Episode Categories:
Resources:
Join the discussion: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
How to Visualize Data with AI: Pinpointed Insights for Business Leaders
Visualizing business data via AI is no longer a technical fantasy—everyday business owners and decision makers can now build bespoke, actionable dashboards with the exact insights they need, using AI tools like ChatGPT, Gemini, and Claude. Here's how these platforms can create instant, interactive visualizations—not just charts, but true problem-solving interfaces—without requiring any coding expertise. This guide compiles specific business value and workflow improvements, directly drawn from a hands-on demonstration.
Data Visualization AI Tools: ChatGPT, Gemini, and Claude Compared
The episode provides a documented side-by-side comparison of ChatGPT, Gemini, and Claude for visualizing business datasets such as podcast performance stats and meeting transcripts. Each tool was set up with custom instructions to parse raw, unstructured data (CSV files, spreadsheets, long documents, transcripts) and instantly generate dashboards.
ChatGPT: Using a custom GPT setup, raw stats pasted directly into the system instantly rendered a full “Podcast Performance Dashboard.” This dashboard surfaced key metrics such as running total downloads over three years, automatic categorization by episode topic, and dynamic filtering (last 7, 30, 90 days, all-time)—none of which were available within the original hosting platform. No advanced prompt engineering was needed; AI transformed data into interactive insights in a single shot.
Gemini: Uploaded files (such as CSVs of podcast episodes) created similar dashboards, with clear visuals and fast processing. Gemini parsed and displayed average downloads, growth trajectories, and segmented episode performance, though dataset sampling limitations were noted for large data files.
Claude: Operating via “Projects” and “Artifacts,” Claude ingested files and produced analytical dashboards, tabulated topic performance, and summarized action items. Its agentic capability designed interactive workflows, identified decision makers, and grouped discussion topics/color-coded next steps—all automatically based on meeting transcript analysis.
Multi-Source Data Handling: Beyond Spreadsheets and Charts
The value goes far beyond basic spreadsheet replacements. Each AI model ingested not only structured tabular data but also large, text-heavy files—such as meeting transcripts and operational SOPs. The custom instructions enabled extraction of actionable business insights like who spoke most in a meeting, key recurring topics, ad performance benchmarks mentioned during the call, and even contextual recommendations sourced live from the web.
Custom GPTs, GEMS, and Projects can be programmed to “triangulate” business metrics—identifying patterns across disparate datasets (e.g., which podcast topics retain audiences, which ads drive newsletter signups, or which meetings produce actionable outcomes).
The agentic features in Claude and ChatGPT went a step further, surfacing not only to-dos and next steps from transcripts but pre-emptively researching solutions, running live web searches, and displaying recommendations side-by-side with extracted data—all within the dashboard.
AI Visualizations: Getting Specific with Business Value
Specific real-world business outcomes were demonstrated:
Faster Analytics: What previously required manual spreadsheet filtering, formula writing, or third-party software now happens instantly via LLMs. For example, detailed episode-by-episode podcast analytics, which weren’t available in the hosting software, were generated and categorized automatically.
Unstructured Data Insight: LLMs analyzed raw meeting transcripts to deliver not only summarized topics and recurring points, but also assigned roles, highlighted the most vocal contributors, and even created interactive Kanban-style action boards for next steps.
Immediate Iteration: With one click or a simple follow-up instruction (e.g., “create better headings, next steps, and solutions for these issues”), the dashboards were iteratively refined—all without a single line of code.
Personalized “Micro-Apps”: Any recurring business process—monthly reviews, sales meetings, campaign reports—can become its own AI-powered dashboard, updated in seconds with minimal input. This drastically reduces reliance on static, generic tooling.
Practical Implementation: Custom Instructions as a Strategic Asset
Business leaders can unlock these benefits by leveraging custom instructions within each AI platform:
Reusable Templates: Crafting advanced, yet simple instructions enables consistent, scalable outputs regardless of data source. Upload the latest file each month and receive instant visualizations—no need to rewrite prompts or formulas.
Agentic Automation: By stacking agentic capabilities (chain-of-thought reasoning, web search integration), LLMs proactively find solutions and surface strategic recommendations, not just report what happened.
Platform Strengths: Fastest results for large datasets were achieved on Gemini, while Claude’s Projects had the highest ceiling for innovative workflow visualizations. ChatGPT offered unparalleled flexibility when combining custom GPTs with Canvas mode.
Future-Proofing Workflows with AI-Powered Data Interfaces
Text-based work is being rapidly overtaken by interactive, multimedia, and visual outputs enabled by AI. As demonstrated, dashboards generated by LLMs aren’t just reporting tools—they foster interactive understanding and decision-making, surfacing patterns and insights not previously obtainable via manual review. Business owners and decision makers now have the ability to turn every operational data source (stats, transcripts, documents) into a custom, visual workspace that grows in sophistication with every iteration.
