use the same prompt inside the reasoning model instead. Here we go. So it's analyzing the situation and you can see it's actually got the reasoning ability here. So it's like right apple availability. Apples are generally harvested in late summer to autumn. So by winter, most apples have fallen or been picked unless it's an evergreen or a special variety that retains fruit, which is uncommon, right? So it's figured out, okay, there's a lot of problems with this. It's also really in depth in its analysis. Look at this. like understands the scenario, analyzes the possibility, assesses the river potential solutions as well. So, re-evaluates the initial assumptions as well. It does feel like a reasoning model, even if it's not. If you compare the output of claw 3. 7 Sonnet versus Deepseek, genuinely Deep Seek is thinking this out a lot more. You're getting a better output from Deep Seek for sure when it comes to reasoning. So, I'm going to say that Deep Seek won this reasoning challenge simply because it gave us more solutions. Analyze the situation a bit more and also it was a lot more focused on analyzing the situation than coming up with solutions, right? Whereas, for example, with Claude, it's really short with its response. So, if we take a look here, it's like this is a peculiar situation since apples don't bear fruit in winter, which is great, but it's not really analyzed the situation in as much detail as Deep Seek. If you need to really reason something out, this is going to give you the most logical and best answer. So, Deep Seek wins on that one as well. Now, let's compare on another challenge. What we're going to do here

is we're going to test the search model. So this is web search using DeepSeek. Now if you're outside the US, I'm just going to double check the settings here, but if you're outside the US, you won't get the option for web search. So Deepseek actually has web search, but I want to make sure it actually works. So I'm going to say, okay, what happened in AI news today? So just to be clear here, Claude only has web search for people in the US. If you're outside the US, you won't get that. However, the search service inside DeepSeek is not working either. You can see it says due to technical issues, the search service is temporarily unavailable. So, both of these failed when it comes to that. Now, you could go inside open router and select web search here and use the same prompt. Right? So, if we go inside open router and grab that, open a new room, web search selected, but you can see it still fails from what I can see. So, we've selected web search, right? We've got that selected on and I've said what happens in AI news today and it still thinks it's June 2024. So, not ideal there. I would say in some ways it's better that Claude just tells you we don't have it, mate, rather than wasting your time trying to use a search that actually doesn't work inside DeepS. So, I'm going to say Claude one there, but both of them don't really do that. The other thing to note here is, and I don't know if this is going to be available to host offline yet. I'm sure it's coming to Oama, but yeah, this was only updated two months ago. So, the new version is not here. You can get it through Hugging Fo, but the main thing to note here is that when you're using Deep Seek, it's an open source model. So, if model, you can host it locally. I'm sure it will come to OAMA pretty soon cuz Deep Seek version 3 is already on there. The other option that you have is you have a free API key, right? So, for example, if you're using Claude, you get charged for tokens. It's pretty expensive, right? If you're using the model for API calls whereas, for example, with DeepSeek, you can go to open router, you can type in deepseek over here, select 0324 for free, and then you can actually grab a free API key from this and use that inside open router for coding, right? So you can build like AI agents or you can build automations or you can do whatever you want for free using Deepseek version 3 which kind of beats claw 3. 7 Sonic as you have to pay for that and a lot of people can't afford it right that's one of the most common sort of problems I see on my YouTube comments is like people complaining that they have to pay for this stuff so you get the point like this is open source and number two this is available to use inside Klein Rode open router chat room etc and it's available to use for free as well. So side by side, I would say Deep Seek version 3 is winning now for content creation. It's winning for reasoning. It's winning for the free API key. It lost on the web search test. What else can we test here? So the next thing that

