WEBVTT

00:00:00.000 --> 00:00:06.480
So I just gave Hermes agent a real phone number, and now it can pick up the phone to call businesses, book appointments,

00:00:06.480 --> 00:00:33.780
chase down leads, and even call you to confirm any details. But the wildest part is it can do so proactively on its own schedule without me having to ask it. This actually is the most powerful and useful Hermes setup that I don't see anyone covering. But, David, isn't this setup too complicated? No. It's literally one MCP installed and you're done. Okay. But what if it costs a fortune? It's actually super cheap. Alright? But I don't have a business. You will use it for personal things. Trust me. Dentist appointments, reservations,

00:00:33.860 --> 00:00:46.755
it can save you so much time. Or maybe you think you're not technical enough. You can't code. Listen. If you can copy paste, you can absolutely build this. So in this video, I'm gonna show you how to install Hermes agent locally, how to connect it to VAPI MCP,

00:00:46.915 --> 00:01:27.870
give Hermes a real phone number, then how to research target businesses, and have it call you a business, get more leads, and make you more money. Literally all done by Hermes agent. Alright. So the first step is to set up Hermes agent. I'm gonna show you how to do that locally. If you have a VPS, you can, of course, do it on a VPS. Either way, the setup is the same. So first, we go to the Hermes agent repo and we scroll down to find the one liner installer command. There it is. The quick install, just copy this command by clicking this button and open a terminal and then paste this in. Boom. This is gonna install Hermes agent on your computer. Once you run it, you should be able to type in Hermes setup and it will open up the setup. One of the first things it will ask you is what provider to use. So I'm gonna go with OpenRouter. Go to openrouter.ai,

00:01:27.870 --> 00:01:36.510
and then make sure to create an account. Super easy. Takes, like, twenty seconds. Then go to top right and click on credits. Make sure to charge up some amount. You don't need $300.

00:01:36.510 --> 00:01:43.145
Just 5 to $10 is enough. Go to left, click on API keys, and click on new key. I'm gonna name this one subscribe.

00:01:43.545 --> 00:01:46.985
If you're watching this, please subscribe. We are so close to 400,000

00:01:46.985 --> 00:01:47.785
subscribers,

00:01:47.785 --> 00:02:01.460
and most of you, like 60% of you, are still not subscribed. So if you find my content valuable and if you want me to make more videos like this one, please go below the video and click the subscribe button. It's completely free. Okay. I'm gonna put some limit on this, maybe, like, $50,

00:02:01.540 --> 00:02:07.355
just a good precaution, and I'm gonna copy the API key. Let's switch back to the terminal. I'm gonna hit open router enter.

00:02:07.915 --> 00:02:11.195
I already have a key, so I'm gonna do r to replace it

00:02:11.515 --> 00:02:14.795
and paste in the new one. API key updated. Beautiful.

00:02:15.115 --> 00:02:28.230
We can choose a model. There's many different models. I'm gonna go with the Opus 4.7. It's asking to add a fallback credential for the same provider. I'm gonna do no. It's not needed for now. Text to speech, you can keep the current one. Hit enter. Enter. Iterations,

00:02:28.230 --> 00:02:29.670
enter. Enter.

00:02:29.830 --> 00:02:43.045
Enter. Just spam through this. The default settings are really good in Hermes. You can just click on enter a bunch of times. This is also good. Four AM, also good. Navigation platform, we actually don't need it, so I'm gonna skip by hitting enter. The CLI,

00:02:43.365 --> 00:02:54.440
that's cool. Well, I can just go to done, and we're probably done. And as it says here, always read the instructions, guys. A lot of people are scared of the terminal, and they don't look at the output. So I'm gonna type in Hermes,

00:02:54.520 --> 00:02:59.800
and this is gonna launch Hermes agent with Clothopus 4.7. Let's send a test message, test,

00:03:00.315 --> 00:03:37.955
And let's see if it responds. Okay. So we have Hermes agent installed locally. And, obviously, Hermes is a very, very powerful agent right off the box. However, there is one problem. It doesn't come with a phone number, and this is what we have to solve next. Real quick, if you want everything from this video, all the assets, all the repos, all the skills, everything I show you, click the second link below the video and grab it now. It's completely free. Okay. So we have Hermes, but the phone is the missing piece. This is still what most people don't trust the AI to do, to take phone calls for you. If you think about it, for 99% of power users, they already use AI for web browsing, for writing code, for doing their email.

00:03:38.195 --> 00:03:51.040
But using the phone, most of us still do it manually. Luckily, there's an elegant AI first solution, and that is VAPI. Basically, to explain it in the most simple way possible, VAPI makes phone calls configurable

00:03:51.040 --> 00:04:03.535
while her mess makes them autonomous. And the synergy between these two is really beautiful. Vapi gives Hermes phone numbers, inbound calls, outbound calls, voice agents, transcripts, call logs, and real time conversations.

