Jev tested on 12 use cases: dominant at classification, upside-down on live Bitcoin trades
Nate Herk runs TypeSafe AI's decision-only model against GPT-5.6 on email, comment, and post classification, then hands it a real paper-trading account to see where the speed stops mattering.
Jev is not a chat model, it is a decisions-only model that is 20-200x faster and 40-400x cheaper than frontier AI at yes/no, category, and score calls, which makes it the right layer for high-volume classification backends and the wrong tool for anything needing explanation, vision, or long context.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
You run AI automations that classify large volumes of emails, comments, leads, or posts and want to cut the model cost of that layer.
You're building backend routing logic (support triage, contract review, lead scoring, meeting analysis) and want a cheaper model than GPT or Claude just for the yes/no/score decisions.
You're deciding whether a specialized decision-only model is worth adding alongside your existing chat model in a production pipeline.
SKIP IF…
You need a model that writes, summarizes, explains its reasoning, or holds a conversation. Jev only outputs a label and a confidence score, never text.
You're hoping for a working trading bot. The paper-trading demo shown here is down money once exchange fees are counted.
You need the model to read images, video, or more than about 64,000 tokens of text at once.
TL;DR
The full version, fast.
Jev, built by TypeSafe AI on a training method called RLCD, is an AI that only makes decisions: a yes/no with a confidence score, a category pick, or a 0-10 score. It never writes or reasons in text, which is what makes it 20-200x faster and 40-400x cheaper than models like GPT-5.6 Terra, Luna, and Sol. Across emails, YouTube comments, community posts, an X feed classifier, meeting transcripts, and video clips, Jev classified 1,000 items in as little as 6 seconds for 9 cents once the backend was parallelized. The honest limits: it cannot summarize, explain, or see images, its context window is a small 64K tokens, and a live paper-trading bot built on it is down $26 once fees are counted, with a separate model still needed to actually execute browser actions.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Cold open teasing the Chrome extension that labels X posts and the real-time Bitcoin trading bot, before promising a breakdown of where Jev actually fits.
00:41 – 02:40
02 · What Jev Is
Jev only outputs decisions (yes/no, category, or score) and never writes text; explains the null/choice/score framework and TypeSafe AI's RLCD training claim.
02:40 – 05:28
03 · Speed, Cost & Limits
TypeSafe's own benchmark shows Jev far faster than GPT-5.6 Terra/Luna/Sol at similar accuracy; covers what Jev cannot do (write, summarize, see images) and its 64K-token context window, plus the free SOP pitch.
05:28 – 08:33
04 · Email Classification Benchmark
Live test classifying 1,000 emails across 7 rules: Jev finishes in 6 seconds for 9 cents once parallelized, versus 5 minutes and 62 cents on GPT-5.6 Luna for a single rule.
08:33 – 10:00
05 · Comments, Communities & Automations
Same classification pattern applied to YouTube comments and Skool community posts; 20,000 total Jev requests cost 85 cents in his console.
10:00 – 10:57
06 · X Feed Chrome Extension
A Chrome extension built on Jev tags X posts as breaking news, golden nuggets, or AI slop as they load, demonstrating near-instant production classification.
10:57 – 12:48
07 · Meetings & Video Clips
Jev applied to meeting transcripts (call type, decisions made, next steps) and to video clip selection (hook strength, quotability), with the point that Jev only scores, the human still has to interpret the pattern.
12:48 – 14:13
08 · Evals & More Use Cases
Recommends running a golden 100-example eval against Jev, Opus, and Sol before trusting it in production; lists further use cases (contract vetting, lead scoring, a personal brain-dump router).
14:13 – 15:40
09 · Real-Time Trading & Handoffs
A Jev-powered Bitcoin paper-trading bot predicts up/down every second but is down $26 on a $1,000 balance once fees are counted; notes Jev cannot control a browser on its own and must hand off to another model for actions.