Ready to see it for yourself? Leveraging AI for instant, actionable data visualizations means putting practical business insight directly into workflow—with zero technical barriers. Reach out for tailored instructions, and start transforming everyday business data into direct strategic advantage.
Topics Covered in This Episode:
- Combining Multiple Features in Large Language Models
- Visualizing Data in ChatGPT, Gemini, and Claude
- Creating Custom GPTs, Gems, and Projects
- Uploading Files for Automated Data Dashboards
- Comparing ChatGPT Canvas, Gemini Canvas, and Claude Artifacts
- Using Agentic Capabilities for Problem Solving
- Visualizing Meeting Transcripts and Unstructured Data
- One-Shot Mini App Creation with AI
Episode Transcript
Jordan Wilson [00:00:17]:
Combining multiple features in a large language model is where you can really start to unlock superhuman esque capabilities. So today, I'm giving you the keys to the castle. We're gonna be combining two of my favorite features in most front end large language models that hopefully will change how you think about working with LLMs. Ultimately, over the next twenty ish minutes, I hope to show you live how how you can not just visualize something inside chat GPT, Gemini, and Claude, but how, hopefully, you can rethink about the way you work. Because this is really an easy entry into vibe coding one zero one, but I'm gonna do it all for you. Alright. I'm excited for today's show. I hope you are too.
Jordan Wilson [00:01:07]:
Let's get into it. What's going on y'all? Welcome to Everyday AI. My name is Jordan Wilson. And if you're new here, this is an unedited, unscripted daily live stream podcast and free daily newsletter, helping everyday business leaders like you and me keep up with all of the large language model and AI updates, make sense of it, cut through the BS, pull out the important insights that we need to grow our companies and our careers. If that's what you're trying to do, sweet. Me too. Starts here with the unedited livestream podcast. But if you really want the most important, insights, make sure to go sign up for our newsletter at youreverydayai.com.
Jordan Wilson [00:01:42]:
We're gonna be recapping the highlights from today's show. So if you miss anything, don't worry about it. It's gonna be in the newsletter as well as all of the other AI news and whatnot that you need to know. Alright. This is AI at Work on Wednesdays. This is a series we've been doing now for, I don't know, nine months or so. And it seems like you all really like it. But one thing that I hear from a lot of people is, hey.
Jordan Wilson [00:02:05]:
It's almost like there's too much information or sometimes things are a little too too advanced. So I wanted to take it back to the fundamentals. Alright. But I'm gonna explain that here in a minute, but we're actually just gonna kick it off live. We're gonna do it a little different today. We're gonna be doing a lot more on the live side. So if you are listening on the podcast, appreciate your support as always. This might be one of those that you're gonna wanna check out the video version.
Jordan Wilson [00:02:27]:
So again, just go to youreverydayai.com, and then find, today's episode, and you can watch the video version. So this is episode six sixty five. So go watch the video version on our website. Alright. We're gonna start a couple of things live. Alright? I do this sometimes. We gotta put the ingredients in the kitchen. So what was I talking about by combining multiple features in a large language model? Well, what I'm talking about is combining, projects, or GPTs or GEMS.
Jordan Wilson [00:03:02]:
Alright. So I'm gonna talk you through that later. So combining those and some of the, capabilities that using those things unlock, but also using each large language model's ability to essentially write and render code. Alright. So like I said, we're combining two separate kind of modes or features in the three, big models in CHAD GPT, Gemini, and Claude. Alright? And then we're gonna be showing you how to essentially vibe one zero one your day, your daily work. Alright. So I'm gonna explain what I'm doing here for our podcast audience.
Jordan Wilson [00:03:39]:
So I have a GPT open, inside Chat GPT. Alright? And stick around to the end. I'm gonna give you everything. Right? Because there's some custom instructions in here that were not easy to get, working correctly. I don't know for whatever reason. I kind of, put out a tweet out there, so I might have to, end up reaching out to someone at OpenAI. But the GPTs, I don't know why, in the last week or so, they've been finicky. So, you you know, GPTs and gems are a kind of a customized version, of chat GPT or Gemini respectively.
Jordan Wilson [00:04:12]:
And then projects is a little different inside Anthropic, but, essentially, it's a way to create a customized version of the main model that just acts specific to your needs. So I have some, pretty in-depth and, advanced custom instructions that I'm gonna be giving away to everyone. Don't worry. So, that's what I'm gonna be doing here. But for whatever reason, like I said, GPTs are having problems with consistently reading uploaded files. So, I'm gonna be doing a couple different tests. So in the first one, I'm just pasting in a bunch of information. So in the first test, like I do on our weekly putting AI at work on Wednesdays, I'm throwing in some podcast stats.
