I Tested Jev on 12 Real Use Cases. My Honest Thoughts.

So Jev is literally everywhere and I So Jev is literally everywhere and I think it's going to change how AI think it's going to change how AI think it's going to change how AI automations are built. So I came in here automations are built. So I came in here automations are built. So I came in here and tested it on 12 use cases and and tested it on 12 use cases and and tested it on 12 use cases and compared it with other AI models on compared it with other AI models on compared it with other AI models on things like speed and cost. I was even things like speed and cost. I was even things like speed and cost. I was even able to build this Chrome extension that able to build this Chrome extension that able to build this Chrome extension that will label X tweets as breaking or, you will label X tweets as breaking or, you will label X tweets as breaking or, you know, golden nuggets or AI slop in real know, golden nuggets or AI slop in real know, golden nuggets or AI slop in real time for me. On the back end you can see time for me. On the back end you can see time for me. On the back end you can see that it uses Jev to actually instantly that it uses Jev to actually instantly that it uses Jev to actually instantly categorize all the stuff as soon as it categorize all the stuff as soon as it categorize all the stuff as soon as it enters my screen. It's not doing very enters my screen. It's not doing very enters my screen. It's not doing very well in the first hour, but I also made well in the first hour, but I also made well in the first hour, but I also made this Jev trader, which is literally this Jev trader, which is literally this Jev trader, which is literally every single second analyzing if every single second analyzing if every single second analyzing if Bitcoin's going to go up or go down or Bitcoin's going to go up or go down or Bitcoin's going to go up or go down or stay and then it basically places trades stay and then it basically places trades stay and then it basically places trades in real time for me. Because this model in real time for me. Because this model in real time for me. Because this model is so good at quick decisions. But is so good at quick decisions. But is so good at quick decisions. But anyways, by the end of this video you'll anyways, by the end of this video you'll anyways, by the end of this video you'll understand how Jev works and where you understand how Jev works and where you understand how Jev works and where you should actually use it in your life. So should actually use it in your life. So should actually use it in your life. So let's not waste any time and just get let's not waste any time and just get let's not waste any time and just get straight into this one. All right, we're straight into this one. All right, we're straight into this one. All right, we're going to start off with just like what going to start off with just like what going to start off with just like what is Jev? I'm not going to do a super is Jev? I'm not going to do a super is Jev? I'm not going to do a super super deep dive, just enough for you to super deep dive, just enough for you to super deep dive, just enough for you to understand how it works and what we're understand how it works and what we're understand how it works and what we're looking at in today's video. So the looking at in today's video. So the looking at in today's video. So the interesting thing about Jev is that it's interesting thing about Jev is that it's interesting thing about Jev is that it's an AI that makes decisions, but it an AI that makes decisions, but it an AI that makes decisions, but it doesn't write anything. It doesn't doesn't write anything. It doesn't doesn't write anything. It doesn't output tokens. It's not anything that output tokens. It's not anything that output tokens. It's not anything that you could actually have a conversation you could actually have a conversation you could actually have a conversation with. It just makes decisions. So here with. It just makes decisions. So here with. It just makes decisions. So here was kind of the announcement tweet from was kind of the announcement tweet from was kind of the announcement tweet from Diogo. He co-invented ChatGPT and then Diogo. He co-invented ChatGPT and then Diogo. He co-invented ChatGPT and then he has been building in the past 2 years he has been building in the past 2 years he has been building in the past 2 years this new way to train models, RLCD. And this new way to train models, RLCD. And this new way to train models, RLCD. And you can see what that stands for is you can see what that stands for is you can see what that stands for is reinforcement learning for calibrated reinforcement learning for calibrated reinforcement learning for calibrated decisions. And this is on TypeSafety's decisions. And this is on TypeSafety's decisions. And this is on TypeSafety's blog and by the way, if you want to blog and by the way, if you want to blog and by the way, if you want to actually get in here so that you can actually get in here so that you can actually get in here so that you can start playing around with Jev, then go start playing around with Jev, then go start playing around with Jev, then go to TypeSafe AI and join the waitlist and to TypeSafe AI and join the waitlist and to TypeSafe AI and join the waitlist and then hopefully in a few hours you're then hopefully in a few hours you're then hopefully in a few hours you're able to sign in. But also this is able to sign in. But also this is able to sign in. But also this is available through like Vercel's gateway available through like Vercel's gateway available through like Vercel's gateway as well as OpenRouter. So if you're not as well as OpenRouter. So if you're not as well as OpenRouter. So if you're not in the waitlist yet, then you can still in the waitlist yet, then you can still in the waitlist yet, then you can still go out and play with Jev. But anyways,

go out and play with Jev. But anyways, go out and play with Jev. But anyways, essentially what happens is instead of a essentially what happens is instead of a essentially what happens is instead of a normal chat model where you would send normal chat model where you would send normal chat model where you would send in a message like this. This is some in a message like this. This is some in a message like this. This is some sort of support ticket and the AI model sort of support ticket and the AI model sort of support ticket and the AI model would read it, would reason, would think would read it, would reason, would think would read it, would reason, would think and then output like a message or output and then output like a message or output and then output like a message or output some sort of classification. It some sort of classification. It some sort of classification. It basically just outputs these types of basically just outputs these types of basically just outputs these types of things, which are a yes or no confidence things, which are a yes or no confidence things, which are a yes or no confidence level, a category and sort of a score. level, a category and sort of a score. level, a category and sort of a score. So for the first one, is it urgent? 99% So for the first one, is it urgent? 99% So for the first one, is it urgent? 