I want to test is actually coding, right? So if we go back to the chat room here, actually coded this earlier. Where is it now? So, I asked it to create a beautiful landing page for my SEO agency, right? And it coded this HTML code right here. So, if we preview this inside liveweave. com and plug that in and it actually created a really nice page, right? Really nice design. Simple, but it does the job. It looks nice. It's clean. It even came up with the brand name, etc. Now, let's compare this versus Claude 3. 7 Sonnet. So, I'm going to give exactly the same prompt. just keep it basic, which is create a beautiful landing page from SEO agency. We're inside the chat here. We'll plug that in and we'll see how it goes. Now, some people are saying that there's only improvements in maths and coding when it comes to Deep Seek. That's an interesting one. I've not seen they've not actually released like the official benchmarks for this new version of Deepseek. So, it's going to be hard to compare, but I've definitely noticed a difference in reasoning. Right? If you compare the old version of Deep Seek version 3, it wasn't very good at reasoning. it did fail in a lot of recent tasks. Whereas, for example, when we looked at that crossing the river riddle before, Deep Sea version 3 actually outperformed Call of 3. 7 Sonet. So, it's really interesting to see that. So, let's see what we get back here. Just waiting for that to load. The other thing that we can test in a separate tab is creating a cool 3JS game. Right. So, if we have a look at that game that we created earlier, this one we take a look. So, we've got the output from Claude over here. Let's take a look. Actually, very similar, isn't it? Look at that. I'm just going to publish this so that we can preview it full screen. So, let's open this up. So, if we have a look through this, I really don't like the way Claude doesn't ask you for an image, but it leaves a little blank space for I never like that cuz it makes the page look a little bit messy. So this is using Clawude 3. 7 Sonet as you can see and the page itself is really thin. So all it's got here is a little title bar, a little image and then that's it, right? It doesn't even fill out that bit properly. Whereas for example, if we go to the Deepseek version, I actually created the full page, designed it nicely, added a footer which the output from Claude doesn't have. Additionally, you can see that we have much nicer title, headings, etc., nice icons. Like the output from Deep Seek is ready to go. Whereas the output from Claude is really poor, right? You wouldn't use that. You can't publish that. It's not ready to go. Now, it does say it hit the max length for a message. So, I guess we could say keep going, but then you're wasting more time. You're going back and forth with it a bit more. It's going to be a little bit more frustrating to use. Next up, we're going to test another coding challenge. So, I'm going to say inside here, create a sleek conversion focused landing page for Goldie agency's automation dashboard. The design should be modern, etc. Here's what to do. So, we'll plug that in and then we'll do the same inside Claude. Open up a new chat and see what we get back. That is not ideal here. I was asked it to create a sleek modern landing page and it's not actually recognized. So, it needs to code something out, right? So, Deepseek has failed on this one right here. Whereas if we go over to Claude, I'm 99% sure it's like smart enough to figure out, okay, this is a coding task, right? It needs to go off and code. And that's exactly what it's done right here. So Claude is already winning by figuring out, okay, this is the user intent of what we want. Whereas Deepseek is feels a bit messy. It doesn't understand what we want. It doesn't have that intelligence to figure out, okay, this is what we're talking about, etc. But yeah, I think overall if you're looking for something that's free to use, gives you good outputs, pretty good at coding, good at reasoning, good at writing content, then I would recommend that you go with Deepseek. But if you are looking for the best of the best, the best UI, the best outputs, the highest quality content, a smarter, more intelligent model that also comes with reasoning, then I would recommend that you stick with Claude. I don't think it's going to be clawed anytime soon. So, thanks so much for watching. If you want to get a free SEO strategy session, feel free to get that link in the comments description. We'll show you how we take websites from zero to 145,000 business month and generate hundreds of thousands of dollars in sales and autopilot. On this free link building acceleration session, you'll get a free SEO domination plan. So, you'll get a custom tailored link building plan so you can generate more leads, sales, and profits from your website. and we'll be able to answer any questions you have. Plus, you'll learn how to 10x your traffic based on what's working for us and our happy clients like you can see right here. And if you haven't already, check out the AI profit boardroom. This is a community focus on making more money and saving hundreds of hours with AI. Right? So, if you want to get my best automations on email and content, social media, AI agents, web automation, automations, crash courses, and SPS, feel free to get that link in the comments description. also comes with weekly Q& A. So, you can jump on the weekly Q& A calls with us, ask us any questions you have, and inside the community, you can post and ask any questions, and then you'll get help from 530 members, all focused on the same goals as you. So, feel free to get that link in the comments in description. Deepc V3. 1 build anything. Today, I'm going to show you how to build anything using Deep. I'll show you multiple different ways and some of the most powerful workflows that you can use with the latest version of Deep Seek V3. 