Resources:
Join the discussion: Ask Jordan questions on OpenAI
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Try Our Free AI Prompting Course: Register for our free Prime, Prompt, and Polish AI Course!
Revolutionizing Work with OpenAI's Operator: A New Era of Efficiency
As business leaders, the quest for efficiency and growth never ends. In the ever-evolving landscape of technology, Artificial Intelligence (AI) has carved a niche as a powerful ally. Among its arsenal, generative AI and large language models have proven their mettle, especially with OpenAI's latest innovation, Operator. This tool is not just about automating tasks, but about elevating your business strategy to new heights.
Understanding OpenAI's Operator: Beyond Simple Automation
Operator represents a significant leap forward in AI capability. Unlike its predecessors focused on singular tasks, Operator offers a multi-agent environment that demonstrates true agency. It can navigate multiple websites, handle credentials, and execute complex tasks autonomously. The true essence of Operator lies in its ability to not just perform tasks but to execute them with the intelligence of a reasoning model, GPT-4o.
Operator's True Potential: Knowledge Work and Strategic Tasks
For decision-makers, the question isn't just about what AI can do but how it can transform how businesses operate. Operator excels in managing knowledge work that traditionally required manual intervention. Think beyond basic automation. Operator thrives on tasks involving research, data analysis, and synthesizing information across different platforms, be it pulling data from Google Gemini, creating presentations, or compiling reports autonomously.
Missteps to Avoid: Learning from Common Mistakes
It's essential to understand how not to use Operator. Many demoed use cases focus on banal tasks like ordering food or booking reservations. While these are interesting showcases, they underutilize the technology. For businesses looking to truly optimize their operations, using Operator for intricate, repetitive tasks that span multiple digital touchpoints will provide exponential benefits.
OpenAI Operator in Action: A Practical Demonstration
Imagine planning a week’s content strategy. Operator can navigate your website, learn past trends, conduct research on emerging industry topics, and even draft comprehensive reports—with virtually no human intervention. This capability doesn't just save time; it liberates team members to focus on higher-order strategic initiatives, enhancing productivity and creativity.
Preparing for AI Integration: What Businesses Need to Know
Though Operator's full potential is currently exclusive to the $200-a-month pro plan, businesses should anticipate its rollout to broader user bases. The preparation starts with understanding and incorporating Operator into your strategy. There might be some initial setup with credentials and fine-tuning of tasks to fit your specific needs, but the long-term gains are invaluable.
The Path Forward: Embracing Agentic Systems
Operator is not just a tool but a harbinger of the next phase in AI development—agentic systems. These systems promise to transition businesses from fragmented task automation to comprehensive problem-solving capabilities. The future is about harnessing AI to not just save time but to dynamically solve complex challenges, redefining what it means to work efficiently.
By embracing these systems, businesses can look forward to a future where AI doesn't just support work efforts but becomes an integral part of crafting strategic visions. OpenAI's Operator offers a glimpse into this future— a future where AI is more than a tool, it's a transformative partner in business growth.
Topics Covered in This Episode
1. OpenAI Operator explained
2. Operator vs. Competition
3. Use Cases for Operator
4. Managing Tasks in Operator
Podcast Transcript
Jordan Wilson [00:00:22]:
There's always been this enormous upside of generative AI and large language models. Right? From the early times of the ChatGPT moment of generative AI to, all these new updates in between. But I think many of us have realized that potential. Right? Especially if you're a daily listener of the show, but I think a lot of the rest of the business world hasn't. There's always those doubters out there that are like, okay. Cool. This AI can go do this, but when will it just go and do my work for me? Well, with OpenAI's operator, that's exactly what can happen, and that's exactly what we're going to be showing you today. Alright.
Jordan Wilson [00:01:08]:
What's going on y'all? My name is Jordan Wilson, and welcome to Everyday AI. This is your daily livestream podcast and free daily newsletter, helping us all not just keep up with AI, but how we can use it to get ahead to grow our companies and our careers. Because, you you know, efficiencies and optimizations are one thing, but when we can actually use them to grow, that's the whole next step that we all need to take. And you can take that next step if you haven't already on our website. So, if you're new here, please go to your everyday a I Com. Sign up for the free daily newsletter. So we recap we're gonna be recapping this very show. Have a nice write up with some additional resources, but we're also gonna keep you in the loop with everything else going on in the world of AI so you can be the smartest person in your company when it comes to generative AI and large language models.
Jordan Wilson [00:02:03]:
Also on our site, you have to go check out the twenty twenty five AI predictions and road map series. It's actually been so helpful to so many people, even though it's from a couple of weeks ago. I think we're gonna do some slight updates and run it again, because I think it is that important that you all, listen to this. So it was five very short episodes on our website at youreverydayai.com. Look for that twenty twenty five AI predictions and road map series. Alright. Normally, we start off each and every day by going over what's new and noteworthy in the AI news. Today's show is going to be a very detailed one with a lot of screen sharing.
Jordan Wilson [00:02:42]:
We're doing live demos. I'm gonna literally show you on today's show how operator is doing my work. Alright? So, if you want the AI news, make sure to go check that out in the newsletter. Also, if this show is helpful, I'm gonna remind you of this again at the end. Make sure to repost this on LinkedIn or Twitter. I'm going to give you all, whoever repost this, the complete instruction set that I use inside of operator, which takes a long time to configure and get right. As well as for anyone that does repost this on LinkedIn, I'm going to be entering y'all into a drawing for a free ninety minute consult so I can help you set up operator, for your team, answer your generative AI questions, teach you a chat, GPT, whatever it is, and we're gonna be giving that away in our newsletter. Alright.
Jordan Wilson [00:03:29]:
That's enough chitchat. Let's get straight into it. Is this OpenAI's best AI agents? And a lot of people are using operator for the exact wrong use cases. Alright. So, let me just answer this. Yes. I think this is OpenAI's best AI agent, and people are using it for the exact wrong reasons. Right? So, operator actually came out before deep research.
Jordan Wilson [00:03:56]:
So, you know, a lot of people just flooded, you know, all the all the thread boys, I think it's what they're called on on Twitter and and LinkedIn. Right? They they go gather all these use cases and they're like, oh, you know, operator's amazing. It's gonna, you know, change the game and blah blah blah. Right? But be because this was before OpenAI's deep research, a lot of these use cases were two things. One, it was very much what OpenAI demoed, which I think was wrong. So I'll get to that in a couple of minutes. And then it was just doing a lot of research. But OpenAI's deep research came out shortly thereafter.
Jordan Wilson [00:04:30]:
I believe deep research came out on January 31, so you shouldn't be using operator to just go research. This is an agent, a very smart agent that can work across multiple websites, copy and paste things, you you know, across different products. You can give it credentials to log in, to whatever you're using. So I think people are using this in probably, like, the worst way possible. Right? So you have to keep in mind OpenAI's other tools, but I do think, you know, OpenAI has officially said they've released two agents. So one in operator, one in deep research, but I'm all I'm almost gonna call it, like, two and a half because I think tasks, ChatGPT tasks where you can essentially schedule anything in ChatGPT, I think that actually has some agentic capability because when you work with it the correct way, right, and when you use your brain, we taught you all how to do that. We did a great show. I thought it was a great show on, ChatGPT task.