99% confidence is yes, it is urgent. Which confidence is yes, it is urgent. Which confidence is yes, it is urgent. Which team? There were probably multiple team? There were probably multiple team? There were probably multiple routes like technical or billing or routes like technical or billing or routes like technical or billing or support, and it labeled it as technical. support, and it labeled it as technical. support, and it labeled it as technical. And then how frustrated, it gave it a And then how frustrated, it gave it a And then how frustrated, it gave it a one out of two on the frustration score one out of two on the frustration score one out of two on the frustration score or scale. But you're fully in control. or scale. But you're fully in control. or scale. But you're fully in control. You basically will set up Jev with, You basically will set up Jev with, You basically will set up Jev with, "Hey, this is essentially how you're "Hey, this is essentially how you're "Hey, this is essentially how you're supposed to make decisions, and here is supposed to make decisions, and here is supposed to make decisions, and here is sort of like the classification sort of like the classification sort of like the classification criteria." So, it's three types of criteria." So, it's three types of criteria." So, it's three types of decisions, like I said. The yes or no is decisions, like I said. The yes or no is decisions, like I said. The yes or no is called a null. The pick one is a choice, called a null. The pick one is a choice, called a null. The pick one is a choice, and then we have an actual score. And and then we have an actual score. And and then we have an actual score. And I'm going to show you guys real examples I'm going to show you guys real examples I'm going to show you guys real examples of all of these being run on these 12 of all of these being run on these 12 of all of these being run on these 12 use cases, so don't worry. But I just use cases, so don't worry. But I just use cases, so don't worry. But I just wanted to sort of lay the foundation wanted to sort of lay the foundation wanted to sort of lay the foundation here. So, like I said, in this example, here. So, like I said, in this example, here. So, like I said, in this example, it's yes or no, and there's a confidence it's yes or no, and there's a confidence it's yes or no, and there's a confidence score. And the team or categorization score. And the team or categorization score. And the team or categorization example, it's different categories, as example, it's different categories, as example, it's different categories, as well as a confidence score, and then a well as a confidence score, and then a well as a confidence score, and then a score from zero to 10 on some sort of score from zero to 10 on some sort of score from zero to 10 on some sort of scale. And in here, one meant that they scale. And in here, one meant that they scale. And in here, one meant that they were frustrated. And the reason why this were frustrated. And the reason why this were frustrated. And the reason why this is getting so much traction is because is getting so much traction is because is getting so much traction is because Diogo said that this is 20 to 200 times Diogo said that this is 20 to 200 times Diogo said that this is 20 to 200 times faster and 40 to 400 times cheaper, with faster and 40 to 400 times cheaper, with faster and 40 to 400 times cheaper, with output tokens being free. And so, if we output tokens being free. And so, if we output tokens being free. And so, if we look at the speed here, compared to look at the speed here, compared to look at the speed here, compared to models like Terra and Luna and Sol, this models like Terra and Luna and Sol, this models like Terra and Luna and Sol, this thing is going to be a lot faster. This thing is going to be a lot faster. This thing is going to be a lot faster. This was just one very quick test I ran. This was just one very quick test I ran. This was just one very quick test I ran. This doesn't mean that Terra's always faster doesn't mean that Terra's always faster doesn't mean that Terra's always faster than Luna, but this was just one quick than Luna, but this was just one quick than Luna, but this was just one quick example of how significantly faster Jev

example of how significantly faster Jev example of how significantly faster Jev is. Once again, it doesn't have to is. Once again, it doesn't have to is. Once again, it doesn't have to output all these tokens or reason. It output all these tokens or reason. It output all these tokens or reason. It just, boom, makes a decision and outputs just, boom, makes a decision and outputs just, boom, makes a decision and outputs it in like this JSON format. And same it in like this JSON format. And same it in like this JSON format. And same thing from a cost perspective, if you thing from a cost perspective, if you thing from a cost perspective, if you were running thousands and thousands of were running thousands and thousands of were running thousands and thousands of decisions per day, this is what it could decisions per day, this is what it could decisions per day, this is what it could actually end up looking like. Now, actually end up looking like. Now, actually end up looking like. Now, obviously, the important thing is you're obviously, the important thing is you're obviously, the important thing is you're paying a lot less, so you want to make paying a lot less, so you want to make paying a lot less, so you want to make sure that the quality is the exact same sure that the quality is the exact same sure that the quality is the exact same as what you'd be getting here or here to as what you'd be getting here or here to as what you'd be getting here or here to justify it. If we're just looking at the justify it. If we're just looking at the justify it. If we're just looking at the cost right now, it is significantly cost right now, it is significantly cost right now, it is significantly cheaper, and it is proven that it's cheaper, and it is proven that it's cheaper, and it is proven that it's significantly cheaper. So, what it significantly cheaper. So, what it significantly cheaper. So, what it cannot do is write or summarize or find cannot do is write or summarize or find cannot do is write or summarize or find themes or do deep analysis. It basically themes or do deep analysis. It basically themes or do deep analysis. It basically just just just outputs decisions. And one other outputs decisions. And one other outputs decisions. And one other limitation right now is that it has a limitation right now is that it has a limitation right now is that it has a very small input context window. It's very small input context window. It's very small input context window. It's 64,000 tokens, whereas a lot of the 64,000 tokens, whereas a lot of the 64,000 tokens, whereas a lot of the models that we're used to using today, models that we're used to using today, models that we're used to using today, whether that be Claude or GPT, are more whether that be Claude or GPT, are more whether that be Claude or GPT, are more on the side of a million tokens. So, if on the side of a million tokens. So, if on the side of a million tokens. So, if we look at this on a use case like a we look at this on a use case like a we look at this on a use case like a YouTube comments, if I fed in 5,000 YouTube comments, if I fed in 5,000 YouTube comments, if I fed in 5,000 YouTube comments, Jev could sort them YouTube comments, Jev could sort them YouTube comments, Jev could sort them for way cheaper and way faster than any for way cheaper and way faster than any for way cheaper and way faster than any AI model could, and then it could AI model could, and then it could AI model could, and then it could categorize them as like, "Hey, these categorize them as like, "Hey, these categorize them as like, "Hey, these need a reply. These are stuck. These need a reply. These are stuck. These need a reply. These are stuck. These people want to buy." And then what you people want to buy." And then what you people want to buy." And then what you could do is feed it a more intelligent could do is feed it a more intelligent could do is feed it a more intelligent AI model, an AI model that actually AI model, an AI model that actually AI model, an AI model that actually responds to things and outputs things.

