start	end	text
160	3066	This is a full social media content machine.
3066	7588	Four AI agents that research, write, design, and publish posts for you.
7588	8961	Watch it work right now.
8961	16044	This content idea, five signs your agent stack is overengineered, is turning itself into a finished Instagram carousel.
16044	22845	Atlas found the angle Vera is writing the slides and in about 2 minutes, Kite renders all of them with just a few clicks.
22845	26448	And here's the thing, nothing goes online without your approval.
26448	29904	You check the words first and you approve the final post.
29904	32426	The agents do the work and you keep control.
32426	34699	Today we are building the entire thing from the scratch.
34699	36813	Every prompt and template is linked below.
36813	43315	If you'd rather skip the 4 plus hours build, there is also an auto installer that can set up everything for you in a matter of minutes.
43315	45556	Hey, Larry here and welcome to the channel.
45556	51510	Today we're building Cadence, a content operations autopilot run by four specialists you just saw.
51520	56751	Packed with over 50 beautifully designed templates, Atlas researches and posts your ideas.
56751	60284	Vera writes every slide, caption, and hashtag for you.
60284	62296	Then Kite does the finished designs.
62296	65818	Once this is done, Orion ships them to your social media platform.
65818	71892	And above them all is an orchestrator agent that can take your orders in the Telegram chat and route every job down the [music] chain.
71892	74205	If you post content regularly, you know the hassle.
74205	76756	You stare at a blank page hunting for [music] an idea.
76756	80954	When you finally get one, now comes the research, then writing slide after slide.
80954	86642	They're making it look good in a template followed by the caption, the hashtag, the scul and all that.
86642	90714	Now, Cadence orchestrates and eats up the entire chain in a matter of minutes.
90714	93309	You tell the agents once what your brand is about.
93309	103934	From then on, one click generates fresh post ideas for you or you type your own rough thought and they build the entire story for you from idea to publish post all handled in a few clicks.
103934	105413	Then your post is online.
105413	108545	And here is where this build beats every other AI slide tool.
108545	113510	Normally, you would generate slides with an image model and you would pay for every single slide.
113520	118149	And even fixing one word means you pay again to regenerate the whole image.
118159	121269	Cadence doesn't touch an [music] image model at all.
121269	127155	Every slide is built from a beautifully designed HTML template with real code, not with AI pixels.
127155	128657	So, every edit is free.
128657	134757	You can grab any elements, change the text, the size, the position, and it rerenders it in a matter of seconds.
134757	138493	Meaning you have unlimited revisions with zero cost per slide.
138493	141731	So your money goes into the words, not into the pictures.
141731	144944	The dashboard shows the whole operation in one glance.
144944	154390	Every number pulled from your own agent's database where every agent logs its name, the task they performed, the AI model they used, and exactly when they performed that task.
154400	156790	So there are no fake metrics anywhere.
156800	158358	My favorite part is the studio.
158358	168544	You can edit every slice text or grab a single element, move it, resize it, rewrite it, plus even the phone preview, a template library, and some that carousel into a video rule.
168544	177181	We would also build a published archive where you can see all the posts that you've generated so far and published, and also a calendar tab where every schedule content can be seen.
177181	184070	We would also have a configurations page which would hold your brand name, handle, voice, and it flows into every word the agent writes.
184080	187618	Now, let me give you a live demo and walk through of what we are building today.
187618	191233	So on the dashboard you see the total number of runs that the agents have performed.
191233	194138	The number of ideas that we have generated in this setup.
194138	195910	The number of posts that we have published.
195920	201119	In my case I just have one because I used this to test for the tutorial and the percentage of runs that have been successful.
201119	205204	Now here we have an agent activity that is pulled from the agents activity database.
205204	216107	So you can see currently on Friday I did a lot with the agents because I was building the setup and that is why you see that this is basically going up and on the right side you can also see which of the agents have currently the largest workload.
216107	223350	So in my case for instance these are Vera who is my content writer and Kite who is a developer because those are the two that were doing most of the work so far.
223360	229146	Now when you come down here you can also see a summary of what the agents have been doing all pulled from the agent login database.
229146	231160	Now the magic happens in the ideas tab.
231160	235484	Here you can see a few ideas that the agents generated for me because I'm doing stuff with AI.
235484	239440	So I just made them generate ideas around AI automation and stuff like that.
239440	246093	Now here you can put in your own idea whatever idea that you have or when you don't even have an idea you can tell the agent hey generate some ideas for me.
246093	250077	So let me just click on generate some ideas and let me see what ideas are going to be generated.
250077	257581	So here you can see that Atlas who is our researcher is the one that is going to look for ideas around what we are building and what we haven't posted before.
257581	266326	And this is going to trigger Atlas who is our researcher who is going to basically look for ideas of what we can post based on what the agents have learned so far about what I'm building.
266326	268646	And then you can see that they generated five ideas.
268646	271590	So the first idea is automation fails at the handoff.
271600	278056	We also have some ideas like your agent should run the test it claims to fix which is going to be a good one because the agents hallucinate a lot.
278056	282390	Now just to demonstrate an example let's say I want to write some slides on this idea.
282400	287270	All I have to do is to just click on promote and then here I can put in a number of slides that I want to put in.
287280	290903	So for instance I want to go for eight slides 10 or whatever number you want to go for.
290903	296179	So what you have to remember is that the first slide is always going to be the hook and then the last slide is going to be the CTA.
296179	298977	So the main content is going to be between the hook and the CTA.
298977	306047	So here if I go for 10 slides or let's say eight slides that it means that I'm going to have six content slides with one being the hook and one being the CTA.
306047	309129	And then here I can decide if the agent should do a deep research.
309129	317401	So for instance if I click research with perplexity then the agents are going to do a deep research through perplexity to really find the right content for this job.
317401	322619	And then here I also built in a sort of a steroids mode where the agents are going to write more punchy slides.
322619	325965	And then when you are done you can just click on write eight slides.
325965	329501	Now what is going to happen is that basically Atlas is done with his job.
329501	332903	Atlas did the research right and now Vera is going to take over.
332903	336199	Vera is the AI agent that does the writing of the content.
336199	339765	So let's wait till Vera is done with the research and have the content ready.
339765	340397	All right.
340397	342061	So Vera is done with the research.
342061	348150	Remember we asked for nice slides and Vera is basically giving us an idea of what the content on each slide is going to be.
348160	351130	Basically you can see the content that is going to come on every slide.
351130	357270	If I do not like the slide and I want to refine the slide, I can click on refine copy and then the agents would basically refine this based on what I tell them.
357280	361371	Now, assuming I'm fine with this and I want to promote this, I can click on approve and pick a templates.
361371	366777	Remember that the contents that the agents did is basically from the idea of what the content should look like.
366777	373048	But here, I have a pile of beautifully designed templates that I'm going to give to you guys, which you can just copy without you having to design everything yourself.
373048	376711	So, what we're going to have to do is just look for whatever templates we want to build with.
376711	379928	Now, because my brand is orange, let me go with this template here, 10 count.
379928	382340	Now what is going to happen is I'm going to click fit copy to this.
382340	383730	Now why do we do this step?
383730	386870	Because every template has the number of characters it can support.
386880	392113	So assuming the number of characters is way more than what a template can support then the design basically looks ugly.
392113	403625	So what Vera is going to do is that Vera is going to look at the template that we have picked and adapt the text that goes onto the slides to match that particular template and then Vera adapted the slide text to the template that we picked.
403625	409347	So here I'm just going to click on render this and then this is going to trigger another agent called kite who is basically for design.
409347	416235	So when I come here you can see that the slide is ready and I can click to open this in the studio or you can also come to the studio tab and this will show you the slides.
416235	419730	So when I click open in studio you can see the slides that the agents generated.
419730	424130	So that you can see that I have eight slides basically tailored to exactly what we did.
424130	436309	Now the beauty about how these slides are generated is that typically when people are generating Instagram slides you need to get an image generation agent or an an image generating model that is going to cost you for every slide that you generate.
436319	441510	And the most painful part is that whenever you want to change any text, then you need to pay for every API call.
441520	445609	The beauty about what we building here is that every slide is rendered as an HTML file.
445609	452627	That means that when you come here and click on fine-tune the slide and I pick on any slide, I can basically edit and add my name Larry here.
452627	455468	I can do whatever I want to do without having to pay for anything.
455468	461575	What you can even also do that I also added is that you can also tune the slide to be left to up down.
461575	462649	You can reduce the slide.
462649	463911	You can change the font size and everything.
463911	466436	And then when you're done, you just click on save and this will be done.
466436	470562	Now assuming you're done and you're basically happy with all the contents, then you can promote this.
470562	474368	Now you can also convert this into a real where you can click on animate this carousel.
474368	482733	You can animate all the slides that are going to come one after the other like a real with a 4 is to 5 aspect ratio or you can also create a full reel with a 9 is to 16 aspect ratio.
482733	489687	Now assuming I'm done and I'm happy with what I've built so far, I can just come here click post now and then in my case I have already configured Instagram.
489687	491227	So I can click on post to only.
491227	496904	And then the agents are going to warn me, hey, are you sure you want to post this image to is I'm going to say yes, post now.
496904	502871	And then the image is going to be pushed through a platform that we're going to be using, which is called Buffer that connects to all the social platforms.
502871	505744	And then this will be pushed directly to Instagram for us.
505744	510454	And now I get a notification from Orion, which is our publisher, that the post has been pushed to buffer.
510454	512961	So in a few minutes, we should see this directly on Instagram.
512961	514214	And right then you see it.
514214	517240	So this is a test account that I created on basically to test what I'm building.
517240	522230	And when I come here, you see that the post that we just created is live on Instagram exactly as we rendered them.
522240	525139	And this exactly what I'm going to be building with you guys today.
525139	530389	We also do have a dedicated agents tab that gives you more insight into the agent architecture that we have.
530389	536156	You can see that we have every sub agents have their dedicated card where you can see the AI model that the agents are using.
536156	543531	You can see the number of runs that particular agent has performed, how many of these runs have been successful and also some of the recent tasks that the agents performed.
543531	548206	On top of all these four agents, we have the orchestrator who is more or less the boss agent.
548206	554753	Now below we have an activity heat map where you can see in a time frame of 24 hours which agent has been active.
554753	559567	So the more brighter the color here, it just means that the agent was more active within that hour window.
559567	563438	And darker spaces just mean that the agent was not active within that time frame.
563438	567930	So the entire build is going to take you about four to 5 hours if you have all the prompts and the templates.
567930	571472	So I also created an auto installer that can do everything for you in a matter of minutes.
571472	575594	If you'll be interested in getting the auto installer, this model will also be in the description section.
575594	576756	Now, let's get into the build.
576756	579212	To get started, we're going to first install her.
579212	591430	He agents allows you to be able to build multiple agent infrastructure where you can be talking to your AI agents using all the popular applications out there like Telegram, Discord, Slack, WhatsApp, and all the popular messaging applications
591440	592336	that are out there.
592336	603103	Additionally, instead of being confined to using one particular AI model, you can use any AI model that you want. been it from OpenAI, Ben from Antropic or any other popular model that is out there.
603103	606424	And to install Hemisen, there are several options that are out there for you.
606424	613713	You can install this on a Windows PC if you have a dedicated PC that you want to run this on, or you can also install this via a Linux operating system.
613713	616482	For this setup, I'm going to be using the Linux approach.
616482	618114	I know Linux sounds intimidating.
618114	619976	Don't worry, I'm going to walk you through the entire step.
619976	629187	And then once we are done with the setup, which is going to take a few minutes, everything that you're going to be doing is going to be from the dashboard that we're going to be building or also from the Telegram messaging application.
629187	632925	So you wouldn't have to come into the terminal to do any stuff with quotes and stuff like that.
632925	637902	But I'm going to walk you through the entire process from A to Z so that you get a breast with how this whole flow would work.
637902	641614	Now, if you have a PC that you can run this on, hey, you can use this as well.
641614	644007	But in my case, for instance, I do not have a dedicated PC.
644007	647380	So you can rent a server somewhere that you used to run this on.
647380	649904	I personally prefer this option, but hey, it's up to you.
649904	657451	With using a private server is that you rent a server from a different company where you pay about $4 a month and then this server is going to be on 24/7.
657451	659555	You do not have to worry about maintenance.
659555	662617	You do not have to worry about internet connectivity and stuff like that.
662617	670699	But of course, this comes for a price and that is why you have to decide if you want to run this on your personal PC that you have at home or if you want to rent a server to run this on.
670699	674583	And for the VPS provider, my personal picks are typically Racknet and Conabo.
674583	688470	Now, with Rocknet, for instance, you can get a server with two CPU cores, 35 GB of this space, 2 GB of RAM for about $35 a year, which amounts to about $2.9 a month, which is quite affordable for a server, considering that you do not have to worry about
688480	692262	keeping it online 24/7, internet activity, maintenance, and stuff like that.
692262	694762	With Rak, you pay once a year and you're basically done.
694762	697735	You don't need to worry about monthly payments and stuff like that.
697735	701058	The second option that you can also go for is from Contabo.
701058	707238	They also do have quite reliable servers and the price are also quite affordable for the specifications of the VPS that you get.
707238	716470	So with Contabo for instance, you can get a server that has four CPU cores, 8 GB of RAM and about 100 GB of SSD disc space for about $8 a month.
716480	720057	This one here is going to be way more sufficient for what we're going to be building.
720057	723590	So you can decide on either going with Raknet or going with Contabo.
723600	726742	So I'm going to put a referral link in the description section that you can get one of these.
726742	729295	And these videos are not sponsored by any of these companies.
729295	732522	I'm just giving you what I typically use when I'm setting up these infrastructures.
732522	734468	If you want to go with Raknet, just come here.
734468	736716	Like I said, my recommended option would be this one here.
736716	737612	Click on order now.
737612	742901	And then you're going to be brought to a page where you would see the summary of the hardware specifications of your VPS that you selected.
742901	747430	And then when you scroll down as well, you see the server label, which you can change later if you want.
747440	751620	Now, in terms of the configuration options, I would recommend that you keep this as a default.
751620	755110	Operating system, we're going to be using Ubuntu 2012.04.
755120	764870	For the RAM, leave everything as a default. immedately you increase the RAM it's going to in an additional cost and that is why I would recommend that you go with the default options that is also here in terms of the location you can
764880	774470	choose whatever location that is closest to you but what we're going to be building latency is not much of an issue so I wouldn't worry too much about having it as close to you cost leave it as a default if you take something
774480	784150	higher you would basically pay more after that click on continue you're going to get an email that would contain all the credentials you're going to need to connect to the VPS ser and I'm going to walk you through that process as well
784160	792966	if you want to go with a contabo option like I said this option that we have here cloudvp4 or the lowest option that they have is going to be way more powerful for what we're going to be building.
792966	794505	So here click on get started here.
794505	796907	Be careful the default is sometimes 24 years.
796907	799916	That means that you're going to be locked with this VPS for 2 years.
799916	803251	And of course it gets cheaper the longer the contract is going to be.
803251	808230	But just be careful because if you go for 2 years then you are locked to pay this amount of money for 2 years.
808240	815942	If you want to have the flexibility of cancelelling this every month then you can go for the one month option where you're going to be paying about 5.5 in my case a month.
815942	826470	Now in terms of the region you can leave this as European Union which is the default because Contabo is in European Union with Contabo immediately you choose a different location then it would incur an additional cost but like I said
826480	830054	earlier with what we're going to be building latency is not going to be that much of an issue.
830054	832804	So you can leave this completely as European Union.
832804	839894	When you scroll down for the storage you can choose SSD 100 GB which is going to be free and way more sufficient for what we want to build.
839894	842947	For the operating system leave this as YUbuntu which is the default.
842947	846879	For data protection, I typically recommend that you go for the auto backup option.
846879	850383	Sometimes I'm working with my agents and something completely gets screwed up.
850383	854502	And then with the auto backup, it basically takes a snapshot of your VPS every day.
854502	863622	So that means that if something goes wrong, you can always go back to about 10 days back and then you can always restore whatever image you had on that VPS for that particular day.
863622	873239	Now this optional but like I said it's highly recommended because if you imagine if you've been building your content management system for over one year and by mistake something screws up you completely lose this.
873239	879648	Now to save this as well you can also configure your own auto backup which is going to take a snapshot of your VPS every day.
879648	888074	This for instance you can build with cloth but if you don't want to do this and you want to go with contabo's default auto backup option you can choose this which would about 1.65 a month.
888074	891073	Now additional features you can leave everything as a default.
891073	895447	In this section here, you're going to have to put in a password where you're going to connect to the VPS server.
895447	898875	Here you can generate a new password or you can put in any password that you want.
898875	903351	This is going to be a password that you're going to have to remember because this is a password that you're going to use to connect to the VPS server.
903351	907797	If you forget this password, you can go into your conso control panel and reset the password.
907797	909290	But why go through the hassle after that?
909290	912521	Just click on next, make the payment, and I'm going to walk you through the next steps.
912521	917110	If you went with a racknet option after making the payments, you're going to get an email like this from Racknet.
917120	919082	With this email, we basically going to need three things.
919082	922920	The first thing that you're going to need is the IP address of your VPS server.
922920	927544	Every VPS server has a unique IP address and they're going to provide this IP address to you.
927544	933198	The second thing that we're going to need is the username of the account that you use to connect to the VPS server.
933198	936195	With Raknet, most of the time name is always going to be root.