Jordan Wilson [00:05:25]:
So when you do something called task stacking and use the context of, the chat, it is it does have agentic capabilities. It can have agency. It can make decisions. It can, create new things for you autonomously. So, you know, OpenAI will say they've released two agents, one in operator, one in deep research. I'll say it's 2.5 because like I said, I think ChatchBT task is pretty much there as well. Alright. So let's get into the, the definitions first y'all, and then we're gonna get to, doing this live.
Jordan Wilson [00:05:58]:
And hey. Good morning. Good morning to everyone joining us. So Pedro, joining the show from Madrid, Jason, from Florida, Douglas, Rolando, Atsham, Harvey, Castro, Christopher, everyone else, Michael, big bogey face. Thanks for thanks for tuning in. If you guys have questions about operator, get them in now. You you know what? And if we have time, I might be able to run an operator, question or two. Alright? We'll see.
Jordan Wilson [00:06:26]:
So what the heck is operator? Alright. So this is from OpenAI. So they said it this is a research preview. Keep that in mind. This is the worst it's ever gonna be. So this is a research preview of an agent that can use its own browser to perform tasks for you. Alright. So it is first there.
Jordan Wilson [00:06:43]:
This was their first official agent release. And if you keep hearing the word Kua, alright, that's what this is. This is a computer use agent or Kua. Alright. So it uses GPT four o to quote unquote see screenshots, and then it operates a virtual computer. So it it is in a slightly different, interface than the normal ChatGPT, although it is essentially the same thing. So it has its own dedicated, its own dedicated, interface. You talk to operator just like you would ChatGPT.
Jordan Wilson [00:07:17]:
It essentially takes a lot of screenshots. It uses computer vision, and then it essentially controls a mouse and a keyboard on a virtual machine, and you can take control at any time. Keep in mind, there's obviously some limits. Right? And I'm gonna walk you through some of those things. The virtual machine is not very powerful. Right? So if you want to go, you know, render, you know, a video editing program or something in the, on this virtual machine that would normally require local computer power, it's not going to work very well. Right? Also, in the same way that my computer will slow down if you have 30 tabs open, so too will, compute, this, operator, from open AI. So keep that in mind.
Jordan Wilson [00:08:03]:
There's there's some limitations. You are using a virtual machine. However, it may slow down if you're trying to do too many things, at the same time. Alright. Let's talk about access and availability. Well, right now, it's available to anyone with the $200 a month pro plan. So that is what I'm using. And, OpenAI CEO Sam Altman did say that this will be rolling out to plus users.
Jordan Wilson [00:08:28]:
So that is the $20 a month plan in the coming months. So there is no you know, if that means one, two months, three, four months, eight months, we don't know. Right? We could see a very long, like, Sora ask rollout where it was eight months, or we could see it drop in a couple of weeks. So right now, it is only available for those on the $200 a month pro plan, which is what I'm using. But like I said, it is going to be coming out at some point, in the, in the near future. So how the heck does this thing work? Right? Well, according to OpenAI, this is how it works. So it says operator uses a model called computer use using agent or CUA built on GPT four o to interpret screenshots and interact with sites using typical browser controls like a cursor and mouse. You describe the task example, book a flight, order groceries, and operator executes the necessary steps.
Jordan Wilson [00:09:26]:
If it encounters a challenge like a CAPTCHA or password field, it will pause and prompt you to take over ensuring you stay stay in control. Let me just call this out right now. These are the absolute worst things to do with operator. Right? And I'll tell you why here in a minute, but we're not gonna do any of these things that OpenAI suggests because it's a terrible use of your time. And I think it's a terrible use of their technology to use it how they've suggested both on their website and when they demoed it. Alright. Let's talk about limits because everyone always wants to know. Alright.
Jordan Wilson [00:10:00]:
Well, if I'm gonna pay $200 a month, can I just have, like, 80 instances of this thing going at once? Well, like I said, it will slow down. Right? Just like a, a normal computer would. Each time you start a new operator chat, think of it like this. Think that you're running an old computer from ten years ago. Right? You should probably only be doing a couple of things at once. You should probably have a couple tabs open at once. But each new operator chat that you start, it is essentially starting a new virtual machine. However, keep this in mind right now.
Jordan Wilson [00:10:36]:
You have to have the tab or the window active for it to keep going. So I've been trying some, like, workarounds. Right? So as an example, if I'm using Chrome or Edge, you know, launching a new profile and continuing to work. So hopefully, it'll actually work here, you know, because I'm in the same instance. I'm using Chrome right now. So, we might only be able to do one thing at a time for that very reason. However, you know, there are some nice workarounds, but you do have to have it active and open. Right? If you listened y'all to my 2025 AI road map series, I said virtual machines and second computers are going to be huge in 2025.
Jordan Wilson [00:11:14]:
And here we are a couple weeks after that show debuted and, yeah, now you see why. Right? Now I'm happy I have a stockpile of extra computers because I can just, you know, launch maybe two operators, give them extremely detailed multi step tasks, and have them literally do my work for me. Right? But I have to wait. So presumably, we'll see the same thing with Google's, Mariner, which is essentially their computer using agent that will be hopefully rolling out in the coming weeks and months. I did talk about that a little bit with, Google's Logan Kilpatrick on Friday if you wanna go back and listen to that conversation. But now's a great time if you have that extra machine, to go ahead and do this because like, operator with Google's Mariner, which will work as a Chrome extension, it needs an active window or an active tab because it's essentially using the instance of your browser to use a virtual machine. That's how operator works. Mariner works.
Jordan Wilson [00:12:11]:
It's literally using your browser, so you can't do anything else. Alright. So now if you're like me and you're slight computer quarter, this is where it pays off. Right? Because you can go, you know, set it up and, you know, essentially have one computer just always doing your work over there in the corner. But you gotta put the work into it, and you have to know how this works and how it doesn't. Alright? So can operator handle multiple tasks at once? So, yes, operator does allow you to run multiple tasks in parallel. However, for security reasons, operator places dynamic limits on the number of simultaneous tasks and open conversations you can have at any given time, and these limits may change. Yeah.
Jordan Wilson [00:12:49]:
So there's no, like, hard limit. It's not like, oh, you can run two things at once or three things at once. It's dynamic, which is gonna make a live demo kind of tricky because we might run into limits. You know, I I tested everything, last night. Everything was going well. But, I mean, we'll see how it actually, how it actually works. Right? Alright. So let's talk about how to actually use it.
Jordan Wilson [00:13:12]:
So you don't it's not in the same ChatGPT interface. So you can go to operator.chatGPT.com. Again, you have to be on that $200 pro plan. Otherwise, this isn't gonna work. Or you can log in to your normal ChatGPT account, and there will be an operator icon in the left hand corner where you would normally see your g p t's. And then like I said, it has to be an active window or tab. So what the heck should you use this for? Right. Here's here's where I'm gonna, enjoy.
Jordan Wilson [00:13:44]:
I'm gonna enjoy this slightly hot take Tuesday. Right? I actually might have a hot take Wednesday for y'all tomorrow, if if if you want it. So number one, on what types of tasks should you be, giving to operator? Probably not what you would think. Okay? Because first, you have to know and understand OpenAI's full tool set. So here's what I mean by that. You have to understand ChatGPT tasks. Alright? And please please, y'all, go listen to my ChatGPT tasks show. Alright? It's it's funny.