00:04:03.695 --> 00:04:04.655
While Hermes

00:04:04.655 --> 00:04:06.175
gives Vapi goals,

00:04:06.255 --> 00:04:52.575
memory, tools, cron jobs, proactive decisions, outcome checking, next actions, self improvement, and anything else that RMS agent can do. So connecting these tools together is really where you get the most OP use cases possible. Let me show you how to set this up. Alright. So the first step is to just type in Wapi into Google and click on the first link. And here, simply create an account. So go to top right and click on get started. Now you can sign in with either Google, GitHub, or Discord or just classic email password. Now, again, creating an account is super simple. Literally takes twenty seconds. I already have account with Vappi, so I'm just gonna sign in. Now Vappi was kind enough to sponsor this video. So if you want to make your Hermes agent super powerful by giving them phone numbers and letting them do anything that a human with a phone can, make sure to show Vappi some love. Click the first link below the video and sign up to Vappy.

00:04:52.815 --> 00:05:09.510
First thing you're gonna see when you get here is the composer. This is this screen right here, and this is the agent that lets you build, debug, and manage your Vappy agents. And you can always access it from the left here, composer. You can even star it. So it's one of your favorites. So when you get to this page, go to left and click on assistance.

00:05:09.670 --> 00:05:11.590
This is where you can see all of the different

00:05:11.830 --> 00:05:28.875
voice agents or voice assistants you have inside of VAPI. This is the main page where you can manage all of the different voice assistants you have and see everything there is to know about them. Now the most interesting thing in here is the breakdown of the cost and latency for each assistant. And you can see that the average cost is just $0.1

00:05:28.875 --> 00:05:43.970
per minute, which is very affordable. The average latency is just one point one five seconds or one thousand one hundred fifty milliseconds. Below it, you can see the transcriber, the model, and the voice voice model. Right? The voice agent. So, obviously, you can configure these and change these to different providers, different languages,

00:05:44.130 --> 00:06:10.800
a bunch of other settings. More on that later. But the main thing to understand is that this is the flow. Right? When a person speaks, the agent first needs to transcribe their speech into English or some text, then it sends to a model. Right? It could be a cheap model like 4.1, or you can use something like more powerful, like g b d five or even g b d 5.4 if you want even more power. And then the third thing is the voice. This is the output. Right? Once the model has the response, it needs to turn it into voice, into spoken sound

00:06:11.375 --> 00:06:19.455
that gets played to the person it's calling. Right? And, again, you can select the provider, the different voice preset, you know, male, female, slow, energetic,

00:06:19.455 --> 00:06:27.470
kinda more monotone. There's many different voices. You can adjust the speed background sounds. There is a lot of settings inside of VAPI. It's really, really advanced.

00:06:27.630 --> 00:08:10.135
And, again, I'm gonna go into this later in the video. Now before I show you more about the VAPI interface, let's make some progress, and let's actually set up Hermes so it can use VAPI. And we're gonna do that by using the VAPI MCP server. This is the simplest way to connect VAPI to Hermes so that it can actually start making calls on your behalf. And in fact, the team had made it super simple, and it's literally these three steps. Get the API key, edit the config, and add the MCP server block. So I'm gonna show you step by step. You can do this even if you're not a developer. And by the way, what you might not realize is that this will allow Hermes to create VAPI agents, to log the calls, to analyze what happened, basically, to make any changes inside of the VAPI dashboard for you. So, really, you don't even have to master the UI. All you need to do is talk to your Hermes in plain English, either in terminal or Discord, WhatsApp. I've made many videos on Hermes agents, so watch those. But, basically, all the heavy lifting will be done by Hermes. You just tell it what to do, and it can do it. It can interact with the full VAPI interface through the MCP. So really setting this up, this might be the most valuable three or four minutes of the entire video. So there's just one thing that you do. Please do this. Give your Hermes agent access to VAPI so it can make phone calls, it can set up these voice agents, and use them to save you time and make your life better and grow your business. I don't care how you use it. You have to use it. Okay? That's the main thing. Just make sure to use it. So first step, get the VAPI API clear. Literally click on this. By the way, I'm gonna link this, um, in the resources. Right? So, again, everything from this video will be linked in the second link blog video. Okay? All the skills, all the repos, everything you need is gonna be bundled together. Click the second link below the video. Grab it completely for free. Alright. So I'm gonna click on this link. It's gonna take me to the dashboard of VAPI, specifically the API key section,

00:08:10.535 --> 00:08:20.230
and I'm gonna create a new API key here. Now believe it or not, the simplest way to actually set this up is copy the URL, go to Hermes, and say, set up this new MCP.

00:08:20.550 --> 00:08:21.190
Boom.