responds to things and outputs things. responds to things and outputs things. And you could say, "Hey, ChatGPT, could And you could say, "Hey, ChatGPT, could And you could say, "Hey, ChatGPT, could you read just these now and then help me you read just these now and then help me you read just these now and then help me like analyze themes or help me respond like analyze themes or help me respond like analyze themes or help me respond to these ones or something like that." to these ones or something like that." to these ones or something like that." And that way you're not using a slower And that way you're not using a slower And that way you're not using a slower and more expensive model to actually and more expensive model to actually and more expensive model to actually categorize all of those comments in the categorize all of those comments in the categorize all of those comments in the first place. Because Jev isn't a first place. Because Jev isn't a first place. Because Jev isn't a frontier AI model. It's not even in the frontier AI model. It's not even in the frontier AI model. It's not even in the same bucket as Astra or Fable. It's a same bucket as Astra or Fable. It's a same bucket as Astra or Fable. It's a completely different type of model. So, completely different type of model. So, completely different type of model. So, when to use it? If you have thousands of when to use it? If you have thousands of when to use it? If you have thousands of things, if you have a corpus of data, if things, if you have a corpus of data, if things, if you have a corpus of data, if you need to classify things, make you need to classify things, make you need to classify things, make decisions, or you're running some sort decisions, or you're running some sort decisions, or you're running some sort of decision-based or of decision-based or of decision-based or classification-based workflow at scale classification-based workflow at scale classification-based workflow at scale and production. If you need like very and production. If you need like very and production. If you need like very quick real-time decisions because it's quick real-time decisions because it's quick real-time decisions because it's really, really fast. And stay with really, really fast. And stay with really, really fast. And stay with ChatGPT if you need things like handful ChatGPT if you need things like handful ChatGPT if you need things like handful of items, you need to understand why, of items, you need to understand why, of items, you need to understand why, you need to brainstorm, you need to you need to brainstorm, you need to you need to brainstorm, you need to chat, things like that. Anyways, let's chat, things like that. Anyways, let's chat, things like that. Anyways, let's just get straight into some use cases just get straight into some use cases just get straight into some use cases here. So, I know this might look a here. So, I know this might look a here. So, I know this might look a little bit intimidating of a screen. little bit intimidating of a screen. little bit intimidating of a screen. But, what I want to show you is But, what I want to show you is But, what I want to show you is a little bit of a playground of how this a little bit of a playground of how this a little bit of a playground of how this actually works. By the way, guys, I've actually works. By the way, guys, I've actually works. By the way, guys, I've got this completely free SOP for you got this completely free SOP for you got this completely free SOP for you about getting your first AI automation about getting your first AI automation about getting your first AI automation clients. It's going to go over the exact clients. It's going to go over the exact clients. It's going to go over the exact steps that has been proven for hundreds steps that has been proven for hundreds steps that has been proven for hundreds of our AIS+ members to get their first of our AIS+ members to get their first of our AIS+ members to get their first paid gigs. It goes over the one-sentence paid gigs. It goes over the one-sentence paid gigs. It goes over the one-sentence service pitch that can get you started service pitch that can get you started service pitch that can get you started today, why your first client should cost today, why your first client should cost today, why your first client should cost you money, the five-minute video that you money, the five-minute video that you money, the five-minute video that answers, "Can this person actually answers, "Can this person actually answers, "Can this person actually deliver?" before you've actually deliver?" before you've actually deliver?" before you've actually received any money, what to do when you received any money, what to do when you received any money, what to do when you have zero case studies. There's so many have zero case studies. There's so many have zero case studies. There's so many good things in here that are going to good things in here that are going to good things in here that are going to help you out. Even if you already do help you out. Even if you already do help you out. Even if you already do have clients, I would recommend grabbing have clients, I would recommend grabbing have clients, I would recommend grabbing this because like I said, it's yours this because like I said, it's yours this because like I said, it's yours completely free. So, if you want to grab completely free. So, if you want to grab completely free. So, if you want to grab this, there's a link for it down in the this, there's a link for it down in the this, there's a link for it down in the description. Let's get back to the description. Let's get back to the description. Let's get back to the video. So, the first one we're looking video. So, the first one we're looking video. So, the first one we're looking at is emails. Now, real quick, you can at is emails. Now, real quick, you can at is emails. Now, real quick, you can see that I've got a bunch of different see that I've got a bunch of different see that I've got a bunch of different categories set up or a bunch of categories set up or a bunch of categories set up or a bunch of different questions set up. The first different questions set up. The first different questions set up. The first one is invoice or receipt. This is a yes one is invoice or receipt. This is a yes one is invoice or receipt. This is a yes or no. The second one is brand deal.