1. All right, so for example, here is an example of a game I actually built using Deep Seek V3. Now, the first way that you can access this and start using Deep Seek and the newest update from it is if you go to deepseat. com like you can see right here, then you're going to go to start now and then inside here you can start using Deep Seek for free. So, for example, if we use a prompt, make me a captivating endless runner game. Key instructions on the screen. P5 JS scene, no HTML. I like pixelated dinosaurs and interesting backgrounds. Who doesn't? All right. We're going to copy this code that we got from Deep Sea V3 right here. And this is how to build games directly. Okay. So, the way that you can start running this code is you can go to editor. p5js. org. or paste in the code from the AI right here. Then we can hit play in the top left. And now we have our game ready to go, right? And we have the pixelated dinosaur. He's having a great time. And then we can start running this. Like you can see if we press R as well. Then we can restart and we're just jumping over the obstacles and building up a top score right there. This should also switch between day and night, I believe, halfway through the code. Like you can see, you're also gathering a score in the top left. And we just created a fun interactive game that's super addictive in the space of one click. Pretty insane if you ask me. And that's how you can build games using Deep Seek or anything you want really inside the chat directly for free. Right. Next up, if you want to start using, for example, like a canvas generator, you can go to huggingface. co/spaces this username/nyhat. Right? So the username is spelled a kh a l iq/ny chat and then you can start using this. So for example if we select from the hugging face model deepseek v30324 we can start building this out. All right so if we say now okay I'm just going to escape off that inside the code here to-do list. All right create a simple to-do list with add and remove functionality. Hit generate just as a basic example to show you. This should start coding out the HTML. So you can see this on the left hand side. Again, this is like a free tool, but you can build out apps and whatever you want. And if we test this out, okay, test deepsee as the example task. Hit add, we're good to go on. All right, we can also, for example, if we clear the history right here, and then we'll say, okay, create a beautiful SEO cost. calculator. Hit generate. Again, that's going to code the HTML on the left hand side over here. And again, this is completely free, right? It doesn't cost you anything to build stuff like this out. It's coding the HTML on the left hand side. And then once that's completed, we'll be able to see a live preview of the tool that we built. Literally just build this out with one single prompt using deep seed. And it didn't cost us a penny. Plus, all we said was create a beautiful SEO cost calculator and boom, shakalaka, we're ready to go. So, you can put in the business type, the competition level, number of keywords to target, number of pages to optimize, hit calculate SEO cost, and then we've got the SEO cost plus a nice little UI right there. Right? And so, you can build tools out with this. You can build apps like the to-do list app. You can build games like we did inside the chat right here. And none of this cost us a single penny, right? Really powerful stuff. So, let's

test something else out right now. So, I'm actually going to go to let's test out on NA10. NA10 is a great place to start building AI agents. We can do this for free as well inside NA10 if you locally host it, right? So, if you host this locally or you self-host your NA10 workplace, I have a video tutorial on exactly how to do that on YouTube or inside the AI profit boardroom. But essentially, we can use this to start building our AI agents. All right. Now, if you want to see how quick and easy this is to do, let me open up Google and we'll set up the stopwatch. All right. So, we're going to go from nothing to setting up a AI agent with Deep Sea version 3 that can just automate stuff for us. All right. So, if we hit the timer right here, we're going to go to create a new workflow. And the timer is on, the race is on. Let's see how long it takes us to build this out. So, we're going to put chat trigger. Here we go. Then, we're going to type in AI agent. There we go. Then from here, we're going to start setting up the chat model. We'll put open router. And then inside the model, we'll type in deepseek. We're going to select v30324, the free API key over here. And then inside the system instructions, we're going to put system message or helpful assistant. Now, that took us 36 seconds. All right, 36 seconds to build out an AI agent that's just like a one-click chatbot. And if we open up the chat over here, let's just test this work. So, we're going to put are you working? That's going to run the API key for open router. Let's see if this actually works. He put me to the test. He put me on the spot here. And boom, shackle. Look at that. All right. So, we said, "Are you working? " And in 36 seconds, we timed it together. You can see that it says, "Great question. As an AI, I don't work in the digital human sense, but yeah, I can help you. " Boom. All right. Now, if you want to make this more advanced, all right, pretty simple stuff. So what we can do over here and we'll add time onto this. All right. So we'll allow extra time onto this and we're going to add in a new tool here. We'll put Gmail. We're going to put send AI can select to from message etc. X off that. Pause the timer. That took us 47 seconds in total to build out an AI agent that hopefully can send us emails. But let's test this out and see if it actually does it. All