15:40 – 16:08
10 · Final Thoughts
Wraps by reiterating Jev's home is fast, cheap, high-volume decisions on the backend, not chat, analysis, or unsupervised action.
Atomic Insights
Lines worth screenshotting.
Jev makes decisions but never writes a word: no summaries, no explanations, no chat, just a label and a confidence score.
TypeSafe AI claims Jev is 20-200x faster and 40-400x cheaper than frontier chat models, with output tokens free.
In Nate Herk's own test, 1,000 emails across 7 classification rules processed in 6 seconds for 9 cents once the backend was parallelized, versus 5 minutes and 62 cents on GPT-5.6 Luna for one rule.
Jev's decisions come in exactly three types: a null (yes/no with confidence), a choice (pick one category), or a score (rate 0-10).
Jev's context window is capped at about 64,000 tokens, versus roughly a million tokens on models like Claude or GPT.
Jev cannot write, summarize, find themes, explain its reasoning, do math or dates, or see images and video.
20,000 classification requests through Jev cost 85 cents total in Nate Herk's console, a volume that would be far more expensive on a frontier chat model.
A Chrome extension built on Jev classifies X posts as breaking news, golden nuggets, or AI slop in near real time as they load.
A real-time paper-trading bot built on Jev to predict Bitcoin's next move every second was down $26 on a $1,000 starting balance, with trading fees costing more than Jev's own decisions.
Jev cannot control a browser on its own; in browser-use tests it made the decision but had to hand off to a different model to actually type or click.
The recommended way to trust Jev in production is to build a golden set of 100 use cases with known correct answers and benchmark Jev against models like Opus and Sol before relying on it.
Takeaway
A decision-only model changes the economics of classification, not the ceiling on what AI can do.
WHAT TO LEARN
Splitting your AI stack into a cheap decision layer and an expensive reasoning layer can cut classification costs by an order of magnitude, but the speed and cost gains disappear the moment the task needs judgment, context, or unsupervised action.
A model that only outputs a label and a confidence score, with no reasoning tokens, can be tens to hundreds of times cheaper and faster than a general chat model at the same classification task.
The right pattern for a large-volume pipeline is to let a cheap decision model do the first-pass sort, then hand only the flagged or ambiguous items to a more expensive model that can explain or respond.
A small context window (Jev's is about 64,000 tokens) is a real constraint, not a footnote, on models optimized purely for decisions rather than deep reading.
Before trusting any specialized model in production, build a golden set of known-correct examples and benchmark it against your current model on both accuracy and cost, not cost alone.
Speed and low cost don't automatically translate to profit: a real-time trading bot built on a fast, cheap decision model still lost money once real-world fees were counted, because the bottleneck moved from compute cost to transaction cost.
A model that only decides still can't act: any workflow that needs to actually execute a step (like controlling a browser) still needs a separate model or system to carry out what the decision model chose.
Glossary
Terms worth knowing.
Jev
A decision-only AI model from TypeSafe AI that outputs a yes/no, a category pick, or a 0-10 score instead of writing text, built for high-volume classification at low cost and high speed.
RLCD
Reinforcement Learning for Calibrated Decisions, the training method TypeSafe AI says underlies Jev, aimed at producing well-calibrated confidence scores rather than free-text answers.
TypeSafe AI
The company behind Jev, co-founded according to the video by a co-inventor of ChatGPT, currently running a waitlist alongside availability through Vercel's AI Gateway and OpenRouter.
Null (decision type)
Jev's term for a yes/no decision paired with a confidence percentage, such as classifying whether an email is urgent.
Choice (decision type)
Jev's term for picking one category from a defined set, such as routing an email to a specific team.
Score (decision type)
Jev's term for rating something on a numeric scale, such as scoring how frustrated a customer sounds from 0 to 10.
Context window
The amount of text a model can read at once, measured in tokens; Jev's is about 64,000 tokens, far smaller than general chat models.