Jordan Wilson [00:04:50]:
But as we go through this, think what is the data that you constantly work with or, you know, long meeting transcripts, you know, long SOPs. Right? Don't just think about visualizing data. Think about visualizing your work. Alright? Because I do think that's going to as we look into 2026, that's a new era of work that we're gonna be, moving toward is just working in much more visual live in AI powered interfaces. So this is a good way to get used to it. So I hope you can follow along with me. All right. So here we go.
Jordan Wilson [00:05:20]:
I'm clicking enter in chat GPT. All right. We're getting these things started off so we can do do it live. So that was a chat GPT custom GPT. Now I am in, Google Gemini and I have paid accounts for all of these. In this case, I'm gonna upload a file. So all this file is is a, CSV with all my podcast stats. Alright.
Jordan Wilson [00:05:45]:
And I'm gonna get this one going. There we go. Our Google Gem, again, a custom version of Google Gemini, it's off and running. Now I am inside Claude. A little different here, I have what's set up as a project. So Claude doesn't have the equivalent of a GPT or a GEM. They have a project, right, which Chad GPT also has projects. Google Gemini is gonna be rolling out projects any day now.
Jordan Wilson [00:06:12]:
There's pros, cons, overlap. Right? But for all intent purposes, we're doing the exact same thing. I have those custom instructions inside this project and all I'm doing again, all I'm doing, I'm uploading file and I'm hitting enter. That's it. Nothing fancy, no prompt engineering. Right? You don't need to know anything. I'm uploading a file, hitting enter, and the custom instructions I'm gonna be giving away to all of you, who repost this episode, by the way, is going to take care of the rest. Well, hopefully.
Jordan Wilson [00:06:45]:
Alright. So now, we have our, pies in the oven, so to speak. Alright. And I'm gonna be kind of keeping my eye on those, and we're probably gonna be testing out a couple other ones, live, but I'm hoping that these ones, that I just kicked off are going to, actually work. Alright. So let's get into it. So like I said, the custom instructions to get all these to work was not easy. All right.
Jordan Wilson [00:07:18]:
So if you want access to this, I built it for you, right? Talking about combining multiple modes. Right? Being able to kind of like a, a a puppeteer, be able to control, certain elements, of Chatt GPT, Gemini, and Claude. So if you want those custom instructions and hopefully you'll be able to see and understand some of the results here at the end when we check-in on these, just go repost today's show and I will send them all to you. Give me a day or three. It just depends on, how many people repost this. Alright? So here's what we're gonna be going over on the rest of today's show. Well, I'm gonna simplify the three best ways to visualize data, visualize data, in the major LLM providers, and I'm gonna talk about some of the pros and the cons. We're gonna go live even more than the three that we just put in.
Jordan Wilson [00:08:05]:
I'm gonna try a couple other things because here's the reality. Not everyone works with data all the time. So think whatever document types that you work with, this should work. So, yeah, gonna go live doing it, doing more, and then I'm gonna give you all the goods right at the end. So you can do this immediately. Alright. So why you might be thinking, why, why do I need to do this? Right. There's there's no, you know, you might be looking at your, workflow and say, Hey, there's nothing broken.
Jordan Wilson [00:08:40]:
If it ain't broke, don't fix it. Right. You could make that argument. Sure. But I, I hope you'll see by the end of this, how this changes, how we work, because no one wants the equivalent of the blinking cursor when it comes to AI. And I think so many, or so much of the sheer power of large language models is their ability to code. But I think when you hear the word code, I think 99%, especially of our audience, which I know a lot of you are non technical. When you hear that you're like, no, that's not for me.
Jordan Wilson [00:09:17]:
Right? So this is really just to challenge you, because here's the thing. Let's just say you work in HR. Guess what you're drowning in? Documents, right? Onboarding forms. You're trying to personalize certain policies. You're trying to update, right? When certain laws come into effect, certain labor laws, etcetera. Right? You're drowning in long documents, right? So this same thing can be used, to help you better visualize and understand key elements of your work, right? When we talk about visualizing data, sometimes data is just words, right? Sometimes it's just piles of documents. So, I want you to think of what is that thing for you. Right? For me, a lot of times, it's stats, right? It's podcast stats, it's stats from our newsletter, it's stats from social media.
Jordan Wilson [00:10:07]:
Right? But not just that, but it's really, triangulating those different stats and finding, the connections. Right? What type of podcast episodes do you like? Right? What's what are things that, you know, bring in a lot of new audiences and retain them across multiple platforms? That's something, right, to do at scale. Generally, you need a big team to do that. Right? And a lot of the, you know, popular podcasts, out there that, you know, our show is luckily rubbing elbows with, you know, on kind of the top podcast charts. They have large teams, very large teams. We don't. Our large teams are exactly what I'm showing you. Right? I'm literally showing you how we run our day to day.