936195	941095	And then thirdly, you're going to need a password which they're also going to provide to you here called root password.
941095	943215	And here's what they're going to provide the password to you.
943215	945674	All these three credentials are going to be in your email.
945674	953608	With the SSH port, you do not have to worry about this because with most of the applications that you use to connect to the VPS server, they always default to an SSH port of three.
953608	960377	Now, with the IP address, with username, and with a password, you would be able to connect to the VPS server, which I would walk you through in the next step.
960377	963833	If you went for the Contabo option, you're going to get an email like this from Contabo.
963833	968751	Mine is in German, but the layout is going to be the same irrespective of which country or which language that you have.
968751	971216	In the email from Contabo, we're going to need two things.
971216	979207	We're going to need on this left side here the IP address which is the unique IP address of your VPS server and we're also going to need the username with Contabo as well.
979207	987926	The username is in most of the cases root the password they wouldn't provide the password to you in the email but this is going to be the password that you put in when you were purchasing the VPS server.
987926	995180	So with the IP address with the username and with the password that you put in when you were purchasing to the VPS server we would be able to connect to the VPS server.
995180	998206	And to connect to the VPS server there are several applications that are out there.
998206	1006598	The good news is that whether you're using a Windows operating system or you're using a Mac operating system, both do come with inbuilt applications that you can use to connect to the VPS server.
1006598	1011512	Using a Windows operating system, just click on the search bar and look for an application that is called Windows PowerShell.
1011512	1014813	And then when you click on this, this is how the Windows PowerShell application looks.
1014813	1018738	If you're using a macrop system, the application that you're going to be using is called terminal.
1018738	1024196	The commands that we're going to be using here in PowerShell are identical to what you would be using in PowerShell.
1024196	1027270	So you do not have to worry about differences in terms of commands.
1027280	1032155	To connect to the VPS server, just put in the command ssh space and then put in root.
1032155	1036855	Root is going to be the username of the VPS server, which is the same for Contabo and for racknet.
1036855	1040160	And after that, you're going to put in the IP address of your VPS server.
1040160	1050964	The trick here with PowerShell is that whenever you have something in the clipboard and you right click on your mouse, it basically paste whatever you have in the clipboard, which can be quite useful, especially when you are typing in passwords.
1050964	1052421	And after that, just press enter.
1052421	1058184	If this is the first time that you're connecting to the server, you're going to be asked whether you want to add this fingerprint of the server to your PC.
1058184	1061750	If you're sure you're connecting to the right server, just type in yes and it should be fine.
1061760	1064806	And after that, you're going to be prompted to put in the password of your VPS server.
1064806	1068501	And here, if you have a complex password, just type this password somewhere.
1068501	1070595	Come in here, just right click on your mouse.
1070595	1073337	It would paste the password into the clipboard and just press enter.
1073337	1076425	And then you can see that in my case, I'm connected to my VPS server.
1076425	1078754	So, I'm going to clear the screen by just typing clear.
1078754	1080996	And then we can start with the configuration process.
1080996	1088551	So now we connected the VPS server using the router name and root as a user is typically the highest authority on a Linux server.
1088551	1097295	Now to install Hermes my tip for you would be not to install Hermes on the root user but create a new profile or a new user on which we're going to run this on.
1097295	1103353	Now this is quite helpful because then you do not have Hermes being the highest authority on your VPS server.
1103353	1107234	In my earlier videos, we always did this on root, which is absolutely fine.
1107234	1111451	But I always try to improve and bring you guys the best safety tips out there.
1111451	1114579	And that is why we're not going to be installing Hemis this time around on root.
1114579	1119220	We're going to be creating a dedicated user on which we're going to install the whole Hemis application on.
1119220	1122599	Now, to create a new user on Linux, just use the command user space.
1122599	1125847	And after that, just put in the name of the user that you want to create.
1125847	1127550	In my case, I'm going to call this Larry.
1127550	1128402	So, add Larry.
1128402	1132135	And after that, you're going to be prompted to put in a password for this user.
1132135	1133399	So, I'm going to put in my password.
1133399	1134496	And after that, just press enter.
1134496	1136430	You're going to be prompted to retype the password.
1136430	1138021	And then after that, just press enter.
1138021	1140392	And then we're going to be asked if you want to put in a full name.
1140392	1142297	You can just skip this by pressing enter.
1142297	1142870	Room number.
1142880	1143271	Enter.
1143271	1143661	Phone.
1143661	1144052	Enter.
1144052	1145029	Just skip this.
1145039	1145583	Home phone.
1145583	1146722	You can also skip this.
1146722	1147455	You can also skip this.
1147455	1150933	And then you're going to be prompted if the information that you have put in is correct.
1150933	1152040	Just press Y for yes.
1152040	1153727	And after that, just press enter.
1153727	1156587	Now, you can see that then Larry is added as a user.
1156587	1164481	Now, we're going to give this Larry user some pseudo privileges so that the user can be able to run some commands and install the Hemis application.
1164481	1166789	And to do that, we're going to use this command here.
1166799	1170130	User mod space minus ag p sudo larry.
1170130	1172927	So here, just replace this Larry with your username.
1172927	1174190	And after that, just press enter.
1174190	1176072	By the way, I'm also going to provide you these commands.
1176072	1178338	So you do not need to type this or you do not need to remember them.
1178338	1179543	After that, just press enter.
1179543	1183990	And then we're going to get Larry now being a user with pseudo privileges.
1184000	1186099	I'm going to clear the screen just to make it a bit cleaner.
1186099	1193188	And now we're going to switch from the root user into the Larry user for us to be able to login into the Larry user that we just created.
1193188	1198904	And for that just use the command su space minus or hyphen space and then just type in Larry.
1198904	1201789	And you can see that the syntax change from root to Larry.
1201789	1205780	So that means that now I'm not on the root application which has the highest authority.
1205780	1209298	I'm now logged in into the Larry path which has this authority.
1209298	1214221	Now when we're connecting to the VPS server, we use the command ss space root the IP address.
1214221	1225909	But here as well if you want to connect to the VPS server instead of root you can use the new user that we created which is in my case Larry and then you can just put in the IP address of the VPS server then press enter put in the password that you
1225919	1238070	created and then you see that I'm also connected to the VPS server so you can connect to the VPS server either using root and after that switching to the larger using su space minus Larry or you can also directly go into that using the
1238080	1239088	SSH path for Larry.
1239088	1243029	So I'm just going to be sticking to with this because I already created a set with this here.
1243039	1244996	I'm just going to type in clear to clear the screen.
1244996	1247466	And then now we can start with the Hemis installation.
1247466	1251160	To install Hemis, we're just going to come to the original website from Hemsus.
1251160	1255788	And then when you're on this page, scroll down here and then come to the install via terminal.
1255788	1258188	We're going to be going with the native application.
1258188	1262226	And here the command always starts with curl so that you are sure that you are on the right one.
1262226	1264578	Now click here to copy the oneline installer.
1264578	1274797	The advantage here is that with this oneline installer, it's going to install all the dependent that required to install or to run hemis without you having to install application A, application B and stuff like that.
1274797	1277794	After that, just press enter and then the installation is going to run.
1277794	1283014	So, it detected that I'm running Linux and it's also going to run all the other things that are missing on my server.
1283014	1288255	Now, here I'm being asked, do you want to install RIP for faster file search for TTS voice message?
1288255	1289305	This would be good.
1289305	1297180	So, we can just type in yes that we want to install this and press enter. and then I'm going to put in a password and then press enter and then the installation is going to proceed.
1297180	1300761	So I'm going to wait for the installation to be done and then we can continue with the build.
1300761	1303173	All right, so the prerequisite installation is done.
1303173	1304715	So now we can start with the setup.
1304715	1307808	Now for here we're going to have to choose how we want to set up Hemis.
1307808	1314575	I would recommend that we go with a quick setup because a full setup is going to ask us so many things that we're going to have to configure which we do not need.
1314575	1316222	And this is also the recommended part.
1316222	1318059	So just make sure that this option is selected.
1318059	1320217	If not, just press up and down on your keyboard.
1320217	1324533	Make sure that the pointer is on this and then press the space bar or enter key.
1324533	1328111	Now in the next stage, we're going to have to create an account with news research.
1328111	1330693	If you do have an account, then you do not have to create a new one.
1330693	1337606	And basically, this is a step where we're going to bind this VPS or this server or this Hemis installation to our news research account.
1337606	1339755	Now, here you can go with their free subscription.
1339755	1346930	Nose research does have some paid plans where you can use a pool of AI models that they have, but in my case, I'm going to be coming with my own AI model.
1346930	1348930	So, I'm going to go with a free option.
1348930	1352149	So just press control on the keyboard and click on this URL here.
1352159	1354966	And if you do not have an account, you're going to get an option to create an account.
1354966	1362060	But in my case, because I already have an account and I'm logged into my account, it directly brings me to a screen where I can bind my account to the setup.
1362060	1363455	So here, just click on connect.
1363455	1366716	And when this is successfully, you're going to get a notification that this has been connected.
1366716	1371695	And then when you come back to the Hemis installer screen, you see that it brings you to the model selection process.
1371695	1377027	Like I said, in my case, I'm not going to be using any of the models that no research provides.
1377027	1378491	I'm going to bring in my own model.
1378491	1382175	So here you can just press enter on the keyboard to skip the model selection process.
1382175	1385546	In the next stage we're going to pick a few tools that you can use with her agent.
1385546	1392124	For instance, you can give your agents the options to be able to search on the internet and script data from the internet on particular websites.
1392124	1396149	And here for instance you can use a tool that is called fire crawl and the same applies.
1396159	1401428	There are other tools that you can use for image generation for text to speech for speech to text and so on.
1401428	1406210	So here you can just press enter to use all of these or you can also uncheck them if you do not need them.
1406210	1408433	In the next stage, we're going to select the terminal back end.
1408433	1412573	Here you can keep this as the default, which is local by just pressing on the space bar.
1412573	1417801	In the next stage, we're going to connect a messaging platform with which we're going to use to talk to all our AI agents.
1417801	1424038	And here, it's recommended that you set this up because we don't want to be talking to the AI agents every time through the terminal here on the VPS.
1424038	1428295	We want to have a simple, more friendly user interface that we can talk to the AI agents.
1428295	1432400	So, here we're going to select set up messaging, which is recommended anyway.
1432400	1438260	So press space bar on the keyboard and then you're going to list all the messaging platforms that are currently configured with Hemis.
1438260	1440675	And as you can see there are a pool of them that you can use.
1440675	1442630	But in this setup we're going to be going with Telegram.
1442640	1445629	So just press down on your keyboard and then here don't press enter.
1445629	1447590	If you press enter it would skip this part.
1447600	1450382	Press spacear on your keyboard to make sure that is checked.
1450382	1452133	And after that you can just press enter.
1452133	1454390	And then here we're going to create a telegram bot.
1454400	1458061	And this is going to be the bot with which we will talk to the agents that we're going to create.
1458061	1461997	For the Telegram B setup, you can either go with the automatic setup or you can also go with a manual.
1461997	1467594	In my case, I'm going to go with the middle option just to show you how you can do this if later you would need this for another application.
1467594	1470077	So for manual, just press two and then press enter.
1470077	1473464	And then HS is going to ask us what is the Telegram bot token.
1473464	1477621	So to do that, just come to Telegram and look for a bot called BotFather.
1477621	1481923	So you can see that the right botfather bot has over 7 million monthly users.
1481923	1484422	So that you are pretty sure that you are using the right bot.
1484422	1485271	Be careful here.
1485271	1487110	As you can see there a lot of botfather here.
1487120	1492599	But the one that you need is this one here with a check mark here and also with over 7 million monthly users.
1492599	1496390	To create a new ground, use the command forward slash and then type in new bot.
1496400	1499354	And then you can press enter or you can click on the suggestion that we have here.
1499354	1501309	Now here we're going to have to give our bot a name.
1501309	1505988	I'm going to call this km in my case for computer mechanic content creation OS.
1505988	1511023	So when you're done with the name just press enter and then you're going to be asked to put in the user of the bot.
1511023	1523269	Now very important here the username has to end with the name but and that is why I copied this because in my case I just want to call it the same name but just add the word but to it and after that just press enter and then the bot is going to be
1523279	1524006	created for you.
1524006	1532880	Now when the bot is created the botfather is going to give you a unique key that means that you are the creator of that bot or you are basically the owner of the bot.
1532880	1540050	So I'm going to click here to copy the key because that is what the hemis installation is asking and I'm going to paste in the key here and after that just press enter.
1540050	1542233	Now this step is a highly recommended step.
1542233	1547850	Hermes is asking you, do you want to put some users who are the only people that are allowed to talk to the bot?
1547850	1553490	Now this is very very important because if someone has the username of your bot, you don't want them to be able to talk to your bot.
1553490	1557998	And that is why we're going to tell her, hey, let me be the only one that can talk to this bot.
1557998	1564183	And the only way Hermes can know that it's you is by giving Hermes what your user ID for Telegram is.
1564183	1571352	And to get your Telegram user ID, we're also going to use a bot that is called user info bot which also has over 400,000 users.
1571352	1573566	There are a lot of other bots out there.
1573566	1575573	So make sure that you have the right one here.
1575573	1578638	And to get your user ID, you can just send the bot any message like hi.
1578638	1581398	And the bot is going to respond with your user ID.
1581398	1583254	So I'm going to click here to copy my user ID.
1583254	1586452	I'm going to come back to the terminal in Hermes installation.
1586452	1589219	I'm going to paste in the user ID and I'm going to press enter.
1589219	1593066	And then Hermes is going to ask you if you want to set this user ID as the home channel.
1593066	1602496	That means that in the messaging chat that you are talking to the bots, whenever the Hemis gateway is restarting or any system things are going on, you're just going to get a notification in this chat window.
1602496	1604568	You can type in a Y for yes and then press enter.
1604568	1609098	And then you're going to be asked if you want to install the Hemis gateway as a system service.
1609098	1618515	This very important because whenever your VPS server restarted due to a system update or anything, the Hemis gateway is going to start automatic which is quite useful so that you do not have to start this manually.
1618515	1620441	Press Y for yes and then press enter.
1620441	1623151	And then here you're going to be asked how do you want to run the gateway?
1623151	1625852	In our case, we're going to go with the system service.
1625852	1626710	So press enter.
1626720	1631510	And then I'm going to be prompted again, do you want to run and install the gateway as a background system service?
1631520	1634296	I'm going to press Y for yes and I'm going to press enter.
1634296	1636256	And then the Hemis installation is completed.
1636256	1642429	Now very important here, we're going to have to reload our shell so that we can just type in Hemus and this will launch the Hemis application.
1642429	1645462	And to do that, just copy the command that they have provided for you here.
1645462	1648580	Paste this command back in the terminal and just press enter.
1648580	1650411	It's basically going to restart the shell for you.
1650411	1653243	Now remember, we are basically done with the Hemis installation.
1653243	1657514	But in my case, I didn't select any AI model because I want to bring in my own AI model.
1657514	1660128	So here we're going to configure our own AI model.
1660128	1665358	And I'm also doing this in this way so that you guys can learn how you can add your own AI models later.
1665358	1670834	Now, if in future you want to add some AI models, you can basically ask your AI agents to do this for you.
1670834	1677394	But I typically do not recommend this because in most of the cases the AI model is not very smart, they basically mess up with your configuration.
1677394	1680305	And that is why for stuffs like that I prefer to do this on my own.
1680305	1683957	Now for which AI model to use this is absolutely up to you.
1683957	1696549	But what I typically use most of the time which a lot of people do not also know is that if you do have a charge GPT subscription if you the plus account or the pro account you would be able to use an AI model from open AAI that is called Codex
1696559	1698370	on her agent basically for free.
1698370	1701445	If you have the $20 plan you can use you can use this.
1701445	1704155	If you have the pro plan you can also use this.
1704155	1707728	I'm I'm not very sure if this is available for the Go plan.
1707728	1710048	In my case, most of the time I'm using the pro plan.
1710048	1715669	And the usage limits that you have for the pro plan is more than you would get for the $20 plan, obviously.
1715679	1718710	So, if you're not sure which one you need, you can go with the plus account.
1718720	1722332	If you hit your limit, you can basically always upgrade to the pro plan.
1722332	1724930	Now, the is also a bit generous in terms of the token limits.
1724930	1728769	So, you would be able to do a lot even if you are using the $20 subscription.
1728769	1731750	The advantage here is that it's not basically a pay as you go.
1731760	1733756	Whenever your limits are done, you are done.
1733756	1739511	You do not get any surprise bill from OPDI that hey, you've used more than your subscription allowed, so you have to pay extra.
1739511	1740389	That does not exist.
1740399	1746456	And that is why I personally go with these options because it's you don't have to worry about having a surprise bill or anything like that.
1746456	1752393	Personally, I'm on the pro plan because I have a lot of Hem setups and that is why my token usage is also very high.
1752393	1763590	And also for the tutorials that I create for you guys, I typically try this over 10 times and that is why I typically need a higher limit in terms of the tokens that they make available to you. when I had one Hemis account or when I had one open
1763600	1766826	CL account, this one was way more sufficient for me.
1766826	1774725	Now, what people also not aware of is that if you also do have an X account, you can also use the Crog model on Hermes agents for free.
1774725	1782870	So whether you have a chat GPT paid account or you have a premium or paid subscription, you can use in both cases their AI models on her agent for free.