“So Jev is literally everywhere and I think it's going to change how AI automations are built.”
cold open hook stating the video's thesis→ TikTok hook↗ Tweet quote
06:15
“That took six seconds and it once again was nine cents.”
concrete, quotable speed/cost proof point from the live demo→ IG reel cold open↗ Tweet quote
15:16
“The fees are way more expensive than Jev actually making decisions for us.”
the honest limit that undercuts the hype, good pull-quote→ newsletter pull-quote↗ Tweet quote
15:58
“Jev being so real-time and making decisions so fast, it's going to be really interesting to see how it affects things like day trading.”
forward-looking claim paired against the trading bot's actual loss→ TikTok hook↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphor
So Jev is literally everywhere and I think it's going to change how AI automations are built. So I came in here and tested it on 12 use cases and compared it with other AI models on things like speed and cost. I was even able to build this Chrome extension that will label X tweets as breaking or golden nuggets or AI slop in real time for me.
On the back end, you can see that it uses Jev to actually instantly categorize all the stuff as soon as it enters my screen. It's not doing very well in the first hour, but I also made this Jev trader, which is literally every single second analyzing if Bitcoin is going to go up or go down or stay. And then it basically places trades in real time for me.
because this model is so good at quick decisions. But anyways, by the end of this video, you'll understand how Jev works and where you should actually use it in your life. So let's not waste any time and just get straight into this one.
All right, we're gonna start off with just like, what is Jev? I'm not gonna do a super, super deep dive, just enough for you to understand how it works and what we're looking at in today's video. So the interesting thing about Jev is that it's an AI that makes decisions, but it doesn't write anything.
It doesn't output tokens. It's not anything that you could actually have a conversation with. It just makes decisions.
So here was kind of the announcement tweet from Diogo. He co -invented ChatGPT and then he has been building in the past two years this new way to train models, RLCD. And you can see what that stands for is Reinforcement Learning for Calibrated Decisions.
And this is on TypeSafe's blog. And by the way, if you want to actually... get in here so that you can start playing around with Jev, then go to TypeSafe AI and join the waitlist.
And then hopefully in a few hours, you're able to sign in. But also this is available through like Vercel's gateway as well as open router. So if you're not in the waitlist yet, then you can still go out and play with Jev.
But anyways, essentially what happens is instead of a normal chat model where you would send in a message like this, this is some sort of support ticket and the AI model would read it, would reason, would think, and then output like a message or output some sort of classification. It basically just outputs. these types of things which are a yes or no confidence level a category and sort of a score.
So for the first one, is it urgent? 99 % confidence is yes, it is urgent. Which team?
There were probably multiple routes like technical or billing or support, and it labeled it as technical. And then how frustrated? It gave it a one out of two on the frustration score or scale.
But you're fully in control. You basically will set up Jev with, hey, this is essentially how you're supposed to make decisions. And here is sort of like the classification criteria.
So it's three types of decisions. Like I said, the yes or no is called a null. The pick one is a choice.
And then we have an actual score. And I'm going to show you guys real examples of all of these being run on these 12 use cases. So don't worry.
But I just wanted to sort of lay the foundation here. So like I said, in this example, it's yes or no. And there's a confidence score.
and the team or categorization example it's different categories as well as a confidence score and then a score from 0 to 10 on some sort of scale and in here one meant that they were frustrated and the reason why this is getting so much traction is because diogo said that this is 20 to 200 times faster and 40 to 400 times cheaper with output tokens being free and so if we look at the speed here compared to models like terra and luna and soul this thing is going to be a lot faster.
This was just one very quick test I ran. This doesn't mean that Terra is always faster than Luna, but this was just one quick example of how significantly faster Jev is. Once again, it doesn't have to output all these tokens or reason.
It just, boom, makes a decision and outputs it in like this JSON format. And same thing from a cost perspective. If you were running thousands and thousands of decisions per day, this is what it could actually end up looking like.