Jordan Wilson [00:14:20]:
I actually had someone from OpenAI reach out after that show, and they're like, you know, this was great. Like, I learned so much from this, listening to this, which I was I was, like, I was, like, kinda shocked on. Right? So you need to go listen to that task show because I don't think people understand how powerful ChatGPT tasks is. So that's episode four forty. Go listen to it. So, again, before using operator, you have to understand tasks, and you have to understand task stacking. Alright. So you can literally go back and reshare reshare that show, put together a huge guide on task stacking.
Jordan Wilson [00:14:54]:
Alright. Then you have to understand chat g b t, their new mode, o3 mini plus chat g b t search. Alright? So a reasoning model that has access to the Internet because that can also change what you think you might want to use operator for. Right? So a lot of the things that you're thinking, oh, I'll I'll use operator to do go do a, b, and c. It's probably already available and you just didn't know how to use it. So go listen to, our o3 mini show as well. Right? And I'm not just saying this, like, you know, I don't get paid $20 every time you go listen to a podcast. I get paid nothing.
Jordan Wilson [00:15:29]:
Alright. I'm doing this to save you time. Alright. And to, help you get the most, you and your company get the most out of, generative AI. So go listen to episode four fifty six on o3 Mini High, and then you have to understand deep research. Alright. We covered that in episode four fifty four. Alright.
Jordan Wilson [00:15:48]:
So OpenAI's deep research is outstanding. That is their other agent. They released it, I believe on the January. So just about less than two weeks ago. So you you have to understand those kind of three or four, kind of tools or modes within ChatGPT because a lot of the things that I see people right? I I I go out and I read people's reviews or watch people's videos, and I'm like, y'all are using this wrong. This is, like, the absolute worst thing to do because, operator is slow. Right? It is slow. In many instances, it is slower than a human.
Jordan Wilson [00:16:23]:
So you have to keep that in mind on the type of agency you are handing over to an agent. Don't hand it over something that is actually going to take the agent longer. Okay? So what type of task should you give them? So like I said, don't give them anything OpenAI use in their demo. In their demo, OpenAI and on their blog posts, they they they leaned very heavily, which I don't know why. Maybe because talking about these things, I don't know, helps you imagine a future where everyone has a Jarvis. Right? So they're, like, trying to order, you you know, like, tickets to an NBA game and trying to order groceries. Right? Don't do that. Don't do that.
Jordan Wilson [00:17:04]:
Just because you can. Right? I think they're trying to perform transactions, and they're trying to show everyone, oh, you can go buy things on the Internet. Right? And let operator do that. Number one, it's it's it's way too time intensive. You are not going to win back your time doing that because, unfortunately, even when you try to overprompt it, operator is still going to ask you a lot of questions. Alright? An agent is not an agent. If it has to ask you more questions, then and if it takes more time than it would take for you to do it on its own. So, yeah, in OpenAI's demos of, you know, reserving a table at a restaurant, ordering tickets, ordering groceries.
Jordan Wilson [00:17:45]:
Those, in my opinion, those are terrible use cases because those are things that the human can probably do two to3 times faster, and it's actually a quite frustrating experience. I think one of the reasons, right, about Megadeth, one of the reasons why they probably demoed that is OpenAI is using this as training data. Right? And I get it. We need all of that training data, in order to build the next version of operators in the next, agentic system. So I get it. I get why they're probably pushing those things and, sure, maybe someone might find, you know, it's a nice party trick, but I don't know. I don't wanna sit there and answer, you know, four to nine questions just to, reserve a table at a restaurant. Right? It doesn't make sense to me.
Jordan Wilson [00:18:29]:
I wanna hand off operator as much of my day to day work as possible. Sit back, go warm up my coffee, and go do something else. Right? That's the point of having an agent. So you should be use you should not be using the prepackaged prompt ideas. Do not use them. Alright. What you should be doing is any basic research, reading, writing, summarizing, data analysis task that cannot be done in ChatGPT's deep or ChatGPT or deep research. Right? So you should be doing these knowledge work tasks that involve you, going into multiple websites, multiple software services.
Jordan Wilson [00:19:10]:
That's what you should be focusing on. Alright. So like I said, reading and writing across different domains and services, that's number one. That's something a large language model is better at. It's faster at. Right? It can, you know, summarize and and synthesize much better, much faster than any human. Alright. So any knowledge work task, connecting multiple services or any manual repetitive tasks that are time consuming and happen across multiple domains.
Jordan Wilson [00:19:39]:
Alright. Let's look live. Are you guys ready? This could this could go horribly if I'm being honest. Let's see how this works. And one of the main reasons is because I have to always have this active, tab. So even when I'm, like, trying to copy and paste some stuff over, it might not work very well. Alright. So livestream audience, if you could, please let me know when you can see my screen.
Jordan Wilson [00:20:07]:
Alright. So right now, I have operator open. I'm gonna start on this right away. Alright. And then I'm going to walk you through what's happening. Podcast audience, I always put the link, to this show. So this is going to be a very visual process. I'm gonna try to do my best to describe you what's going on.
Jordan Wilson [00:20:25]:
But if you want to actually see it with your eyes, alright, we always leave the link to our website. On the website, we put the YouTube video or you can go watch it on LinkedIn. Alright. So I just pasted a prompt in. Alright. And I'm going to alright. Let me, thanks thanks, live stream audience that you can see. Alright.
Jordan Wilson [00:20:42]:
So what's happening? I'm gonna go ahead and click this button here that says expand. Well, actually, I'm not. So first, I'm gonna write down what, you know what? I I I have multiple screens here. Let's do this. Let's do this. Alright. Hopefully hopefully of course, it did this. I literally just signed in.
Jordan Wilson [00:21:04]:
I signed in to to my Gmail account before this started. Tested it. It worked fine. So sometimes you have to enter in your credentials multiple times. So I was hoping I wouldn't have to do this, and I was hoping that we could do this do this whole thing autonomously. Alright. So give me a second. I'm logging into my this is my personal, Gmail.
Jordan Wilson [00:21:31]:
So, please don't spam me. I guess you can if you want. Alright. Alright. So now I am super, super zoomed in here, and I can't zoom out. So give me a second. Alright. There we go.
Jordan Wilson [00:21:51]:
So now the screen sharing should be back. I told you all. I I I I'm not always a fan, of of doing this live, even though I know y'all love, doing these things live. So let's see if I can get this to work because, of course, it worked one shot when I demoed it last night. Alright. Here we go. So here's what I told operator to do. So I copy and pasted this in.
Jordan Wilson [00:22:23]:
Alright? And all I did so far is I had to log in to my Gmail. I'll tell you why. So I said, step one, go to gemini.google.com and ask it to complete a very basic SWAT report for the Everyday AI podcast by Jordan Wilson, then hit enter. And to our livestream audience, you see it's working on its own right now. My hands are right here. I'm not typing this in. Alright. I said step two, then go to Google Slides and copy and paste the input and outputs from that Google Gemini prompt in response.