1782880	1790455	If you do not want any of these and probably you want a particular model like from Antropic, oo, sonet or whatever, we can also come to open router.
1790455	1795274	Open router has quite a pool of a models like all the popular AI models that are out there.
1795274	1796518	You can get them on Open Router.
1796518	1803445	The advantage with Open Router is that they're going to give you one API key and with that API key, you can get access to all the models that are out there.
1803445	1807669	The tricky thing that you have to take note of the fact that with Open Router is basically pay as you go.
1807679	1811551	It's not a case where you paid a month and then when you hit your limit, you hit your limits.
1811551	1812791	You basically pay as you go.
1812791	1814701	The more you use, the more you pay.
1814701	1818230	So, I mean with whatever model that you want to use is completely up to you.
1818240	1820951	just go for the option that makes the most sense to you.
1820951	1825147	Now, in my case, I'm going to be going with my OpenAI because I have a CHBT subscription.
1825147	1827953	And to use that, I'm going to clear the screen here to make it a bit cleaner.
1827953	1831038	Just put in a command Heis space model and then press enter.
1831038	1835625	And [clears throat] this is going to load all the models that are currently available on Hemis agent.
1835625	1841438	If you do have an paid premium X account, then your option would be here, the X AI Grock.
1841438	1844506	The process is going to be the same irrespective of which option that you go for.
1844506	1847350	So, in my case, I'm going to select this by pressing the space bar.
1847360	1850878	And then here we're going to have the option to choose between open open AI API.
1850878	1853971	If you go with API then you pay as you go.
1853971	1859310	So the more you use the more you pay and then you would have to create a dedicated API key to collect this.
1859310	1861872	But in our setup we're going to be using our charging subscription.
1861872	1864005	So I'm going to go with the open AAI codeex.
1864005	1868745	And to do that we're going to press control and we're going to click on this URL that is provided here.
1868745	1872166	And in the process we're going to have to enter this code that is over here.
1872166	1873750	So just highlight this code.
1873760	1874696	Very important.
1874696	1876070	Press control shift C.
1876080	1878040	Do not press Ctrl C.
1878040	1886230	Ctrl C in Linux cancel an application and this would quit this whole screen and that is why you press control shift C and then the link is going to bring you to this page.
1886240	1889466	All you're going to have to do is to just log into your OpenAI account.
1889466	1898037	So I'm going to click here and then click on continue and then just put in the code that we copied from the PowerShell from the Hermise installation and click continue.
1898037	1908810	And then our CEX account or our OpenAI account is now bound to our Hemis setup and then when you come here you see that the authentication is done and then here we are being asked to select an AI model.
1908810	1912216	And then here you can use any of the models that you have here.
1912216	1920095	Remember the higher the number like 5.6 takes way more tokens than 5.4 4 than 5.5, which also takes higher tokens than 5.4.
1920095	1926022	In my case, I go with 5.5 most of the time because it's still a very super powerful model and I always want more tokens.
1926022	1931350	But hey, if you are on the $100 plan and you have a lot of tokens, you can also go with a 5.6.
1931360	1932503	That's absolutely up to you.
1932503	1933885	I'm going to go with 5.5 here.
1933885	1935205	I'm going to press spacebar.
1935205	1939664	And then you can see that it says that my default model has been set to GPT 5.5.
1939664	1951869	Now before we go into the telegram to test to see if everything works from the Hemis installation and from the model configuration just type in Hemus and this is going to open what is called a Hermes terminal user interface.
1951869	1957461	Now it's going to be a chat box where you can basically talk to your default AI agents to make sure that everything works.
1957461	1964516	But a lot of people like me do not use this part because then you always have to log into your VPS come to this weird page to talk to the AI agent.
1964516	1967691	We just want to make sure that the setup works and that is why I'm coming here.
1967691	1972938	So here I'm just going to send in a message like hi and if the agent responds then it means that the hemis installation works.
1972938	1979076	It also means that the AI model configuration worked and here you can see that the agent response hi what can I help you with?
1979076	1982711	So that means that our installation worked the AI model configuration works.
1982711	1993082	Now to leave this screen you can press Ctrl C on your keyboard or you can also just type forward slash and type in exit and press enter and this is going to kick you out of the Hemis terminal user interface.
1993082	1997840	A quick word from today's sponsor, Sudalis AI, and it's worth paying attention to this one.
1997840	2002230	Problem they are solving is that enterprises are currently drowning in disconnected AI.
2002240	2005902	Most companies are using AI tools that do not even talk to each other.
2005902	2009275	One tool does this, another does that, but nothing connects.
2009275	2011333	So nothing really works together.
2011333	2015001	Sudalis AI built a system that connects everything into one stack.
2015001	2019238	Check them out at sudalis.ai with all the links in the description section.
2019238	2021250	Thanks Sudalis AI for sponsoring this video.
2021250	2023912	Now we're going to come back to botfather.
2023912	2029167	When bot created them for us, he also gives us this URL with which we can start talking to the bots.
2029167	2030810	So here just click on this URL here.
2030810	2034070	It's going to open a new chat session with the bot that was created.
2034080	2035350	You can just click start.
2035350	2037897	Now this is going to send a message like start to the bot.
2037897	2041669	But the bot doesn't respond but it doesn't understand what start means.
2041679	2044653	So here we're just going to send a message to the bot like hi.
2044653	2047270	And if everything works the bot is going to start typing it.
2047270	2053039	So if you see this typing symbol then it means that the bot is configured and the bot is going to respond to you.
2053039	2055850	So the bot responded hi what can I help you with today.
2055850	2058207	Now we're not going to be talking to the bot in this session here.
2058207	2061588	What we want to create is we're going to create a telegram group for our bots.
2061588	2064985	The reason why we're going to create a group is that we're going to have basically three topics.
2064985	2069672	The first topic is going to be where we're going to be talking to the bots which is going to be our orchestrator.
2069672	2076906	And then we're going to have a second topic or a second channel which we're going to use to talk to our developer agent who is going to build the whole dashboard for us.
2076906	2080177	And then we're going to have a third channel which we're going to call studio.
2080177	2083333	And that is where we're going to brainstorm ideas and stuff like that with our agents.
2083333	2088717	When we are creating the group, a prerequisite to create a group is that you have to get at least two people in the group.
2088717	2093494	So we're going to need the username of our bots so that we can add this bot to the group that we're going to create.
2093494	2095187	I'm going to click on the name of the bot here.
2095187	2098194	And then here we can click to copy the username of the bot.
2098194	2102041	And after that we can close this dialogue box and then we can create this new group.
2102041	2107425	Now to create a new group, click on the hamburger menu that you have here on the left section here and then click on new group.
2107425	2108910	And then we're going to name the group.
2108910	2112653	In my case, I'm going to call this KM Content OS and then click on next.
2112653	2115630	And then we're going to have to add at least one person to the group.
2115630	2117944	And that is why we copy the username of our bots.
2117944	2122152	So I paste in the username and I'm going to click to select the bots and I'm going to click on create.
2122152	2124266	And then now we have our group created.
2124266	2127438	But like I said, we want to create different channels in this group.
2127438	2133030	Now, we're going to have to make the bots that we added an administrator so that the bots can talk in this group.
2133040	2134736	Click on the three dots that we have here.
2134736	2136013	Come to group info.
2136013	2136937	Click on manage.
2136937	2139249	Come down here and click on administrators.
2139249	2140267	Add administrator.
2140267	2143775	We're going to select the board that we created because the board is already in that group.
2143775	2147086	And just review the permissions that you want to give to the board and just click on save.
2147086	2150392	And then now you see that our bot has an admin privileges.
2150392	2151750	After that, click on close.
2151760	2155977	Now, whilst we are here, we also going to enable this aspect that I call channels.
2155977	2161404	So by default, Telegram doesn't enable these channels or what is called in Telegram topics for you.
2161404	2165883	So to enable this, just click on the topics section here, which is in my case by default off.
2165883	2167888	Click on this and then you can enable this.
2167888	2170230	And then here you can decide the view that you want to go for.
2170240	2172307	In this case, I'm going to go with the tabs option here.
2172307	2173633	And then just click on save.
2173633	2175097	And I'm going to click on save again.
2175097	2176630	And then we can now close this.
2176640	2178964	And then immediately we do that when we enable topics.
2178964	2181074	You see that now we have different channels.
2181074	2184406	We have all channel where we going to see all the messages from all the channels.
2184406	2186243	And also we have the general channel.
2186243	2188401	So first let's rename this general channel.
2188401	2189861	Click on the three dots here.
2189861	2190551	Come to edit.
2190551	2195537	And then we can call this channel orchestrator because this is the channel where we're going to talk to our main bot.
2195537	2196737	I'm going to click on save.
2196737	2198844	And then we're going to start talking to orchestrator here.
2198844	2201218	So let me just send a message in the chat here.
2201218	2205382	When I send hi and our bot is typing that means that orchestrator is in this chat.
2205382	2208069	So we can basically start talking to orchestrator.
2208079	2209861	We are going to create other two channels.
2209861	2211030	But we are not there yet.
2211040	2214862	Let's just build the foundation and then when we get there, we're going to go through that process as well.
2214862	2219214	All the prompts that I'm going to be using in this build can be made available if you interested.
2219214	2225533	You can get this for a token of support on my website or if you are also a member of my community, you can also get this.
2225533	2236096	If you guys want to be a member of my community, it's $10 a month and you can get basically access to all the prompts and all the templates and all the tutorials prompts that I have on my channel.
2236096	2238586	And this goes to also support the work that I do.
2238586	2243154	A lot of effort goes into creating all these tutorials, creating all these forms that I give to you.
2243154	2253485	All the AI models that I also use in building these are also quite expensive and that is why I would need to get this with a token of support to help me to be able to keep bringing these tutorials to you as well.
2253485	2256624	So if you want to join my membership group, I'll be very happy to have you there.
2256624	2267092	We also do have a telegram channel where you can basically get access to me or all the people in the community ask any questions that you want and everyone there would be happy to support you with the questions that you have.
2267092	2268633	And I also do create auto installers.
2268633	2274208	For instance, for the setup that I'm creating, I'm building an auto installer that would build the entire thing for you in less than 5 minutes.
2274208	2278632	And this is going to be available to people in my community or my membership as well.
2278632	2281466	Said, hey, if you want to join, I'm very happy to have you on board.
2281466	2288591	So, what I did now is that I moved Telegram to the left and it basically had all the prompts on the right so that we can basically copy this and it will be very easy.
2288591	2293032	Now, whenever you set up Hemis for the first time, the bot has no idea who you are.
2293032	2298420	The bot doesn't have a name. the bot has no idea how the bots can help you with with whatever you want to do.
2298420	2302941	So the first thing that I always recommend to users is hey let the bot understand who you are.
2302941	2304047	Give the bot a name.
2304047	2308748	Tell the bot your name and give the B a gist of how he or she can help you for this.
2308748	2311037	My first point that I'm going to give to my bot is this.
2311037	2312930	Your name is going to be orchestrator.
2312930	2319519	You are going to be my top level coordinator for my multi- aent setup and I am the owner and I have the highest authority.
2319519	2321637	And then here you're going to fill in your name to the agents.
2321637	2323956	You're going to also give the agents your brand name.
2323956	2329589	You're going to give the agents your social media handle because remember we are creating a social media content creation machine.
2329599	2332001	You're going to tell the agents what your brand teaches.
2332001	2336270	Now, this is very important because we're going to have this dashboard that is going to create ideas for us.
2336270	2343109	And for the agents to be able to create these content creation ideas or these post ideas for you, they need to understand what you're building.
2343119	2345596	And that is why this part here is non-negotiable.
2345596	2348583	You can also tell the agent what your audience is and stuff like that.
2348583	2349510	So, I'm going to copy this.
2349520	2350759	I'm going to paste this in here.
2350759	2352878	And I'm going to fill in the sections for my build.
2352878	2354979	So here I bought, hey, my name is Larry.
2354979	2356677	My brand is computer mechanic.
2356677	2358486	My social handle is computer mechanic.
2358486	2365699	And here I teach it technical builders to build AI agents and automation, who my audience is, my voice, and my working time zone.
2365699	2373771	Now the working time zone, for instance, is important because when the agent is creating like Chrome jobs, then the agents will basically know when to reach you and stuff like that.
2373771	2378630	Now I'm going to send this to orchestrator to get him breast with who I am and also what we're going to be building today.
2378640	2380510	And then orchestrator responded, "Hey, got it.
2380510	2382204	I'm orchestrator and you are Larry.
2382204	2392298	Your brand is computer mechanic and your content is plain direct content teaching builders to build agents and automation." Now, the next two prompts here are what I would recommend that you do.
2392298	2396267	The second prompt here is basically where you're telling orchestrator to interview you.
2396267	2399899	Now, what you give to orchestrator here is basically the backbone, the foundation.
2399899	2403159	But there are so much that you can let your agents learn about you.
2403159	2411318	So just take time and give this prompt to Kasha is going to ask you some questions to understand who you are of the setup that you want to build your audience and all those things.
2411318	2417992	But I'm going to skip this in the tutorial because otherwise the tutorial will get lengthy because for my testing or would ask you about 10 15 questions.
2417992	2421367	So I would skip this just not to get the tutorial too lengthy.
2421367	2424934	The second thing that I would also suggest to you is this permanent operating rules.
2424934	2432591	Now when you are working with the agents it's always advisable to let the agents always give you a plan before they do anything they want to do.
2432591	2437539	And also when the agents are working, you always want the agents to keep you updated in the process of what they are building.
2437539	2442556	Otherwise, sometimes you just sit in the dark and you do not know if the task is completed or the task is is done.
2442556	2447395	And that is why I prepare always these permanent operating rules which you can also give to your agent.
2447395	2450971	It's optional for you if you want to have this this there ready for you.
2450971	2459323	I'm going to skip this part as well otherwise in my build orchestrator is always going to ask me give me a plan that I have to type a proof before he does it and this would slow down the build.
2459323	2461569	Now we're going to start with the main hat of the build.
2461569	2465196	We're going to tell orchestrator that hey we're going to create different agents.
2465196	2470102	We're going to create an agent like Atlas who is going to take care of content creates carousel ideas.
2470102	2472299	We're going to have Vera who is going to be our writer.
2472299	2476728	We're going to have Kite who is going to be our designer and also Kite is going to be our developer.
2476728	2482103	And we're also going to have origin who is going to be our publisher publishing things to whatever channel that we want to use.
2482103	2486897	And here we are basically giving orchestrator a prep or a gist of what we want to build.
2486897	2487111	Right?
2487111	2492299	And we are telling orchestrator that hey you are already one of these five agents that we're going to create.
2492299	2495853	You are going to be the main agent and you are the one I'm talking to right now.
2495853	2506630	And also important I'm telling him when he is creating these profiles he shouldn't create one for himself because I did test with some AI models that created a profile for themsel as well which doesn't make sense and that is why I also tell it here that
2506640	2508415	hey you do not need to create one for yourself.
2508415	2512755	So I'm going to copy this prompt and I'm going to give this to orchestrator to prep him what we're going to be building.
2512755	2520895	I'm also telling him, hey, confirm that you understand the plan, the five rows and the profile name mapping before he even goes to change or build anything.
2520895	2528526	And what I like about Hermes is that whenever you send Hermes something that if he finds useful long-term, he commits this to the memory.
2528526	2531017	And that is why you always see this message like memory.
2531017	2533150	It means that something has been written to the memory.
2533150	2537591	And by the way, cadence is the name that I give to the content creating OS that we're going to be working on today.
2537591	2543589	And then he's just saying hey the five cadence rules are orchestrator which is me and then the other profiles that we're going to be creating.
2543589	2547126	And he's saying that you are Larry the owner and the final authority.
2547126	2549880	Now in the next prompt this is going to be the most important prompt.
2549880	2553772	This is going to be the prompt that is going to create the AI agents that we're going to need.
2553772	2555254	I'm going to send the prompt to orchestrator.
2555254	2559265	So I'm telling orchestrator that hey create five persistent hemis profiles.
2559265	2566942	Now the reason why I use persistent is that hemis can also create agents that are basically called in to do a task and then after that they basically dead.
2566942	2569321	So what I want to create is that I be created permanently.
2569321	2572139	So that means that whenever we need them, they are going to be there.
2572139	2577589	Now here whenever you are creating an agent always with Hermes there is always one default agent.
2577599	2582091	There's always one agent who is going to be at the top and that is typically the default agent.
2582091	2588550	And below the default agent you can have whatever number of agents that you want to have but there's always going to be one agent at the top.
2588560	2596630	And that is why in my setup I typically make the default agent who is at the top orchestrator and then he builds the other agents that would work under him.
2596640	2599828	So someone for instance asked if you can have two orchestrators.
2599828	2607432	In principle you can have two orchestrators that but it means that one orchestrator would have to be under the default orchestrator which you can also do.
2607432	2609949	This is basically up to you how you want to configure this.
2609949	2615495	Now in creating a profile for an agent you basically need to tell the agent hey what am I as an agent?
2615495	2622800	So for all the agents we are telling orchestrator to add this information into a document that would be called their soul.md.
2622800	2627069	So a soul.md is a document that tells an agent hey my name is Larry.
2627069	2628088	This is what I do.
2628088	2629743	This is the person that I'm working with.
2629743	2631899	This is the system that we are working with and stuff like that.
2631899	2637934	And that is why in this prompt for all the agents I tell orchestrator what he is supposed to put in their description.