right. So, I'm going to say send an email to me at juliangoldoldie. com telling him how crazy it is that I just built an AI agent in 47 seconds that can automate my emails. So, let's see if this works. It looks like we might. It says no endpoints here. Let's just double check that actually works. I'm going to switch over the APIs to v324. We'll see if that works. That seems to actually be working. Wait for it to load. If you're using the Gmail, it's sending over. You can actually see what it's doing and how it's doing. So, if you go over here, you can see the output, the response, etc. And we have sent the message. Beautiful. All right. Incredible. We'll put the output right here. It says email has successfully been sent. Subject equals mind-blowing AI agent in 47 seconds. And look at that. We've got the send email right there. Mind-blowing AI agent in 47 seconds. Hey Julian, I just had to share this with you. I built an AI agent in literally 47 seconds that can automate my emails. How crazy is that? The future is here in this world. Let me know what you think. The actual writing is super nice as well. It feels like really humanized and it is way more interesting than most emails I've read this week to be honest with you. So this is just wild stuff. All right, so just to recap here, I've shown you how to build games in one single prompt that work perfectly using simple prompts like this. I've shown you how to build apps and tools that are more beautiful than most software developers can do in like the space of a few clicks. And I've also shown you how to automate and build a chatbot in 36 seconds that's completely free and answers your questions. And also how to build an email agent that automates your emails in 47 seconds and sends emails that are better than humans and far better than most assistants you're going to hire. Right? And we did it in what? 47 seconds. We dived it together. Wow. Crazy stuff. All right, so next up, let's keep it rolling, peeps, because it's not enough to end it there. All right, so what we're going to do here is we're going to go over to Visual Studio Code. Now, if you don't have this set up, I've got full SPS on it inside the AR profit boardroom, link in the comments description, but just go to code. visisualstudio. com and you can download this for free. Once you've done that, then you're going to go over to Visual Studio Code. I personally prefer Ruko to be honest with you. And what we can do in here is we can start automating and building out like for example websites, right? For example, if we go to settings over here, open router and then you can see we can select between the different API keys. So actually I think it's better to type in V3. That seems to come up with the option better and quicker. So we can type in deep V3 and it'll come up with DeepSeek chat V3 0324 colon free. All right. So that's a free API key if you want to use a free API key. Like you can see doesn't support images or computer use, but it can code for you. All right. So we're going to hit done. And then what we're going to do over here is we can say, okay, create a landing page for my SEO agency. All right. Beautifully designed modern plus interesting. Okay. And what we can do inside Recode is this is really good for building projects locally. So, for example, if you got a big website that you want to automate with AI, then you can use the API key that's free from open router, plug that into root code and visual studio code and then start automating and building stuff out and it shouldn't cost you a penny, my friends. All right. Now, this is a beta API just came out like I think about 24 hours ago. So, it may be slower than most things that you use, but it's free. You can build it locally. It doesn't cost you anything to do. It's very quick and easy to use. You don't need any coding experience and you can just automate and build websites like you can see right here. So let's wait for this to load and we'll see what we get back. So yeah, you can see now it started coding out the project. It's even come up with a name for SEO agency. So it's put Elevate SEO and it's just going to start building out the HTML, the CSS and the JS. So this is really powerful. You might be asking as well, can I use this for rebuilding my website as well? The way that you would do that is you would take your existing content, you would download it as a project and then you can open up that project folder inside R code or client or Visual Studio Code and edit the website from there. Now, always keep a backup. This could mess things up, but that's a cool thing because if you download it and use it locally, then you can edit it later or you can push it to a GitHub or whatever you want, right? Public, sorry, a private GitHub and host the project files right there. But it's so easy to automate and build stuff, for example, websites or land pages directly using this process. Pro tip for you as well, just whilst we're waiting for that to load, is that if you actually go into open router and you select Gemini 2. 5 Pro, you can use the latest API key from Gemini 2. 5 Pro. And that's even more powerful for automating and building stuff offline than Deep Seed version 3. But if you want to build out websites or build anything with DC version 3, go ahead, my friend. I've shown you exactly how to do it. All right, so it's building that out step by step like you can see right here. Really easy and simple. It's now coding the CSS. So it's got the HTML, then it's going to do the CSS. You can switch between the tabs at the top like you can see over here. And that does not take long at all. All right, so I've shown you how to build agents, how to build websites and landing pages. I've shown you how to, for example, build out games, shown you how to build out email assistants, and also apps as well. All