Jordan Wilson [00:22:52]:
And then I'm explaining, this is after using it a little bit. I'm saying sometimes it may ask you to install an extension for copying and pasting. If so, allow it. If not, go about your copying and pasting. Use your best discretion on formatting. The Google Slides doc should only be five pages long. Number one, title page. Two, strength.
Jordan Wilson [00:23:11]:
So this is SWOT. Right? So, essentially a title page and then a page for SWOT, strength, weaknesses, opportunity, threats. Step three, export the Google Slides as a PDF doc. Step four, log in to my Gmail and then send that PDF reports to info@youreverydayai.com. Write a short subject line and a one sentence email summary. And then I'm saying, do not and this part is important y'all. I've been playing with operator, a lot over the past, like, two weeks. So, I'm saying do not ask me for permission for anything.
Jordan Wilson [00:23:49]:
Use your best judgment. Please complete this autonomously. If you run into any issues, try a second time. If your second attempt doesn't work, then try another route or get creative in accomplishing the goal. The only important thing for you to do is to finish all four steps without human input. Please complete this task autonomously. So, yeah, you'll you'll you'll notice that I, did multiple times remind operator, like, yo, don't talk to me. Right? I'm not here to be your friend.
Jordan Wilson [00:24:20]:
Right? You have a job to do. Go do this autonomously. I gave you detailed directions. Take your time. Make sure you get this done correctly. Alright? So, you'll see over here for my livestream audience, I'm kind of clicking through this and a couple of things to know. So you can see a kind of summarized chain of thought on what operator is doing. So remember, this is based off of GPT four, but we almost get these, this o level, right, of the o series, the reasoning models.
Jordan Wilson [00:24:53]:
We almost get that kind of under the hood look of what it's doing. Also, know at any time, you can go back and replay this if you want. Right? And I would highly encourage you to do this. Right? So even if you don't have the 200 a month pro plan right now, you need to access this. When this does come out to maybe the plus plan, I encourage you. You have to always look, at this kind of, summarized chain of thought. You have to see and understand what it's doing. So you get to that by clicking this expand button.
Jordan Wilson [00:25:29]:
Okay. So, otherwise, you can't really follow along. So I click this expand browser window button. Again, I'm in the operator interface and you'll see right here, it says one task in progress. I didn't wanna do two simultaneous tasks. Alright. So we can hopefully really walk and talk through. So you'll see also when I hover over, my this the my virtual screen here, it says take control.
Jordan Wilson [00:25:57]:
So at any point, if something is going wrong, I can click take control. Right now, I don't need to. I I I had to log in even though literally right before I hit record, this was working fine. But, you know, there's always human in the loop. Right? But in my prompting, I really pushed and requested operator to do this all on its own. Right? There's no point in, using an agent, you know, to do a task that would take a you know, take you five minutes that, oh, working with, you know, operator takes me eight minutes. That makes no sense. Right? So you are gonna have to put a little bit of work into, you know, prompt engineering one zero one.
Jordan Wilson [00:26:40]:
Alright. You're gonna have to put in some work into learning. Alright. So now as an example, I'm looking down and I'm seeing what's happening here. Right? I can see the actual step by step how this is thinking. So right now, I can see it was struggling to scroll down on the page. So it's about, it's about halfway done with this task. So it was struggling to find the opportunity section of the SWAT report that I asked it to generate.
Jordan Wilson [00:27:09]:
So, again, let's even back up. So we started in operator, and then I had operator log in to Google Gemini. Right? So, unfortunately, operator right now can't use, operator. Right? But it can use a lot of other tools that you would log into, which is great. Some websites right now, and I would assume that as computer using agents become more and more prominent, that they're going to figure out how to block these virtual machines, how to block this virtual traffic. Right? At least for me, it was showing up as like a device in Iowa. I know I read back a couple of months ago that OpenAI and and Microsoft and others were looking at data centers, in Iowa. So I'm not sure if that's what it is or if it's always just going to dynamically show up in a new place.
Jordan Wilson [00:27:58]:
So you will probably have to do a lot of two factor authentication if you are logging into sites that require your credentials. But in my opinion, that's what you should be doing. So I wouldn't be again, I wouldn't be uploading, sensitive proprietary, documents, anything like that. You know, right now, this is just my personal Gmail account, but I'm having it go in, open Google Gemini. Alright? Run a a research task. Right? This is something that I would normally be doing, and you'll see it's already done. So right now, it it's it completed, the presentation. It looks like it's downloading it right now.
Jordan Wilson [00:28:37]:
And again, I'll walk everyone through this. I wanna get the second prompt started, But it's it's already downloaded the file. Alright. So I asked it. I said, hey, operator, go out, use Google Gemini, then, go create. So it's it's working between Google Gemini and Google Slides. It's copying and pasting all this information. It was even resizing text.
Jordan Wilson [00:29:02]:
Right? Because it would enter a text box, and it didn't fit. So it was resizing it all. And it's pretty impressive because it's doing this all with screenshots. Alright? Let's see. So it looks like it looks like it might have stopped there. So yeah. Unfortunately, it did not, complete the entire task because the rest of the task let's see Let's see if I can just reenter this and have it continue on. Again, y'all, like, maybe I'll share the video, but it literally did this entire thing, last night.
Jordan Wilson [00:29:43]:
But, you know, generative AI is generative. It's a roll of the dice. It's gonna be a little bit different. So it looks like it didn't do step three and four, which was emailing this to myself. So now I just repasted that in there. So it's going into, it's going into my Gmail account. It's clicking on compose. Alright.
Jordan Wilson [00:30:02]:
So now let's see. It's looks like it's finding out pretty quickly there. It entered my email, the info@everydayai. This is where it generally struggles is attaching files. So it essentially has this right here, a file system. And I told it over time, I I found out where operator kind of, shares its or keeps its files that it downloads because it's on a virtual machine. I'll probably have to fine tune those instructions a little bit because I know it's in that o a I, that open a I folder in a shared folder. So for whatever reason, I need to add, a little bit more, detailed instructions about where to find it because right now operator is struggling to remember.
Jordan Wilson [00:30:45]:
So it's in that share folder. So we'll save it kinda double clicks in there. So, yeah, for whatever reason, it is struggling right now to find, files. But that's fine. Alright. So I'm gonna go ahead. I'm gonna stop this task. So we'll give it, we'll give it, maybe, I don't know, a b a b or a c on that one.
Jordan Wilson [00:31:05]:
But let's do something even more difficult. Right? That makes sense. You know, if it fails at a task that's, you know, three out of 10, let's give it something that's extremely, even even harder to do. Right? That makes sense. Alright. So now, livestream audience, you see this. I am this is very long. This is very long.
Jordan Wilson [00:31:26]:
Alright. I'm giving it a very, very difficult task. So this is something I do all the time. Right? I'm not asking it to go order my pizza or, you know, go to, you know, go find me tickets to the warriors game, whatever. Alright. So I'm telling it. Here's what I'm doing. And I'm also intentionally being a little vague.