or no. The second one is brand deal. or no. The second one is brand deal. This is yes or no. Scammer fishing, yes This is yes or no. Scammer fishing, yes This is yes or no. Scammer fishing, yes or no. We also have email type. We also or no. We also have email type. We also or no. We also have email type. We also have urgency, and we also have sponsor have urgency, and we also have sponsor have urgency, and we also have sponsor fit. So, we've got different types of fit. So, we've got different types of fit. So, we've got different types of scoring and different types of scoring and different types of scoring and different types of categorization. And you can see here, if categorization. And you can see here, if categorization. And you can see here, if I run this real quick, if I go to redo I run this real quick, if I go to redo I run this real quick, if I go to redo everything and I hit run, we're everything and I hit run, we're everything and I hit run, we're currently using the model Jev, and this currently using the model Jev, and this currently using the model Jev, and this is 1,000 emails. Like, look how quick is 1,000 emails. Like, look how quick is 1,000 emails. Like, look how quick this is able to classify 1,000 emails. this is able to classify 1,000 emails. this is able to classify 1,000 emails. So, it did that in about 70 seconds for So, it did that in about 70 seconds for So, it did that in about 70 seconds for 9 cents. Now, obviously, that's not like 9 cents. Now, obviously, that's not like 9 cents. Now, obviously, that's not like super super fast, like lightning fast, super super fast, like lightning fast, super super fast, like lightning fast, but this was not parallelized. If we but this was not parallelized. If we but this was not parallelized. If we were to run all of those individually in were to run all of those individually in were to run all of those individually in parallel, it would have been so much parallel, it would have been so much parallel, it would have been so much faster. But, I just wanted to show the faster. But, I just wanted to show the faster. But, I just wanted to show the difference here. Let's even go to difference here. Let's even go to difference here. Let's even go to something like GPT 5.6 Luna, and we'll something like GPT 5.6 Luna, and we'll something like GPT 5.6 Luna, and we'll run this again on everything. So, all run this again on everything. So, all run this again on everything. So, all 1,000. I mean, this feels like it took 1,000. I mean, this feels like it took 1,000. I mean, this feels like it took forever. With Luna, that took 5 minutes, forever. With Luna, that took 5 minutes, forever. With Luna, that took 5 minutes, and it was 62 cents, compared to 70 and it was 62 cents, compared to 70 and it was 62 cents, compared to 70 seconds, and I think it was 9 cents. And seconds, and I think it was 9 cents. And seconds, and I think it was 9 cents. And also, think about it wasn't just doing also, think about it wasn't just doing also, think about it wasn't just doing one sort of classification, it was doing one sort of classification, it was doing one sort of classification, it was doing all seven of these rules. And I actually all seven of these rules. And I actually all seven of these rules. And I actually just changed the back end to make this just changed the back end to make this just changed the back end to make this actually process things more in parallel actually process things more in parallel actually process things more in parallel with bigger payloads. So, I'm just going with bigger payloads. So, I'm just going with bigger payloads. So, I'm just going to run this now, and we'll see how much to run this now, and we'll see how much to run this now, and we'll see how much quicker this really is. Boom. Look how quicker this really is. Boom. Look how quicker this really is. Boom. Look how fast that went. That took 6 seconds, and fast that went. That took 6 seconds, and fast that went. That took 6 seconds, and it once again was 9 cents. So, that just it once again was 9 cents. So, that just it once again was 9 cents. So, that just shows how you can optimize that back end shows how you can optimize that back end shows how you can optimize that back end to make Jev go even faster. And yes, you to make Jev go even faster. And yes, you to make Jev go even faster. And yes, you can do the same thing with Luna, but can do the same thing with Luna, but can do the same thing with Luna, but it's just not going to be as fast as 6 it's just not going to be as fast as 6 it's just not going to be as fast as 6 seconds for 1,000 emails across seven seconds for 1,000 emails across seven seconds for 1,000 emails across seven categories. So, I know that this categories. So, I know that this categories. So, I know that this interface may be a little overwhelming.

interface may be a little overwhelming. interface may be a little overwhelming. Let's just get rid of everything here Let's just get rid of everything here Let's just get rid of everything here except for invoice or receipt. So, this except for invoice or receipt. So, this except for invoice or receipt. So, this is literally just us saying, "Okay, we is literally just us saying, "Okay, we is literally just us saying, "Okay, we want to set up some sort of want to set up some sort of want to set up some sort of classification for all of these 1,000 classification for all of these 1,000 classification for all of these 1,000 emails. We're going to give it a name. emails. We're going to give it a name. emails. We're going to give it a name. We're going to ask the question, is this We're going to ask the question, is this We're going to ask the question, is this email a receipt, invoice, payment email a receipt, invoice, payment email a receipt, invoice, payment confirmation, or billing notice?" And confirmation, or billing notice?" And confirmation, or billing notice?" And then we just define like what counts as then we just define like what counts as then we just define like what counts as yes. So, it has a a charge, a payment, a yes. So, it has a a charge, a payment, a yes. So, it has a a charge, a payment, a payout, or some sort of failed payout, payout, or some sort of failed payout, payout, or some sort of failed payout, and we call it a yes when Jev is at and we call it a yes when Jev is at and we call it a yes when Jev is at least 50% confident. So, that's kind of least 50% confident. So, that's kind of least 50% confident. So, that's kind of the thing that we're running here, and I the thing that we're running here, and I the thing that we're running here, and I would just go ahead and choose redo would just go ahead and choose redo would just go ahead and choose redo everything. And so, when we run this, everything. And so, when we run this, everything. And so, when we run this, it's basically going to look at all it's basically going to look at all it's basically going to look at all 1,000 of those emails and just decide, 1,000 of those emails and just decide, 1,000 of those emails and just decide, "Is that an invoice or receipt?" It "Is that an invoice or receipt?" It "Is that an invoice or receipt?" It comes back in 4 seconds for 5 cents, and comes back in 4 seconds for 5 cents, and comes back in 4 seconds for 5 cents, and it where it landed was no on 763 of it where it landed was no on 763 of it where it landed was no on 763 of them, but yes on 237 of them. Here is a them, but yes on 237 of them. Here is a them, but yes on 237 of them. Here is a category example where we actually set category example where we actually set category example where we actually set up the email type, whether it's up the email type, whether it's up the email type, whether it's notification, newsletter, billing, notification, newsletter, billing, notification, newsletter, billing, opportunity. And you can see if I edit opportunity. And you can see if I edit opportunity. And you can see if I edit this, what we did is we actually had to this, what we did is we actually had to this, what we did is we actually had to choose the options and define each of choose the options and define each of choose the options and define each of them. So, this is a pretty standard AI them. So, this is a pretty standard AI them. So, this is a pretty standard AI classification type of