00:08:21.350 --> 00:08:51.170
And let Hermes set it up for itself. Because Hermes comes with a skill that knows how it's architected. Right? It knows how it's built, and it knows how to set up MCP servers inside of itself. You are probably underestimating these agents, all of you. You're probably giving them too easy of a task, or you're micromanaging them too much. You can literally say, set this up and link what MCB server you want. It will set it up, and then it will ask you for the API key, which, again, that's the last step we have to do. So, again, if you click here, you'll get redirected to the VAPI dashboard,

00:08:51.170 --> 00:09:08.385
and you have the two keys. Now we need the private one here. But if you're not sure, just take a screenshot, go to Hermes, and ask it which of these keys do you need, and it will tell you. So there it is. Vapi, z, z, space. Okay. I need your API key. Again, just copy it right here. And by the way, anytime you're not sure which key, just screenshot,

00:09:08.385 --> 00:09:19.480
boom, copy to clipboard, paste it in with control v, and say, which key do you need? Answer in short. Private key server side. Okay? So it wants the private key. I'm gonna copy it. Say,

00:09:19.800 --> 00:09:22.520
here is the key. Store it securely.

00:09:22.760 --> 00:09:25.800
Obviously, this is not the best practice pasting API keys

00:09:26.040 --> 00:09:39.535
into the Hermes, and I'm gonna revoke my key before uploading this video. You can also do Hermes config set VAPI API key and then paste it in. That's the more secure way, but this is the fastest and the simplest way. And since Hermes will be basically doing everything else with the VAPI MCP,

00:09:39.695 --> 00:10:24.295
it's not that big of a risk. Alright. It's asking for permission to write this in. I'm gonna allow it for this session. And as you can see, it's setting every everything up. I haven't made a single change, single manual change to the config file of Hermes. It's setting it up itself. Like, this is the magic of self improving AI agents like Hermes. They can improve themselves. They can do all the things. K? It wants permissions for this command. I'm gonna allow for this session. And you basically just tell it what you want, and it will do it. Now there's two reasons why most people don't see the value in AI agents. Either they never set them up. Right, so they don't watch a video like this, or they only watch it and they don't follow the steps. And the second reason is they don't know what to tell it. They don't know how to ask it for what they want. So if you can actually set this up, if you can follow the steps I'm showing you and just do this yourself either on a VPS or locally,

00:10:24.535 --> 00:10:56.105
and then actually start telling it the things like, yo, make a phone call to that sauna. I need a reservation. Or find me 10 leads in this city and call the phone number on Google Maps. Like, if you can tell it what you need, it will do it. Issue is most people never set it up or don't tell it what to do. Okay. There it is. Confirmed. Here's the variable. Restart her mess to pick up the new server. Okay. So I'm gonna do control c to kill her mess. Clear. Launch it again. I'm gonna say check your config and let me know which MCP servers you see in there. Be concise.

00:10:56.345 --> 00:11:04.745
Just a quick double check to see that the VAPI MCP server is there set up correctly. There it is. Just one VAPI. Beautiful. Now check. Boom.

00:11:05.460 --> 00:11:09.140
And let me know if you see any API keys in there.

00:11:10.020 --> 00:11:12.420
Don't read the the values.

00:11:12.980 --> 00:11:29.375
Just let me know which keys you see. Okay. As you can see, already have some, but there it is. VAPI API key. Beautiful. It's there. So we can continue. Alright. So we have the API key here. We have the MCP server here. Before we jump to the first use case, I wanna show you a bit more about the UI in VAPI,

00:11:29.535 --> 00:11:53.005
especially the messages. Here, have the first message aka what happens. Right? Whether assistant speaks first or the assistant waits for the user or assistant speaks first with a model generated message. Right? So you can say, hey. I'm John or, I'm calling on behalf of David, stuff like that. And then the system prompts. This is the main thing. This is where you implement and influence the behavior of the voice assistant, how verbose it should be, whether it should be formal, informal,

00:11:53.325 --> 00:12:14.900
how it should talk, what level of English it should have, all of that. And then here, can select any external files, such as documents, PDF files, markdown files, anything else that would give it more context. But the setting we're looking for the most inside of VAPI is the phone numbers. If you go left, this is where we can see our phone numbers that we have. Right? So we I have two American ones, one Polish one, but

00:12:15.220 --> 00:12:33.270
this is what gives Hermes the ability to make phone calls through VAPI. Right? So these phone numbers, you can put different labels on it. You can see the provider. I think VAPI even gives you free phone numbers. If you click, uh, yeah, free phone number, you can get up to 10 per account. So if you're not convinced to try Vappi, this alone might be convincing.

00:12:33.350 --> 00:12:35.590
10 free US phone numbers

00:12:35.590 --> 00:12:41.910
for your AI assistants to make phone calls. Right? Very, very OP. But, yeah, as you can see, Vappi gives you all the configuration,

00:12:41.990 --> 00:12:55.235
and Hermes gives you the powerful AI agent can solve problems and do basically anything else, and now it can also take phone calls. So the first use case is gonna be having Hermes make an external call. So it could be book something or,

00:12:55.715 --> 00:13:12.370
you know, just call a business on your behalf, save you time, anything. Like, there's many situations where you might need someone to make a phone call. Right? So I'm gonna kill it. I'm gonna start her her mess from scratch, and I'm gonna give it a very simple prompt. Research me, spa massage in New York for today near Manhattan.