2637934	2643941	So for instance for scout I'm saying hey your name is scout you are a content scout for candid studio.
2643941	2649990	Your job is to find fresh scroll stopping Instagram Tik Tok carousel ideas and to research facts behind them.
2650000	2652708	So for all the agents I'm telling them what they are going to be doing.
2652708	2655561	And for instance Kite Kite is also going to be our designer.
2655561	2657257	He's also going to be our engineer.
2657257	2660912	So he has what I'm describing for Skype for him to understand what he does.
2660912	2666119	Now whenever you start a new chat session with an agent, they always load in their soul.md.
2666119	2671510	And that is why it's very advisable that we describe in detail what the agents are going to do.
2671520	2675383	Now he can change the text to whatever you want, whatever fits what you are doing.
2675383	2680557	For instance, in my case, I said Instagram and Tik Tok, but maybe you want to have both, LinkedIn and stuff like that.
2680557	2682169	You can basically add this here as well.
2682169	2683396	So, orchestrator responded.
2683396	2684067	He says done.
2684067	2688138	I have created a persistent herm profiles each with their own soul.MD.
2688138	2691044	And then you can see here we have scout who is Atlas.
2691044	2692462	We have Scribe who is Vera.
2692462	2693750	We have Dev who is Kite.
2693750	2695298	We have Rich who is Orin.
2695298	2698415	And he also confirmed that the profiles indeed exist.
2698415	2702716	Now if you want to also confirm yourself because sometimes the agents do hallucinate.
2702716	2710315	It can be that the agent orchestrator told you especially if you're not using a very good model or can tell you hey I created the agents but basically they were not created.
2710315	2711864	So you can double check this yourself.
2711864	2719896	You can come into your terminal and just type in a command hemis profile list and then press enter and then this is going to list all the profiles that you have on your hemis setup.
2719896	2726161	So you can see that in my case I have default which is orchestrator and then we also have the four agents that we created.
2726161	2728374	Now here you can see that the gateways are not running.
2728374	2734579	Their gateways are stopped which is fine because we want the gateway only to be activated when the agents are working.
2734579	2737791	So we verify that indeed orchestrator created all these agents.
2737791	2740724	Now this is going to be a prompt that is also very very important.
2740724	2744762	Now in this prompt I'm telling orchestrator to define this for each agent.
2744762	2748225	Now I want every agent to have their own dedicated memory.
2748225	2750150	Imagine you have five agents.
2750160	2752375	Every agent has their own particular role.
2752375	2757249	It's going to be a mess if all these agents are sharing one file for their memory.
2757249	2761315	So agents always write long-term stuffs into a file that is called memory.mmd.
2761315	2764572	So if all the five agents are using one file, it's going to be a mess.
2764572	2771670	Now that means that orchestrator is going to dump his long-term memory in there very it's going to dump her long-term memory stuff in there and it's going to be a mess.
2771680	2775305	And additionally, this is going to make the memory file very very heavy.
2775305	2778892	And remember, the bigger the memory MD file, the more tokens that you use.
2778892	2785773	And that is why I typically like to go with a dedicated memory for every agent so that every agent writes own stuff into their own lane.
2785773	2791589	And every agent is also going to have their unique identity, their dedicated folders and role boundaries.
2791599	2796353	So here we are telling every agent to only do stuffs that are within their role.
2796353	2806009	So for instance, if I go to my agent who does my research like Scout and I tell Scout, hey build me a dashboard, and Scout will tell me, hey, no, probably you should talk to Jeff because he's a developer.
2806009	2817750	Now this is quite important because for instance imagine that you have an agent who is your finance and this agent maybe has access to your PayPal has access to your stripe and stuff like that and you give your finance agent the particular rules
2817760	2821278	that he's supposed to work with maybe don't withdraw money from my account and stuff like that.
2821278	2833109	So finance agents knows these rules but if another agent comes in and does that particular thing and the agent doesn't even know what the rules that you give to finance is then the agent can basically mess up your setup and that is why I always have this
2833119	2845109	sort of role boundaries where every agent understands what their particular role is and then here orchestrator is working on that as well for us and here orchestrator is done as well all the agents have their dedicated memory and
2845119	2853190	he also created dedicated folders for all the agents and he also tested the role boundaries for instance he asked Vera, Vera, can you write a code for me?
2853200	2856223	And then Vera responded, hey, that is Kite's department.
2856223	2860456	And he also asked Kite's ver research and kite responded that is Atlas department.
2860456	2862550	So that means that the role boundaries are working.
2862560	2865626	Now in the next step, we're going to create a project folder that is going to host our project.
2865626	2869370	And very important, we're going to create the agents login database system.
2869370	2873817	Now, whenever the agents are performing a task, we want them to log whatever they do.
2873817	2876542	So we're going to build sort of an agent login database.
2876542	2881647	The idea here is that before an agent sends you a message that, hey, I'm done with this task.
2881647	2886813	The agent is going to log their name into the list, they're going to log exactly a description of what they did.
2886813	2892234	They also going to log the time stamp that they did this and they're also going to write the AI model that they use for that particular task.
2892234	2895545	And then we're going to do this using what is called an SQL lightsaber.
2895545	2900504	We're going to build a small database server on our server where the agents are going to log all the activities.
2900504	2903418	For instance, when we come to the dashboard I'm going to be building.
2903418	2908686	When you come to the agents tab, you can see that we have this heat map where we see when every agent was active.
2908686	2913424	And here for instance, the agents also post the work that they did, the most recent work that they did.
2913424	2916243	So this gives you full transparency of what the agents are doing.
2916243	2920749	So that if an agent is stuck somewhere, then you know that the agent for instance didn't perform that task.
2920749	2923106	And by the way, this is the dashboard that we're going to be building.
2923106	2928239	And for that, I'm going to give this prompt to orchestrator to build this agent login database system for us.
2928239	2931268	So orchestrator is done with the agent login database.
2931268	2939374	And he also did a smoke test where we can see dev built the cadence store the AI model that he used and the state that he's completed and when he performed this task.
2939374	2942124	Now remember we have created a base but the agents do not know.
2942124	2945423	So currently it's only orchestrator that knows that such a database exists.
2945423	2956286	So we're going to have to roll this out to all the agents and then we are telling the orchestrator hey save this operating rule in your own memory and then first distribute it to Atlas Vera and all the other agents.
2956286	2958394	And this is the instruction that we are giving to them.
2958394	2964862	Before sending any response, log what you did into the kid into the cadence runs table by running this command.
2964862	2969708	So that's going to be the command that you're going to run to basically insert what they did into the database.
2969708	2976059	I'm going to copy this and I'm going to send this to install this to make sure that all the agents are aware of the setup that we did.
2976059	2981910	And after that I'm also going to tell him hey have every agent run a smoke test so that they lock something into the database.
2981920	2986700	Now this would help us for us to know that all the agents have access to this database that we created.
2986700	2992702	Now when the agents are working sometimes you get a prompt like this where you're going to have to allow them to be able to run some commands.
2992702	3001142	In my case you can either go with allow once allow only for this particular session or you can also allow this always so that they don't ask you this every time and then that is also done.
3001142	3010710	So he also did a smoke test where all the five agents that we have performed the smoke test where they just completed the AI model that they used and the time that he performed and the date and time that he performed this
3010720	3011013	task.
3011013	3013852	Now we're going to move in to one of the major parts.
3013852	3024390	So currently you can see that we are sending all our messages in the orchestrator channel because so far we've been working with orchestrator but now we're going to move into the aspect where we're going to start building the dashboard and for that
3024400	3025796	we're not going to be using orchestrator.
3025796	3033562	We're going to have a dedicated agent kite who is our designer and our developer who is going to be creating the dashboard for us because he's going to be our developer.
3033562	3041288	We're also going to have a third channel which we're going to call studio and that is going to be the channel we're going to use to brainstorm ideas on new content to create and stuff like that.
3041288	3047272	Now, by default, the issue is that Telegram doesn't allow you to use one bot token to talk to several bots.
3047272	3049443	So, with Telegram, one bot, one token.
3049443	3056063	So, if we want to create another dedicated Telegram channel where we're going to talk to Kite, then we basically can't use orchestrators B token.
3056063	3059109	We have to create a dedicated bot token for kite.
3059119	3064608	Now, there are workarounds around this like I did in my earlier video where we basically created a router plugin.
3064608	3074470	So what the router basically does is that whenever you send a message in a channel it first goes through that single B token and the router determines hey this is a message that is coming from orchestrator's channel so let me send
3074480	3084710	this to orchestrator the same thing that also happens for instance if you have an agent that is called a message comes from that scribe telegram channel then it goes to your same bin and then the router determines hey this is coming
3084720	3094075	from thread 4 because every channel has their dedicated ID so with that ID the router is able to determine where the message is coming from and then it routes it to that particular agent.
3094075	3097522	Now, this is quite useful if you have different channels that you want to create.
3097522	3099458	But in our setup, we're going to create only three channels.
3099458	3105170	So, I'm going to show you another workar around because with every tutorial, I try to bring in a new flavor so you guys can learn also new things as well.
3105170	3110908	So, what we're going to do in this setup is that we're going to create another bot token exclusively for kites.
3110908	3117660	So, that means that every message that goes through this particular gateway or this particular telegram bot token would go directly to kite.
3117660	3119635	But then we have another challenge.
3119635	3126408	So by default whenever you create channels in telegram all the messages that we create in these channels are going to go through one bot.
3126408	3137351	So which is now our case every message is going to go through orchestrator but which doesn't make sense right we want orchestrator to only listen in a particular channel and we also want kite to only listen in the channel that we'll create for him.
3137351	3144650	So what we're going to do is we're going to tell orchestrator to build sort of a plug-in where orchestrator would only listen in the channels that are dedicated to him.
3144650	3148497	So orchestrator would never listen in the channel that we would create for Kite.
3148497	3150492	And the same thing also applies to Kite.
3150492	3153280	Kite would only listen to his channel that we'll create for him.
3153280	3154475	This would all make sense soon.
3154475	3154863	Trust me.
3154863	3156449	Because this is very very complex.
3156449	3162256	I typically like to brief the agents whenever we want to create something complex for them to know what is coming.
3162256	3166052	So here I'm sending this message to prep him on what we want to do.
3166052	3168687	So I'm telling Oka, hey, we're going to build something together.
3168687	3182870	The goal is that kite by default is going to build our studios dashboard and I want to talk to this engineer directly in his own group where he would have his own bot and his own identity and then I'm explaining to why we need a second bot
3182880	3186711	and you can also read this to understand basically the reason why we need the second bot.
3186711	3191270	So I'm basically telling him hey this is what we're going to build so that can understand what we going to do.
3191280	3199494	Now, whilst orchestrator is working on this, we're going to have to create a second bot token for Kite because remember that Kite would need his own dedicated bot token.
3199494	3205336	Orchestrator responded that he understands the goal is that Kite has his own Telegram presence where we can speak to him directly.
3205336	3208027	But we first going to have to create this bot for Kite.
3208027	3213233	And to do so, we're going to come back to our bot fer that we used to create the first B that we have forestrator.
3213233	3214847	And we're going to create a second bot.
3214847	3218323	So, just type in new bot just like we did for the first time for orchestrator.
3218323	3221105	And we're going to call this bot km kite content.
3221105	3222862	Let me call this content kites.
3222862	3223198	Right?
3223198	3224703	And I'm going to copy the username.
3224703	3225346	We press enter.
3225346	3228803	And just like we did earlier, I'm going to use the same name that I g.
3228803	3234081	But I'm just going to end with a bot because every username with telegram for a bot has to end with the name bot.
3234081	3235367	And I'm going to press enter.
3235367	3237710	And then we get a dedicated token for bot.
3237710	3241258	Remember this was the token that we had for orchestrator.
3241258	3243887	And we have now create a dedicated token for kite.
3243887	3248048	So we're going to have to add this bottle for kites also to our hemis setup.
3248048	3250470	And to do that I created this command for you here.
3250480	3250953	Come here.
3250953	3252041	Copy this command here.
3252041	3253991	Come back into your terminal instance.
3253991	3255032	Let me clear the screen.
3255032	3255661	Very important.
3255661	3257022	Make sure that you're not on root.
3257022	3260511	You are on Larry or the new user that you created and just paste in this command.
3260511	3263196	Now this command is going to ask you to put in the bot token.
3263196	3267984	So I'm just going to run the command here and then it's going to tell you hey paste your kite token and press enter.
3267984	3269543	So I'm going to come back to Telegram.
3269543	3270710	I'm going to click here.
3270720	3272447	Make sure that you are copying the one for kite.
3272447	3273701	I'm going to click to copy this.
3273701	3274681	I'm going to minimize this.
3274681	3277467	I'm going to come back to the and I'm going to right click to paste this in.
3277467	3278803	And then the key is pasted here.
3278803	3280445	And after that, I'm just going to press enter.
3280445	3283628	And this is going to save the keys into our dashboard.
3283628	3285291	So, let's go back into our setup.
3285291	3287109	And then let's go into our group.
3287119	3293970	And then I'm going to tell the I have created this B token for Kite and I have also added the B token myself in this space here.
3293970	3300398	So, I'm telling him to verify that the token that I have added exist and also to do a few sanity checks to make sure that it would work for Kite.
3300398	3303451	I'm going to copy this and I'm going to send this to orchestrator.
3303451	3313430	And also what is quite useful and what I always recommend to you guys is that whenever you're giving your agent a complex tax that you're not sure if the agents would be able to pull this off, you can always give the agents reference
3313440	3314043	to the hemis.
3314043	3322466	So for instance, if I'm telling you, hey, if you are unsure, please look into the hemis in this part here so that the agents would basically understand how he's supposed to build this.
3322466	3324543	Then I get this command approval from orchestrator.
3324543	3325623	I'm going to click on always.
3325623	3328400	And then orchestrator said, hey, step one is completed.
3328400	3333115	He's verified that the token that we added exists and he's also saying that hey the bot is live.
3333115	3335996	We can basically send stats to him to directly message Kite.
3335996	3339267	Now what we're going to do now is that we're going to create the channels that we need.
3339267	3340668	So we're going to create one channel for Kite.
3340668	3346900	We're going to create one channel as well for studio which we're going to use for the brainstorming before we even bring Kite into that chat.
3346900	3349267	So to do that we're going to click on the three dots here.
3349267	3351155	You wouldn't see the option to create a group.
3351155	3354385	So we're going to come back to all and then you're going to click on the three dots here.
3354385	3355791	Then you're going to create a topic.
3355791	3357130	Now you're going to have to give the topic a name.
3357130	3359175	In our case, I'm going to call this kite, right?
3359175	3362933	And because kite is going to be a developer, let me just give him a laptop icon.
3362933	3364638	And after that, just click on create.
3364638	3370320	Now, whenever you are creating a new topic, before topic can be activated, you're going to have to send a message in that topic.
3370320	3378986	For this topic that we are creating, we're going to need the thread ID for this topic because it is with this ID that orchestrator would bind this topic exclusively to kite.
3378986	3386728	So to kick off this group, I'm just going to copy this prompt here and I'm going to send this immediately to orchestrate that hey, what is this topic's thread ID?
3386728	3387830	You can send it any message.
3387830	3393792	We could have sent in hi just to create the channel and then we could follow up with a message like what is the topic thread of this ID.
3393792	3396306	I'm also going to show you that other approach as well.
3396306	3397446	Now kite is created.
3397446	3399270	We have the telegram topic ID.
3399280	3400571	We have the thread ID.
3400571	3403505	Come back to all and then here click on create topic.
3403505	3405990	And then we're going to create the next topic which is going to be the studio.
3406000	3411141	Now remember the studio is where we're going to be brainstorming ideas on new content, promos, ideas and stuff like that.
3411141	3416489	So I'm going to call this idea with this icon here and I'm going to click on create and to trigger and create this as well.
3416489	3422470	I'm just going to use a welcome message like hey what is the topic ID of this group and then here as well we're going to get a response.
3422480	3429246	Now remember we have created kites but still it's orchestrator that we are talking to because kite hasn't even been added to this group yet.
3429246	3429537	Right?
3429537	3437451	So all the messages that you are seeing here the thread the response to the thread ID for kite the response ID for studio all of this is still coming from orchestrator.
3437451	3438685	So now we have the thread ID.
3438685	3442352	So we're going to send a message to orchestrator that hey now we have the thread ids.
3442352	3444468	So we want you to wire our telegram group.
3444468	3447708	I'm going to give orchestrator telegram group ID of our current group.
3447708	3450564	And I'm also going to give him the thread ids of all the channels.
3450564	3453343	So he would have the thread ID of where I'm talking to him.
3453343	3455246	He would have the thread ID for kite.
3455246	3457556	He would also have the thread ID for the studio group.
3457556	3461989	And then only with this he would be able to bind the channels to the particular agent.
3461989	3472710	So for orchestrator would have access to this channel that we are talking to him and orchestrator would also have access to the studio channel because that is what we going to he's the boss and basically we will be brainstorming the ideas with him on the
3472720	3479834	studio channel but kite would only listen in this channel and kite would have no access to the orchestra channel and also to the kite channel.
3479834	3483792	I'm going to open notepad and I'm going to paste in this prompt because we're going to change a few things in there.
3483792	3486525	The first thing that we're going to need is the telegram group ID.
3486525	3488274	Now to get your telegram group ID.