Jordan Wilson [00:10:47]:
That's putting AI to work at Wednesdays. I'm showing you how I use it. So I want you to do it as well. And I need you to think of the future. Talk is cheap. So is text. Right? Unfortunately, I think AI has really cheapened the written word, which sucks for me as a former journalist, as someone that, you know, I would say is above average, at writing. I've won a couple, writing awards in my day, fuller, former, Pulitzer Fellow, all that good stuff.
Jordan Wilson [00:11:16]:
But text is cheap now, and overwhelming. Right? Because of large language models. AI slop. Right? Obviously, when we think of AI slop, we now all think of, you know, AI photos and AI videos. But the OG AI slop was text. Right? Walls and walls of text. And I think that not just what we output is going to change and what we're expected to output is gonna change. Right? I'd say for the majority of our listeners, you know, what, what are your outputs? You're responding to emails, your, you know, maybe PowerPoints, Excel sheets.
Jordan Wilson [00:11:51]:
Right? Normally, text based things, even, you know, PowerPoints, pretty much text based, and you try to make the text look pretty. It's gonna change in the future. Right? I I I I love one of our four, recent guests, said something, demos over memos. And I think that's the future of work. It it it was Richard, chief evangelist, over there at, Google Cloud. He said demos over memos. I think that's how we're gonna be working in the future with AI. Right? And, you you know, just putting out text based work, whether it's emails, presentations, documents, Excel sheets, whatever, It's not gonna cut it for much longer.
Jordan Wilson [00:12:33]:
Right? Because I think how we learn, how we interact and how we build value for our companies is going to be well in a very visual multimedia and interactive experience. Like what we're gonna be showing you here today, Because what we're going over, this is like vibe coding. I'm not gonna call this vibe coding one zero one because it's not. This is vibe coding o o one. This is like if you were in a college class and you wanted to take vibe coding one zero one, this is like one of the first prereqs that you need before you go to vibe coding one zero one because ultimately, this is what we're doing. We are having ChatGPT, Gemini, and, Claude code us useful information that we as non technical business leaders can you can do. Alright. And, and like I said, this is so easy, but I think so few people take advantage of this.
Jordan Wilson [00:13:19]:
And it's best, I think, when you stack features and make it simple. Because even what I'm doing right here, it's technically not easy. Right? Because not only am I having to, you know, get the data together, to give to a large language model, but normally, what you're faced with is writing out these long instructions. Right? So this is where, the GPTs, inside chat g p t, the gems inside of Google Gemini, and Claude's, kind of projects and the custom instructions and projects really comes in handy because if you get it working right, and you can build in that reproducibility and scalability right in these custom instructions that I'll share with you. It doesn't matter or it shouldn't matter. Right? I'm gonna fine tune it a a a little bit more before I send it out to everyone, but it doesn't matter if you're uploading a bunch of spreadsheets, a bunch of documents, bunch of text, meeting transcripts. It should be able to provide you instant, instant feedback and instant visualizations, that you can really take advantage of. Alright.
Jordan Wilson [00:14:18]:
So let me just real quick give you the pros and the cons of, of each. Alright. So, ChatChippet's canvas mode. Okay. Technically, ChatChippet's canvas mode, there's a duality to it. The same thing with Gemini's canvas mode. Number one, it's kind of like an interactive text editor. Right? So here, I'm I'm just gonna talk about ChatGPT Canvas and Gemini Canvas in the same breath.
Jordan Wilson [00:14:42]:
A lot of people think of it as an interactive text editor. Right? So instead of going back and forth in a chat style, with a large language model, you have, like, a doc. Right? And you can go in line. Right? So if you have a 10 paragraph document and, oh, man, paragraph number six stinks. You know, normally in a chat interface, you just tell Chat GPT or tell Gemini, hey. Keep everything the same, but change paragraph six, and, oh, shoot. It changed paragraph two and number eight as well. So, you know, in a canvas mode, it's interactive and in line.
Jordan Wilson [00:15:11]:
Right? You can put your cursor in the middle and highlight something and say, just change this, and it just changes that. People think that's what canvas mode is in chat g p t and in Google Gemini. Well, that's the half of it. The other half is it can run and render many different types of codes. So you can have these interactive environments. It's almost like you're spinning up apps or you're spinning spinning up demos. Right? Demos over memos, in chat without knowing how to code. Just being like, yo, chat, yo, Gemini.
Jordan Wilson [00:15:38]:
Here's a bunch of information. Go build me something useful. Right? But then having that scalability, of the custom instructions on top of it. So I think that, ChatGPT Canvas, it can be finicky. Right? Especially in my case right now, when I'm using it with a GPT because, if you look in your GPT settings, you can enable people don't know this. You can enable or disable canvas mode. Right? So obviously, in my example, I have it enabled. But, yeah, it can be a little finicky when attaching, files in a GPT while using canvas mode.