00:13:12.825 --> 00:13:21.065
Find their phone number. Okay? Very simple problem. Plain English. There's literally typos in there, but Hermes agent has all the tools and all the skills on

00:13:21.225 --> 00:13:24.985
how to do this, and we will do it right now. So does multiple web searches,

00:13:25.225 --> 00:13:33.760
best spa massage, here on top spa massages, boom, with the phone numbers. Very easy. Took a couple of seconds. It's already asking here, by the way. Want me to call any of these to confirm availability?

00:13:34.080 --> 00:13:49.525
Yes. Choose one of them and call them using VAPI right now. Calling renew day spa. Best walking availability using the appointment booking assistant with US phone number briefs her message today. Let's see this. This this is always exciting. We can actually go back to VAPI and probably see it

00:13:50.405 --> 00:13:54.005
in our assistance. So to use the appointment booking one, let's click here,

00:13:54.565 --> 00:14:15.115
and we can click on logs. Check status now. Let me reload here to see what's going on. Call in progress. Call connected. Conversation happening now. This crazy. I'm gonna confirm that it's the right assistant in VAPI. Which VAPI voice assistant is taking the call? Oh, wait. There it is. Look at this. We see it. Call ID, outbound duration, ninety seconds, cost 5¢.

00:14:15.355 --> 00:14:27.470
It cost us just 5¢ of VAPI credits to make this phone call. Let's look at it. Let's click on it and see what happened. We can see it right here. Okay? So we can even play it. Hi. I'm calling to check availability for a massage today.

00:14:28.510 --> 00:14:41.445
Today, what time? I'd like to know what times you have available. I wanted to a lot opening. You can tell me the price. Great. Thank you. Could you tell me what types of massages you offer and the pricing for a sixty minute session? Okay. So the call happened. Okay? Call happened

00:14:41.605 --> 00:14:43.125
was nineteen seconds.

00:14:43.365 --> 00:14:51.285
We need to probably fine tune the length of responses because here, it started speaking too soon, and then it interrupted the lady,

00:14:51.605 --> 00:14:53.285
and then the lady interrupted him.

00:14:53.525 --> 00:14:55.205
But this is a great start. Okay?

00:14:56.110 --> 00:15:10.750
As I said, in Vappi, you can fine tune everything. How fast the response, what model we're using, the tone of voice. We can change all of that, but the call happened. Cost us 5¢, which is incredible cost. I mean, think how much you would have to pay a human to sit on a call sit on a phone and do phone calls for you. Right?

00:15:11.625 --> 00:15:27.440
This is a huge first step. So, obviously, not every call is gonna be successful. This is still highly experimental technology. I mean, we're trying to be on the cutting edge here, but this is a great start, and we can actually fine tune a lot of this. When you click here, when you click on assistant, we can improve the model. G b d four o is very weak.

00:15:27.840 --> 00:15:37.040
I'm gonna go with something faster, maybe g b d 5.4 mini. I think that's a much better option. Or even g b d 5.4 itself, it's even better. Here, temperature controls randomness.

00:15:37.625 --> 00:15:46.025
I think, like, 0.7 is fine. All of this thing is good enough. Okay? So I think the model is setting. The Deepgram one, let's see. We have Deepgram,

00:15:46.985 --> 00:15:58.040
long language e English model Nova three. It's probably fine. Background denoising, numerals, profanity filter. K. All of this looks decent. Let's optimize the voice. Maybe we can try some of the VAPI voices. Let's see.

00:15:58.520 --> 00:16:02.520
Elliot. Maybe we can try a female voice like Emma from VAPI.

00:16:02.920 --> 00:16:04.920
Speed, I think a bit

00:16:05.320 --> 00:16:06.120
slower,

00:16:06.200 --> 00:16:06.920
maybe like one.

00:16:08.175 --> 00:16:10.895
Background sounds, let's try office

00:16:11.375 --> 00:16:17.615
and maybe for okay. For we don't need a full black voice. And then we can click publish, and it's gonna publish all these changes to the assistant.

00:16:18.255 --> 00:16:29.290
Looks good. Publish. And boom. Just like that, we've changed this assistant so that when Hermes uses it, it's gonna use a better AI model and a female voice model. Maybe this will be more successful. Obviously, just like with any

00:16:29.850 --> 00:16:53.110
anything in AI, you need to fine tune it. You need to play around with it, see what system prompt works best, and, yeah, test it out. But, honestly, this is a huge first win. The phone call happened. There were no errors, and it cost us just 5¢. But if you think this use case is crazy, just wait until you see what's coming. Because of the MCP, Hermes can create new assistants inside of VAPI optimized for any type of use case. So for example, I can say,

00:16:53.590 --> 00:16:57.110
create a new assistant inside of VAPI using the MCP.

