Eric Siu presents Jev, a middle layer for LLM workflows that generates dozens of ideas, filters them automatically, and classifies data. It charges only for input tokens, cutting costs 34.5 times compared to Claude Sonnet 5 while running faster.
Jev is an absolute game changer for marketing. Everybody's talking about it. And when you have a Jev that can help you make decisions, it makes it better, right? It gave 40 ideas here and what Jev did was it evaluated, do we already have similar content? So here's 40 ideas, it shortlisted 10, eliminated 30, and it said, hey, you know, is this type of content already live on your website already? Okay, because all the knowledge work that we do, there's a lot of time that we spend classifying things, right? Look at it as a classifier. It can intake the data that you have that's coming in and it can classify it very quickly. And you can see not only can it evaluate very quickly, but it's also very cheap as well. And they're not going to charge you on output tokens. It's really the input tokens that are coming inside. And so the way you want to think about Jev, it's a middle layer that you add into the work that you're doing. There's also examples where it's classifying what's happening on Wikipedia. And so you can see there's a little WikiRace tool that was run over here and you can see how quickly It's able to Jev up here, boom, done. When you compare it to Claude Sonnet 5, it is 34.5x less and you can get the work done a lot faster. These are the absolute best marketing use cases that you need to start with, with Jev. And hopefully this is going to give you some ideas to get going.