Jordan Wilson [00:31:55]:
Alright? So I said, for this task, you you will find a trending topic in the generative in generative AI in research potential hot take Tuesday topics for an everyday a a AI podcast. So I'm saying, before I get give it its steps, I'm kind of walking it through what's happening. In livestream audience, you can already see it. It's on my website. It's searching, but I'm gonna walk our pod podcast audience through how we got there. So I'm saying you will research a Google URL identifying an interesting trend or story that will be a good podcast episode. Then you will use Google's Google Gemini's deep research tool to conduct more in-depth research on that topic. Also, you will make sure to look at the context of this chat.
Jordan Wilson [00:32:36]:
That is important y'all. Right? Lights, like, lights. Gem, gem, gem. Right? Because what I'm gonna do is I'm going to run this task probably a couple of times a week, and I don't want it to keep, suggesting the same thing over and over. So I'm telling it, yo, look back at the context of this chat, so don't suggest something to me you've already done. Alright? So then I'm saying step one. First, you will go to the everyday AI podcast episodes page. So I didn't give it the URL I wanted to see.
Jordan Wilson [00:33:06]:
So what it did is it went to ping. It typed in everyday AI podcast. It went to the homepage, then it went to the episode page. It did this on its own and it clicked it clicked the search button. I wasn't, looking at it closely because I was looking at my prompt here on the other screen. Let me just, go through, kind of check my, chain of thought a little bit. Let's see what it did. Yep.
Jordan Wilson [00:33:30]:
Okay. So then it clicked the search button and it searched for hot take Tuesday. Right? So those are my Tuesday episodes where sometimes I bring in hot takes. Alright. So now alright. It's it's working this time y'all with no hands. This is good. So then I'm saying you need to go look at all of my hot take Tuesday episodes so you understand the type of topics.
Jordan Wilson [00:33:49]:
Then I gave it a essentially, a a a Boolean search on Google. Right? And this Boolean search, it essentially, it's it's a little, complex, but, it essentially brings up AI news over the last twenty four hours from a bunch of big companies. So there's, it's it's a very advanced Google search. So I copy and pasted that long URL string in there. Alright. And then I said, this shows you when you paste this into Google, this shows you some of the top AI news stories for the week. Step three, you will identify one trending topic that could make a good episode idea for everyday AI. Again, play play pay close attention to the types of hot take Tuesday episodes that we've already covered.
Jordan Wilson [00:34:37]:
Step four, you will research that topic. This is what's happening on the screen now, and it's gonna take a couple of minutes. Is you will research that topic using Google Gemini's deep research feature. Alright. You will go to gemini dot Google dot com, sign in with the account that is on the screen. It did that. I said do not skip that part. So this time without me typing it in, it properly logged into my, into my Google Gemini account.
Jordan Wilson [00:35:04]:
I have a paid account, and then I said Google Gemini's deep research is an AI tool that performs research. You will need to click the model selector drop down in the upper left hand corner and select 1.5 pro with deep research. You will write a prompt instructing that mode to research the hot take Tuesday topic that you selected, and include any relevant information that is needed to properly research that topic for the hot take Tuesday show. And then I gave it an example. You should always be walking this through step by step because, again, this is a human process that would take me probably, about twenty or thirty minutes without distraction. Alright? And you might be saying, okay, Jordan. Looks like it's already taken five to ten minutes. Yes.
Jordan Wilson [00:35:48]:
Right? But I can let this run autonomously. And I do believe that there will be a way to schedule these as well in the near future. Alright. So now after that, I gave an example of the type of prompt that it should put in. I'm not gonna read that because it's kinda long. But, essentially, I'm I'm saying when you use Google deep research, you need to put in this type of prompt. So just like you would, you know, give a large language model shots. Right? A a five shot prompt.
Jordan Wilson [00:36:16]:
Five shot is is better than a no shot prompt. I'm giving it some examples of what's good and what's bad, when it's using deep research. Alright. And then I'm saying, please be, please be exhaustive in your search, making sure to tackle this from every angle. And then I'm saying step five. Google deep research will give you a content plan, and you will click select the blue button that says start research. Right? So there's actually multiple steps, inside Google Deep Research. So it first needed to look at my example of a prompt, apply that to the, essentially, the Boolean research that it went off and did on its own.
Jordan Wilson [00:36:55]:
Right? So are you looking at the number of steps here, y'all? And, essentially, the agency that I'm giving this agent. Right? I'm saying, yo. Go look at my hot take Tuesday. Essentially, think like me. See what I cover. Then go do all my research. I believe it went through about, 40 to 50, search results using that Boolean, essentially search URL that I shared with it. So it's looking at all these different news stories, trying to identify trends based on things that I already cover.
Jordan Wilson [00:37:23]:
Alright. This is great. Then on top of that, without you know, my hands have been in the air the whole time more or less. Right? Then without any other instruction, it is going straight into Google Gemini's deep research. I gave it an example of how to use it. Otherwise, it's gonna stink. It had to verify. Right? That's the other thing.
Jordan Wilson [00:37:42]:
Google deep research essentially starts and puts this plan together for you. And then they had to click to verify it. And then I told it. I think I told it or maybe I told it in a different one. Okay. So I I didn't even okay. I did. Okay.
Jordan Wilson [00:38:00]:
So I I did say, step seven. You will have to wait two to ten minutes for this to finish. Right? And you'll see on my screen right now, it keeps, operator essentially keeps taking a screenshot. And it keeps saying, awaiting completion of research analysis. Right? Waiting for research analysis completion. But I told it. I said, you will have to wait two to ten minutes for it for it to finish. There is a small icon that looks like two windows, and a purple ish status indicator.
Jordan Wilson [00:38:30]:
Alright. You will need to be patient for this to finish. And then I said, eventually, on the left hand side, it will say something like, I've completed your research. Then on the upper right hand portion of the screen, there will be a light blue button that says open in docs. Please click that button. So you'll see right now, in Google Deep Research, it's researched 76 websites already. Right? I hope in the future, right, that you will be able to use, which I'm I'm sure you'll be able to, that you'll be able to use OpenAI's operator, with tasks, with OpenAI deep research, but right now you can't. Right? But this is the literal process that I always do.
Jordan Wilson [00:39:11]:
So you'll see right now live stream audience. It finished. It finished completing the document. So it looks like it's trying to open the document and for whatever okay. There we go. It had to, try it a couple of times, but it put together, it put together this document. So what it was what it decided the hot take Tuesday to be was kind of the ethical, the impact of AI on pricing and its ethical implications, which is actually, pretty pretty fascinating. Right? Because when intelligence becomes cheaper and cheaper, what happens to humans and the ethics behind that.
Jordan Wilson [00:39:47]:
Right? So pretty, pretty cool, topic there that it decided to put together. Alright. So now I told it, I said, please save this document as a PDF. So it looks like it saved it as a PDF. So that's good. Then I also said, before exiting this Google Doc, we want to copy all the text. You can do that by clicking and dragging or just by pressing command a or control a, then command a or control c. Then I told it, please go to NotebookLM.
Jordan Wilson [00:40:19]:
Right? If it does not log you in, click on the try NotebookLM button. If it does log you in, click on the blue create new button in the upper left hand side of the screen, which is what it's doing now. Then I said click on add source. It's literally doing this in real time. And then I said paste in all that information. Bam. It just did that. Let's see if it does the, the next step here.