00:16:57.190 --> 00:17:01.030
Make it about calls outreach to businesses to set appointments

00:17:01.190 --> 00:17:15.085
to get more leads. For example, let's focus on car detailing businesses in New Jersey. Create this assistant and do the first call. Plain English. Again, just prompt it in natural language and watch it do the task. It's initializing the agent.

00:17:15.325 --> 00:17:37.365
It will find the MCP. MCP VAPI list phone numbers. Boom. It checks the available phone numbers we have. K. It sees before it needs two things for me. Okay? Okay. Number one, you should research that yourself. And number two, just choose the first phone number. Get to work and actually do it. I feel like in this case, it didn't really need to ask me, but fair enough. So what we should do is inside of VAPI dashboard, inside of assistance, we should see a new

00:17:37.925 --> 00:17:39.285
assistant being created.

00:17:40.325 --> 00:17:46.725
There it is. MCP VAPI create assistant. Let's see what name it gives. Top tier Autospa. Hopefully, these businesses don't get too annoyed

00:17:47.120 --> 00:17:53.040
with our testing. K. We should have there it is. New Jersey car detailing legion outreach. Okay? Boom.

00:17:53.280 --> 00:17:54.720
Optimized agent

00:17:55.120 --> 00:17:59.280
with a custom system prompt. You are Morgan, SDR from Brightlane, Legioneration Agency.

00:17:59.755 --> 00:18:03.515
Look at this. Hermes agent wrote all of this. Objection handling.

00:18:03.915 --> 00:18:04.635
Damn.

00:18:05.515 --> 00:18:09.755
Be warm, casual, confident, American English. This is not bad at all.

00:18:10.715 --> 00:18:11.035
Okay.

00:18:12.290 --> 00:18:17.170
MCPOP create call. It's doing a call. Wait. Wait. Wait. We should see logs for this guy.

00:18:17.730 --> 00:18:19.730
No session. Okay. Nothing yet.

00:18:20.130 --> 00:18:21.330
Call started.

00:18:22.450 --> 00:18:23.730
Check progress

00:18:23.730 --> 00:18:31.285
on this call. This is amazing. Like, the synergy between Hermes and VaPi is insane. Call failed, never connected. Okay. Yes.

00:18:32.165 --> 00:18:34.165
Try the other number.

00:18:35.125 --> 00:18:38.165
Last time, it didn't have this issue, so I don't know what's what's the

00:18:38.325 --> 00:18:39.285
problem here. Cool.

00:18:41.010 --> 00:18:43.090
Make sure to auto check-in

00:18:43.090 --> 00:18:49.650
thirty seconds. And by the way, you can run this in parallel. So you can have multiple different voice assistants on Vappy,

00:18:49.810 --> 00:18:59.325
all orchestrated with Hermes to run multiple calls in parallel. So one of them could be set booking appointments, one of them could be confirming calls, one of them could be qualifying leads.

00:18:59.565 --> 00:19:02.285
Like, whatever you can imagine, you can build.

00:19:02.845 --> 00:19:10.130
It really is up to you to figure out the use cases. And I'm showing you just a couple to get inspired, but really sit aside and think about this.

00:19:10.370 --> 00:19:10.930
Because

00:19:11.250 --> 00:19:13.170
the businesses that will adopt this

00:19:13.410 --> 00:19:39.705
will just crush the people who ignore it. It's that simple. The world really is turning into people who embrace AI and people who hate AI. There is like, it's a it's a barbell. Right? Both of these ends, there's nothing in the middle. It's just people who embrace AI and they love it because they can build any app. They're way more productive. They can do things like this, and then people who hate AI. It's more more like, I guess, left leaning, but college students. This is a big, like, you know, artists. There's a big hate

00:19:39.960 --> 00:19:45.480
towards AI, and those people are just gonna get crushed. I mean, it is what it is. You know? Either they adopt a new technology

00:19:45.720 --> 00:20:01.305
or they're gonna be left behind. I mean, you and me know that. We're you know, you're watching this video, so hopefully, you're on the future side of the AI equation. But I'm telling you, this is the landscape. It's either people who fully embrace AI and people who hate it. There's nothing in between. Live now in progress. Okay.

00:20:01.785 --> 00:20:02.745
It's happening.

00:20:05.065 --> 00:20:08.585
I don't know if it's a good talk because I'm in Poland in Katowice.

00:20:08.665 --> 00:20:12.720
If you wanna join our Katowice office, click the link below. We're hiring for multiple positions.

00:20:12.960 --> 00:20:13.520
But

00:20:14.320 --> 00:20:18.240
this is this is good. We're calling American companies, so it's probably morning in America.