automation. But classification type of automation. But classification type of automation. But then if we look at the scoring, so for then if we look at the scoring, so for then if we look at the scoring, so for example, if we look at the sponsor fit, example, if we look at the sponsor fit, example, if we look at the sponsor fit, if I go to what this one looks like, if I go to what this one looks like, if I go to what this one looks like, this is rating it on a scale and we this is rating it on a scale and we this is rating it on a scale and we basically choose from lowest to highest basically choose from lowest to highest basically choose from lowest to highest what that looks like as far as not a what that looks like as far as not a what that looks like as far as not a sponsorship inquiry at all, or if it's a sponsorship inquiry at all, or if it's a sponsorship inquiry at all, or if it's a strong fit. And it will choose the strong fit. And it will choose the strong fit. And it will choose the level. So, you can see here, it shows level. So, you can see here, it shows level. So, you can see here, it shows that 942 of them were won and then it that 942 of them were won and then it that 942 of them were won and then it you know, we didn't have any that were you know, we didn't have any that were you know, we didn't have any that were strong fits. You can see there was strong fits. You can see there was strong fits. You can see there was another score one that was urgency about another score one that was urgency about another score one that was urgency about if there was action needed or nothing if there was action needed or nothing if there was action needed or nothing needed at all. And this was a little bit needed at all. And this was a little bit needed at all. And this was a little bit more even across the board. The average more even across the board. The average more even across the board. The average was 2.8 out of five. So, anyways, email was 2.8 out of five. So, anyways, email was 2.8 out of five. So, anyways, email classification is one example and classification is one example and classification is one example and obviously when you're looking at the obviously when you're looking at the obviously when you're looking at the actual cost and speed here, that first actual cost and speed here, that first actual cost and speed here, that first example we ran, Luna was 12 times the

example we ran, Luna was 12 times the example we ran, Luna was 12 times the cost and 46 times the time and that was cost and 46 times the time and that was cost and 46 times the time and that was also just Luna. What if we went up to also just Luna. What if we went up to also just Luna. What if we went up to Terra and Sol? How much more expensive Terra and Sol? How much more expensive Terra and Sol? How much more expensive that would have been and how much more that would have been and how much more that would have been and how much more that would have cost us? So, a lot of that would have cost us? So, a lot of that would have cost us? So, a lot of these use cases are kind of on the these use cases are kind of on the these use cases are kind of on the classification side. I did the exact classification side. I did the exact classification side. I did the exact same thing here with YouTube comments same thing here with YouTube comments same thing here with YouTube comments where I can choose categories or yes and where I can choose categories or yes and where I can choose categories or yes and no and score and I can analyze thousands no and score and I can analyze thousands no and score and I can analyze thousands of comments at a time on things like of comments at a time on things like of comments at a time on things like comment type, if they're worth a reply, comment type, if they're worth a reply, comment type, if they're worth a reply, if it gives me a video idea, what the if it gives me a video idea, what the if it gives me a video idea, what the sentiment is, what the question sentiment is, what the question sentiment is, what the question difficulty is. And once again, if I run difficulty is. And once again, if I run difficulty is. And once again, if I run Jev on all of a thousand of these, look Jev on all of a thousand of these, look Jev on all of a thousand of these, look how quick that actually goes. It would how quick that actually goes. It would how quick that actually goes. It would be so much longer if we used any other be so much longer if we used any other be so much longer if we used any other sort of AI model. 5 seconds for 5 cents. sort of AI model. 5 seconds for 5 cents. sort of AI model. 5 seconds for 5 cents. And if we actually go to my Jev console And if we actually go to my Jev console And if we actually go to my Jev console real quick and I go ahead and refresh, real quick and I go ahead and refresh, real quick and I go ahead and refresh, this is going to show that I've used 85 this is going to show that I've used 85 this is going to show that I've used 85 cents with Jev. But look how many cents with Jev. But look how many cents with Jev. But look how many requests I've done. I've done almost requests I've done. I've done almost requests I've done. I've done almost 20,000 requests. Think about what 20,000 20,000 requests. Think about what 20,000 20,000 requests. Think about what 20,000 requests on a different AI model would requests on a different AI model would requests on a different AI model would have cost us. And I can also do the have cost us. And I can also do the have cost us. And I can also do the exact same thing with my school posts. I exact same thing with my school posts. I exact same thing with my school posts. I can set up my custom categories or my can set up my custom categories or my can set up my custom categories or my custom classification criteria to see custom classification criteria to see custom classification criteria to see what type of questions we have, if they what type of questions we have, if they what type of questions we have, if they need help, if we need a team answer, if need help, if we need a team answer, if need help, if we need a team answer, if there's churn risk, member experience there's churn risk, member experience there's churn risk, member experience level, testimonial strength. And yes, level, testimonial strength. And yes, level, testimonial strength. And yes, this is kind of like a dashboard this is kind of like a dashboard this is kind of like a dashboard playground view, but what if you had playground view, but what if you had playground view, but what if you had this in an actual automation? Where this in an actual automation? Where this in an actual automation? Where every single time a new post got made, every single time a new post got made, every single time a new post got made, you updated the database. Every single you updated the database. Every single you updated the database. Every single time a new YouTube comment came in, you time a new YouTube comment came in, you time a new YouTube comment came in, you updated the database. Every time there's updated the database. Every time there's updated the database. Every time there's a new internal CRM entry or every time a new internal CRM entry or every time a new internal CRM entry or every time there's a new lead that submitted a form there's a new lead that submitted a form there's a new lead that submitted a form on your website. There's so many things on your website. There's so many things on your website. There's so many things you can do here and even though the you can do here and even though the you can do here and even though the speed might not not matter a ton when it speed might not not matter a ton when it speed might not not matter a ton when it comes to like actually having comes to like actually having comes to like actually having automations in production, what does add automations in production, what does add automations in production, what does add up really quickly is the cost. Because up really quickly is the cost. Because up really quickly is the cost. Because once again, when you start to run once again, when you start to run once again, when you start to run thousands and thousands of requests thousands and thousands of requests thousands and thousands of requests through, it's going to add up big time.

