Gemini Decision 1 vs Jev: Google Wins? 🤯

Julian Goldie (0:00)

Google just launched Gemini Decision One, a free AI model that makes decisions for your business faster than you can blink. You give it an email, a photo, a sales call, or a PDF. You give it your questions, and it answers up to a thousand of them in one go.

Is this customer angry? Is this lead worth a call? Is this product photo good enough for the store? Which AI should handle this job?

Every answer comes back with a confidence score, so you know exactly how sure it is. That means your inbox sorts itself, your best leads jump to the top, and nothing off-brand ever reaches a client. Today, I'll show you six real systems I built with it, for online stores and for agencies running on real examples. One of them picked the best thumbnail out of 30 in a few seconds, and the winner matched the style that actually wins on my channel. Later in the video, I'll also show you the one number you have to set before you let it run on its own, because without it, it will make a bad call on exactly the emails that matter most. By the end of this video, you'll know what Gemini Decision One is, how to try it for free today, and how to plug it into the automations you already run. Let's get into it.

Here's the news, plain and simple. Google released a brand new model called Gemini Decision One. It comes with a new tool called the Gemini Decisions API.

An API is just a doorway that lets your other software talk to Google's model. You can try it right now inside Google AI Studio, which is Google's free website for testing their models. And there's a free tier, so you can build and test all of this without signing up for anything paid.

Now, here's what makes this model different from every other Gemini model you've used. Normal AI models write. You ask a question and they type out an answer, one word at a time. That's great for writing an e-mail or a blog post. Gemini Decision 1 skips the writing completely. It reads what you give it, looks at the answers you allowed, and scores every one of them in a single pass. Google says it does that in about a fifth of a second. On my own machine, most of my tests came back in around half a second, and that includes the trip over the internet. It can answer three kinds of questions. The first kind is yes or no.

Is this email a complaint? Does this post break a brand rule? The second kind is pick one from a list. Is this email a refund, a where's my order, a product question, or a wholesale inquiry? You can give it anywhere from two to 255 options. The third kind is a score on a scale you write yourself.

Score this lead from cold to book a call today. And it reads almost anything. Text, images, audio, video, and PDFs. Even a mix, like a recording of a sales call plus the notes from your form in the same request. Then it gives you every answer back with a confidence number between and 1 So you don't just get a yes, you get a yes 97% sure. That one detail is what makes it safe to build real automations on.

If this sounds familiar, you might be thinking of Jev.

Jev is a decision model from a company called TypeSafe, and it does the same kind of job. It answers yes or no, pick one and score questions with a confidence number on every answer.

The yes or no question type even has the same funny name in both tools, Newell.

So the easy way to think about it is this. Gemini decision one is Google's version of Jev, and Google clearly sees it that way too, because in its own launch post, Jev is the main model it compares against. On Google's own charts, decision one comes out slightly ahead of Jev on most of the tests, and Jev still wins a couple. Those are Google's numbers, so treat them as Google's numbers.

For a business owner, the big news is simple. Most of the jobs you want to automate are decisions. Which email first? Which lead first? Which photo goes live? Which AI gets which job? And now Google has a fast model you can try for free, built just for those jobs.

Let me show you what that looks like in Google's own playground first. This is the Gemini Decisions Playground inside Google AI Studio. On one side, you drop in your input. On the other side, you write your questions. You hit run, and the answers appear with a bar showing how confident it is for each one. That's the whole tool. And the reason it matters is what happens after the answer. Because once a computer can answer, is this urgent, in half a second, you can build a whole system around that answer.