Jordan Wilson [00:16:13]:
So I know that's a lot there. One of the plus sides, of using, Chachapiti Canvas is if you tell it in the prompt to use canvas, you don't even, usually have to click the canvas button. In Google Gemini, you do. Even if you explicitly tell it, in the GEMS, custom instructions, to use canvas mode, it won't always do so. Alright. I I think the highest the the best visual outputs in the fastest amount of time, if we look at speed, quality, and reliability, I think it's Google Gemini hands hands down. The highest ceiling might be Claude, right, with their, artifacts. And I'm gonna talk about that a little bit more when I show you that.
Jordan Wilson [00:16:57]:
So that's their version. So we're using projects, but their version, the thing that renders code is just called artifacts. It's not an interactive inline editor like canvas mode, but it does, render code and it's really good. The ceiling is high. It's it's finicky though. Right? So in terms of reliability, I think, reliability and speed, I think Google Gemini takes the cake. In terms of flexibility, I think it might actually be chat GPTs, just because you can use GPTs in a variety of different ways. Right? And when you can bake in canvas mode in a GPT and take advantage of all the different, scaffolding essentially in the agentic nature of the, GPT five one thinking models.
Jordan Wilson [00:17:41]:
It's really good. It's really robust, but it's slow. But when it works, it's great. And then I think in the middle ground there, you have Claude. Super high ceiling, but still fast enough, but finicky as well. So hopefully that helps and it's really just down to your own experience. Alright. So enough on that, let's check-in live and maybe we'll cook up one or two other quick experiences here.
Jordan Wilson [00:18:03]:
Alright. So, let's go and check out. There we go. All right, cool. We got it. So, on my screen here, I am in, ChatGPT. So, this is when I just pasted in the information, because like I said, I am using a GBT. And for whatever reason, when you upload a, file, it can be a little finicky.
Jordan Wilson [00:18:26]:
So I just pasted in all the information, and now, you'll see it created a dashboard for me here. It says everyday AI podcast performance dashboard. All I have to do to to launch this experience is click the preview button. Okay. So now I'm gonna try to resize this a little bit here to make the, dashboard, the interactive dashboard a little bit bigger. And here you see. I'm gonna zoom out a little bit on my screen, and I have a pretty nice dashboard. So it did a nice job.
Jordan Wilson [00:18:54]:
So, it gave me kind of a a running total of the number of downloads of my podcast over time. Really cool. It's interactive. I can hover. It's actually really impressive. It goes day by day over the course of three years, and it shows me running total downloads. That's pretty cool. I don't even have that in my podcast platform.
Jordan Wilson [00:19:14]:
It breaks down the number of total downloads by category type, which is cool. Another thing I don't have. Right? Great thing about large language models is, it takes unstructured data. Right? So just look at the title of my podcast, and then it started to categorize them automatically. I don't have those categories baked in. So, you know, it looks like strategy is my top performing podcast category, then news, then how to tutorials, etcetera. So pretty cool. If I scroll down here, I have another, looks like some of the last, 10, podcasts, the total number of downloads.
Jordan Wilson [00:19:48]:
I have a oh, cool here. Okay. Nice. Yeah. This is this is pretty good. Chat CPT, you know, I I kinda knocked it and said it could be a little finicky. Really knocked this one out of the park. So I have a different window here.
Jordan Wilson [00:19:59]:
I can do the last seven days, and it's giving me the episode, and then the last seven days of downloads, last thirty days of downloads, last ninety days in all time. That's really, really good. Because again, these are stats that I do not have in my podcast host. Right? So you can see immediately where the value already lies for me. This is amazing. Cause a lot of times I have to go export all my data, you know, go in, put a couple of filters in a spreadsheet, right? Pre gen AI, run some formulas, spend a couple hours Googling how to write these formulas. They're not working. Right? Essentially, you're, you know, building a very archaic, simple man's version of, of an algorithm inside of a spreadsheet.
Jordan Wilson [00:20:44]:
I have it all here. It did it for me. Alright. This is very, very impressive. Alright. So, let's see if there's anything else. So nothing super robust in terms of the amount of data, but the data that it did give me really, really good. So chat, chippity, good here.
Jordan Wilson [00:21:01]:
Alright. So let's look at Gemini. Alright. So unfortunately, I can't, kind of zoom zoom too far in and out. But same thing. It gave me a very, very good, looking dashboard here. So similarly, similarly, it gave me linear growth, over time for my podcast. It gives me average episode downloads.
Jordan Wilson [00:21:27]:
It's not correct though. So it looks like there's, maybe some issues here, a growth trajectory. Oh, here's why for, for whatever reason, it only, sampled 13 episodes in my data set. Alright. I've done this similar thing before on my Ultra account, and it did a little bit better. So this is probably a limitation of the paid account that I'm using, but to have all of these in one window, I just did this for simplicity. So maybe not the best example for Google Gemini, but, hey, it looks like maybe I'm proving myself wrong. So if I'm going head to head here, I'd like the, the ChatChibuty version.