also how to build out apps as well. All right, last thing that I want to show you is how to build out workflows and automations using make. com and Deepseek. All right, so if you want to do that, pretty simple as well. I would actually say that make. com is easier to get your head around than n. And this is a free tool if you only do 1,000 operations per month. What you do is create a new scenario over here and then you can just start building out whatever you want using for example like Google sheets or whatever and an open router. All right. So if we type in open rout over here create a chat completion you can connect your open router API key to this module over here. Then inside the this section, you're going to type in DeepSeek. And as you can see, you can select between these free models of Deepseek. All right. So, what you're going to be using if you want to use the latest version of Deepseek V3. 1, you select this option right here. It is free to use. You can hit save. You add a little message. We add the message roll as user. And then you can connect this to, for example, like WordPress. All right. Create a post. Boom. Shack lack. You can just automate stuff like that, right? If you want to see an example of that in action, I'm going to discard that. Number one, you can actually get my best make automations inside the AI profit boardroom. So, if you actually type make. com here, go to the classroom, we have 12 different make AI automations right here. So, for example, we've got a blog creator and a Telegram bot, but we've also got 10 more make templates right here that you can just import if you just want us to give you the templates, right? But if you want to see an example of it in action, let me show you how that works. All right. So, if we scroll down here, we're going to take a look. We've got the Deep Seat V3 content creator example. And let's just check what we got here. All right. Output and HTML. Okay. So, we've got a Google sheet with a bunch of keywords that's going through Open Router and it's using DeepC V3 as you can see. And then that's going to plug that over to WordPress. All right. So basically we're automating content creation and we're taking a Google sheet creating AI content posting onto WordPress. Now if you want to test an example and you want to see okay how do you do this? So you can choose a keyword manually off the list. So we'll choose manually over here. By the way I always recommend like content quality control in your content before you publish it. But just as an example we can put like the keyword new SEO from our spreadsheet over here. And then we'll just run this through open router and the example workflow right here. All right. So, what you can see now is we've built out a very linear workflow where we're taking keywords from Google Sheets. It's now going to create the content and then it's going to go off to WordPress. Now, if you want to see an example of what I built yesterday with that whilst it's loading cuz it is going to be quite slow. It's a beta API. Everyone's using it for free. All right? So, it's going to be a bit slow when you're using this stuff. But, if we go to the post section over here and you want to see an example, let me show you an example from yesterday. So, this was created yesterday when I was messing around with this stuff. We'll click on preview. And if we open this up, we've got the content as an example right here, published onto WordPress, right? Really simple and easy. We should use the same workflow as we've got right here. And it was simple stuff, right? That is super slow, but again, it's because everyone's releasing it and using the API key and also it's in beta version as well. So, you now know how to build anything with AI, right? Just to

recap, you've got Deepseek and the chat. You've got any chat and the hugging face canvas right there. You got none one-click AI agents and you can build pretty much anything you want with that. You can use make. com create nice little linear automations like so. You can go on to Visual Studio Code and Recode and use the API key from DC 3. 1 right there as well. So, anything you want to build is right there. The only limit is your imagination and time. And once you set up these automations, they do change everything for you, right? They change everything for your business. They save you hundreds of hours. They're really easy to set up and you can even just download the templates from our community and then import them right there. Thanks so much for watching. If you want to get all of my best workflows, templates, etc. using DeepSeek, we've got a 3-hour course in there on how to, you know, how to make money and save time with AI and Deepseek. We've also got courses on Manis and NA10 agents and everything else. Feel free to get that inside the AI profit boardroom. Prices are going up this month. It's a community dedicated to making more money and saving time with AI. So make sure you lock in your legacy price now before prices go up. And also inside the classroom it comes with our best