NVIDIA's AI Agents Just Replaced Your Entire Team

Hello, I'm Mike with this week's new and trending AI tools. You can't afford to miss. This week's been huge because CES, the Consumer Electronics Show, has taken place in Las Vegas for 2025.

And I think the company that blew everyone away was NVIDIA with their talk of AI agents. Jensen Huang gave an amazing keynote. one of the most important things that's happening in the world of enterprise is agenetic AI.

So not only did we learn about agenetic AI, but we also saw a preview of those tasty GTX 50 series GPUs. this is a good time to run local AI. So a quick look at agentic AI.

It's like a team of AI models all working together, getting info and using tools to do things. Now NVIDIA is making tools to build these AI agents even easier. So AI agents essentially are going to become part of the digital workforce.

Or as Sam Altman would say, they'll enter the workforce in 2025. Let's take a look at what NVIDIA have been building. I'm pretty impressed with it.

If we go to try now on their AI website, which of course I'll link down below, you can create AI agents and something really cool my AI, in fact it's top at the moment as I click in is the PDF to podcast agent. So let's go in there we get a broad overview. We get the architecture diagram here on what it's going to do.

You can see it does multiple things to make this podcast. It uses Llama LangChain and a bunch of other cool stuff. And it's kind of ready to go.

So let's deploy and see if we can get it working. Now I need to use an NVIDIA account. Agree to the Terms of Service here.

As you can see right now, it's deploying my GPU. It's going to install the software and give me access to my notebook to run this agent. This really is crazy how easy it is to make things happen.

Okay. Now, this is up and running, and charging is $0. 77 an hour.

We're going to go to the notebook and follow the instructions, which I'll fast forward through so you can see how this works. We'll start by cloning the repository. Then we'll click here to get our NVIDIA API key, which actually gives us free credits to get started with.

Once we've got our NVIDIA API key, and also one from ElevenLabs, we'll go ahead and run the bash script to configure it. Then we'll install dependencies. Next I'll make sure I've got Docker up and running here on my desktop.

And I'll spin up the blueprint. And there you go. That took a few minutes to get up and running.

But my AI agent is now active using NVIDIA and ElevenLabs APIs. Let's use another terminal window to test it. And yes, it's testing and we can see things are up.

The agent is up. It's ready to create a podcast. Now we get on to the exciting stuff.

We can create a podcast using this Python file they give and it will just run this. I'm going to create a virtual Python environment inside Cursor. Now we can create that Python file.

Now I've edited the instructions here to look for the create a magic PDF to create a podcast all about this YouTube channel. Let's click play and you can see it's submitted a job and it's waiting to initialize. And boom, all PDFs processed successfully.

It's summarizing again using NVIDIA agents to do so. Next agent picked up the job and is generating the initial outline of the show. Creating the monologue.

Transcript. This is really cool stuff. Formatting the final conversation a bunch of agents all working together, to make something amazing.

Now, the text to speech processing. And the podcast generation is completed. Let's have a listen.

Welcome to our analysis of Creator Magic, a leading YouTube channel on AI powered content creation with a consistent stream of weekly updates. Mike Russell shares his hands on experience with the latest AI tools. From video editing to content summarization, this broad scope and emphasis on practical applications make the channel a valuable resource for content creators.

As the field of AI powered tools rapidly grows, Creator Magic is well positioned to adapt and cover new developments. and there you go. Using NVIDIA's AI agent tools, I've created my own set of agents that find out information, scripts, produce, and finally voice a podcast.

For me, this is the future. I've basically built a Notebook LM podcast creation clone using NVIDIA agents, and I can't wait to see what you're going to do with this. Do let me know in the comments down below because I'm there helping and join my community as well.

If you want to get involved because we're creating from the ground level in the Creator Magic community, and that link is also down below. If you like what you see right now, throw like and subscribe to my channel for more stuff just like this in the future. Okay.

Next up. This is insane. Somebody built an open source clone of Perplexity, and it's actually available on GitHub.

So you can clone this and you can run this yourself locally, but they're actually hosting it here at this web address. Then of course I'll post down below and you can ask questions just like you can Perplexity. Not only can it search across the web, but it can also look at X and YouTube as well.

So if we go in search X and we type in, what did Jensen Huang say about AI agents during his keynote at CES 2025? straight away. And it's searching for the latest news as well.

So it popped up quickly, gave me an answer. Then it's pulling in latest from X and it's saying that he shared his vision for the future of AI agents. It goes on it references Let's do a new search and look for YouTube.

And again, we'll ask the same question and see if it'll search YouTube videos to find out. And again, yeah, here we go. It's searching through YouTube to find the answer.