3488274	3493074	We're going to use the same bot that we used to fetch our telegram ID called user infobot.
3493074	3498069	So when this opens, click on forum down here and select the group that you just created.
3498079	3499852	In my case, this is KM content.
3499852	3501910	And then when you click on this, just press send.
3501920	3504863	And then the bot will send you the ID of the Telegram group.
3504863	3506333	You can click on here to copy this.
3506333	3509655	And I'm just going to replace this with this section here called Telegram ID.
3509655	3513239	In the next stage, we're going to fill in the thread ID for the three channels.
3513239	3515726	And for that, I'm going to come back into our Telegram group.
3515726	3519904	But in most of the cases, the first channel that you create always has a thread ID one.
3519904	3522470	So most likely orchestrator would reply that is one.
3522480	3524535	But just to be sure, let me just ask him this as well.
3524535	3528118	Okay, she responded that his thread ID is one because that is that was created.
3528118	3529283	So I'm going to put in one here.
3529283	3530574	I'm going to go to kite.
3530574	3531191	Kite was 36.
3531191	3535841	I'm going to put in 30 and I'm going to come to studio and studio is 40.
3535841	3537455	And then basically we're done.
3537455	3540563	Only these are the four parameters that you're going to have to fill in in this prompt.
3540563	3541998	And after that, copy the message.
3541998	3542593	Very important.
3542593	3553750	Don't do this in studio or kite. do this in orchestrator's channel and then paste this message and send this message to orchestrator to basically implement the topic lane agents binding and he orchestrator responds hey I've saved the
3553760	3563430	four lane members to memory and completed the save part but there is an issue that he's having he's not able to run this command to restart the gateway so he's telling us if we can run this for him so I'm just going to copy the
3563440	3572069	command here I'm going to come back to my terminal let me just clear the screen to make it a bit cleaner and I'm going to paste in this command here very very important again make sure that if you created a new user you are on the new
3572079	3574336	user not your root account and and press enter.
3574336	3579470	And then it happened as well when I was testing this that you get this response failed to connect to bus.
3579470	3585473	So just copy everything here and then come to telegram and then tell okay I got this error and just paste it.
3585473	3586727	Oops, I think I didn't copy it.
3586727	3590164	Well, let me come back into PowerShell control shift C to copy this.
3590164	3592789	I'm going to come back to Telegram and I'm going to paste this.
3592799	3596917	And then he would basically correct this and give me another command that I can use to fix this issue.
3596917	3598163	And I should have found this.
3598163	3600931	He says the error means your shell didn't use a bus environment.
3600931	3602949	So he's basically giving me another command to run.
3602949	3605634	So I'm going to copy this and I'm going to clear the screen again.
3605634	3607003	I'm going to paste in this new command.
3607003	3607794	I'm going to press enter.
3607794	3611374	And then you see that immediately I get a notification that my gateway is restarting.
3611374	3615270	So that means that the command is so it took a few seconds for everything to complete.
3615280	3617674	So just be a bit more patient when you see this.
3617674	3618839	So I'm going to copy this here.
3618839	3622630	Control shift C and I'm going to send this orchestrator it worked out.
3622640	3624135	This is the message I got.
3624135	3629749	So you see that when I sent it to immediately orchestrator, he didn't respond because the gateway I think was still booting all the agents.
3629749	3635655	So sometimes when you restart a gateway immediately it takes a while for all the gateways for the agents to get restarted.
3635655	3639510	So when you send this immediately and you do not see a response just be a bit more patient.
3639520	3647105	And here just as a tip when you come back into your terminal and you type in hemis profile list and enter you would see that now we have two gateways running.
3647105	3651738	Initially we only had the default gateway that was running and the gateway for dev was stopped.
3651738	3656160	But now you can see that we have another gateway that we have built for kite which is running.
3656160	3660152	So what we're going to do now is we're going to have to add kite into this group that we have created.
3660152	3665429	And to do that we're going to come to botfather click on the URL that he gave to us to be able to fetch the ID for kite.
3665429	3670407	Click on the name and then we're going to click to copy the of kite and then we're going to come back into our group.
3670407	3671211	I'm going to go to all.
3671211	3674464	I'm going to click on the three dots here and go to view group info.
3674464	3683277	And then here I'm going to click on manage and I'm going to come to members down here and I'm going to click on add members and I'm going to put in the username of kitespot.
3683277	3686003	And I'm going to select this and I'm going to click on add.
3686003	3688360	And then now Kite is added to this group.
3688360	3691517	We also have to make Kite an administrator for him to be able to work here.
3691517	3694527	Still on the all tab, I'm going to click on the three dots.
3694527	3695838	I'm going to come to manage group.
3695838	3699697	Then I'm going to come to administrator and I'm going to click on add administrator.
3699697	3701199	I'm going to add Kite there.
3701199	3702549	Review the permissions.
3702559	3704283	If you're fine with that, just click on save.
3704283	3705811	And then we can close this.
3705811	3707662	So now we have added Kite to the group.
3707662	3713186	So what we're going to do now, we're going to come into Kite's channel and we're going to send a message like who are you?
3713186	3719117	And this is the part that always gets me nervous because that is the point that you see if the agent to channel binding works.
3719117	3722649	If everything works, we are supposed to see a message from Kite that I am Kite.
3722649	3724648	So let's see if this is going to work.
3724648	3725217	Perfect.
3725217	3726568	I'm a bit relieved.
3726568	3728032	So here Kite responded.
3728032	3730721	I'm Kite Laris Cadence designer and engineer.
3730721	3734130	Now just to make sure that the other parts are working, I'm also going to send this to orchestrator.
3734130	3736862	And if this should respond that he is orchestrator.
3736862	3739762	So if Kite is responding in the shadow, then we are screwed up.
3739762	3745112	Let me do the same thing for studio just to be on the safe side that we have the right agents behind these channels.
3745112	3745481	Great.
3745481	3750626	So in orchestrator's channel he still responded I'm orchestrator which means that this is working very well.
3750626	3752742	Kite if you remember also responded he is kite.
3752742	3756570	And then now when I go to studio orchestrator also responded orchestrator is there.
3756570	3759530	So that means that the telegram channel to agent binding work.
3759530	3766684	Kite is never going to listen in orchestrator's channel and orchestrator would also not listen to ka's channel and that's exactly what we want.
3766684	3777030	So now that we have all the core aspects of the framework that we need ready, her message agent is ready, orchestrator is fully set up and kite our developer is also set up, group is ready, we can now start with the build
3777040	3777753	of the dashboard.
3777753	3783635	Now with the entire build of the dashboard, we're going to be using Kite who is basically playing the role of a designer and also our developer.
3783635	3792504	And before we even let Kite start building the dashboard, we're going to have to brief Kite on the whole thing that we want to build from the beginning to the end and a concept that we have for what we're building.
3792504	3796418	And for that I'm going to give Kite this prompt here as a briefing to know what we want to do.
3796418	3800565	So I just sent this to Kite and in the process I'll be explaining to you guys what I just sent to Kite.
3800565	3805915	I'm telling Kite, hey before we even write any single line of code, here is the whole picture of what we building.
3805915	3810530	So I'm telling Kite we're building a premium content automation studio with a beautiful web dashboard.
3810530	3812752	I'm telling Kite how the whole process is going to work.
3812752	3823990	So we're going to have Atlas who is going to be our researcher. basically go and propose some ideas and then we will promote one as a user and then Vera would write the content of the slides and after this is done Kite who is also
3824000	3837029	our developer and our designer would fit this content into one of the templates that we would pick and then we would render that template from an HTML document into an image with about 10 1080 to 1350p and then Orin who is going
3837039	3846150	to be our publisher would publish this to any network that we want to build this on and I'm also telling Sky that we're going to set this on a small Python server which is going to be on dashboard and also very important I'm
3846160	3855349	telling Kai that we're going to give him or a template that we're going to be working with and I want this template to be the design source of truth because I don't want him to change anything that we're going to be putting in the
3855359	3861942	template and also a few things that I'm giving him that I want to have a backup protocol and also some principles of how the whole build is going to be.
3861942	3865774	So Kite responded that hey understood here is the plan in my own words.
3865774	3877444	Candice is a complete content automation studio with a polished web dashboard as a control interface and he's basically just repeating all the things that we told Kite in the sequence how the whole flow is going to work.
3877444	3880797	So Kite is basically ready to fill in to build the dashboard with us.
3880797	3887022	So in the next stage we're going to tell Kite to build the Python back end on which this web dashboard is going to be running on.
3887022	3889349	I'm going to give this prompt here to get that ready.
3889359	3893479	I'm telling Kai that hey we're going to build this dashboard in a way that is going to be very secured.
3893479	3897361	So for the first part we're going to be setting this thing on what is called SSA tunneling.
3897361	3906000	So that means that whenever you want to connect to the dashboard you're going to use a command like SS minus N minus L this port here and at the end you're going to put in your username and your IP address.
3906000	3907349	But I'm going to show you how this would work.
3907359	3913225	Now the reason why we are using this in the first place is that the web dashboard is not going to be available to the public internet.
3913225	3918495	It's only someone who knows the password of your VPS server that would be able to connect to the dashboard.
3918495	3920146	And that is why it makes it so secured.
3920146	3925286	But even after we are done with the build, we're going to be installing tails skill that will save the dashboard for us.
3925286	3930526	Now tail skill is one of the most solid security setups that we can use to get our dashboard online.
3930526	3933885	So for the first time, we're going to use SSH tunneling to access the dashboard.
3933885	3938150	But when we are done, we're going to be installing tail skill which is going to host the whole thing for us.
3938160	3945315	And the best thing about tail skill is that we would then be able to access the dashboard on any PC that is running our tail skill account or even on your mobile phone.
3945315	3945772	All right.
3945772	3946444	So kite is done.
3946444	3952802	He set up the back end that we used to run the dashboard and he also gave us the SSH tunnel command that we're going to use to access the dashboard.
3952802	3957009	So what we're going to have to do is to just copy this command that Kite has provided for us here.
3957009	3961283	We're going to go back into PowerShell and then in PowerShell just put in this command ssh minus L.
3961283	3963743	This is the port that we use to save the dashboard.
3963743	3971785	This is the security end and also this is the your username which in my case I created a new username if you remember called Larry and this is the IP address of the VPS server.
3971785	3974470	Now here I'm going to put in my password and then just press enter.
3974480	3976248	Now it's going to bring you to this point here.
3976248	3977979	It's going to be a ca just blinking.
3977979	3980882	That means that you are connected to the back end of the VPS server.
3980882	3987670	So what we're going to do now is we're going to open a browser and then just as Kite gave to us, he says that we should open this URL on our browser.
3987680	3988996	We're going to copy this URL here.
3988996	3990906	We're going to paste this in here and press enter.
3990906	3993062	And then you see that we are connected to the dashboard.
3993062	3996667	But because we do not have anything there yet, that is why we get this error response.
3996667	3999714	But in principle, we are connected to the back end of the Python server.
3999714	4004790	Now what we're going to do is in the next thing we're going to have to put something on the dashboard for us to see basically what we're building.
4004790	4007731	And for that we're going to tell Kite to create a web upload page.
4007731	4012943	Now in this web upload page we're going to upload all the files that is going to save the template of what we want to build.
4012943	4020299	I'm going to copy this prompt to Kite and I'm going to send this to Kite to build the upload point where we can upload all the dashboard stuffs that we need.
4020299	4027927	And this would contain the HTML template to the dashboard and all the the slides that we're going to be using when we building these carousel slides.
4027927	4030921	Whilst Kite is building that, let me show you how the template looks.
4030921	4035510	So this is the empty template that we're going to give to Kite to upload on the dashboard for us.
4035520	4038198	So we see that we have the content tab which is a bit populated.
4038198	4039551	The idea tab looks empty.
4039551	4041270	The studio tab also looks empty.
4041270	4042457	Everything looks empty.
4042457	4048503	But once he's done, he's going to basically add this to the back end and then we're going to populate this dashboard template as we build.
4048503	4049048	All right.
4049048	4049801	So Kite is done.
4049801	4054381	He's built the back end which we're going to use to upload all the files that he would need to build the dashboard.
4054381	4056038	And he gave us this URL here for that.
4056038	4057190	So I'm going to copy the URL.
4057200	4059661	I'm going to open the browser and I'm going to paste in this URL.
4059661	4062390	Hopefully, we have a web upload upload dashboard.
4062400	4063794	Okay, so this is working quite well.
4063794	4068487	So, he built the cadence upload back end and he's telling us that he expects four files.
4068487	4075245	So, the template, so the HTML templates and three JSON files which are going to be the templates of the carousel slides and for the reuse.
4075245	4080292	So, I uploaded all the four files that are required and also this is confirmed on the dashboard that these four files are saved.
4080292	4087083	So the next point what I'm going to tell Kite is that hey I have uploaded all the four files that are required to build the templates to build the dashboard.
4087083	4091915	So I want him to serve these files on the Python temp so that we can actually see that this is working.
4091915	4103669	So what we're basically telling Kite in this prompt is that the file that we upload the template is called cadence dashboard template.html but I want him to rename this to index.html into the dedicated folder that we have created
4103679	4105147	for the dashboard that we're going to be building.
4105147	4113749	And also very very important at least in my case if you want to change the templates then you don't need to give Kite this instruction but what I'm telling Kite is that hey this is going to be the design source of truth.
4113759	4123110	So whenever he's building anything he should always check for the template to make sure that he hasn't made any design changes to the temp so that whatever he's going to be building is going to be identical to what we have in the
4123120	4134309	templates. on telling him that hey the template contains basically mock values like hardcoded stuff so that nothing basically looks empty but those numbers that we have on the templates are going to be replaced with real metrics once we
4134319	4143110	start building the dashboard and this one of the nice things not that I like about Hermes so what you can see here for instance is that he's done with basically the work that we give to him and you can see that he's using an
4143120	4155590	inbuilt browser to check to see if everything that is there is correct so he's clicking and taking browser snapshots he's clicking different sections and taking snapshots of that aspect just to be sure that whatever he did is identical to what is in the
4155600	4155877	template.
4155877	4160309	And this is one of the main reasons why I really like working with Hemis because I build dashboards a lot.
4160319	4166644	And if the agents or Hemis allows the agent to be able to work with a headless browser to be able to see what it's building, this is really cool.
4166644	4167131	All right.
4167131	4168402	So Kite says he's done.
4168402	4172986	He says the template is logged in but is partially complete because there's one file that is missing.
4172986	4177127	So when I look here, he says that he didn't find the templates packed because it's false zero.
4177127	4178709	Let me see why this is the case.
4178719	4180231	So it could be that our upload didn't work.
4180231	4183678	So he's saying that we should re-upload this file through the upload point.
4183678	4187446	So I'm going to put in this here again and I'm going to re-upload the templates pack.
4187446	4190934	So I'm going to tell Kite I have re-upload templates pack.json.
4190934	4192175	Can you confirm?
4192175	4192795	Perfect.
4192795	4195546	So it appears that something happened the first time that I uploaded this.
4195546	4197410	So he says that yes, he can see it now.
4197410	4203997	He checked the file and all the uploaded source files are now present in the folder that we require them to be which is perfect.
4203997	4208544	So now let's go to the dashboard and see if the dashboard is actually rendering on the Python ser.
4208544	4211750	So to do that we're going to use local host to do that we're going to use local host col8892.
4211760	4218570	The 8892 is the part of the server and the local host is basically the local area on our server that we're going to use to access the dashboard.
4218570	4220692	And then when I open this hopefully beautiful.
4220692	4223737	So you can see that now we have the dashboard loaded just as we had in the template.
4223737	4226635	So let me open the template for us to do a one is to one copy.
4226635	4230216	This what we had in the template and this is what is being saved on our dashboard.
4230216	4233766	So all the pages are identical to what we had in the template.
4233766	4235240	So kite is doing a pretty good job.
4235240	4239590	Now, in the next stage, we're going to, this is one of the things that I always recommend when you're building stuffs with the agents.
4239600	4243456	Let the agents always create a copy of the dashboard before they make any changes.
4243456	4250070	I always say this in every video that I worked on the dashboard for several days and my agent just made a mistake and basically I lost everything.
4250080	4257345	And that is why it's very important that you tell your agent that, hey, before you make any changes to the dashboard, please create a copy of the dashboard and save it somewhere.
4257345	4260877	And also on the dashboard, we have this section here that is the version number.
4260877	4264700	And I want him to update a version number anytime he makes a change to the dashboard.
4264700	4269510	So I'm going to copy this prompt and I'm going to send it to Kite to implement this and Kite is done with that as well.
4269520	4272012	So when we come to the dashboard and we reload the template.
4272012	4274143	So we should now see that he has changed.
4274143	4275522	So we used to have editorial.
4275522	4278417	Let me open the template for you to see what this looked like before.
4278417	4289350	So in the template in this bottom section here we used to have version 0.1 editorial and you can see that now this is updated in our version to version 0.1 which means that kite is going to keep the version update always
4289360	4290543	updated as we move on.
4290543	4292403	So currently we're going to start with the build.
4292403	4301644	So all the parameters that you see here in the content tab are basically hardcoded from the template that I built and also the all the stuffs that we have in the agents tab, the heat map, everything is hardcoded.
4301644	4313270	So we're going to tell Kite, we're going to give Kite a prompt to basically update the dashboard metrics that we have here and also the agents tab so that we have real data, real data from our hemis setup that we have but
4313280	4315714	not from the hardcoded stuff that we have in the template.