Jordan Wilson [00:22:04]:
But, visually, I think the Gemini one is better. Utility, which is ultimately more important, the Chat GbT one is better. So now let's jump into Claude. Let's see how Claude did. I can resize this. So, a little more simple and straightforward, not quite as flashy visually. So this gave me kind of, everyday AI podcast analytics, different tabs that I can click that are, oh, I thought they were sortable, but they're not. Alright.
Jordan Wilson [00:22:31]:
And I did use Opus 4.5. Alright. That that probably is worth noting. So I used, Gemini three Pro. I used Opus 4.5, and then I used, five one thinking. So I use kind of the most powerful models, for each of these. So the Claude artifact, not that great. Like I said, there's these tabs here.
Jordan Wilson [00:22:53]:
They don't do anything. So, it didn't work correctly. Again, I'm I'm one shotting things here. Right? So, it has some monthly, monthly trends. I'm scrolling through these and these are not maybe they're correct. Alright. Performance by topic. So again, this did a good job of breaking, certain things down by topic and then giving the average download.
Jordan Wilson [00:23:16]:
So it looks like AI agents is top, then how to tutorials, business ROI. Okay. Cool. That's pretty helpful. It looks like hey. Claude even found my Claude in Anthropic episodes are not very popular compared to Chad GPT and Gemini that are more popular. Alright. And then it has a content, performance.
Jordan Wilson [00:23:34]:
That's cool. So it says when I have a numbered list podcast, it usually gets a little bit more downloads, tutorials. There we go. Cool stuff. And then it has a couple key insights from my data. So, maybe a little bit to be desired from a user experience, and visual standpoint, but it did the job. So all three of them, just right there. Even if you're not able to see my screen, again, go to your everyday ai.com.
Jordan Wilson [00:23:59]:
Watch the video version if you care. They all produced one shot. Right? I wasn't iterating back and forth. I did this live. Probably with one or two follow ups on each of these, I'm telling you, this is right when I call when when I say this is vibe coding zero zero one. And when I told you all last year that it would become very common for nontechnical people to just be building their own mini apps, this is it. I told you. My podcast provider doesn't even give me some of these things that I had.
Jordan Wilson [00:24:31]:
Right? Because it doesn't have this layer. Number one, it doesn't have the layer of large language models, that I can, you know, manipulate and better understand data and turning unstructured, data into structured insights. But then, obviously, having that, you know, combination factor of the custom instructions that I gave each of these models to really deliver me what I want. Alright. Let's go ahead. I don't know how this is gonna go y'all. We're gonna try. Alright.
Jordan Wilson [00:24:57]:
I'm gonna try, let's see. I have another file. I'm gonna do what are we gonna do here? I have a document. Alright. This is an old, I'm just gonna say, please visualize. So I'm doing nothing. I have a transcript from a meeting. This is an older meeting.
Jordan Wilson [00:25:20]:
I define one where there wasn't an external client. This is just two, two of my coworkers. This is, I don't know, a couple years old. We were having a meeting about, advertising on on Meta. I think it was, you know, we did some, ads for everyday AI, maybe like a year and a half ago, two years ago on Meta. So I think that's what this is. So I'm actually not sure. We'll see, once it maybe does this.
Jordan Wilson [00:25:41]:
Alright. Let's see. So, again, we're we're we're we're we're having this issue here, in, in chat g p t with the g p t and uploading files, this combination for whatever reason, not working very well. So I'm just gonna copy and paste this, and then do nothing else. So we'll see, if that works a little bit better. Alright. We're gonna do the same thing in Gemini. We're gonna go back into our gem.
Jordan Wilson [00:26:10]:
Let's see if this works. I'm just gonna upload this meeting transcript and absolutely nothing else. Alright? I'm gonna make sure whoops. I don't want nano banana, although that could be fun. Alright. Let me try that again. So here I am in my gem. I'm just uploading this transcript doc.
Jordan Wilson [00:26:26]:
Right? And then I'm enabling Canvas mode and going to town. And then the same thing, I'm gonna go back, into a and see here, go into my projects. That's not the right one. There we go. Alright. Go to my projects here inside Claude. I'm gonna upload that same meeting transcripts, and let's see. Let's see if we can get something usable here live.
Jordan Wilson [00:26:55]:
And we're not giving this one as much time. Right? I started the one before, with more time to spare. Right? Gave myself a little time to put it in the oven and cook. But, well, now we can kind of see how they do this live and, you know, I'll tell you a little bit more about some of the custom instructions that I put in here. Right? I did this to handle any type of data. Right? So like I said, whether you throw in multiple spreadsheets, PDFs aside from the bug, you know, that's going on inside ChatTpT, which hopefully they squash. Aside from that, you can really put in any type of data, including, meeting transcripts. Right? And the cool thing that I baked in here, you know, I said, don't just visualize.