Jordan Wilson [00:40:41]:
This is pretty pretty impressive. Good. It just clicked generate. So it's generating an audio overview for me at the same time. Right? Are you guys seeing what's happening here? This is this is what I do. This is what I do all the time. Right? I look on my website. I'm like, alright.
Jordan Wilson [00:40:56]:
I gotta plan a show for this week. Let me see what I've covered recently. Right? I might go look at stats from our podcast as well, which I could do this. Right? I I could do this. Alright. Let's see. It looks like I was hoping it would it would finish it all. Let's see if it's if it's going to.
Jordan Wilson [00:41:12]:
But this is what I would do. I would go look on my website. I would go do a bunch of research on, you know, Google, or, you know, deep deep research, honestly, from, OpenAI, but I can't do that right now. And then I would go in I would go into deep research. I would take that topic, have it do a bunch of research. I would copy and paste that, put it in a NotebookLM, generate an audio overview. This is literally what I would do. Alright? And now, hopefully, it's wouldn't this be weird? Let's see.
Jordan Wilson [00:41:43]:
It oh, it said it it paused while I was away, because I I wasn't clicked on there. So I'm not gonna count that, as anything because I was just clicked on my other window. Alright. So isn't this isn't this wild? So now it's going to let's see if it can actually finish this task because the first time, it failed a little bit. Alright. So, my last parts of the task, of the task are to go to my Gmail, send this to info@youreverydayai.com, put a subject line in a brief love this. Oh, look at that. It actually did it it did it correctly on the second on the second time there.
Jordan Wilson [00:42:20]:
It found the attachment right away. Bam. Look at that. It did the entire thing. Right? It did the entire thing. Alright. So now just to hopefully prove to everyone, I'm gonna go ahead and open my email account. Alright.
Jordan Wilson [00:42:38]:
There's a reason. There's a reason I did this, on my old, camera here. I'm sure no one really noticed, but, I have to have my phone, my my phone available here for all the two f a's because now my computer because I was essentially, using a browser from a probably another state here in The US. It's getting a little confused and I'm having to re log in to everything, which is a little annoying, but that's fine. So alright. Let's see. Let's go ahead and share my screen here. Y'all Look at this.
Jordan Wilson [00:43:14]:
Email email from myself. Look at this. Here's the email, y'all. Hello. Please find the attached PDF document detailing the impact of AI on pricing strategies and the ethical considerations surrounding its use. This report highlights key points such as AI's potential to lower prices, ethical concerns like bias and lack of transparency, and the importance of regulatory measures. Best regards. I love that I just best regarded myself, live here on the, Everyday AI Show.
Jordan Wilson [00:43:52]:
Then I can click. Here is the, deep research. So look at this. There we go. And then I would probably take it one step further, and have it, also, download the m p three, from, from NotebookLM and attach that as well. Right? But I wanted to show you an example of this is what I actually do. Right? This task would have probably taken me, like I said, twenty minutes. I should have timed it.
Jordan Wilson [00:44:23]:
I can go back and I can go back and look. And you know what? We're gonna go share we're gonna go share that screen anyways. So we can go back and look and exactly see see exactly what happened. Alright. So if I go up here alright. So it says worked for eleven minutes. Alright. Here we go.
Jordan Wilson [00:44:42]:
Worked for eleven minutes. So this process by myself would probably, like I said, probably takes me about twenty minutes. So you might be thinking, okay, Jordan. Well, a two for one trade off. What's the big deal? Right? Number one, this is something I can go be doing other things. Right? I did get this working, last night when I'm not doing a live stream where I was doing my own work just in another Chrome or Edge profile, and it was working perfectly. Right? So it just did my work at a very high level. Right? And this was essentially my first time doing this.
Jordan Wilson [00:45:19]:
And as I always tell you, anyone that's taken our, you know, free prime prop polish course, and I know it's been like two months since we did that. I'm sorry. We're gonna have new dates coming up. I'm getting a ton of emails on that. Essentially, our, you know, hosting provider changed their plan. So we're we're moving it. We're rebuilding it literally from scratch. It's I think it is going to be the best basic ChatGPT course on the Internet.
Jordan Wilson [00:45:44]:
I think it's gonna be better than courses that cost, you know, a thousand dollars. It's all gonna be for free. So even if you've taken our PPP course like five times, you're gonna wanna take this new updated one, FYI. So anyways, this is a task that I would do in getting a two to one. And anyways, what I was getting back to, I'm gonna go back and I'm gonna look. I'm gonna look at this kind of chain of thought. I'm gonna see what worked well and and what didn't. Right? Alright.
Jordan Wilson [00:46:15]:
So doing this one time doesn't doesn't mean a whole lot. Right? That's just to get the process down. So I want you to think, what are those manual time consuming tasks that you do across different domains, across different websites that you maybe have to be logged into. I just gave you an example of a task that I do fairly often. Right? I'm going back. I'm looking at my old episodes. I'm doing some research on Google. I'm using my brain.
Jordan Wilson [00:46:45]:
I'm thinking. Right? But now I can go back and look at this kind of chain of thought on operator, see see what it see what I'd like that it did because I can literally go back and watch the recording, which is great, and I can see step by step. So then I can kind of save my set of instructions, change them, improve them. Right? So maybe that eleven minutes will get down to eight minutes. But not only that, but then I can look at, increasing the quality of the output. So now I can not only do it in half the time, but I could do it even better. Right? I can maybe make that task, oh, this is something that would now take me thirty or forty minutes, and maybe I can still do it in ten minutes while I'm doing something else. And then think think of these three, five, 10 ongoing little projects or tasks that you do all the time.
Jordan Wilson [00:47:36]:
And maybe right now, there's no other way to automate them. Right? Maybe right now, you're just automating the pieces, but you can't automate the whole. This is where operator changes that. Right? So, yes, some of these things were already, you know, you could already do by by using something maybe, like Zapier, by using some some APIs or make.com or something like that. Right? And speaking of, we have to talk about APIs. Right? This is how, like, 1% of the Internet talks to each other. Right? But what about for the other 99%? This is where Kua or computer use agents comes into play. You also have to, you know, tip your hat to the anthropic team, that came out with their computer using agent, I think it was back in October.
Jordan Wilson [00:48:23]:
It just wasn't usable. Right? You had to download like Docker, which is an extremely, you know, compute intensive program on your on your desktop. You had to go into a GitHub repo, you you know, and it timed out, like, every five seconds. There you you just saw it did in eleven minute task all on its own. I didn't, you know, limit out or anything like that. Granted, I am on that $200 a month pro plan. Alright. I I do wanna show you a couple other things on the operator interface.
Jordan Wilson [00:48:54]:
Okay? So like I said, this does look kind of like a ChatGPT. Alright? A couple of things I wish you could rename, rename these kind of, operator tasks. So you can't right now. You can only delete them. That's one thing to keep in mind. Alright. Another thing is, you're always gonna have your active tasks. So I have run up to3 at the same time.
Jordan Wilson [00:49:18]:
I don't know if that actually slowed it down or not. But keep in mind, there's limits that are dynamic, so you don't know, what that actually means. Let's go into the settings because this is, kind of important. So you can go in here to save tasks. So, I'm gonna go into the one that we just did and then I'm gonna go click save tasks. Alright. It's going to auto generate, a title, the detailed instructions. So in this case, I would not use these detailed instructions.