through, it's going to add up big time. through, it's going to add up big time. So, when you talk about AI economics and So, when you talk about AI economics and So, when you talk about AI economics and model routing, this is definitely going model routing, this is definitely going model routing, this is definitely going to be a game changer. Now, here's to be a game changer. Now, here's to be a game changer. Now, here's another interesting one where the speed another interesting one where the speed another interesting one where the speed really did matter. I have this one really did matter. I have this one really did matter. I have this one called X feed where it basically like called X feed where it basically like called X feed where it basically like pulled in a bunch of posts on my feed pulled in a bunch of posts on my feed pulled in a bunch of posts on my feed and it will tell me are they on topic or and it will tell me are they on topic or and it will tell me are they on topic or you know, like what's the category? Is you know, like what's the category? Is you know, like what's the category? Is it breaking news? Is there video idea it breaking news? Is there video idea it breaking news? Is there video idea potential? So, similar classification as potential? So, similar classification as potential? So, similar classification as we saw on these first three, but look we saw on these first three, but look we saw on these first three, but look what else I did. If I give my X a hard what else I did. If I give my X a hard what else I did. If I give my X a hard refresh real quick, you'll see that in refresh real quick, you'll see that in refresh real quick, you'll see that in the bottom left I have this thing called the bottom left I have this thing called the bottom left I have this thing called Jev Judged. And you can see that it Jev Judged. And you can see that it Jev Judged. And you can see that it judged that one a slop and as I scroll judged that one a slop and as I scroll judged that one a slop and as I scroll through, this is a Chrome extension that through, this is a Chrome extension that through, this is a Chrome extension that I built for me where it's looking at the I built for me where it's looking at the I built for me where it's looking at the X posts and really quickly reading them X posts and really quickly reading them X posts and really quickly reading them and classifying them as breaking or and classifying them as breaking or and classifying them as breaking or golden nuggets or AI slop. It's golden nuggets or AI slop. It's golden nuggets or AI slop. It's basically going to help me keep me more basically going to help me keep me more basically going to help me keep me more focused while I'm scrolling through X to focused while I'm scrolling through X to focused while I'm scrolling through X to see, you know, like highlighting what see, you know, like highlighting what see, you know, like highlighting what might be good to read and what are might be good to read and what are might be good to read and what are things that I should probably just things that I should probably just things that I should probably just ignore because of AI slop. And those are ignore because of AI slop. And those are ignore because of AI slop. And those are just a Chrome extension that I built just a Chrome extension that I built just a Chrome extension that I built where I has Jev on the back end powering where I has Jev on the back end powering where I has Jev on the back end powering all of this. So, that is a pretty cool all of this. So, that is a pretty cool all of this. So, that is a pretty cool use case and it shows how fast this use case and it shows how fast this use case and it shows how fast this thing actually happens in production. I thing actually happens in production. I thing actually happens in production. I mean, look how fast it's reacting to mean, look how fast it's reacting to mean, look how fast it's reacting to these posts as they come onto my screen.

these posts as they come onto my screen. these posts as they come onto my screen. It's basically instant. I also thought It's basically instant. I also thought It's basically instant. I also thought about what you could do with your about what you could do with your about what you could do with your meetings here. You could analyze meetings here. You could analyze meetings here. You could analyze meetings as they get transcribed in meetings as they get transcribed in meetings as they get transcribed in Fireflies or Granola or whatever you use Fireflies or Granola or whatever you use Fireflies or Granola or whatever you use and as soon as they come in, you can and as soon as they come in, you can and as soon as they come in, you can categorize them by what type of call it categorize them by what type of call it categorize them by what type of call it was, if you had decisions made, if you was, if you had decisions made, if you was, if you had decisions made, if you had like action steps. I thought this had like action steps. I thought this had like action steps. I thought this one was an interesting one because let's one was an interesting one because let's one was an interesting one because let's say you see that in a lot of your calls say you see that in a lot of your calls say you see that in a lot of your calls you have no next steps discussed or you have no next steps discussed or you have no next steps discussed or defined clearly with ownership and defined clearly with ownership and defined clearly with ownership and timelines, then you can use the data to timelines, then you can use the data to timelines, then you can use the data to change how you're conducting your calls. change how you're conducting your calls. change how you're conducting your calls. So, what I think is interesting is Jev So, what I think is interesting is Jev So, what I think is interesting is Jev on its own doesn't analyze things for on its own doesn't analyze things for on its own doesn't analyze things for you. But if you're strategic with the you. But if you're strategic with the you. But if you're strategic with the way that you set up the questions, you way that you set up the questions, you way that you set up the questions, you can get analysis from it. You can have can get analysis from it. You can have can get analysis from it. You can have this data tell a story. You can't have this data tell a story. You can't have this data tell a story. You can't have Jev look at thousands of transcripts and Jev look at thousands of transcripts and Jev look at thousands of transcripts and say, "Hey, tell me what I need to do say, "Hey, tell me what I need to do say, "Hey, tell me what I need to do better about these meetings or tell me better about these meetings or tell me better about these meetings or tell me common themes." But what you can do is common themes." But what you can do is common themes." But what you can do is you can give it categories and you can you can give it categories and you can you can give it categories and you can give it scores and then from all of give it scores and then from all of give it scores and then from all of these different types of questions that these different types of questions that these different types of questions that you set up, you tell your own story with you set up, you tell your own story with you set up, you tell your own story with that data. You can see that there's not that data. You can see that there's not that data. You can see that there's not much tension in some of our calls. I much tension in some of our calls. I much tension in some of our calls. I mean, this one has mean, this one has mean, this one has Someone says they're frustrated or Someone says they're frustrated or Someone says they're frustrated or overloaded, but but all of these overloaded, but but all of these overloaded, but but all of these questions that I created for Jev here, questions that I created for Jev here, questions that I created for Jev