automations on like social media email 10 agents AI trends and updates automations and templates crash course and AI plus all of our best SPS and workflows get updated pretty much daily. So if you want to get that link in the comments description also comes with a community so you can post in the community and ask any questions you have and get answers to your questions like you see right here. And then also you can jump on the weekly Q& A if you want to jump on live call with us and ask us any questions you have. Link in the comments. And if you want to get a free one to one SEO strategy session, feel free to get that link in the comments description. We'll show you how we take websites from zero to 145,000 business month and generate hundreds of thousands of dollars in sales and autopilot. On this free link building acceleration session, you get a free SEO domination plan. So this will be custom tailored to you and your business. We'll be asked to answer any questions you have onetoone and you'll learn how to 10x your traffic based on what's working for us and our happy clients like you can see right here. Feel free to get that link in the comments in description. Google Gemini 2. 5 versus Deepseek V3. 1. All right, so in the last 24 hours, Google Gemini have just released their latest model, which is Gemini 2. 5 Pro Experimental. As you can see right here, you can actually get free access to it and you can also access Deep Seek as well for free. So, they have Deepseek V3. 1 and that is available to access at deepseat. com. You can also get free APIs for both of them and we'll be testing those out in a second. And basically what we're going to be doing today is just comparing them side by side. So, these are the two latest AI updates, the two biggest ones in the game I would say. And today we're going to be testing them out side by side and seeing which one performs the best. Now, the first thing that we're going to kick off with because I like to give AI a challenge is by coding a game. All right. So, let me pull up an example right here. What I'm going to say to both of these models is make me a captivating endless runner game. Key instructions on the screen. P5 JS scene, no HTML. I like pixelated dinosaurs and interesting crows. Now, I could use it inside Google Gemini, but this is like the paid version, right? is the advanced paid version. I want to make keep it fair. I want to keep it even Stevens on this comparison. So, what I'm going to do is I'm going to pull up Deep Seek V3 side by side versus Gemini 2. 5 Pro and compare which model performs the best. Now, one thing to note here is that Deepseek version 3. 1 is not a reasoning model, right? Whereas Gemini 2. 5 Pro is a reasoning model. So there is a significant gap between them, but I've been getting this request to compare them both side by side and compare the latest recent models. So let's see how they perform. I'm going to hit enter on both of them. So we'll give him exactly the same prompt right here. The other thing that I was struggling with yesterday, I don't know if anyone else had the same problem as soon as this came out, was that actually with Deepseek V3. 1 after they released a new update, tons of people were on the website, right? And so the servers were absolutely rinsed. It was super slow responding to us. So, let's see if it gives us better responses today and how it performs. Here's an example of the difference between a thinking model and a base model. So, this base model with no thinking, it just jumps straight into answering the question. Whereas, for example, what you can see with Gemini 2. 5 Pro is that it really thinks things out before it does anything, right? And it's going to spend about 10, 20, maybe even 30 seconds doing that before it finally comes up with the output. So, we've got this back right here. But we've got the example and it's finish the outputs before Deep Seek, so it's actually a lot faster. Bear in mind, this is free, but Gemini 2. 5 Pro is a lot faster at getting back to us and typically smarter as well. And it gives us instructions on how to run it as well. So, you can see how much slower Deep Seek V301 is. Now, what we're going to do is we're going to test this out. So, we're going to copy the JS from Google 2. 5 Pro Experimental. We'll plug that in and we'll open this up. All right. So, we're going to hit preview still. Open this bad boy up. See how it performs. And there we go. We've got the game ready to go. All right. That was pretty amazing. Incredibly easy to set up. Works perfectly. Actually quite a fun game as well. That's addictive. So, I'm going to close that now. And now we have the output back from Deepseek as well. So, let's copy that JavaScript over here. So, let's go into this. We'll plug it in. We'll open this up. So, this is the version from Deepseek instead. Let's see what we got. Not bad, actually. Which one would you prefer? I actually think that look at that's not bad. It's quite hard to see the score in the UI right there, but I do prefer the design. Like, it's got more flying objects. For some reason, they put game over there when we didn't have a game over. has got differences between night and dark, but it's broken. Look at that. I've not done anything and it just broke and said game over for no reason. It seems to switch between night and dark, like in between each night and day, in between each go, but there's not many enemies coming here as well, so it's not as addictive as a game. All right, so I'm going to say Gemini 2. 