4315714	4322374	And I'm telling him that hey when you are done confirm that both tabs show the real data and the heat map matches the run table.
4322374	4327379	Now for the heat map all the information is going to be pulled from the agents login database that we built.
4327379	4334540	If you remember we built something where every agent is going to log the activity whenever they do something whenever they perform any action.
4334540	4334970	All right.
4334970	4336327	So Kite is done with that as well.
4336327	4337499	Let's look at what Kite built.
4337499	4338850	Let's reload the dashboard.
4338850	4343289	So here you can see that he's now pulling the real metrics from our data agent database that we built.
4343289	4348470	So you can see that now kite is trying to pull the real metrics from the agents login database.
4348480	4359544	So you can see that currently in the agent workload because none of the agents have done something today that is why everything stays at zero for atlas vera and origin and kite is the only one that'll be working with today.
4359544	4361083	So kite is basically at 100%.
4361083	4367967	And the same thing when you come to the agent database you can see that everything is almost zero for all the agents because they haven't done anything today.
4367967	4370179	So I'm recording today on the second day.
4370179	4373725	So basically I would expect that there would be some metrics from the previous day.
4373725	4381619	So I'm going to tell Kai that hey it appears that the metrics that are being pulled are only being pulled from today but there should be some activity from the agents the previous day.
4381619	4388636	So he should make sure that the dashboard doesn't only reflect today but basically reflects all the data that we have in the agent login database.
4388636	4391016	So I'm telling Kite hey this looks awesome.
4391016	4391430	Thanks.
4391440	4395154	However it appears that the agent metrics being displayed are only from today.
4395154	4400100	I do not see any data for instance from yesterday. even though the database should contain this.
4400100	4406185	So he should basically investigate and see what is wrong and make sure that we are serving all the data that is currently in our agent login database.
4406185	4406709	All right.
4406719	4407733	So Kai says he's done.
4407733	4409011	It appears there was an issue.
4409011	4416737	So he says that the real problem was there was this issue with the test server Python server that was basically deleting stuff from the production database.
4416737	4418315	So he basically fixed this as well.
4418315	4419898	So he says that the fixes are made.
4419898	4426688	The test no longer touch the production database and he's basically put in some metrics some implementations to make sure that this does not happen.
4426688	4431724	But what I would like Kai to do here before we even proceed further, I want to be sure that this problem is fixed.
4431724	4442641	I'm going to tell Kai that hey perform a quick end to end smoke test to all the agent trigger a few test activities and verify that the resulting data are saved in the database and also correctly reflected on the dashboard.
4442641	4449602	If there is anything that is not there, he should fix it as well because the agent login database is going to be an integral part of what we are going to be building.
4449602	4457588	And that is why I want to be thousand% sure that the agents are logging and also that all the things that they do also reflect here on the dashboard.
4457588	4461326	And by the way, all these deep prompts that I'm adding, I'm going to make these available to you.
4461326	4466586	So that should you have the same situation, you can just copy paste the prompt and give it to the agents or Kite to fix this for you.
4466586	4467049	All right.
4467049	4468963	So Kite says he's done with the smoke test.
4468963	4470576	He repeated this across all the agents.
4470576	4473110	And currently you can see that all the agents completed.
4473120	4476942	When we come back to the dashboard, you can see that now we don't have the 00 that we had.
4476942	4481590	We basically have metrics from all the agents that is being pulled correctly from the agent login database.
4481600	4483317	And the same thing also applies to the heat map.
4483317	4487450	And when we come to the dashboard, we also see that the agents total runs are also correct.
4487450	4492226	There is one more thing that is not correct here which has to do with the agent workload distribution.
4492226	4497521	This would always have to sum up to 100 so that we can always see which agent has the most workload.
4497521	4501172	I'm also going to tell Kite to fix this and after that we can continue with the build.
4501172	4506278	And for that I'm telling Kite, hey on the dashboard homepage, the agent workload share distribution does not make sense.
4506278	4511189	So basically I'm telling him that everything should add up to 100% but currently everything adds up to 350.
4511199	4515069	The idea is that whenever I look at this I'm supposed to see which agent has been more active.
4515069	4517521	So he should basically correct this for us as well.
4517521	4518965	And Kite has done with that as well.
4518965	4522883	So basically now when I look on the dashboard you can see that the distribution now makes sense.
4522883	4530057	It all adds up to 100% and I can see clearly that Kite is the most active agent because he is the one building the dashboard anyway.
4530057	4539344	So now the agent login database is working correctly. all the metrics that have been put on the agent tab are also making sense so we can start with the build of the other components of the dashboard.
4539344	4547597	I'm going to explain the concept of what all the prompts are going to do and I'm going to put in all these prompts in one go so that you don't have to sit and watch me put in one after the other.
4547597	4551930	Now in the next prompt we're going to build an exporter and let me explain why we need this.
4551930	4559303	So initially, previously whenever you wanted to build a carousel image like a slide or something like that, you always had to design everything in a photo editor, right?
4559303	4563001	And then save it, export it as a picture and then you had your carousel image.
4563001	4566341	But the trick what we're going to be using here is we're going to render every slide.
4566341	4568564	We're going to build every slide as an HTML.
4568564	4573495	Now, if you build a slide as an image, you pay for every image that you generate.
4573495	4581189	So if you want to change any text in the image, then it means that you always have to pay for API calls, which makes it not fun anymore to work on slides.
4581199	4582916	So, we're going to build this in a smarter way.
4582916	4586929	What we're going to do is we're going to build every carousel as an HTML file.
4586929	4592540	Now, because it's going to be an HTML file, it will be very easy for us to edit any text that we want to edit.
4592540	4597549	And let me just go into my setup just to explain for you guys to get a concept of how we're going to build a slice.
4597549	4599370	So, let me take this one here for instance.
4599370	4603840	Everything that you are seeing here looks like an image, but it's basically not an image.
4603840	4607002	It's an HTML document that is rendering the file like this.
4607002	4612677	So whenever I want to export this as an image then I'm going to deploy what is called a headless browser.
4612677	4615466	So a headless browser doesn't need a desktop to run.
4615466	4622121	It's basically going to render this file here which is basically an HTML file and then take a snapshot of what it sees.
4622121	4633765	So eventually all the things here that we are seeing which is rendered as a code would be then exported as a JPEG and then with that you can upload this to Instagram, Tik Tok or whatever wherever you want to build this on.
4633765	4640572	Now the reason why we do it in this smart way is that originally whenever you want to build any carousel slide you have to use an image generator.
4640572	4645172	Maybe you can use nano banana or all the AI models that are out there to generate images.
4645172	4650547	But when you even want to change one text then you have to tell the AI model again hey I want to change the text.
4650547	4658267	Maybe for instance I want to change this from most people to most users and I have to tell my a model again hey I want to change the text from most people to most users.
4658267	4662628	And then you pay for every edit that you do which is probably not the smartest way.
4662628	4667264	So how I build this and what most users are using is that you build the whole slide as an HTML file.
4667264	4675270	And by so doing when you can change everything that you want to do in the file without having to regenerate the prompts or regenerate some API keys.
4675280	4677858	So here for instance this is what our dashboard is also going to do.
4677858	4683880	When I click on fine-tune and I pick this element I can just change the text here from people to most builders, right?
4683880	4690390	And you see that it does I can save and rerender and then I have my new slide without me having to do any API call.
4690400	4691150	the same thing.
4691150	4692545	I can change all the contents.
4692545	4694634	This is why I really like what we're building here.
4694634	4695641	I can change the layout.
4695641	4702398	I can move every content here, change the size, put it in every format that I want to do it without me having to pay for any API calls.
4702398	4715270	So, what we build, we're building every carousel slide as an HTML file and then when we are ready, we deploy a headless browser that looks at that HTML file we have created and creates a snapshot of as a picture that we can then upload to more
4715280	4716614	any social media platform.
4716614	4724232	So we avoiding the aspect of complicating the whole carousel image design where you have to make an API call for every edit and pay for every edit.
4724232	4728147	We are rendering everything as an HTML file that will be completely edited.
4728147	4730525	Quite crazy the things that you can do with standard HTML.
4730525	4734675	Like you see here all these templates that you are seeing here, none of it is a picture.
4734675	4741559	Everything is built with standls that someone might not even believe you that this built with HTML.
4741559	4753510	So basically with this prompt here, what the prompt is doing is that we're going to build this setup of this headless browser that would render whatever that we build from an HTML file into an image that can be uploaded on any social media platform
4753520	4754081	that we have.
4754081	4756562	So we are not building images straight ahead.
4756562	4759479	We build an HTML file which contains the structure that we want.
4759479	4762960	Then once we are satisfied with it, we export it into an image.
4762960	4766123	And for this we are using a headless browser that is called Chromium.
4766123	4769507	And by default, most of the Hemis setups come with Chromium.
4769507	4771754	So we might not even need to install this on our own.
4771754	4775830	We can just leverage what Hemis already has and then use it to build what we want to build.
4775840	4780310	If you remember when we were building the dashboard, there was a aspect that I told you that the agents were basically.
4780320	4786315	So here for instance, you can see that Kite was rendering a browser where he was going to the dashboard and making sure that everything was working.
4786315	4787830	That is the same concept I'm going to use.
4787840	4791779	We're going to let the designer in this case as well is going to be Kite use the same headless browser.
4791779	4796893	But right now he's not going to use it to check the dashboard, but he's going to use it lots of what the HTML file contains.
4796893	4801472	It makes it so easy to be able to build slides without having to pay for API calls every time.
4801472	4803292	And Kite is done with that as well.
4803292	4810793	He did a smoke test and he verified that the images were indeed being rendered from the browser into for instance here a PNG file.
4810793	4814557	Now in the next stage we're going to build all the things that are going to run from the back end.
4814557	4823414	So I'm going to explain all these backend prompts and then I'm going to give these to kites but I'm going to explain all these prompts to the point where we get to a prompt that would trigger a front-end design.
4823414	4829264	So when you are using the prompt everything that I say backend back end I try to add this so that you can see what to expect.
4829264	4832608	If it's a backend prompt then it wouldn't show anything on the dashboard.
4832608	4836731	It's basically building the foundation on which we would build to show something on the dashboard.
4836731	4841853	When we get to the aspect here where I write design then it means that what you going to do is going to show a design.
4841853	4849277	But if I get to an aspect where I realize that it's quite useful to explain I'm going to explain this to you guys as well so that you can also understand what these prompts look like.
4849277	4856052	And in every case I always include sort of a description to basically explain what the prompt is going to do and what you should expect.
4856052	4858094	So now we are done with the exporter prompt.
4858094	4861108	The next prompt is going to be the template packs auto fit.
4861108	4866070	Now whenever we are generating an idea, let me use my setup to give you a concept of what I'm doing.
4866080	4867872	So when I click on generate ideas, let's see.
4867872	4870599	I already have some ideas that are already generated here.
4870599	4874670	So let's look at for instance building a one person AI operation team.
4874670	4880609	Now when I like this idea and I click on promote basically I can decide on the number of slides that I want to generate.
4880609	4883893	So let's say for instance I want to generate six slides and I say write slides.
4883893	4892762	What is going to happen is that Vera who is going to be our right is going to write the slides for the carousel or the content or the text for the carousel that we want to generate.
4892762	4900006	Now like I said all these things that Vera is going to give to us is just going to be raw text but we have to be able to insert these text into the template.
4900006	4908304	This prompt that we're going to build here is going to build that part where it's going to take the content that has been generated by Vera and insert it into the HTML template that we have.
4908304	4912098	So all the templates that you see here like I said these are basically HTML templates.
4912098	4917405	So for instance when I look at this example here you can see that some of it have longer word characters than some.
4917405	4919580	So this one for instance has longer characters.
4919580	4921536	This has a different layout and stuff like that.
4921536	4930117	So then what is going to happen is that the back end that we're going to build is going to look at a template that you select and then adapt the text that Vera generated here to fit that template.
4930117	4932324	And this is what I call the auto fit feature.
4932324	4938381	And for this to work, we have to build a render engine that is going to look at the content that Vera generated look at a destination template.
4938381	4941170	So here for instance, if I say that, hey, I like this content.
4941170	4945644	When I come to approve and pick templates, then it ask me which of the templates I want to use.
4945644	4955750	So whenever I select the template that I want to use, then the back end that we're going to build here is going to look at the template that we selected, look at the number of words and characters that are in there and then adapt the text that
4955760	4957892	Vera generated to fit that template.
4957892	4969189	Now imagine that if the words that Vera generated are way longer than what the template can fit, then the carousel just becomes ugly and that is why we build this render take care of that for us and after that we're going to build a
4969199	4970612	pipeline to talk to the crew.
4970612	4980790	So currently whenever I'm talking to the crew right I'm chatting with Kite able to chat with Vera I'm not able to chat to our publisher but we want to be able to chat with them from the dashboard and by chat what I mean is that when I come
4980800	4988195	to the idea tab and I click on generate idea this sends a message to Atlas who is our research look for ideas of what we can build.
4988195	4995447	I'm talking to Atlas through a code where I send a trigger to Atlas that hey generate some ideas and the same thing applies for all the other agents.
4995447	4999502	Whenever we want to publish something we're not going to come to Telegram and tell them to publish.
4999502	5003729	We want to push a button the dashboard that is going to trigger the agent to publish the content.
5003729	5006768	And these are the things that prompt 17 is going to do.
5006768	5013990	It's going to build an interface where whenever we click a button on the dashboard, it sends and triggers an agent to do that particular task for us.
5014000	5015750	And then we're going to have prompt 18.
5015760	5020583	Prompt 18 is going to be exclusively for Atlas who is our ideas guy and our researcher.
5020583	5024755	And I'm basically just telling Atlas how I want the carousels to be designed.
5024755	5026628	So here, these are just examples of what I put in.
5026628	5036263	I'm telling Atlas that hey whenever you're writing the carousel slides I want to have this written in plain simple language short words short sentences no hype no buzz words and stuff like that.
5036263	5046041	So this prompt is basically giving Atlas an orientation of how we want the content and also Vera who is our content writer how we want the content of the slides to look like.
5046041	5049861	And here we're also giving them an orientation on how he's generating an idea.
5049861	5055767	He should generate four ideas and basically an orientation on how we want the whole carousel slides to look like.
5055767	5061258	And then we're going to have this last prompt here which is going to be basically for our publisher whenever we want to publish.
5061258	5071910	So for instance when we come to the dashboard and I come to my studio tab for instance if I want to publish something here I'm just going to click on post and then this can be published directly to Instagram to Tik Tok or wherever you
5071920	5073008	want to apply this to.
5073008	5076732	But for that as well we need to build a backend and that is what this prompt is going to do.
5076732	5084834	This prompt is going to build a backend so that whenever we trigger an upload then the upload can be pushed directly to whatever social media platform that we want to push this in.
5084834	5086433	So I'm going to render all these prompts.
5086433	5091212	The first prompt being the one that is going to take the text that has been generated and adapt it to the template.
5091212	5097884	The next prompt which is going to be taking care of that we can use all the buttons on our dashboard to trigger an action to the agent.
5097884	5102027	The prompt 18 which is going to take care of how we want our ideas to be generated.
5102027	5108276	The number of ideas that we want to be generated, how we want the cast, how we want the carousel slides, the content to look like.
5108276	5115102	And we would also have the last prompt that is going to take care of publishing to the server or the social media platform that we want to publish this to.
5115102	5116732	So I'm going to run all these prompts.
5116732	5121750	If I get any backs, I'm going to pause and I'm going to explain this to you so that you guys can also follow what we would do there.
5121760	5122057	Right.
5122057	5124633	So Kite is done with processing all those prompts as well.
5124633	5126746	Like I said, I didn't have to respond to anything.
5126746	5130255	I just copy pasted all the prompts to Kite and he processed all the back end.
5130255	5136021	Now in the next stage, we're going to grab some API keys and I'm going to explain every API key and why we need that.
5136021	5139024	The first API key that we're going to search is for publicity.
5139024	5144293	So perplexity is one of the AI models that you can use that is very very strong in research.
5144293	5155830	So I added this feature so that when you are writing a carousel and you want the agents to really use recent data then for instance you can use perplexity as a research model where Atlas is going to query perplexity to do the research
5155840	5158130	before the contents of the slides have been written.
5158130	5160194	Just to give you an example of where we would need this.
5160194	5166281	For instance, when I come to my dashboard and I click on generate ideas, you see that I have a couple of ideas that have been generated for me.
5166281	5169533	So for instance, let's go for the builder AI automation map.
5169533	5176920	Now when I want to promote this article or when I want to promote this idea into slides, I do have this option where I take research with publicity.
5176920	5183768	If you take research with publicity, then the agent will query publicity as a research tool to gather this information on this new idea.
5183768	5191481	If you do not take this article, then the agent will just do a standard web search to get ideas for this content or probably what the agent is also already trained on.
5191481	5202896	But if you want really research based content, then you can toggle this research perplexity and then the agents will basically do a researchbased content for the article or for the idea that you want to create.
5202896	5204950	So that's going to be the first key that we're going to get.
5204960	5208229	Now to get this, you can come to Now to get this, you can come to console.plexity.ai.
5208239	5211073	I'm also going to provide a link to this in the description section.
5211073	5213865	Then when you're here, just create an account or login if you already have one.
5213865	5216481	And then when you are logged in into the console, you do not have to do much here.