Jordan Wilson [00:49:46]:
It's the same, the same, kind of piece of advice that I gave you guys for ChatGPT tasks. Never let ChatGPT, save instructions on its own. It's not gonna work. So it it really just abbreviated those instructions. So I'm gonna paste all of these in so it has it. And then so it says title, research trending AI topic, the detailed instructions. I copy and pasted those in manually. And then, it says websites.
Jordan Wilson [00:50:17]:
Right? So it's it's going to use, you know, g mail dot com. It's going to use your everyday a I dot com. So if it ever starts going in the wrong direction, you can put that there. Right? Gemini.google.com, and then we had NotebookLM. Right? So now if I am running into issues, I can essentially, save this, save this as a task first. Let's see. It doesn't look like it saved it. Let me just double check that there.
Jordan Wilson [00:50:52]:
I'm so zoomed in on my interface here. I think I just had to zoom out. There we go. Alright. So then, yeah, I can go here, type in the URLs, whatever. I'm just showing you all an example. Oh, here's the downside. So it looks like this is why I didn't save.
Jordan Wilson [00:51:09]:
The instructions cannot exceed, a thousand characters, which that stinks. So, let's just show you what this looks like. So this wouldn't work now. Alright. Well, let's just go let's just click save task. Sorry, y'all. Alright. I'm gonna save that.
Jordan Wilson [00:51:33]:
So now that is going to show up in my saved task right there. So then at any time, I can go in and modify that as well. Alright. A couple other things, and these are things I don't even think you should pay much attention to if I'm being honest. Right? So when you do go to the home page here, so now I have my saved task and I can, click that. I can edit it or I can click it and it will launch it right there. But don't pay attention. These are the things that OpenAI demo.
Jordan Wilson [00:52:04]:
Don't pay attention to these these dining and events. So these are essentially prepackaged, props and, you know, it does look like OpenAI partnered, with some of these, websites and companies to provide a more seamless experience. Like I said, I would never use operator for any of these tasks because it requires too much human in the loop. I like, when I'm using an agent, I wanna save time. I don't wanna sit there and just be like, oh, cool. And then, like, answer a question every forty five seconds. That's a waste of time. Right? So you can go through here and, you know, use OpenTable to reserve a table or StubHub to do tickets, you you know, Uber Eats, Instacart.
Jordan Wilson [00:52:44]:
Right? All all all these things, Thumbtack, Uber, like, no. I'm not gonna use operator to do an Uber. I'm gonna use my Uber app. Right? But a couple of other things to keep in mind, you can go in here into your, into your websites. So for all of these, you can give them custom instructions. So for booking.com, I can go in and set instructions. I could say, you know, like, I like, you know, modern modern interiors and outdoor spaces. Right? So then if I'm using Booking.com or whatever, it will take those preferences into mind.
Jordan Wilson [00:53:27]:
So I I wish so you can do that for, all of those websites that they work with as well as news. So these are all the news organizations that OpenAI has partnered with. So I can go to, you know, the Associated Press, I can click edit, and, you you know, type in custom instructions for the associated press as one example. So I hope and wish that in the future you'll be able to add your own websites, that you'll be able to store, your credentials for all of those. Right. That would be extremely helpful. Alright, y'all. That was a lot.
Jordan Wilson [00:54:01]:
So, I think there's a couple of questions. I know that this is already an extremely long episode. Angie just said, holy shh. Alright. Sandra said she was blown away. Alright. That's good. So this is this was helpful.
Jordan Wilson [00:54:15]:
Alright. That's good. So, yeah, even though even though this was a little bit of a longer, of a longer process here, y'all, thank you. So alright. I see a couple of questions. I'm gonna try to answer some of these as quickly as possible. Alright. Just scrolling through.
Jordan Wilson [00:54:32]:
Let's look at some questions. Douglas, have you checked out any open source operator solutions? Yes. So there's browser use. There's a couple of other ones that have become extremely popular. I've I've I've done, a couple tests, but I'm using operator more. Right. The reason why, there's yes. There's other great kind of open source ask, and fully open source, projects that do this.
Jordan Wilson [00:54:57]:
The reason I'm not doing them is because you have to think of the future. Right? The future is operator is probably within hopefully weeks or months going to be able to work with ChatGPT tasks. It's going to be able to work with open research. So in my mind, it is not worth, like, I think you have to choose your ecosystem. Right? And I'm choosing, right, for at least when I'm on my Mac. Right? I have my Windows, computer, my Windows Copilot Plus PC. I still gotta get set up and using. But for the most part, I'm using in my day to day, I'm using ChatGibbet.
Jordan Wilson [00:55:32]:
Right? I have free plans, plus plans, team plans, pro plans, enterprise plans because we train companies, obviously. Right? This is my business operating system. So I'm not even though there are, you you know, some other better or I won't say better. There's some alternatives that may be cheaper, but I'm working for the future here, Douglas. I'm not working for today. Right? Because in the coming, probably weeks, months, operator is probably going to start working with everything else. So, I am currently building skills and using operator that are going to pay off as number one, operator gets better. And number two, it starts to work with all the other products and tools in OpenAI's ecosystem.
Jordan Wilson [00:56:17]:
Woozy, what's the coolest use case you've seen anyone do with it, Jordan? What's up, Woozy? Hey. I'm sorry about your Chiefs, buddy. I'm sorry. Caught caught a beating there. Alright. So what's the coolest use case you've seen? I mean, it's limited. Right? It's limited because right now, the virtual machines that this use, they don't have a lot of computing power. So I don't know.
Jordan Wilson [00:56:40]:
If I'm being honest, some of the coolest stuff I is what I showed you guys. Right? Using deep research, using other large language models, I think is great. I think it would be cool, when it can consistently handle using something, like a cursor or something like GitHub Copilot. Right? But right now it's not there because you still have to have kind of that quote unquote virtual machine compute and it doesn't have. So anytime you try to do anything, that's a little too, you know, power intensive, you're gonna get a warning. Sandra, one of your prompt classes resuming hopefully in March. Pedro, how could you prompt the model to be iterative with other AI models? So, yeah, I I kind of just showed you an example of that. Right? It was using Gemini.
Jordan Wilson [00:57:29]:
So and I did give it an example, of a prompt, to do the deep research. So you have to give it examples, you know, in your instructions essentially. Another question, Pedro, would you use this to dive deep into x using Grok to search for news and hot topics and process the data as you did? Maybe. I personally think Grok stinks. The only thing that I think Grok is decent at is searching axe or Twitter. And in many instances for what I wanna use it for, it doesn't do well. So a lot of times I'll say like, okay, today's, you know, February let's say today's February 11. Right? I'll say, hey.
Jordan Wilson [00:58:07]:
Give me the top AI news for February 11, and it'll bring in things from two weeks ago. Right? So I don't think Croc is a good model. I wouldn't recommend businesses use it. So I'm not using operator to, you know, do anything. Big Bogey says, looks like it needs some prove it. Hot take, how do you rate it? It's an a. Right? Especially after using some of these open source tools and, Claude's, computer use. It's an a.