Jordan Wilson [00:27:35]:
Right? Don't just visualize things. Help solve problems. So even in the example I said, and we'll see if it works because I didn't even, test this part out. But all of these models are agentic by nature. Right? So, Opus 4.5 from, Claude, Claude Opus 4.5, Google Gemini three pro, and, GPT five one thinking they are agentic. So what does that mean? And what does that mean when we are kind of stacking or combining these capabilities? Let me break it down for you really simply, right. They're not just going through and coding and parsing data and building things. They are doing that, but they're thinking about things hopefully step by step, right? Chain of thought.
Jordan Wilson [00:28:18]:
But also I've built them to go solve problems. So hopefully what it should do is not just tell me what went on in the meeting and hopefully give me a visual dashboard to show some of those things, but what it should be doing. Hopefully, we'll see. Now I'm gonna be kind of, looking through the the the chain of thought a little bit here. It should be solving the problems. Right? So there's probably some next steps that we talked about in the meeting. Right? And maybe you pay for some, you know, AI software that does this for you. Well, here, this does it by default, or it should do it by default.
Jordan Wilson [00:28:50]:
It should pull out, kind of action items, next step to do's. Right? Which is pretty cool. But then it should hopefully go out and start researching those and providing potential solutions. Yeah. No AI platforms do that, but, I mean, I don't wanna overpromise, set of custom instructions, but hopefully it does. Right? But that's what these models are agenda by nature. They should be able to go through, see that, and then go start researching things and be like, wait. Not only do I need to extract to dos, I need to visualize, this meeting transcript, but I need to go out and help these people that had problems or next steps or things that they were gonna research and do it for them.
Jordan Wilson [00:29:27]:
That is what an agentic model should be doing. Right? When it can, you know, start down path a and be like, nope. This isn't right. It can go back, research more, and go down a different path. Alright. So, hopefully, we'll see that here, without me having to, go on for for for too much longer. Yeah. Because this is a little bit more of a complex situation.
Jordan Wilson [00:29:48]:
So let's just see, as an example, I'm opening the chain of thoughts here inside JetGPD. So I can kinda see what's going on and I'm gonna see if it did this right. So first it says it's building, a user interface for a meta ads overview dashboard. Cool. Because there's probably some statistics that we talked about out loud. So it's probably gonna be pulling those, and creating a dashboard. I really wanted to see, if it did what I snuck in there. Yes.
Jordan Wilson [00:30:15]:
It did it. Alright. Chat g b t did it, and I assumed that I was gonna be able to see that because one thing that I love and one of the reasons why, I still use Chad GPT as much as I do and not Gemini more is because in the chain of thought, at least right now, Gemini doesn't show when it goes out to certain websites, which I always need to know. I have talked to the Google team. I do think that they're gonna be building that in here. But now I can see by reading these summarized chain of thought. Alright? This doesn't it's not crazy. Just just go in.
Jordan Wilson [00:30:46]:
I'll give you these custom instructions. You put your own stuff in there. There should be a little button on there that says thought for. Alright? So it's kinda hidden. You have to click it, and then I can go see exactly what this GPT with my custom instructions using this very powerful model did. And I see it did it correctly, and it went and it looked up. So cool. It went up and looked, looked up potential solutions for things we didn't even know at the time, and it went out and started solving our problems.
Jordan Wilson [00:31:14]:
So I'm excited to see, how this one is ultimately, going to, going to, show this information. So, it's still working, but cool to see that that little custom instruction working in action, and it should work, across multiple, different different things. Alright. Let's look at Gemini. So Gemini, like I said, fast. It's done. My gosh. This looks really good.
Jordan Wilson [00:31:43]:
Alright. Yeah. Okay. Sweet. So, interesting. Yeah. This is this is nice. So like I said, this this meeting was, maybe, like, a year and a half ago.
Jordan Wilson [00:31:58]:
Okay. Yeah. Here yeah. Okay. Here's here's the date. Okay. Yeah. I was right.
Jordan Wilson [00:32:01]:
It's from July 2024. So it was an older meeting. So this was with some of my colleagues and we were talking about, some different tactics that we were, you know, doing on meta ads to, you know, you're just more or less, you know, testing different customer acquisition costs, right, to get people to sign up for our email newsletter if we were to do meta ads. I completely forgot about most of this. But yeah. So it it gave us, like, hey, a list of our, inactive targets, ad relevancy, very nice, right? Again, interactive. So number of users views. So it looks like it pulled out different things that we talked about out loud.
Jordan Wilson [00:32:38]:
Right? So we didn't, you know, spit out every single metric out loud, but those that we did, it put them in a nice chart there, which looks good. And and then we have this is like a meeting dashboard, which is really cool. So then it says tech stack status, so it looks like there was a failure on one of the pieces of technology called split hero that we were using. Something about beehive integration, said that it was going correctly. That's good. There's an action plan here with little, status indicators. Really cool. Right? So we needed to fix the Split Hero, because the m a v two was not triggering.