Now, obviously the important thing is you're paying a lot less. So you want to make sure that the quality is the exact same as what you'd be getting here or here to justify it. If we're just looking at the cost right now, it is significantly cheaper and it is proven that it's significantly cheaper.
So what it cannot do is write or summarize or find themes or do deep analysis. It basically just outputs decisions. And one other limitation right now is that it has a very small input context window.
It's 64 ,000 tokens, whereas a lot of the models that we're used to using today, whether that be Claude or GBT, are more on the side of a million tokens. So if we look at this on a use case like YouTube comments, if I fed in 5 ,000 YouTube comments, Jeff could sort them for way cheaper and way faster than any AI model could.
And then it could categorize them as like, hey, these need a reply. These are stuck. These people want to buy.
And then what you could do is feed a more intelligent AI model, an AI model that actually responds to things and outputs things. And you can say, hey, ChatGPT, could you read just these now and then help me like analyze themes or help me respond to these ones or something like that.
And that way you're not using a slower and more expensive model to actually categorize all of those comments in the first place. Because Jev isn't a frontier AI model. It's not even in the same bucket as Astra or Fable.
It's a completely different type of model. So when to use it, if you have thousands of things, if you have a corpus of data, if you need to classify things, make decisions, or you're running some sort of decision -based or classification -based workflow at scale and production, if you need like very quick real -time decisions, because it's really, really fast, and stay with ChatGPT if you need things like a handful of items, you need to understand why, you need to brainstorm, you need to chat, things like that.
Anyways, let's just get straight into some use cases here. So I know this might look a little bit intimidating of a screen, but what I want to show you is... a little bit of a playground of how this actually works.
By the way, guys, I've got this completely free SOP for you about getting your first AI automation client. It's going to go over the exact steps that has been proven for hundreds of our AIS Plus members to get their first paid gigs. It goes over the one sentence service pitch that can get you started today, why your first client should cost you money, the five minute video that answers can this person actually deliver before you've actually...
received any money. What to do when you have zero case studies. There's so many good things in here that are going to help you out.
Even if you already do have clients, I would recommend grabbing this because like I said, it's yours completely free. So if you want to grab this, there's a link for it down in the description. Let's get back to the video.
So the first one we're looking at is emails. Now, real quick, you can see that I've got a bunch of different categories set up or a bunch of different questions set up. The first one is invoice or receipt.
This is a yes or no. The second one is brand deal. This is yes or no.
Scam or phishing, yes or no. We also have email type. We also have urgency and we also have sponsor fit.
So we've got different types of scoring and different types of categorization. And you can see here, if I run this real quick, if I go to redo everything and I hit run, we're currently using the model Jev and this is a thousand emails. Like look how quick this is able to classify a thousand emails.
So it did that in about 70 seconds for 9 cents. Now, obviously, that's not like super, super fast, like lightning fast, but this was not parallelized. If we were to run all of those individually in parallel, it would have been so much faster.
But I just wanted to show the difference here. Let's even go to something like GBD 5 .6 Luna, and we'll run this again on everything. So all 1 ,000.
I mean, this feels like it took forever. With Luna, that took five minutes and it was 62 cents compared to 70 seconds and I think it was nine cents. And also think about it wasn't just doing one sort of classification, it was doing all seven of these rules.
And I actually just changed the backend to make this actually process things more in parallel with bigger payloads. So I'm just gonna run this now and we'll see how much quicker this really is. Boom, look how fast that went.
That took six seconds and it once again was nine cents. So that just shows how you can optimize that backend to make Jev go even faster. And yes, you could do the same thing with Luna, but it's just not gonna be as fast as six seconds for a thousand emails across seven categories.
So I know that this interface may be a little overwhelming. Let's just get rid of everything here except for invoice or receipt. So this is literally just us saying, okay, we wanna set up some sort of classification for all of these a thousand emails.