5216481	5219274	You can just come to the left section here and click on API keys.
5219274	5223843	And then under API keys, just come to the top right section here, click on generate API key.
5223843	5225830	And you can put in web key you want to go with.
5225840	5230593	For this tutorial, I'm going to call this comp mechanic tutorial test and then just click on create a key.
5230593	5233451	And after that, you see that an API key would be generated for you.
5233451	5237628	So just copy this API key, save it in the safe space, and we're going to use this API key.
5237628	5240271	The next stage we're going to get an API key from imageB.
5240271	5242427	But let me explain to you why we need this.
5242427	5249345	So what we want to do with our setup is that we have our cadence and we want to push images from here to Instagram for an example.
5249345	5249750	Right?
5249760	5255486	The issue is that if we want to push our slides directly from cadence to we need to get Instagram API key.
5255486	5258837	If you want to do this for Tik Tok, you need to build your own Tik Tok flow.
5258837	5263873	If you want to do this for Facebook, you have to create your own keys, your own flow and stuff like that.
5263873	5265539	And this is very very complex, right?
5265539	5270731	We're going to spend more time building those connections than basically focusing on the dashboard that we want to create.
5270731	5275338	So what we're going to do is that there are some platforms like buffer or metrical.
5275338	5281720	And what these platforms do is they have access to all the social media platforms and they have worked on all those backends for you.
5281720	5290790	So all we would have to do is to push our slides through a platform like metricle or buffer and they would push the slides to the social media platforms that we want to go to.
5290800	5296810	There is one c however that at least from my testing buffer doesn't allow us to push our images directly to that platform.
5296810	5306315	So what we're going to need is an intermediate storage where the images that we generate will be pushed to and then from there the images would go to buffer and for that we're going to need a platform called image BB.
5306315	5307366	Now this BB is free.
5307366	5317829	So what is going to happen is that whenever you push an image or whenever you push a story or a carousel from our cadence this would be first be pushed to BB and then from image they would go to Instagram.
5317829	5321358	Now, it looks complicated from the setup that I'm explaining to you, but we're going to wire this in.
5321358	5328286	And when you click on post, like for instance, when I come to my dashboard here and I click on post and I choose, for instance, I want to post to Instagram.
5328286	5329413	This is going to happen.
5329413	5331450	All this transfer is going to happen automatically.
5331450	5334340	So, you do not have to go here, push from here to here, push from here to here.
5334340	5336454	We're going to wire in all those connections.
5336454	5338790	And to do that, we're going to come to image.b.
5338800	5339611	It's completely free.
5339611	5341153	So, you can just create an free account.
5341153	5344897	And then once you create the account, come to the left section here and click on API.
5344897	5346959	And this brings you to the API page.
5346959	5349423	When you are here, just click on add API key.
5349423	5354849	Create an API key, store the API key, and then we can proceed to the next API key that we will need.
5354849	5361110	Now, the next API key that we will need is the platform that is going to push our slides to the social media platform that we want to go to.
5361120	5363281	Now, here there are several platforms that are out there.
5363281	5365913	As an example, we have Buffer who can do this for us.
5365913	5368411	And we also have Metro who can also do this for us.
5368411	5369466	Both of them work.
5369466	5374117	I know that a lot of people use metrical because they have a very very powerful dashboard that they use.
5374117	5386278	But from my testing, I realized that for you to be able to push our slides from Cadence OS to Instagram or Tik Tok, if you want to use metrical, then we have to go for a higher payment plan.
5386278	5392772	It's only the advanced option where you're going to pay 43 in my case a month that would come with the metrical API.
5392772	5402912	So this was quite expensive for me because in my case if you really need metric code to work with kers then you would have to go with advance where you pay dollars a month a month to be able to get access to their API.
5402912	5406841	Remember an AP is an interface that would allow us to be able to communicate with the platform.
5406841	5410126	And in my case I had just two social media accounts that I was using to test.
5410126	5413751	So I didn't want to pay €43 a month just for two social media platforms.
5413751	5423521	But advantage with metricle is that you can go for instance with their starter plan where you would pay $16 a month and then you can add so many social media platforms without having to increase your pricing.
5423521	5432936	So for instance if you have four social media platforms Tik Tok, Facebook, LinkedIn etc. you would still be paying $16 a month which I find pretty cool and I'm going to show you when I would go with metric.
5432936	5437193	We have another platform that is called buffer and that is what I used in what we are building with hidden.
5437193	5442665	Advantage with buffer is that they would allow us to be able to use their API assets even with a standard plan.
5442665	5446266	And I think in my case I went with the five plan which is essential right?
5446266	5454445	So even with this you have access to three API keys and you would be able to use this but with metrical you can only get access to the API key if you have the dollar plan.
5454445	5459187	But the caveat with Buffer is that every social media platform that you add you pay an extra $5.
5459187	5462669	So if you have Tik Tok, Facebook, Instagram it becomes $15.
5462669	5466608	If you add LinkedIn it becomes $20 and so it can get a bit expensive.
5466608	5476955	So in that case, if you don't really care about pushing directly from cadence to the social media platform, I also did add an option on the dashboard where you can basically download all the slides.
5476955	5478312	Let me do an example here for you.
5478312	5481747	When I click on slides, you can see that the slides are downloaded here.
5481747	5485415	When I click on this, you see that I have all the slides downloaded here.
5485415	5488363	Let me go to thumbnails and you can see that I have all the images.
5488363	5499270	And what I also added for you is that you can click on caption where you're going to see the caption that is going to be required for you to post. and then you can post this yourself and in that case then probably metrical would be a best option because
5499280	5509990	they do have for instance for the $16 plan you would be able to add more social media you can see here up to 10 brands which makes it very cool but if you really want to leverage the push from cadence directly to your social
5510000	5518870	media platform then buffer might be a cheaper option I'm just trying to explain how you can decide on which are the platforms that you want to go for so for this example we're going to be going with Buffer because like I said I had
5518880	5527729	only two social media accounts and I didn't want to pay €43 here for my testing so you can just create an account with whatever platform that you want to go for and then just loging into your account.
5527729	5538066	Once you're logged in into your buffer dashboard, just come to the bottom section here where you have my organization and click on API and then here click on new key and then you can create an API key.
5538066	5545525	Now with these three API keys from perplexity, imageb and buffer, we would be able to wire this into cadence and continue with the build.
5545525	5549253	Now with these API keys that we have gathered, we have to store these API keys to our server.
5549253	5551430	And to do that, we're going to come back to PowerShell.
5551440	5555856	I'm going to log in back into the terminal. come back into the and I'm going to paste in this command.
5555856	5567669	Now this command is going to ask us for all the API keys and these are going to be secretly stored into the you can in principle just give kite directly into the API keys but this is not a recommended approach because if gets
5567679	5576654	compromised then someone has access to your API keys and that is why whenever I'm adding API keys or secrets I prefer to do it from the rather than directly giving it to kite or telegram.
5576654	5580201	So just press enter and then it's going to ask you for your buffer access token.
5580201	5582286	So here I'm going to paste in my buffer key.
5582286	5583009	Paste this in.
5583009	5584452	And after that just press enter.
5584452	5587630	And then it's going to ask you if your image BB API key.
5587630	5589090	I'm going to copy this as well.
5589090	5590173	I'm going to paste this in.
5590173	5590792	Press enter.
5590792	5593547	And then the last one you're going to be asked for your perplexity.
5593547	5593777	Oops.
5593777	5595294	I realized that I made a mistake.
5595294	5598041	So the first one that I put in wasn't for buffer.
5598041	5599156	It was for perplexity.
5599156	5601443	So I'm going to cancel this and I'm going to run this again.
5601443	5602699	I hope it doesn't get messed up.
5602699	5604921	I'm going to tell Kite in the process that I made a mistake.
5604921	5606631	I'm going to recall the same command that I used.
5606631	5609358	I'm going to press enter and then I'm going to copy the right buffer key.
5609358	5611010	Then I'm going to copy the image PV.
5611010	5613023	Then I'm going to copy the Plexity API key.
5613023	5614278	I'm going to paste this in.
5614278	5618307	And then you can see that all the characters are saved and we get a notification that all done.
5618307	5623430	So what I'm going to do now is I'm going to come to Kite and I'm going to tell Kite that hey, we've stored these three API keys.
5623440	5626377	He should do a smoke test to make sure that all the keys are working.
5626377	5628149	So I'm going to copy this and I'm going to give to Kite.
5628149	5636219	But because I made a mistake and did it twice, I'm going to send him a I'm going to write I did make a mistake and added it twice so you can ignore this entry.
5636219	5638124	Then I'm going to tell him to do a smoke test.
5638124	5642642	I hope that the first mistake that I did, he would be able to just rectify it and see that all the keys are working.
5642642	5652337	Hey, if you're finding value in this content that I'm creating, hit the subscribe button, subscribe to my channel, and hit the like button for YouTube algorithm to keep pushing this video to other people that will be out there.
5652337	5655153	It doesn't cost you anything, but it really does support my channel's growth.
5655153	5664464	A lot of work goes into crafting all these tutorials, creating that, creating the prompt, and that is why I'm not even able to upload a video every week because I test everything about 20 times before I push it out there.
5664464	5669631	And that is why I have to upload videos on a bi-weekly schedule because a lot of work goes into crafting all these things.
5669631	5670705	And kite is done as well.
5670705	5671740	So he did a smoke test.
5671740	5674991	He verified that buffer works, imageb works, and perplexity works.
5674991	5675430	All right.
5675440	5677285	In the next stage, we're going to put in prompt 20.
5677285	5685269	Prompt 20 is basically going to give us a trigger where we can publish an idea, create an idea, render a content, render a carousel and stuff like that.
5685269	5688380	So just copy this prompt here and we're going to give this as well to Kite.
5688380	5688822	All right.
5688822	5690370	And Kite is done with that as well.
5690370	5693272	Now the next three prompts are basically going to be the design prompts.
5693272	5697454	This is going to wire the ideas tab, the promotes tab, and also the studio tab.
5697454	5699906	And after that, we're going to basically test the whole thing.
5699906	5702458	So now we have this idea tab that has nothing there.
5702458	5704407	We have the studio tab that has nothing there.
5704407	5706470	We have the publish tab that also has nothing there.
5706480	5707552	And also the templates tab.
5707552	5710803	So what we're going to do is we're going to give Kite these prompts to wire those up.
5710803	5714452	And after that, we can test some functions so that you guys can see what we are building.
5714452	5718460	So I'm going to give all these prompts to Kite sequentially and then we can go to see the test.
5718460	5718868	All right.
5718868	5721157	So Kite is done with processing all those prompts.
5721157	5723232	Now, I know we've been building for some time now.
5723232	5726849	Now, let's see a real demo of the end to end to make sure that everything is working.
5726849	5731834	So, I'm going to come back to the dashboard and I'm going to reload the dashboard and then let's go to the ideas tab.
5731834	5737350	Now, I see that Kite did a smoke test where he tested one agent tonight before you trusted.
5737360	5740160	So, he just did a smoke test to make sure that the ideas are working.
5740160	5746733	Now, let's click on generate ideas to see if the end to end flow with Atlas doing the research, giving us some ideas is going to work.
5746733	5749317	So, I see a notification that he's doing the research.
5749317	5750927	Let's wait till the results come out.
5750927	5751922	And this worked very well.
5751922	5755110	So you can see that we have four ideas that was generated by Atlas.
5755120	5757998	Browser agents should verify, not just click.
5757998	5760659	Your agent needs a sandbox before it needs more tokens.
5760659	5763189	Now let's say that we want to promote one of these ideas.
5763199	5765593	So let's go with stop giving agents your whole app.
5765593	5766870	And let's click on promote.
5766880	5770151	And then here, let's say we want to generate 10 carousel slides.
5770151	5772167	And I'm going to say research perlexity.
5772167	5779007	And then here perplexity is enabled because we want to research perplexity is enabled just to make sure that we test that the API key is working.
5779007	5781283	And I also added this option here steroid mode.
5781283	5785806	Now this is going to create more of like a power sort of words for the carousel slides.
5785806	5787470	So let's just enable those two as well.
5787470	5789384	And then let's go to write 10 slides.
5789384	5790611	And then this is working.
5790611	5791784	So Vera is triggered.
5791784	5794384	Vera is the agent that does the writing of the content.
5794384	5798284	So he's basically reading the idea and doing the research to make sure that everything is working.
5798284	5802419	Doing the research to make sure that she got us all the information that we need to write that content.
5802419	5802892	All right.
5802892	5804013	And Vera created the content.
5804013	5806999	So you can see here that we have all the 10 slides generated.
5806999	5815059	We have the cover text which says your agent is not dump your packet is bloated and then it basically writes all the content that would be on every slide that we have.
5815059	5818064	Now let's say we want to approve this and we want to promote this into a template.
5818064	5821245	So let's click on approve and then let's pick a template in the next stage.
5821245	5823896	Now here we're going to be generating an Instagram carousel.
5823896	5825810	So we need a 4 is to5 aspect ratio.
5825810	5829213	Let's say just for this example I'm going to go with this purple one that we have here.
5829213	5832040	I'm going to select that and I'm going to click fit copy to this.
5832040	5844129	Now what is going to happen is that Vera is going to check if the content the text that she generated fits the number of characters that are in that template because if the words are way more than what the template can fit then the whole design gets ugly.
5844129	5854709	So what Vera is going to do is Vera is going to read all the hardcoded text that are in the template and try to adapt and fit the content that she generated to that particular template and Vera basically readapted the content
5854719	5857048	that she generated to fit the template that we have.
5857048	5862723	So because the template that we chose has less words in the cover, she just rewrote the package into agent.
5862723	5866987	Okay, package fat and then basically wrote all the content that would be on the slide.
5866987	5873188	Now I'm going to click on render now to push this into the studio tab so that we would see how this would look on the template that we selected.
5873188	5875116	Now you see a notification open in studio.
5875116	5879990	Now we can click open in studio here and this would open the slide that we just generated in studio.
5880000	5891990	Now let's click on this and you can see that just as Barard wrote agent okay packet fat packet fat bad agent run starts with too much context whole ripple noise guesses and then when you click on this you can see all the text
5892000	5902950	that was generated so assuming maybe we don't want to go with this text here for the cover we want to just fine-tune you can click on fine-tune the slide here and this would basically load the slide here and when we click on this here just
5902960	5914629	for an example I can write agents not the problem packet fat and then you can also move the slides up and down however you want to have them right this is all possible in the fine tune tab so I'm going to close this I'm going to discard
5914639	5926149	the changes and then let's say we want to push this to Instagram and this is the part that makes me nervous and for that I created a dummy Instagram account called content vibe so that when we push directly from our this would come
5926159	5935990	hopefully it would go through buffer and then this would come to this Instagram account open the package again let me click on and then here by the way you can come here and you can always change the template whenever you want to pick a
5936000	5941759	different template you can pick whatever template that you want and then cadence would basically rewrite the content to fit that template.
5941759	5942731	Now, let me come here.
5942731	5943988	Let me click on post now.
5943988	5947503	And then here, because I've configured only Instagram, it's only going to show Instagram.
5947503	5949061	I'm going to click on Instagram only.
5949061	5951430	And it's going to warn me and I'm going to get notification.
5951440	5952870	Hey, are you sure you want to post this?
5952880	5954715	I'm going to say yes, post now.
5954715	5956629	And then this is going to be pushed to buffer.
5956639	5962248	And hopefully, if the end to end stream works, we should see the post coming directly to Instagram.
5962248	5964844	And we get notification that this has been pushed to buffer.
5964844	5965891	Let's click on okay.
5965891	5968618	And this gets put from the studio tab into the publish tab.
5968618	5970038	Once this is pushed to buffer.
5970038	5972134	Now let's go to Instagram and see if we'll see this post.
5972134	5975964	I'm going to come to my Instagram and hey you see this it posted directly to Instagram.
5975964	5982302	So you can see this exact post that we had and generated in our cadence which is the first post that I've tested with this account.
5982302	5986970	And then you can see that all the text came just as we rendered them on the cadence website.
5986970	5992521	And then here as well we have the text that was generated also by the AI for the description section.
5992521	5993811	So this is working very well.
5993811	5998772	Now when I come back to the studio tab and I go to the published I should see oh so this is not working.
5998772	6002552	So it renders that we have one all but I do not see the slide that was generated.
6002552	6006260	So I'm telling kite hey the publish tab is not displaying any published content.
6006260	6011377	I can see a count of one which indicates that the item exists but the page itself is completely empty.
6011377	6016021	So that kite should fix this for us and hopefully after that we should see the content popping up here.
6016021	6017462	Now two more things that we're going to do.
6017462	6020595	I'm going to be show you how that tab would work like on the configuration tab.
6020595	6031680	You would have the opportunity to be able to always edit your brand name, edit your handle, write a bit about what content you are creating so that the agents would always read this to find ideas and to generate your content for you.
6031680	6035167	And then you can also select the number of generation defaults that you want to have.
6035167	6038554	And for that, we're going to give Cadence this prompt here to wire the configuration tab.
6038554	6041930	But I'm going to wait till he's done with the back that we have on the publish tab.
6041930	6045146	And after that, we can go into the configuration tab and wire this in as well.
6045146	6055830	And then also whilst we are here we also do have the calendar tab where whenever you schedule a post maybe you don't want to publish immediately you want to schedule this as a particular date when you come into your calendar you would also see the number
6055840	6057036	of posts that you have scheduled.