here, there's some sort of takeaway from each there's some sort of takeaway from each there's some sort of takeaway from each of these. Are things waiting on Nate? Is of these. Are things waiting on Nate? Is of these. Are things waiting on Nate? Is there revenue relevance? Things like there revenue relevance? Things like there revenue relevance? Things like that. And I also tried this use case that. And I also tried this use case that. And I also tried this use case with video clips where I basically had with video clips where I basically had with video clips where I basically had Jev or I had, you know, Astra break up a Jev or I had, you know, Astra break up a Jev or I had, you know, Astra break up a bunch of my YouTube videos into clips bunch of my YouTube videos into clips bunch of my YouTube videos into clips and then I had Jev look at those clips and then I had Jev look at those clips and then I had Jev look at those clips and tell me, you know, is this possible and tell me, you know, is this possible and tell me, you know, is this possible to be posted on its own as a clip? A lot to be posted on its own as a clip? A lot to be posted on its own as a clip? A lot of them, no. What is the hook strength of them, no. What is the hook strength of them, no. What is the hook strength of these clips? What type of clips are of these clips? What type of clips are of these clips? What type of clips are these? Do I need the screen on them? Is these? Do I need the screen on them? Is these? Do I need the screen on them? Is there a quotable line inside of this there a quotable line inside of this there a quotable line inside of this clip? And then I could start to have it clip? And then I could start to have it clip? And then I could start to have it pull out things that might be worth pull out things that might be worth pull out things that might be worth reposting somewhere else or might be reposting somewhere else or might be reposting somewhere else or might be worth me thinking about the way that I worth me thinking about the way that I worth me thinking about the way that I actually speak in these videos and actually speak in these videos and actually speak in these videos and things like that. And so these were a things like that. And so these were a things like that. And so these were a lot of ways that I would think about how

lot of ways that I would think about how lot of ways that I would think about how do I take a corpus of information, a ton do I take a corpus of information, a ton do I take a corpus of information, a ton and ton of data that I want to have AI and ton of data that I want to have AI and ton of data that I want to have AI analyze, but instead of paying more for analyze, but instead of paying more for analyze, but instead of paying more for it and waiting longer, let's figure out it and waiting longer, let's figure out it and waiting longer, let's figure out how we can how we can how we can use the right questions to have Jev do use the right questions to have Jev do use the right questions to have Jev do it for us. And then, not only can we it for us. And then, not only can we it for us. And then, not only can we maybe have some sort of dashboard view, maybe have some sort of dashboard view, maybe have some sort of dashboard view, but how do we build Jev into our actual but how do we build Jev into our actual but how do we build Jev into our actual back-end automations where it's really back-end automations where it's really back-end automations where it's really going to benefit us to having a really going to benefit us to having a really going to benefit us to having a really cheap and fast model as we increase the cheap and fast model as we increase the cheap and fast model as we increase the throughput. Now, I will say don't just throughput. Now, I will say don't just throughput. Now, I will say don't just plug in Jev and trust what it says plug in Jev and trust what it says plug in Jev and trust what it says automatically. What you're really going automatically. What you're really going automatically. What you're really going to want to do is run evals, meaning to want to do is run evals, meaning to want to do is run evals, meaning you're going to have a golden data set you're going to have a golden data set you're going to have a golden data set of 100 use cases and 100 correct answers of 100 use cases and 100 correct answers of 100 use cases and 100 correct answers and then you're going to run Jev through and then you're going to run Jev through and then you're going to run Jev through those and you're going to run Opus those and you're going to run Opus those and you're going to run Opus through those and you're going to run through those and you're going to run through those and you're going to run Soul through those and you're going to Soul through those and you're going to Soul through those and you're going to see which model gives you the best see which model gives you the best see which model gives you the best balance of accuracy and cost. And if you balance of accuracy and cost. And if you balance of accuracy and cost. And if you care about speed in that use case, then care about speed in that use case, then care about speed in that use case, then also speed as well. But here's some also speed as well. But here's some also speed as well. But here's some other things you could do. You could other things you could do. You could other things you could do. You could have it vet contracts for you as they have it vet contracts for you as they have it vet contracts for you as they come in. You could see the type of risk, come in. You could see the type of risk, come in. You could see the type of risk, you could see the type of clause, you you could see the type of clause, you you could see the type of clause, you could create any sort of questions that could create any sort of questions that could create any sort of questions that actually matter to you when you're actually matter to you when you're actually matter to you when you're vetting contracts. Same thing with jobs vetting contracts. Same thing with jobs vetting contracts. Same thing with jobs and leads. You can get red flags, you and leads. You can get red flags, you and leads. You can get red flags, you can get lead quality, you can get next can get lead quality, you can get next can get lead quality, you can get next steps. You can also do something like a steps. You can also do something like a steps. You can also do something like a brain dump router where you're brain dump router where you're brain dump router where you're constantly just talking into your phone constantly just talking into your phone constantly just talking into your phone or you're talking into something and or you're talking into something and or you're talking into something and then you're feeding that into Jev and it then you're feeding that into Jev and it then you're feeding that into Jev and it can tell you what type of things you're can tell you what type of things you're can tell you what type of things you're talking about, if they're ideas or tasks talking about, if they're ideas or tasks talking about, if they're ideas or tasks or journals. If you have things that or journals. If you have things that or journals. If you have things that have deadlines, if you have things that have deadlines, if you have things that have deadlines, if you have things that are high priority, what area of your are high priority, what area of your are high priority, what area of your life they're in. There's so many ways to life they're in. There's so many ways to life they're in. There's so many ways to use this because a big part of what we use this because a big part of what we use this because a big part of what we do with AI, like I said, is just do with AI, like I said, is just do with AI, like I said, is just figuring out what to do with all of our figuring out what to do with all of our figuring out what to do with all of our data and Jev can do that really well.