We're gonna give it a name. We're going to ask the question, is this email a receipt, invoice, payment confirmation, or billing notice? And then we just define like what counts as yes.
So it has a charge, a payment, a payout, or some sort of failed payout. And we call it a yes when Jev is at least 50 % confident. So that's kind of the thing that we're running here.
And I would just go ahead and choose redo everything. And so when we run this, it's basically going to look at all 1 ,000 of those emails and just decide, is that an invoice or receipt? It comes back in four seconds for 5 cents.
And where it landed was no on 763 of them, but yes on 237 of them. Here is a category example where we actually set up the email type, whether it's notification, newsletter, billing, opportunity. And you can see if I edit this, what we did is we actually had to choose the options and define each of them.
So this is a pretty standard AI classification type of automation. But then if we look at the scoring, so for example, if we look at the sponsor fit, if I go to what this one looks like, this is rating it on a scale. And we basically choose from lowest to highest what that looks like as far as not a sponsorship inquiry at all, or if it's a strong fit and it will choose the level.
So you can see here, it shows that, 942 of them were one, and then we didn't have any that were strong fits. You can see there was another score when that was urgency about if there was action needed or nothing needed at all.
And this was a little bit more even across the board. The average was 2 .8 out of five. So anyways, email classification is one example.
And obviously... when you're looking at the actual cost and speed here. That first example we ran, Luna was 12 times the cost and 46 times the time.
And that was also just Luna. What if we went up to Terra and Sol? How much more expensive that would have been and how much more that would have cost us.
So a lot of these use cases are kind of on the classification side. I did the exact same thing here with YouTube comments where I can choose categories or yes and no and score. And I can analyze thousands of comments at a time.
on things like comment type, if they're worth a reply, if it gives me a video idea, what the sentiment is, what the question difficulty is. And once again, if I run Jev on all a thousand of these, look how quick that actually goes. It would be so much longer if we used any other sort of AI model, five seconds for five cents.
And if we actually go to my Jev console real quick and I go ahead and refresh, this is going to show that I've used 85 cents with Jev, but look how many requests I've done. I've done almost 20 ,000 requests. Think about what 20 ,000 requests on a different AI model would have cost us.
And I can also - do the exact same thing with my school posts. I can set up.
my custom categories or my custom classification criteria to see what type of questions we have, if they need help, if we need a team answer, if there's churn risk, member experience level, testimonial strength. And yes, this is kind of like a dashboard playground view, but what if you had this in an actual automation where every single time a new post got made, you updated the database.
Every single time a new YouTube comment came in, you updated the database. Every time there's a new internal CRM entry or every time there's a new lead that submitted a form on your website, there's so many things you can do here. And even though the speed might not matter a ton when it comes to like actually having automations in production.
What does add up really quickly is the cost. Because once again, when you start to run thousands and thousands of requests through, it's going to add up big time. So when you talk about AI economics and model routing, this is definitely going to be a game changer.
Now here's another interesting one where the speed really did matter. I have this one called X feed where it basically like pulls in a bunch of posts on my feed and it will tell me, are they on topic or, you know, like what's the category? Is it breaking news?
Is there a video idea potential? So similar class. as we saw in these first three, but look what else I did.
If I give my X a hard refresh real quick, you'll see that in the bottom left, I have this thing called Jev Judged. And you can see that it judged that one as slop. And as I scroll through, this is a Chrome extension that it built for me, where it's looking at the X posts and really quickly reading them and classifying them as breaking or golden nuggets or AI slop.
It's basically gonna help me keep me more focused while I'm scrolling through X to see, you know, like. highlighting what might be good to read and what are things that I should probably just ignore because of AI slop. And this was just a Chrome extension that I built where it has Jev on the backend powering all of this.
So that is a pretty cool use case. And it shows how fast this thing actually happens in production. I mean, look how fast it's reacting to these posts as they come onto my screen.