00:20:18.880 --> 00:20:22.400
The status there, call is still alive. Okay. Check again.

00:20:22.880 --> 00:20:37.760
I wanna see what's happening. This is exciting. Anytime agent is on the call, this is super exciting. And by the way, another thing is the advantage of Hermes is that you can create a cron job. So you can do these calls automatically. So I could say, create a cron job that every ten minutes calls a different

00:20:38.080 --> 00:20:38.880
lead

00:20:39.120 --> 00:20:39.760
from

00:20:40.080 --> 00:20:41.120
New Jersey

00:20:41.280 --> 00:20:42.560
that is a

00:20:42.960 --> 00:20:44.240
car detailing

00:20:44.880 --> 00:20:45.600
business.

00:20:45.920 --> 00:20:47.440
Build a SQLite

00:20:47.440 --> 00:20:51.200
DB to keep track which businesses

00:20:51.325 --> 00:20:53.245
you've already called.

00:20:54.125 --> 00:20:56.045
And literally with a single prompt,

00:20:56.205 --> 00:21:01.645
we have a outreach strategy. We have a cold outreach strategy to slowly and surely

00:21:01.805 --> 00:21:07.730
well, actually, not slowly, quickly, like every 10 minutes. Right? And it's gonna work twenty four seven, so even humans cannot work twenty four seven,

00:21:08.050 --> 00:21:18.770
to call every car detailing company from New Jersey. Right? And it's gonna build SQLite database to keep track. Okay. Did I follow-up with these guys? Did I already call with these guys? And you can use that context in the future calls. Like, people don't realize

00:21:19.385 --> 00:21:19.945
how

00:21:20.185 --> 00:21:25.705
easy it is to build something that's truly useful, something that can grow your business today,

00:21:26.025 --> 00:21:31.785
not hypothetically in the future. If you need car detailing leads or if you need chiropractors,

00:21:31.945 --> 00:21:32.425
gyms,

00:21:33.530 --> 00:21:36.330
anything, like, anything. This is not just from, you know,

00:21:36.730 --> 00:21:41.370
brick and mortar businesses. Like, get creative. You need to call doctors. You need to call lawyers. You need to call

00:21:41.930 --> 00:21:48.090
finance firms, private equity firms, whatever. Right? It can do these phone calls. You can fine tune the the

00:21:48.885 --> 00:21:54.485
system prompt, and then it just say, Hermes. Okay. Clear new crunch up that every fifteen minutes, it rings a different

00:21:54.805 --> 00:21:57.765
venture capital firm pitching my start up. Boom.

00:21:58.245 --> 00:22:02.485
Would you pitch your start up faster? Would you get investors faster if you build this? Probably,

00:22:02.920 --> 00:22:05.080
It's like, get creative with this, guys.

00:22:05.720 --> 00:22:08.520
Use it for your business. Use it for something. This is truly, like

00:22:09.240 --> 00:22:16.280
it's truly incredible what you can do. Anyways, in the meantime, Hermes is creating Cronjob to build our automated outreach system. And, I just said a single sentence.

00:22:16.835 --> 00:22:19.155
Single sentence on what it should do,

00:22:19.635 --> 00:22:21.395
and it created SQL database.

00:22:21.395 --> 00:22:32.940
It's it's set up the MCP. It's created the skill, cron job, all of that because Hermes counts with, like, 82 prebuilt skills. So it it knows how to do this. Okay. I can actually do another Hermes, and I can

00:22:33.500 --> 00:22:35.100
copy this assistant,

00:22:35.900 --> 00:22:40.940
use the VAPI MCP to check on this voice assistant

00:22:40.940 --> 00:22:42.140
and progress

00:22:42.140 --> 00:22:51.155
on most recent call. Probably could have given it just the call ID to be fair. It's probably better. Here is the call ID for Vappi.

00:22:52.195 --> 00:22:54.675
So we're running multiple Hermes in parallel,

00:22:55.075 --> 00:22:57.155
which you can do very easily. Oh, there it is.

00:22:58.320 --> 00:23:00.960
The reason customer wait. Wait. Wait. This is insane.

00:23:01.280 --> 00:23:06.320
Eight minute call. Yo, guys. This is crazy. Eight minute call. Okay. Is this voice mail?

00:23:06.800 --> 00:23:09.600
Please, no. Lead to the following menu options.

00:23:09.760 --> 00:23:19.795
For operating hours, press 1. For address Okay. So it got stuck on voice mail. Alright. That's that's unlucky. Okay? So here what you should do is you should go to assistant

00:23:20.515 --> 00:23:21.235
and

00:23:21.955 --> 00:23:23.315
update the rules. Right?

00:23:24.275 --> 00:23:26.675
If you notice voice mail,

00:23:26.915 --> 00:23:35.790
just hang up. Boom. Something like this. Then I would go to model. This is definitely something we should change. Four o cluster is not good enough.

00:23:36.110 --> 00:23:38.670
5.4 would recognize this much better.