5 Pro one there, but not bad at all. I'm impressed by Deep Sea V301's response right there. Pretty good stuff. Next up, what we're going to do is we're going to compare this for the content creation. All right. So, I'm going to grab an example prompt from the AI profit boardroom and this is going to be my content prompt. All right. So, we're going to grab this. So, we'll copy this as you can see. So, this is one of my favorite prompts for writing SEO content. And we're going to run this through Gemini 2. 5 Pro, as you can see. And we'll put keyword equals SEO training in New York. And then we'll do the same inside DeepC V3. And we'll see which one creates the best content. One of the strange things here is like Deep Seek has just gone off and started creating a HTML page, which doesn't really make sense cuz we only want an optimized article. I know why. It's because on the prompt it says creating HTML at the end. That's okay. All right. We'll see what the performance comes back with in a second. For sure, Gemini, even though it's a thinking model, this is way faster than DeepSeek. Look how much quicker it is responding versus Deep Seek. This already finished. Deepseek is still going. All right. So, we're going to test this out now. We'll grab that content, the HTML, and we'll plug it into the preview over here, and we'll see which one performs the best. All right. So, if we compare the titles, so we got the Gemini 2. 5 Pro output over here, and we have the output from Deep Sea version 3 on the right hand side. Okay. So, if we compare the output, first thing that I would say is that the title is pretty bad from Gemini Pro, right? So, it said real SEO training in New York. Stop guessing, start ranking. Pretty average to be honest with you. SEO training New York, the fast track to dominate in search. Not bad at all. Honestly, Claude can write much better headlines than both of these, but you get the point. And then what we're going to do from here is we'll compare them side by side. So, if we look at the first line, Deep Seek just feels a lot more humanized in his content writing. So, for example, we see here it says, "Need SEO training New York that actually works. Not just theory, but battle tested strategies from someone who's built a sevenfigure agency. " like that is not bad at all as that's better than most humans could do as an introduction. If we look at this, it's like looking for effective SEO training. Effective being like a weird rule because your website's buried somewhere on page 10. Okay. Tired of SEO gurus selling you fluff. Feeling overwhelmed by conflicting advice. Yeah, I get it. I just don't think that's as convincing versus deep seats output right here. And then I really like this bit. Says here's the truth. Most SEO courses waste your time. Mine won't. and it's all personalized to me and what I sell and it's already selling me from paragraph one. So I would say the output from Deep Seek version 3 actually wins in terms of writing content humanization. I would say both are not as good as the typical content that I get back from Gemini 2. 5 Pro but you get the point. So in terms of coding and this makes sense. building stuff out, Gemini 2. 5 Pro definitely seems a lot better, right? in terms of writing content and humanizing it. Deep Seek version 3 is outperforming both. All right. So, let's come on to another example and this time I'm going to say there's a tree on the other side of the river and I need to pick it apples in winter. Okay. And then we'll say, but the river is frozen. What do you recommend? All right. And what we're looking for here is it's like a reasoning challenge. So, we're trying to figure out, okay, can it come up with solutions? Can it figure out that the trees actually don't have apples in winter and that sort of thing? But we'll see what it comes back with and see which one. Now, honestly, Google Gemini 2. 5 Pro should smash this. All right. So, you see here how the first thing the Gemini 2. 5 Pro recommends is like assess the apples first, mate. Are they like even worth it? Cuz most apples ripen in late summer and winter. Apples still on the tree in winter are likely frozen, rotten, overripe, or damaged. All right, so first things first, like why would you even be picking apples in winter, mate? That's what it's saying. Whereas, for example, if we go over to Deep Seek version 3, he just doesn't figure out. So, let's check the ice thickness. Let's get over the river. It doesn't really recognize that actually in winter there are no apples on the tree. So you can see the difference here. This is certainly a lot better for reasoning, a lot smarter also for speed here. It's a lot faster, right? It's a lot faster when we get the outputs. So let's keep going right now. So in terms of just to recap here, in terms of coding, Gemini 2. 5 Pro wins, right? For reasoning, Google wins. And for writing content, Deep See version 3 wins. So now what we're going to do is we are going to test this out for the API. All right. Now the way that we're going to do this is I'm going to go over to open router keys and I've created a API key from open router. All right. And then what we can do inside Visual Studio Code is we can say to root code inside the settings use Gemini 2. 5 Pro experimental for now and we'll say create the best possible SEO ROI calculator you can both for UI and functionality. All right. And that's going to use the API key from Gemini 2. 