Jordan Wilson [00:58:33]:
Right? A lot of times, what I find is once you go through and you improve, you run something once, you look step by step and see what it does, and then you improve your instructions, in most cases, it's going to do it extremely well. I mean, in my use case, I had it query something, click on my website, click on the search bar, search for something, go back, use the the the, pagination or pagination. Right? Look at multiple pages of my website, understand trends, then go use Boolean search, research something, find what it thought was helpful, go in, then in deep research, which requires multiple steps. Right? Like, you saw what it did. That is amazing. And maybe I'm just blown away because these are the, what I feel, are mundane, repetitive tasks that I do over and over. And now I can just be like, yo, operator, you go do this. And then it's gonna get better at it than me because guess what? It is using the GPT four o model.
Jordan Wilson [00:59:29]:
So it will be able to summarize, synthesize, and understand information better than I can, period. Right? So how do I rate it a? Right? If if I look at this in six months because it's probably gonna improve, I will probably look back at it and be like, yo, that was a d. But right now, it's extremely exciting. Cecilia, how are your passwords protected when you have the agent log into your accounts? So that's a good question, Cecilia. I read that last night. I thought I took a screenshot of it and put in my presentation. I didn't. So I'll make sure to put that in the newsletter.
Jordan Wilson [01:00:03]:
Pedro, should companies set agent accounts? Yeah. I mean, companies need to be using agents, period. Marie says, I see it can save the task. Does it also save the sidebar commentary? That is saved by default. So you don't have to click save task to save that sidebar commentary. So I can go through at any time anything that I've run-in operator. I can literally go and rewatch the entire process with the commentary. So you just have to click that expand window, and I can go just like you can kinda see that, chain of thought.
Jordan Wilson [01:00:43]:
I can see the entire step by step process in there. Alright? Sandra says, can it use, can it use Canva? I don't know. Should should we find out? Should we find out here? Well, actually, no. That's gonna take too long. I'm gonna I'm gonna have to two FA it. But I I believe, yes, it can, from what I remember in my research, Sandra. But it's not gonna work very well. Right? It's not for anything you want it to do that's extremely visual, it's not gonna work very well because essentially what it does, even a click and and type things in, it takes a screenshot.
Jordan Wilson [01:01:21]:
So if you were like, oh, go, you know, you know, update this template or create a design, that's not really what it's for. Right now, at least, maybe in the future, it will do a good job at that. But you saw it put together a very I mean, albeit plain. It put together a a a PDF presentation for me. It resized the font. You know, it's not gonna win any design awards, but it at least went to Google Slides and copy and pasted all that information over there that it did for the SWOT analysis. Alright. Doug was asking, does the refined Q principles work here? Yes.
Jordan Wilson [01:01:53]:
It does. Your basic prompt engineering basics are always going to work. It's always going to improve it. You always need to iterate on the result. Don't run it once and say, oh, this is the best it's going to be. No. Run it once. Watch it.
Jordan Wilson [01:02:06]:
Right? It's it's it's very tempting to just let it run and then go do something else. But again, think of that task that you do every single day that takes you thirty minutes, takes you two hours. It might take you way more than that to, you know, automate this and to make it, you know, a solid operator workflow. But think, if then you can get that two hour task to you don't have to do it, That's amazing. But you're gonna have to reiterate. So, yes, the refined queue approach that we teach in our free prime prompt polished PPP course, does work fairly well. And, yes, basic prompt engineering, you know, works well. Give it examples.
Jordan Wilson [01:02:47]:
Tell it what's good and what's bad. Right? Provide feedback. You know, improve your set of instructions each time. Rerun it. Tweak it. Right? You you need to be doing these things. It's not, you know, agentic systems are not one shot. They require human in the loop.
Jordan Wilson [01:03:03]:
They require constant improvement, constant refinement because they're going to get better and better as we go. Alright. Looks like I tackled all the questions. So I hope this was helpful, but let me just recap it. Is OpenAI's best AI agent operator? Yes. It is. Is it the one I'm going to use the most? Probably not. Right? If I'm being honest, I'm using deep research a ton.
Jordan Wilson [01:03:27]:
I'm using task a ton because they're running their schedule. They're running autonomously. But I do think operator is the best because, like, I started the show out with. Right? I think a lot of people are seeing these individual these fragmented use cases of AI. Right? But they're like, I still have to take these 20 pieces and put them together. Right? So a lot of people say, okay. It's not just doing my work yet. I thought that's what, you know, the future of AI and large language models, it was just gonna do our work.
Jordan Wilson [01:04:00]:
Well, here we are, you know, going from the the the reasoner's step to the agent. We're there. Right? I just showed you. That is a task that I do over and over and over and over again. I just train live here on the show. I just trained operator to do it for me. And I'm gonna go in and I'm going to improve it. Right? I'm gonna have them send me that, you know, NotebookLM deep dive or maybe send me a link to it.
Jordan Wilson [01:04:30]:
Right? But now I can do better. Right? I can do better. Instead of maybe looking at one of those reports, I can have it do3. And then I can sit, I can read the report, I can listen to the deep dive, and I can use more of my brain, more of my, creative ability, more of my, kind of strategic decision making. Right? I can leave some of those mundane, repetitive, manual tasks that up until operator, I could not fully automate, but now I can't. So that's why I do think I'm not saying I don't say these things lightly. This is a revolutionary step. This is a giant leap, for the future of AI because the future of AI, like we've been saying for a long time, it's agentic.
Jordan Wilson [01:05:15]:
Right? It is working in a multi agent environment, giving agency decision making passwords. Right? Giving everything to an AI system, keeping the human in the loop, but then changing what we as humans work on. Alright. I hope this was helpful y'all. If so, if you want to put this in practice, I'm going to send you an example of exactly what I did. I will send you my instructions. So just go click repost if this was helpful. You're listening on LinkedIn or Twitter, just click that repost button.
Jordan Wilson [01:05:44]:
You can tag me in the post and, you know, to make sure I'll send this to you. You know, also, for anyone that does repost this, I'm putting this out there. I don't know what we charge anymore for, like, a ninety minute consult. I think it's, I don't know, 4 like, $3.03 50 or $400, something like that. Right? Anyone that goes and shares this on LinkedIn, I'm gonna enter you, into a little giveaway. I'm going to announce it in the newsletter, probably next week. So then that way our podcast audience, you all have time to go click the, the LinkedIn show for this. Go click repost.
Jordan Wilson [01:06:19]:
Right? So I don't know whether there's two people or 50 people that reshare this. I'm gonna put all all your names in a digital hat. I'm gonna draw one, and then give you all, who whoever does win this a ninety minute consult. Alright. So whether you want me to help walk your team through operator, whether you have questions about ChatGPT, whatever it may be. You get ninety minutes. Alright? I'm not gonna, you know, put together anything for you. You essentially just get get my time.
Jordan Wilson [01:06:47]:
Right? Talk to me. I'll answer questions. Whatever it is you need, I'll do that. So, make sure to share and repost this if this was helpful. Also, go make sure you check out that AI predictions and road map series. Thank you for tuning in. I know this was a long one. I hope it was helpful.
Jordan Wilson [01:07:02]:
I hope I see you back tomorrow and every day for more everyday AI. Thanks, y'all.