00:23:38.990 --> 00:23:42.350
So, obviously, inside of her mess, it created the skill. Say, I'm gonna say

00:23:42.865 --> 00:23:45.345
update the skill you created for VAPI

00:23:45.585 --> 00:23:56.065
so that you always use g p t 5.4 as the model instead of g p t four o. That was a mistake from Hermes. It shows a worse model. So, yeah, I'm gonna publish this change

00:23:56.710 --> 00:24:44.025
so that we don't get stuck on voice mail in the future. Now before I show you the second VAPI use case, which is inbound agents, right, when you get inbound calls, let me first explain how VAPI actually works. So VAPI is the system and the platform used to build AI voice agents. Basically, apps that can talk to people over phone calls in real time. Now the most important elements of VAPI are the transcriber, the large language model, the voice model, and the orchestrator. And as you might have noticed, VAPI gives you all of this in a single platform. Now the orchestrator, this might be the most important one. It stops when people interrupt. It cuts our background noise. It knows when you're done talking and picks up on the mood of the people talking to your agent. Right? So all of these are very those are the hard part. There is voice models. There is LLMs from every company. But putting it all together to something that understands these nuances of phone calls, that is the hard part. Not just having

00:24:44.345 --> 00:24:52.760
generated AI voice, but making it into a truly useful assistant. That is what Vappi did. Now to show you the second use case, you can just create Hermes.

00:24:53.000 --> 00:24:56.920
And let's say you run a business that gets a lot of inbound calls. You can say,

00:24:57.960 --> 00:24:59.160
I run a

00:24:59.560 --> 00:25:01.640
massage place in Katowice,

00:25:01.640 --> 00:25:06.155
Poland, and we get a lot of inbound calls. I want you to use the VAPI MCP

00:25:06.395 --> 00:25:09.195
to create a new voice assistant

00:25:09.195 --> 00:25:11.275
for handling these inbound calls

00:25:11.435 --> 00:25:13.915
to just let them know about our availability,

00:25:13.995 --> 00:25:17.670
you know, which hours and which type of massages we offer, and

00:25:17.830 --> 00:25:21.670
help them book and schedule stuff using our internal software.

00:25:21.990 --> 00:25:27.190
I'm gonna give you more context later, but just use the VAPI MCP to create this new inbound voice assistant.

00:25:27.990 --> 00:25:39.405
If you have a business like that, you probably are paying two, three, four people on retainer every single month to just handle the calls. Right? To to handle the, you know, like, secretary or to for the phone call.

00:25:39.885 --> 00:25:51.820
Or you just deploy one VAPI assistant to do that twenty four seven, way cheaper. And if you put an effort into the system prompt, more reliably because, again, you can just customize this. You can test out different transcribers,

00:25:51.820 --> 00:25:55.740
different LLMs, different voice models, test out different opening messages,

00:25:55.820 --> 00:26:07.845
system prompts, connect it with other tools. Right? So if you have your own internal software, your own API, you can connect this here. Uh, as you can see, there's many different tools here we have. Prebuild, we can also create a new tool and put in the schema

00:26:08.085 --> 00:26:11.765
and connect it to your software or maybe Zapier or n a 10, whatever use.

00:26:12.670 --> 00:26:27.150
There is a lot of possibilities. So if you have a business that takes inbound, I would say it's nonnegotiable. You absolute absolutely have to do this. In okay. This interesting Hermes realized that we have the Polish number. It assumed that's for that, and it created a new assistant. Language Polish auto switches to English.

00:26:27.975 --> 00:26:46.580
This is crazy. In fifty five seconds, all of this is set up. In fifty five seconds, I can deploy this with inbound. Voice agents are here, and I showed you two use cases. Let me show you the third one. The third use case is the most impressive by far, and it uses custom tools. So inside of Vapi, go to left, click on tools. And here you can see a bunch of tools. A lot of them are prebuilt.

00:26:46.820 --> 00:26:58.395
But one is custom, ask Hermes. Right? And this is the way you can use Hermes agent as your personal concierge. So instead of Hermes delegating to Vapi, Vapi can contact Hermes. So during the conversation,

00:26:58.555 --> 00:26:59.515
let's say,

00:26:59.915 --> 00:27:04.315
in a client, right, with a client, call with a client and it needs more info about your business or something,

00:27:04.875 --> 00:27:16.220
it can contact your personal Hermes agent deployed on the VPS and ask him questions and get contacts with him. Maybe the Hermes agent can send you a DM in the middle of the call on Discord or Telegram or WhatsApp,

00:27:16.540 --> 00:27:18.300
wherever your Hermes is authenticated.

00:27:18.460 --> 00:27:19.340
They're like, yo.

00:27:19.740 --> 00:27:21.340
The the this client is very promising.