6057036	6062466	So here for instance you can see that the post that we posted today 24th of July this is already showing up in the calendar tab.
6062466	6064087	All right so kite is done with that.
6064087	6065189	Let's reload the dashboard.
6065199	6066629	Then let's come to the publish tab.
6066639	6066948	Perfect.
6066948	6069839	And now you see that the post that was published is already here.
6069839	6079510	Now the next two things that we're going to work on like I said is a configuration tab where you can basically alter the configurations here and the agent would pick the new updates that you have and for that I'm going to send kite to this
6079520	6081350	prompt to wire in the configuration tab.
6081360	6081735	All right.
6081735	6084689	So that means that when we come to the configuration put up, let me reload this.
6084689	6091072	You can basically change your brand name, the handle, the number of slides that you want to default with, if you want to have perlexity by default.
6091072	6098470	For instance, when I toggle this off and I save the configuration and I'm generating an idea, it wouldn't use publicity toggle on as a default.
6098480	6101476	And after that, we're basically done with the main aspect of the build.
6101476	6106857	I do have some other prompts that I'm giving to you as optional things that you can add to your setup to make it even more powerful.
6106857	6111195	Now what we're going to build now is going to be the telegram remote control.
6111195	6118852	So if you remember we do have this studio tab that we created which ideally we want to also use to be able to generate ideas without us having to come to the dashboard.
6118852	6125477	Now the idea here is that whenever you want to create an idea you can just come to the studio tab here in telegram generate an idea promoted and stuff like that.
6125477	6129200	So for that we're going to give kite as prompt here to set up the telegram remote control.
6129200	6134220	All right so kite says he's done he built and verified the telegram remote so far as he could.
6134220	6136111	He also said that he did a smoke test.
6136111	6142172	So let's come to the studio tab and then we can see that he did a test where we can see the things that he triggered on the studio tab.
6142172	6144426	Now he did mention something that he couldn't run.
6144426	6145969	Let me scroll down to the bottom.
6145969	6147447	He said that he's he has a blocker.
6147447	6150408	So he wasn't able to restart the hermits gateway himself.
6150408	6155744	So he's telling us from a separate shell on the machine we should run this and then we should just tell him that it's restarted.
6155744	6156672	So let me copy this.
6156672	6157780	Let me come to PowerShell.
6157780	6158957	Let me clear the screen here.
6158957	6159990	Then let me paste in this.
6160000	6161642	Let me connect to the server again.
6161642	6163590	Then let me run the command he gave to us.
6163600	6164148	All right.
6164148	6165607	So this gateway has restarted.
6165607	6168184	So, I'm going to wait a bit for the gateway to completely boot.
6168184	6170387	And after that, I'm going to send a message to Kite restarted.
6170387	6172994	So, I'm going to now send Kite a message restarted.
6172994	6176033	And then hopefully he should be able to continue with what he was doing.
6176033	6176431	All right.
6176431	6177747	And he says that he's done.
6177747	6179795	So, basically, everything is wired in.
6179795	6185430	Now, let's go to the studio tab and let's write something like let's forward slash let's run idea.
6185440	6187156	Now, let me check what the slash command was.
6187156	6189748	I don't remember if it was ideas or if it was idea.
6189748	6190616	So, it's ideas.
6190616	6192509	So, let's send forward slash ideas.
6192509	6197610	And then hopefully this should trigger the ideas tab on the studio right in this work in this workown.
6197610	6200576	So we have fresh ideas stop asking one agent to do the whole job.
6200576	6202980	So when I come to the studio tab I also see the same thing.
6202980	6205751	So basically this is mirroring whatever that we have on our dashboard.
6205751	6212180	Now the reason why we are doing this is that I want you to be able to build ideas and stuff like that without you having to always come to the dashboard.
6212180	6217544	Now let's say we want to promote this idea/promote and then let's put in the number of that idea 11.
6217544	6218838	Oops, I made a mistake.
6218838	6220249	I intended to type in 11.
6220249	6221878	And this was exactly correct.
6221878	6223818	He says that idea one was not found.
6223818	6225055	So let me do it again.
6225055	6227320	Forward/promotees and then let me send 11.
6227320	6228627	That was what I intended to send.
6228627	6230707	And then you can see that immediately we triggered this.
6230707	6232205	This is also live on the dashboard.
6232205	6234222	We can see that Vera is now promoted.
6234222	6238759	You can see that the idea was promoted and Vera is basically writing this idea that we have.
6238759	6243134	And we can see exactly the same thing here is actually done with the promotion of the idea.
6243134	6244708	So it worked on the dashboard.
6244708	6246614	We can see the ideas have been generated.
6246614	6250663	But on Telegram we did get this promotes field list attributes no get.
6250663	6253203	So I'm going to tell Kite to fix this as well for us.
6253203	6254733	So I'm giving Kite this prompt.
6254733	6257273	I tested the idea telegram command enabled perfectly.
6257273	6264467	However, when I promote an idea using the command promote idea number, the idea is promoted correctly on the dashboard, but Telegram sends us this message.
6264467	6266446	So you see what the problem is and fix it for us.
6266446	6266865	All right.
6266865	6267830	So Kite says he's done.
6267840	6268498	Let's try this again.
6268498	6270754	I'm going to come back to this app and I'm going to trigger ideas.
6270754	6277186	Now what you can also do to make it a bit easier when you are promoting an idea, you can also directly add the template that you want to use, right?
6277186	6287270	And then what I would suggest to you is that just use it to basically brainstorm ideas and then promote it to come into the studio tab and then once you're in the studio tab then you do all the stuff to do with the templates which
6287280	6296149	templates you want to use the edits that you want to do and stuff like that but it would be better to use the telegram just for the idea generation and stuff like that or maybe whenever you want to have an idea you can just come here and
6296159	6299750	tell which agent say hey give me some ideas on automation and stuff like that.
6299760	6303128	So let's say here for instance that we want to promote just an example.
6303128	6306070	Let me go to promote and let me put in oops 18.
6306080	6309801	Sorry there's a typo here promote 18 and then let me put in the templates.
6309801	6312394	Let me go to the templates tab just to get an example.
6312394	6315194	Let's say I want to go with the statement template.
6315194	6319662	Let me just type in statements then enter and then hopefully this will be produced then for us.
6319662	6321667	So weirdly it says template not found.
6321667	6322982	Let me see why this is the case.
6322982	6325831	Let me type in templates to see if I can get a list of templates.
6325831	6329072	So it appears that the names of the templates are different than what I see here.
6329072	6330641	So let's look for an example.
6330641	6334191	Let me say I want to go with a template called isometric.
6334191	6334644	Right?
6334644	6336865	Let me come back and promote this again.
6336865	6339148	And then let me go to isometric.
6339148	6350107	Now what you can also tell kites to do for you later would be to basically make sure that the names that you see for the template stylist with the names that is on the dashboard so that it becomes a bit easier for you to work with it.
6350107	6361109	I think the reason why there are different names is that for instance tip deck has two words and then for you to use it you have to use tip hyphen deck but it's just a prompt we can tell kite to just do this and he would be able to correct
6361119	6364210	this for you as well and then basically you can see that the slides are generated.
6364210	6369722	So when I come to this now you can see that the template that we picked is here and then we can see all the slides that are generated.
6369722	6379030	Now, what I think I can also do for you is I can just give you the prompts to correct this inconsistency where we have the temp name been different than the templates that we can use in Telegram.
6379040	6382427	And then I'm also going to give you this prompt that we can just give to Kite to fix this for us.
6382427	6388837	So, we're just going to tell Kite, hey, the template names shown on the dashboard do not match the names accepted by promote command.
6388837	6392753	For instance, on the dashboard when I type statement, it tells me template not found.
6392753	6394231	So, he should make sure that he fixes this.
6394231	6402264	Now I'm going to provide all these prompts to you so that you guys can also if you have the same issue you can just copy paste the prompts and your agent should be able to fix this for you.
6402264	6408964	Now whilst kite is building and correcting the issue with the templates name not matching telegram there is one more thing that we want to do.
6408964	6412534	I just want to make good use of the time whilst we are waiting for kite to be done.
6412534	6425430	So currently if you remember whenever we want to access a dashboard we do this through what is called SSH tunneling right where we put in this command here SSH minus N minus L and all the name and stuff like that we press enter and then
6425440	6437715	we put in the password of our user account and then only with that the SSH handling is activated that we are able to access the dashboard but what you can do which is even a better way to access the dashboard is to use tail skill.
6437715	6444773	Now what tails skill does is that tilk skill gives you with which you can access the dashboard without you having to go through SSA tunneling and stuff like that.
6444773	6455030	The idea is that you going to download the tail skill application connect your account and right there you get a unique with that URL you would be able to connect to the dashboard very easily without you having to put in your
6455040	6455896	password every time.
6455896	6465189	The best part about tail skill in the setup is that on every PC for instance in my case I have a desktop that I'm working with and I have a MacBook I have my mobile phone and a whole lot of devices that I work with.
6465199	6475947	Now on any of these devices that I have installed tail skill on and connected my account I can also access the dashboard without me having to go through all the terminal every time especially on your mobile phone.
6475947	6481430	Wherever you are you can work with the dashboard on your mobile phone so long as you have the tail skill app installed and connect your account.
6481440	6484664	Now to do this we're going to download the application that is called tail skill.
6484664	6486070	Now this is completely for free.
6486080	6490290	I have seven servers currently running on tail skill and I do not pay anything for this.
6490290	6494007	Now when you are here just come to this section here and click on get started.
6494007	6500927	Now when you click on get started you can basically sign up create an account everything is free you you would not have to pay for anything.
6500927	6505153	Now once the installation is complete you can then come here and download sales skills.
6505153	6511108	So on their homepage.com just click on the download button here and then this is going to download the tail skill application here.
6511108	6513171	Select whatever operating system that you're working with.
6513171	6514584	In my case I'm working with Windows.
6514584	6518272	So I'm going to click on the Windows and download the Windows application for TK skill.
6518272	6522977	If you're using the interface for Mac OS is even way better than the interface for Windows.
6522977	6524408	So I'm going to open the installer.
6524408	6527261	I'm going to accept the terms and conditions and then just click on install.
6527261	6529471	And the tail scale application is going to be completed.
6529471	6535093	Looks like the task that I gave to Kite to basically make sure that the template matches with the was a pretty heavy tax.
6535093	6537585	He's been working for close to 15 minutes now.
6537585	6538663	And he's still not done.
6538663	6543054	Now once the tail installation is completed on my end, I can basically click on close here.
6543054	6547189	And then when I come down here in Windows, you're going to see a small symbol here.
6547199	6551430	Yeah, this one here for tail skill with some I think about eight or seven dots.
6551440	6551685	Right?
6551685	6555299	When you right click on this then you would have to sign in into your tailskll account.
6555299	6559703	Now once you are signing into your tailskll account you are basically done with the installation on tailskll.
6559703	6565669	Now when you loging into your tail skill account you would see all the devices that are currently connected to your tail skill account.
6565679	6571648	And with all these devices you're going to get a unique URL that you would be able to use to access the server that we are building.
6571648	6573632	So now the tail skill application is installed.
6573632	6577030	We've created a tail skill account or if you already have an account this would be perfect.
6577040	6588950	What we would have to then do is to tell kites to install tailskll for us and bind the dashboard or the cadence dashboard that we have built to our tail skill server and with that we would be able to access the dashboard directly
6588960	6594094	from the URL directly on the browser without us having to go through the part where the sit tunneling.
6594094	6596595	So let me wait for kite to finish the task that he's doing.
6596595	6597738	I think he's almost done.
6597738	6607750	So currently you can see that he's browsing to make sure that all the changes that he did are working and then once he's done we can basically give Kite the command to do the tail skill wiring for us and then we would be done with this
6607760	6608182	tutorial.
6608182	6613097	And hey I'm working on an auto installer that is going to install all this for you in a matter of minutes.
6613097	6614258	So just sign up to my membership.
6614258	6621815	You're going to get a unique key which would you'll be able to use the installer and I will also create a tutorial for you on how to use the installer as well when this is ready.
6621815	6624628	And now finally kite is done with that big job.
6624628	6631065	The names of the templates that we see on the dashboard here would tally with the names that we see on Telegram.
6631065	6633924	Going back to the tail skill points, Kite is done with the work.
6633924	6637654	So, we can basically give Kite the prompt to work on the tail skill connection for us.
6637654	6639714	And for that, I'm going to give Kite this prompt here.
6639714	6646775	I'm telling Kite, hey, set up tail skill access to the dashboard so I can securely access it from my own devices without the SSA tunnel.
6646775	6649924	And I'm just giving him the guide on how I want this to be.
6649924	6656086	And when he's done, he's going to give us a link that we're going to use click to bind this particular server to our tail skill account.
6656086	6659513	So let make sure I'm on kite stop and let me send this prompt to kite to do this.
6659513	6662709	And then once we are done with this, then we are basically at the end of the tutorial.
6662719	6663734	I'm already exhausted.
6663734	6665843	I've been recording for more than 10 hours.
6665843	6667303	So I'm getting tired myself.
6667303	6667848	All right.
6667848	6668669	So Kite is done.
6668669	6674297	He's given us this login link that we're going to use to authenticate our account to this particular server that we have built.
6674297	6677803	So I'm going to open a new tab and just put in the URL that Kite gave to us.
6677803	6681684	And after that, all you're going to have to do is to connect and sign in into your tail skill account.
6681684	6688346	Now, this is going to bring you to a page here where tailskll is going to ask you, hey, I want to connect the device cadence dashboard to your computer.
6688346	6690265	So, in my case, computer mechanic.com tailnet.
6690265	6693422	I'm going to click on connect and then the login is accessible.
6693422	6696593	So, our device has now been bound to our tail skill account.
6696593	6702435	So, I'm going to come here and I'm going to tell kite done because he says that when I'm done with authentication, I should just reply we're done.
6702435	6702758	Right.
6702758	6704457	So, kite is done with that as well.
6704457	6711794	He also said that he did a public IP testing and all failed to connect which means that the dashboard can only be accessed through the tail skill IP.
6711794	6713626	Now let me be sure that this is working.
6713626	6714743	Let me reload the dashboard.
6714743	6717375	Here we have the SSA tunneling working which is expected.
6717375	6727189	I'm going to come to PowerShell and I'm going to kill the SSH connection and then I'm going to come back to the dashboard and I'm going to try to access the dashboard through the SSA tunnel and you see that I get the sites cannot be
6727199	6727517	reached.
6727517	6732075	Now whenever I want to connect to the dashboard I can just use this URL that Kite gave to us.
6732075	6733811	So let me copy the dashboard URL.
6733811	6735189	Let me paste in this URL.
6735199	6735780	And then hooray.
6735780	6740675	You see that we can access the dashboard without us having to go through the complication with the SSA tunnel.
6740675	6745752	Now tails skill works by setting sort of a local viva or on the PC on which it's installed.
6745752	6755093	So if you have any other VPN services running, you would have to stop this VPN before tail skill can work because if you have two parallel services running, then tails scale would not be able to work.
6755093	6760227	So make sure that you always stop any other running so that tail scale would be able to deploy the server for you.
6760227	6762470	So this brings us to the end of the tutorial.
6762480	6764326	Let me walk you through shortly what we have built.
6764326	6771099	We have the dashboard tab where we can see and all the things that the agents are doing an activity log all pulled from the agents database.
6771099	6779787	Now when you come to the ideas tab, we can always create any new idea by picking your idea and the agents at last is going to pick up that idea and build it into a content for you.
6779787	6785679	And then also whenever you don't have any idea, you can just come and click on the generate idea and an idea will be generated for you.
6785679	6790551	Whenever we want to promote an idea, we can just click on promote and this will be promoted for us into the studio tab.
6790551	6794683	And whenever we want to push any of the post to Instagram, Tik Tok, whatever we want to do.
6794683	6799128	When we click on post now, this will directly be pushed to the social media platform that we want to use.
6799128	6804786	And then when this is done, this will bring the post to the publish tab so that you can always refer to it whenever you want to do something with it.
6804786	6812625	We also have a templates tab that is packed with a lot of templates currently in the setup that you can always pick from and develop any carousel slide that you want to develop.
6812625	6817208	And then we have the dedicated agents tab where we see all the agents that we have their heat map.
6817208	6823043	You have your calendar where you can see the post that you have scheduled, post that you have already published and also upcoming post.
6823043	6830867	A configuration tab where you can configure your brand name, the things that you want the agents to work on when they are generating the and a docs tab where you can basically understand the dashboard.
6830867	6836034	Now I do have way more prompts that I'm going to provide to you that you can also use that I would highly recommend that you use.
6836034	6841189	For instance, for the agent login activity, the agents are going to log in the database whenever they perform a task.
6841199	6844786	But if you run this for a whole year, then your database is going to get so cluttered.
6844786	6851783	So you can set up sort of a weekly cleanup where the agents are going to look for activities that are older than 7 days and basically clean all of them.
6851783	6856221	And I also included some additional problems that you can use to basically amplify the setup that you have.
6856221	6862381	I know it's a lengthy tutorial, but I wanted to go through everything that we are building, the thought process that I have when I'm building something like this.
6862381	6867307	And also you see me troubleshoot all the errors that we have so that when you have a similar situation, you can do the same thing as well.
6867307	6869525	If you found the video helpful, please hit the like button.
6869525	6873119	Subscribe to my channel to see more like this.