And there we go. It's directly referencing transcripts from YouTube videos to give me a comprehensive breakdown on everything that Jensen said about AI agents at CES 2025. That is incredible.

So you can test this really cool tool out at mplx. run, or you can go to GitHub again. I'll post that link down below so you can clone this repo and maybe try it out and maybe even alter it for yourself.

But it can do so much like web search. You can do weather search, it can look for maps, YouTube search. I don't know how this developer has managed to create a Perplexity clone, but the future is really exciting because if Perplexity can be cloned, well, so can every single tool out there.

Also worth to mention, it's not the only game in town. Perplexica is also a very busy GitHub repo, which is an AI powered search engine, again, very much based on Perplexity, and you can clone it. It's got 18,000 stars at the moment.

At the time of making this, I round up so pretty cool. And again, another alternative to look into if you're interested in running your own Perplexity clone. So seeing as this video is all about AI agents.

Yes, AI agents that use NVIDIA GPUs to create podcasts from your contents to AI agents that go across the web and crawl it for answers. In the style of Perplexity, I signed up again. Yes, for Google Gemini.

The Google Gemini Advanced is pretty incredible, and they added a tool actually at the end of last year, which is Google 1. 5 Pro with deep research. Again, you can get in-depth answers on anything.

And Google is using its own special mix of AI agents. I want to show you how cool this tool is. So I can ask Gemini when I'm in deep research mode.

Find out everything you can about MiniPerplx, who's behind it, what it does, and anything else. That's relevant. And rather than give me an answer straight away like most AI models will, this will go across the web and use agents to find out everything it can.

And in fact, right now it's creating me a little plan of what it's going to do. And it's told me it's going to find the website, it's going to find news articles, it's going to find the history, find the founders, and a lot more. So a bunch of AI agents are going to go out, crawl the web and give me the answers I need.

I'm loving deep research right now. Let's start the research. Now.

As you'll see, this is not instant. It actually goes out and a genetically crawls the web and does basically what I might spend all morning doing in just a couple of minutes. You'll see straight away it's pulled up the site, the GitHub repo of MiniPerplx, and a bunch of other articles all about this and related to MiniPerplx, even YouTube videos.

So far it's looked at 23 websites that would have taken me at least 10 or 15 minutes, and very shortly will get the answers back. Now, while it's doing that research, I think it's really important to do this. Let's look at Notebook LM.

I love Notebook LM, and you've seen other videos where I spoken about it in depth. Recording your thoughts, adding sources, and creating AI generated podcasts. Well, I realized when I signed up to my Google One AI plan to get Gemini Advanced.

It also gave me better limits for my notebooks. So you'll see here. I've been jamming about the Creator Magic channel, where I've essentially added all of my videos to a notebook now.

Previously on the free plan from Google 50 sources was the maximum. When I paid for an account with Google, my source limit is 300, so I can add a maximum of 300 YouTube videos to one notebook in Notebook Elm and ask a bunch of questions and get answers based on all of the content on my channel. Okay, with that said, it seems to have researched 42 websites.

It's now analyzing the results, and very soon it's going to build me a report. And now you can see. The ring is nearly closed here.

And it's creating my report. Very soon I'll have something to look at. And here it is, a deep dive into the minimalist AI search engine.

It says that it's getting a significant buzz right now in the tech community. As an open source AI search engine. As I scroll down, it'll show you all of the features and functionality, including that YouTube search, academic search that I've mentioned and X search as well.

It's all here in the summary. now? Who's behind MiniPerplx?

Well, again Google the research has found out. It's the brainchild of Zaid Mukaddam, an indie developer with a background in software engineering and cybersecurity. Pretty cool AI research there.

now scrolling along here. Media coverage. It said.

During our research, we explored various news sources, however, found limited news coverage suggests the project is still in its early stages, which indeed it is. So Google Gemini Deep Research has done an incredible job. It provides a conclusion here at the bottom, and it lists all of the sources it crawled and all of the websites to find the information.

And if I want to then save this for later reference, I can open it in docs. And boom! Now I have a full report from Google Gemini Deep Research that I can scour over however I wish or share with someone at the click of a button.

So there you go NVIDIA talking about the AI agent future that we're all heading towards. MiniPerplx for searching the web using free and open source tools to look at YouTube and other sources as well. And Google Gemini advanced with deep research to a genetically scour the web and build you complex reports on anything you can think of.

The world in 2025 is getting better and better by the day, and I'm here every week to bring you all of the AI tools and ideas that you can use yourself to make life incredible. I hope this has helped you. And by the way, if you enjoyed this video, throw a like subscribe and there's a video showing on your screen now that you should probably watch next.