data and Jev can do that really well. data and Jev can do that really well. And then I think one of the best And then I think one of the best And then I think one of the best examples here is customer support. Just examples here is customer support. Just examples here is customer support. Just routing emails around, figuring out, you routing emails around, figuring out, you routing emails around, figuring out, you know, sentiment, urgency, what we need know, sentiment, urgency, what we need know, sentiment, urgency, what we need to do, how we categorize these sorts of to do, how we categorize these sorts of to do, how we categorize these sorts of things. I think that this is going to be things. I think that this is going to be things. I think that this is going to be a huge game changer for customer support a huge game changer for customer support a huge game changer for customer support because there's so many different like because there's so many different like because there's so many different like decisions that have to be made and Jev decisions that have to be made and Jev decisions that have to be made and Jev is really good and really fast and is really good and really fast and is really good and really fast and really cheap at making decisions. So, really cheap at making decisions. So, really cheap at making decisions. So, here's another use case that I thought here's another use case that I thought here's another use case that I thought would be cool to just sort of like POC. would be cool to just sort of like POC. would be cool to just sort of like POC. So, this is paper trading. This isn't So, this is paper trading. This isn't So, this is paper trading. This isn't very vetted. There's a lot that's like very vetted. There's a lot that's like very vetted. There's a lot that's like wrong with this, but I think that Jev wrong with this, but I think that Jev wrong with this, but I think that Jev being so real-time and making decisions being so real-time and making decisions being so real-time and making decisions so fast, it's going to be really so fast, it's going to be really so fast, it's going to be really interesting to see how it affects things interesting to see how it affects things interesting to see how it affects things like day trading or trading crypto in like day trading or trading crypto in like day trading or trading crypto in real time. So, you can see every single real time. So, you can see every single real time. So, you can see every single second Jev is basically predicting, is second Jev is basically predicting, is second Jev is basically predicting, is this going to go up? Am I unclear? Is it this going to go up? Am I unclear? Is it this going to go up? Am I unclear? Is it going to go down? You can see these going to go down? You can see these going to go down? You can see these confidence scores jumping around every confidence scores jumping around every confidence scores jumping around every single second and that's how it decides single second and that's how it decides single second and that's how it decides what to do. That's how it decides down what to do. That's how it decides down what to do. That's how it decides down here to place trades, to buy things or here to place trades, to buy things or here to place trades, to buy things or to sell things. Now, unfortunately, to sell things. Now, unfortunately, to sell things. Now, unfortunately, there's a lot of these fees here. So, there's a lot of these fees here. So, there's a lot of these fees here. So, the fees are way more expensive than Jev the fees are way more expensive than Jev the fees are way more expensive than Jev actually um making decisions for us. So, actually um making decisions for us. So, actually um making decisions for us. So, that's one issue where it's like, okay, that's one issue where it's like, okay, that's one issue where it's like, okay, well, how much would we actually have to well, how much would we actually have to well, how much would we actually have to be able to profit to make this worth it?

be able to profit to make this worth it? be able to profit to make this worth it? But right here you can see just the cost But right here you can see just the cost But right here you can see just the cost of running these decisions. Look how of running these decisions. Look how of running these decisions. Look how much more this would have cost us per much more this would have cost us per much more this would have cost us per day with other models. Whereas Jev would day with other models. Whereas Jev would day with other models. Whereas Jev would just be costing us about two bucks a day just be costing us about two bucks a day just be costing us about two bucks a day to run this 24/7 and Soul and Opus and to run this 24/7 and Soul and Opus and to run this 24/7 and Soul and Opus and Fable would be significantly more than Fable would be significantly more than Fable would be significantly more than Jev. Now, I've also seen people on X Jev. Now, I've also seen people on X Jev. Now, I've also seen people on X doing things like having Jev play video doing things like having Jev play video doing things like having Jev play video games and having Jev like do different games and having Jev like do different games and having Jev like do different creative fun things and I think it's creative fun things and I think it's creative fun things and I think it's really cool, like the browser use and really cool, like the browser use and really cool, like the browser use and all that. It's cool to see what's all that. It's cool to see what's all that. It's cool to see what's possible, but I think you have to think possible, but I think you have to think possible, but I think you have to think about where's the handoff because with about where's the handoff because with about where's the handoff because with browser use it was unable to like browser use it was unable to like browser use it was unable to like actually type things in. It would actually type things in. It would actually type things in. It would basically make decisions and then it basically make decisions and then it basically make decisions and then it would have to route to a different model would have to route to a different model would have to route to a different model that's better with actually controlling that's better with actually controlling that's better with actually controlling the browser to do things. And that's why the browser to do things. And that's why the browser to do things. And that's why I wanted to show what this looks like I wanted to show what this looks like I wanted to show what this looks like for these examples because I think for these examples because I think for these examples because I think building dashboards or automations where building dashboards or automations where building dashboards or automations where you have Jev powering it on the back end you have Jev powering it on the back end you have Jev powering it on the back end for things that you actually care about for things that you actually care about for things that you actually care about in your life like these sorts of things in your life like these sorts of things in your life like these sorts of things is where you'll start to play with Jev is where you'll start to play with Jev is where you'll start to play with Jev and actually get some return and then and actually get some return and then and actually get some return and then later figure out how you can expand or later figure out how you can expand or later figure out how you can expand or extend your workflows with other models extend your workflows with other models extend your workflows with other models on the back. But anyways, I hope seeing on the back. But anyways, I hope seeing on the back. But anyways, I hope seeing these examples even though all of these these examples even though all of these these examples even though all of these were very similar in the you know the were very similar in the you know the were very similar in the you know the the realm of classification. I hope that the realm of classification. I hope that the realm of classification. I hope that it helps you understand how you can it helps you understand how you can it helps you understand how you can start to ask the right questions in here start to ask the right questions in here start to ask the right questions in here and how you can start to work it into and how you can start to work it into and how you can start to work it into things that you're doing to actually things that you're doing to actually things that you're doing to actually make sense out of it. But that is going make sense out of it. But that is going make sense out of it. But that is going to do it for this one. So if you guys to do it for this one. So if you guys to do it for this one. So if you guys enjoyed and learned something new, enjoyed and learned something new, enjoyed and learned something new, please give it a like it helps me out a please give it a like it helps me out a please give it a like it helps me out a ton. And as always, I appreciate you ton. And as always, I appreciate you ton. And as always, I appreciate you guys making it to the end of the video guys making it to the end of the video guys making it to the end of the video and I'll see you on the next one.

and I'll see you on the next one. and I'll see you on the next one. Thanks everyone.