00:27:22.075 --> 00:27:31.115
He wants to talk to you directly. Like, stuff like that. Right? It really is insane what you can do with this, and I have this tool here, AskRMS. It uses Angular to create a tunnel,

00:27:31.595 --> 00:27:35.515
and this really takes it to the next level. As I told you, VAPI is very, very configurable.

00:27:35.960 --> 00:27:40.760
So let's test this out. I'm gonna copy this ID of the tool, switch back to the terminal.

00:27:40.840 --> 00:27:47.320
I'm gonna do control c to just kill this to create a fresh hermes session. I know I can do slash new, but this is cleaner.

00:27:47.400 --> 00:27:49.000
I'll say list out all

00:27:49.595 --> 00:27:50.555
tools,

00:27:50.555 --> 00:27:53.595
all MCPs we have with VAPI.

00:27:53.915 --> 00:27:55.195
Then use

00:27:55.755 --> 00:27:56.795
this tool

00:27:57.435 --> 00:28:00.315
to ask Hermes something specific,

00:28:01.290 --> 00:28:06.810
perhaps to list out its internal folder structure. VAPI gets tool. Okay.

00:28:07.610 --> 00:28:13.290
Hopefully, it gets the but also get okay. Tools. Boom. Here's the ID. And this really

00:28:13.610 --> 00:28:17.130
fills in the last gap where if the VAPI assistant isn't sure

00:28:17.505 --> 00:28:20.145
on what to do during a call, it can use AskHermes

00:28:20.145 --> 00:28:26.305
to ask your Hermes agent, which can have connections to a lot more things and, you know, usually uses a more expensive model

00:28:26.545 --> 00:28:32.800
and has more context about you and the business to complete the request. So inside of the VAPI dashboard, I have this assistance,

00:28:32.800 --> 00:28:35.440
and I have this Hermes voice concierge.

00:28:35.440 --> 00:28:46.195
Here, have the tool attached. Ask Hermes. You need to give the specific tool to that specific assistant so it can use it, and we can actually talk to it. Right? So we can click on talk and do a test. I need to allow the microphone.

00:28:46.915 --> 00:28:49.235
Click allow. Hey. This is your AI assistant.

00:28:49.395 --> 00:28:50.595
What can I help you with?

00:28:51.555 --> 00:28:52.355
Hey.

00:28:53.075 --> 00:28:57.155
What tools do you have available? You have quite a few quite a few tools, browser control,

00:28:57.820 --> 00:29:00.540
terminal and file editing on your VPS,

00:29:00.620 --> 00:29:02.620
web search, VAPI management,

00:29:02.780 --> 00:29:04.860
cron jobs, sending messages,

00:29:05.100 --> 00:29:10.220
memory, skills, and delegating to sub agents. Want me to explain any of these in more detail?

00:29:10.865 --> 00:29:28.090
I want you to ask Hermes and tell it what is the internal file structure and folder structure. That's really good, guys. We got the ask Hermes tool here. It obviously takes a few seconds because it hits a VPS server. There it is. Hit again. Top level has Hermes and WAF root on Hermes, your VAPI adapter, and opt VAPI adapter,

00:29:28.330 --> 00:29:33.530
plus the usual root home dot files. Want me to dive deeper into the Hermes folder or the adapter?

00:29:34.330 --> 00:29:37.370
Really nice. So you can attach this as a tool

00:29:37.855 --> 00:29:46.415
to any of the voice assistants, and it can use it during a conversation. Right? So now I'm testing it myself, but, obviously, ideally, it's a potential client, a potential lead, maybe an applicant,

00:29:46.575 --> 00:29:49.215
whatever. There is, like, hundreds of use cases for voice agents.

00:29:49.790 --> 00:30:04.910
But now you know how with VAPI and the tools feature, you can use Hermes not only as a orchestrator, because so far, we've used Hermes to manage and create VAPI assistants. Right? But now you can use you can do the other way, where, basically,

00:30:05.685 --> 00:30:11.445
a VAPI assistant during the conversation can call to Hermes to get, you know, more more context,

00:30:11.605 --> 00:30:25.950
more tools, more connections, whatever is needed. So this really is the ultimate platform. With VAPI, you can build anything you imagine when it comes to voice agents, especially when you connect with with Hermes. So, again, I have to thank VAPI for sponsoring this video. And if you have a business,

00:30:26.510 --> 00:30:29.790
whether it's one that gets inbound or one that could use outbound,

00:30:30.110 --> 00:31:00.930
please start building voice agents. I don't care how you use it. You just need to start using it. Even if it takes you a couple weeks to figure out and really crack the code, get started now. Click the first link below the video. Give Vappi a shot. They have multiple different plans, so choose the one that makes sense for you and actually build this today. And as I mentioned before, if you want all of the resources from this video, for the different use cases for inbound, for the different use cases for outbound, and everything else mentioned in this video, click the second link below the video. It's completely free. You'll get a bundle with everything I mentioned in this video. So go below, click the second link, and grab it now.