Gemini CLI 3.0: NEW GenKit Extension is INSANE! (Free Update 🔥)

Today I'm going to show you something that just dropped and it's absolutely crazy. Google just released the Genkit extension for Gemini CLI and it's a complete gamecher. I'm talking about building AI apps in minutes instead of hours. This thing writes entire AI workflows for you. It debugs your code automatically. It understands Genkit patterns better than most developers. And the best part is completely free. I'm going to install it right in front of you and build a working AI app in under 5 minutes. No fluff, no theory, just pure hands-on demo. And Julian Goldie reads every comment, so make sure you comment below what AI tool you want me to cover next. Hey, if we haven't met already, I'm the digital avatar of Julian Goldie, CEO of SEO agency, Goldie Agency. Whilst he's helping clients get more leads and customers, I'm here to help you get the latest AI updates. Let me tell you why this matters. If you've been building AI apps with Genkit, you know it can be a pain. You're writing flows. You're setting up evaluators. You're debugging traces. It takes forever. But now, Gemini CLI can do all of that for you. It understands Genkit inside and out. It scaffolds code. It generates tests. It fixes bugs by reading your traces. And here's the thing, most people don't understand. The companies making real money with AI right now aren't the ones with the best ideas. They're the ones who can ship fast. They prototype in hours instead of weeks. This extension gives you that speed and speed is the only competitive advantage that matters in 2025. So what exactly is this Genkit extension? Let me break it down simple. Jenkit is Google's framework for building AI apps. It's basically Firebase for AI. You write flows which are like AI workflows. You set up evaluators to test if your AI is working right. It's powerful but it's complex. The Jenkit extension turns Gemini CLI into a Jenkit expert. You can ask it to write flows and it knows the exact patterns to use. You can show it a broken trace and it tells you exactly what's wrong. It's context aware. It knows your project structure. It reads your code. Now, before I show you the install and demo, let me tell you what you need. You need Node and PX installed. That's it. You need Gemini CLI installed and authenticated. And that takes like 2 minutes. There's no complex setup. No dependencies from hell. Just install and go. And real quick, if you want to scale your business and save hundreds of hours with AI automation, you need to check out my AI profit boardroom. This is where the real AI builders hang out, you get access to AI money-making strategies. You get 1,000 plus free workflows. You get direct access to me and my team. Link is in the description. All right, let's install this thing. Open your terminal first. Make sure you have Gemini CLI. If you don't, run this command. npm install-g Google/Gemini- CLI at latest. Hit enter. Wait for it to install. Takes like 30 seconds. Now, here's the magic command. Gemini extensions install https colon/github. com/gemini-cli-extensions/jenkit. That's it. One command. The extension downloads and installs automatically. You'll see a success message. It takes maybe 10 seconds. Want to confirm it worked? Run Gemini extensions list. You'll see Genkit in the list. That means it's active and ready. Now, your Gemini CLI understands Jenkit. Here's where it gets insane. Let me show you what this thing can actually do. I'm going to give it a prompt and watch it build a working Jenkit flow from scratch. Ready? Here's the prompt. Write a flow that tests an input string for profanity. Watch what happens. The CLI thinks for a second. Then it scaffolds the entire flow. It writes the function. It sets up the input schema. It adds the logic to check for profanity. It includes proper error handling. This isn't just copypaste code. This is production ready. But here's what blows my mind. Look at what else it added. It generated a sample evaluator. It created a test data set. It even added comments explaining how to run it. This is the kind of code a senior developer would write. And it took 10 seconds. Let me show you another example. Let's say I want an evaluator with a sample data set for this flow. I just ask write an evaluator with a sample data set for my profanity checker flow. The CLI looks at my existing code. It understands the flow structure. It generates test cases. It creates the evaluator function. This is contextaware code generation at its finest. Now, here's where it gets really powerful. Debugging. Let's say I ran this flow and got a weird result. I don't know what's wrong. I just tell the CLI. The last invocation of profanity checker flow produced a weird result. Can you fix it? The CLI reads my trace data. It analyzes the flow execution. It spots the problem. then it suggests the exact fix. It might show me a code difference. It might rewrite the function. This is like having a debugging expert on call 247. And this works because of how Jenkit MCP tools integrate with the CLI. The extension can read your traces. It can analyze your flow data. It understands the

execution context. So when something breaks, it doesn't just guess. It knows exactly what went wrong. Let me give you some real world use cases. Say you're building a content moderation system. Normally this takes days. With this extension, you scaffold everything in an hour. You ask for flows. You ask for tests. The CLI does the heavy lifting. Now, let me give you some tips because there are a few things you need to know. First, always run your Genkit MCP server locally for full functionality. The extension works best when it can read your traces and context. Second, keep your API keys out of your repo. Use environment variables. Use a git in your file. The extension generates secure code, but you still need to handle secrets properly. Third, remember this extension is open source, you can inspect the code on GitHub. If you find a bug or want a feature, submit an issue. Fourth, if you're using the hosted Gemini code assist with the free license, be aware of rate limits. If you're building production apps, you might want to use a Vertex AI key for higher usage. Here's something most people miss. You can use this extension to generate tests and then run them automatically in CI. You ask the CLI to write evaluators. It generates the test code. You add it to your test suite. Now, every deploy runs those tests. Let me tell you why this matters for making money. The businesses winning with AI right now are the ones who can test ideas fast. They build a prototype in a day. They test it with real users. If it works, they scale. If it doesn't, they pivot. This extension gives you that speed. Say you have an idea for an AI service. Without this tool, you spend a week building in the first version. With this tool, you build it in an afternoon, you test it the next day, you're in market while your competitors are still writing code. And if you're an agency owner or freelancer, this tool multiplies your output. You can take on more clients because you deliver faster. You can charge more because your quality is higher. This is leverage. Now, let me show you how to think about your next steps. First, install the extension right now. Don't wait. Takes 30 seconds. Second, pick one genkit flow you need to build. Ask the CLI to generate it. See what happens. Third, experiment. Ask it to generate complex flows. Ask it to debug messy traces. Push it. The more you use it, the more you'll find creative applications. Fourth, integrate this into your workflow. Make it part of how you build. Every time you need a flow, start with the CLI. Every time you hit a bug, ask the CLI. Make it automatic. And fifth, share what you learn. Comment below with the craziest flow you want me to build and test. I'll make a follow-up video showing it in production. Let's build together. Here's the bottom line. AI development is getting faster. And this tool is proof. What used to take days now takes hours. hours now takes minutes. The people who win are the ones who adopt tools like this first. So, here's what you do next. Number one, go install the extension. Link is in the description. Number two, join my AI profit boardroom where we talk about tools like this every day. You get access to over 1,000 workflows. You get AI money-making strategies. And number three, join the free AI money lab with Julian Goldie. Inside, you'll get 50 plus free AI tools and 200 plus chat GPT SEO prompts. You'll learn how to make money with AI agents. You'll get 1,000 plus free workflows. You'll get a full blueprint to generate thousands of leads free with AI. You also get a free AI community, free AI course, and proven AI case studies. This is the kind of content we're bringing you every single day. Real tools, real demos, real results. If you got value from this, smash that like button. Subscribe if you haven't already, and comment below what AI tool you want me to cover next. Remember, the people making money with AI aren't the ones with the best ideas. They're tools and the fastest execution. This extension gives you both. So, go install it, build something, ship it, and I'll see you in the next