It's basically instant. I also thought about what you could do with your meetings here. You could analyze meetings as they get transcribed in Fireflies or Granola or whatever you use.
And as soon as they come in, you can categorize them by what type of call it was, if you had decisions made, if you had like action steps. I thought this one was an interesting one because let's say you see that in a lot of your calls, you have no next steps discussed or defined clearly with ownership and timelines. Then you can use the data to change.
how you're conducting your calls. So what I think is interesting is, Jev on its own doesn't analyze things for you. But if you're strategic with the way that you set up, the questions, you can get analysis from it.
You can have this data tell a story. You can't have Jev look at thousands of transcripts and say, hey, tell me what I need to do better about these meetings or tell me common themes. But what you can do is you can give it categories and you can give it scores.
And then from all of these different types of questions that you set up, you tell your own story with that data. You can see that there's not much tension in some of our calls. I mean, this one has, someone says they're frustrated or overloaded, but all of these questions that I created for Jev here.
there's some sort of takeaway from each of these. Are things waiting on Nate? Is there revenue relevance?
Things like that. And I also tried this use case with video clips where I basically had Jev or I had, you know, Astra break up a bunch of my YouTube videos into clips. And then I had Jev look at those clips and tell me, you know, is this possible to be posted on its own as a clip?
A lot of them know. What is the hook strength of these clips? What type of clips are these?
Do I need the screen on them? Is there a quotable line inside of this clip? And then I could start to have it pull out things that might be...
worth reposting somewhere else, or might be worth me thinking about the way that I actually speak in these videos and things like that. And so these were a lot of ways that I would think about, how do I take a corpus of information, a ton and ton of data that I want to have AI analyze, but instead of paying more for it and waiting longer, let's figure out how we can.
use the right questions to have Jev do it for us. And then not only can we maybe have some sort of dashboard view, but how do we build Jev into our actual backend automations where it's really gonna benefit us to having a really cheap and fast model as we increase the throughput. Now I will say.
Don't just plug in Jev and trust what it says automatically. What you're really going to want to do is run evals, meaning you're going to have a golden data set of 100 use cases and 100 correct answers. And then you're going to run Jev through those.
And you're going to run Opus through those. And you're going to run Sol through those. And you're going to see which model gives you the best balance of accuracy and cost.
And if you care about speed in that use case, then also speed as well. But here's some other things you could do. You could have it vet contracts for you as they come in.
You could see the type of risk. You could see the type of clause. You could...
create any sort of questions that actually matter to you when you're vetting contracts. Same thing with jobs and leads. You can get red flags, you can get lead quality, you can get next steps.
You can also do something like a brain dump router where you're constantly just talking into your phone or you're talking into something and then you're feeding that into Jev and it can tell you what type of things you're talking about. If they're ideas or tasks or journals, if you have things that have deadlines, if you have things that are high priority, what area of your life they're in.
There's so many ways to use this because a big part of what we do with AI, like I said, is just figuring out what to do with all of our data. And Jev can do that really well.
And then I think one of the best examples here is customer support, just routing emails around, figuring out sentiment, urgency, what we need to do, how we categorize these sorts of things. I think that this is going to be a huge game changer for customer support because there's so many different decisions that have to be made.
And Jev is really good and really fast and really cheap at making decisions. So here's another use case that I thought would be cool to just sort of like... poc so this is paper trading this isn't very vetted there's a lot that's like wrong with this but i think that jeff being so real time and making decisions so fast it's going to be really interesting to see how it affects things like day trading or trading crypto in real time So you can see every single second, Jev is basically predicting, is this going to go up?
Am I unclear? Is it going to go down? You can see these confidence scores jumping around every single second.
And that's how it decides what to do. That's how it decides down here to place trades, to buy things or to sell things. Now, unfortunately, there's a lot of these fees here.
So the fees are way more expensive than Jev actually making decisions for us. So that's one issue where it's like, okay, well, how much would we actually have to be able? to profit, to make this worth it.