5 Pro as you can see. And you can see here that actually the API request has failed. So even though this key is free to use inside open router, it's actually not working inside client when we test out. Now if we switch to the settings and we'll test if deepseats works. All right. So, we'll switch over to DeepSeek. And then we're going to use V3 0324, which is the latest update. And we're going give it exactly the same prompt. Start new chat. Same prompt. We're using DeepSeek here. We'll see if this works. Here's a moment of truth. Which API key works? Taking it sweet time. Yeah. So, you can see here it's finally getting back to us. It's super slow to be honest with you. If you're using the free version of DeepSeek, super slow. Look how slow that is to start creating stuff. Now, let's test out versus Google. All right. So, we're going to go over to select Google Gemini inside the API key section here. Just going to cancel this. So, we'll cancel that task. We'll go over to the API key. And then what I'm going to do is select Google Gemini. I'll grab an API key and make sure that we can use 2. 5 Pro Experimental. Is that available here? Actually, can't see it. Yeah, we can't use 2. 5. And let's have a look inside R code. Can we use 2. 5 yet for Google Gemini? No, we cannot, my friends. All right, that settles it. So, Deepseek might be slow on the API key, but it actually responds. All right, it actually works. Whereas, if you're using 2. 5 via Open Router as an API key in client or Visual Studio Code, you can't use it, right? If you're going to be coding with these tools, then I would recommend DeepSeek V3324 simply because it actually works. whereas Google's API is not available inside client or root code yet and also with open router the API call requests just don't work yet. So that gives you an idea. One thing I want to check as well is if we compare these side by side it's not available yet but I think that will come soon which is deepseek v3. 1 right so for example deepseek's models are open source which means that you can host them locally. So, for example, the last version of Deepseek V3 is available to host locally with Olama. You can't host V3. 1 yet, but I think that is coming. So, give it a bit of time and that'll be available, I reckon, to download and start using straight away as well. Now again just to be clear here you can use you can select Gemini 2. 5 Pro on open router as the API key but it's not working when you call it. So if you go into root code here we'll select Gemini 2. 5. All right save or done. We'll give it the same prompt. Start a new chat. When I checked it was not working. All right. So, let's just double check. Actually, it seems to be coming back and working now. Fair play to it. Oh, yeah. So, I suppose maybe it's a little bit temperamental, but that seems to work inside Root Code to be fair. So, actually, it seems like Open Routter and Root Code work really well, but client didn't seem to work right there. So, if you're going to code, Gemini 2. 5 Pro works, but use it inside R code. Don't use it inside client. And then you can get the API keys. And I think that'll be much better for creating content and coding. It seems to be a lot faster than DC version 3's API key as well. And again, it is free to use as well. So, let's see what it comes back with now in a second. Wait for that code to load. But then it runs out. Look at that. It runs out right there. Yeah, look at that. So, we actually just building a simple SEO RAI calculator. The API request gets exhausted. And also, for some reason, it says it's using Gemini 2. 0. O Pro experimental, but in the settings we've selected 2. 5 Pro experimental, so that doesn't make sense either. Just something to be aware of. It seemed to get itself back on track there, but it seems super buggy, quite slow, quite buggy. I would be careful using that for now. If you want something super reliable, just use the older versions of Google and you'll probably get better outputs and better response rates. All right, so thanks so much for watching. If you want to get access to all the prompts, tips, workflows, my best Asian workflows, etc., You can get that inside the AI profit boardroom link in the comments description. Prices are going up at the end of the month, so make sure you sign up now. This is a community. This is a community dedicated to making more money and saving time with AI. And also inside the community, you can post any questions you have and ask 543 members for help. You can also jump on the weekly Q& A, ask any questions you have. And inside the classroom here, we have a crash course on all my best AI systems for saving time, making money, along with all of these SAPs, including, for example, a 3hour course on DeepSeek, which you can see right here. All my best AI agents and Deepseek automations. We've got all sorts of stuff inside here, including MCP agents, root code, computer use, etc. So, if you want to get the latest cutting edge stuff, all of the best stuff is inside the AI profit wardrobe. And if you want to get a free one to one SEO strategy session, then feel free to get that. We'll show you how we take websites from zero to 145,000 visits this month and generate hundreds of thousands of dollars in sales and multiple on this free link building acceleration session. You'll get a custom tailored game plan. We'll be able to ask any questions you have.