But right here, you can see just the cost of running these decisions. Look how much more this would have cost us per day with other models. Whereas Jeff would just be costing us about two bucks a day to run this 24 seven and Sol and Opus and Fable would be significantly more.
than jev now i've also seen people on x doing things like having jev play video games and having jev like do different creative fun things and i think it's really cool like the browser use and all that it's cool to see what's possible but i think you have to think about where's the handoff because with browser use it was unable to like actually type things in it would basically make decisions then it would have to route to a different model that's better with actually controlling the browser to do things and that's why i wanted to show what this looks like for these examples because i think building dashboards or automations where you have jev powering it on the back end for things that you actually care about in your life like these sorts of things, is where you'll start to play with Jev and actually get some return and then later figure out how you can expand or extend your workflows with other models on the back.
But anyways, I hope seeing these examples, even though all of these were very similar in the realm of classification, I hope that it helps you understand how you can start to ask the right questions in here and how you can start to work it into things that you're doing to actually make sense out of it. But that is gonna do it for this one.
So if you guys enjoyed or you learned something new, please give it a like, it helps me out a ton. And as always, I appreciate you guys made it to end of the video and I'll see you on the next one. Thanks everyone.
The Hook
The bait, then the rug-pull.
Nate Herk opens with the claim that a new decision-only model called Jev is about to change how AI automations get built, then spends 16 minutes finding out where that claim holds up and where it does not.
Frameworks
Named ideas worth stealing.
02:19list
Three kinds of decisions
Null - a yes/no answer with a confidence score
Choice - pick one category from a defined set
Score - rate on a numeric scale, e.g. 0-10
Jev's entire output space is limited to these three decision shapes, which is what lets it skip writing tokens entirely.
Steal forstructuring any classification or triage automation's output schema
04:32list
When to use Jev vs. stay with a chat model
Use Jev when you have a large corpus to classify, need real-time decisions at scale, or are running a production classification workflow
Stay with a chat model like ChatGPT when you need a handful of items handled, need to understand why, need to brainstorm, or need to chat
Nate Herk's own decision rule for routing a task to Jev versus a general chat model.
Steal fordeciding which parts of a pipeline get the cheap decision model versus the expensive reasoning model
CTA Breakdown
How they asked for the click.
VERBAL ASK
04:56link
“I've got this completely free SOP for you about getting your first AI automation client... there's a link for it down in the description.”
Soft mid-roll pitch for his own free lead magnet, framed as a bonus rather than a hard sell, delivered as a break from the Jev demo before returning to it.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A screen-share walkthrough of using Codex to plan and build automations, then hosting the generated code on Trigger.dev instead of burning your weekly usage limit.
Nate Herk builds ClientPack, an AI tool that turns discovery-call transcripts into branded client proposal decks, from a blank folder to a live paid subscription in about eight hours of prompting three different AI agents.
A YouTube creator argues the real AI job threat isn't robots — it's coworkers who learned to direct agentic AI — then live-demos three tasks it can already do and a three-step plan for learning to manage it yourself.
00:22
00:25
00:58
01:08
01:13
01:31
01:42
01:54
02:07
02:19
02:31
02:50
03:07
03:19
03:31
03:43
03:55
04:08
04:20
04:32
04:44
04:56
05:08
05:32
05:44
05:56
06:09
06:21
06:33
06:45
06:57
07:09
07:21
07:33
07:45
07:57
08:10
08:22
08:46
08:58
09:10
09:22
09:34
09:46
10:16
10:18
10:35
10:47
11:11
11:23
11:35
11:47
11:59
12:12
12:25
12:36
13:00
13:13
13:24
13:36
13:48
14:00
14:25
14:37
14:49
15:01
15:13
15:25
15:37
15:58
35:25
19:49
16:13
2:22:51
14:03
Video of the Day30:53