Jordan Wilson [00:33:12]:
The owner on that was Brandon. Right? So it literally created like a dashboard, almost like Kanban style, you you know, follow-up action plan, and then it had a creative and offer pivot. So it went in, offered some examples on what we could do. So very cool. I don't think it did a fantastic job of going out and finding new solutions. So I don't know if it, you know, just used its own training data. I don't know if it went out and, you know, looked at certain up to date websites, but regardless, y'all think of all these meetings that you're in. Imagine if you could have a custom personalized dashboard like this that just visualizes everything.
Jordan Wilson [00:33:52]:
So like I said, yeah, there's a lot of AI note takers out there that give you, you know, next step, action plans, all that. But combine it with, like, Gemini three Pro, it it it's it's good. Alright? Podcast audience, you you can't see my face, but this is one of those where I'm like, what the heck? This is really, really good. Alright. I wanna see what Chad GpT was cooking. Alright. Here we go. Because I'm excited because the Chad GpT one, I can see the websites that it went out to, So it might've done a really good job at kind of solving some of these problems for us.
Jordan Wilson [00:34:23]:
Right? When we talk about the future of work, this is huge. Y'all. All right. So I'm gonna click preview. All right. So now it's previewing. Let's see what we got. All right.
Jordan Wilson [00:34:35]:
So here is our meta ads overview, kind of the people in the meeting. Oh, this is cool. Top talker. So it analyzed who talked the most, the number, the, the words, the key ad topics. Very cool. So did some kind of, like, word clouding. Very cool. So it counts how often key concepts came up.
Jordan Wilson [00:34:55]:
Right? Not just by the words, but it categorized what we talked about most. Really cool. So it looks like we talked about the creatives the most, the PPP course, then the newsletter, then the audiences, then conversions. Very cool. Number of people speaking and the number of words. That's awesome. All right. Let's see what we got here.
Jordan Wilson [00:35:17]:
Okay. It gave kind of, I'm not sure it didn't create a label for this whole section, but it, again, it looks like it kind of had some follow-up pieces here. And then. Okay, and then it looks like it pulled in some new information from the web. It got some benchmarks and it gave us some average meta, CPMs from October 2025. Like I said, this was from July 2024. So I'll tell you this. And then it says like money, you know, there's a money mentioned section, so pretty cool.
Jordan Wilson [00:35:49]:
I wish I wish I could combine these two different ones. Right? And here's the thing y'all. I can go back and just say, make this better. Or, you know, I can just say, you know, make, you know, I'm not gonna, I might not wait for this because it might take too long, but I'm gonna say, you know, create better headings, next steps and research, potential solutions for these issues discussed. Right? This is all iterative. Everything I did so far was one shot. I didn't even put a prompt in. Right.
Jordan Wilson [00:36:21]:
It was built into the customer instructions. I just uploaded a document and this was all done for me. Right? So imagine, it looks like it's still, still still rendering here because it's spitting back all of this information in text. So imagine just going through a prompt or two. Right? At that point, that's when you have bespoke software for whatever you do. So then imagine if you have the same type of meeting once a month and it's huge and it's a big part of what you do. You have now a literal personalized piece of software that you can use reliably and consistent consistently every time just by updating it. And that can be your kind of home checkpoint every single day.
Jordan Wilson [00:37:01]:
Maybe that's where you start your work. Right? So very cool. Let's check-in on Claude. Alright. Alright. So Claude, here we go. Surprisingly nice visuals from Claude. Not that that's what I care about the most.
Jordan Wilson [00:37:17]:
Alright. So it says the meta ads performance review. I'm gonna see if the tabs work this time. For whatever reason, when Claude builds tabs, they don't always work. Okay. This time it did. So this one's pretty robust if all this works. Okay.
Jordan Wilson [00:37:31]:
This is nice. Claude probably won this one. Opus 4.5, impressive here. I do want to look though, in the chain of thought here. I wanna see. Alright. I'll have to look at this a little bit more later, because there's a lot of steps. But it did give me a nice overview.
Jordan Wilson [00:37:51]:
It talked about total ad spend, landing page users, all these things, performance benchmark, gave me some nice, nice charts and graph. It kind of okay. This is cool. It kind of labeled people even though we didn't label ourselves. Right? It said Brandon was the marketing lead. George was the ad specialist and myself, the decision maker. It's kind of true how that, meeting was set up. Right? So it did a good job of even understanding who's who based on the the discussion.
Jordan Wilson [00:38:21]:
Right? Same thing. It broke down key discussion topics, issues, great. It it, put them color coordinated. I think Claude definitely won this one. Action plans really, really good. And then let's see what else it did here. Recommendations, really, really good. So, hey, on this one, Claude did crush it.
Jordan Wilson [00:38:42]:
So Opus 4.5, impressive. Whereas on our demo, last week, it kind of missed this, missed the mark. I said, don't, don't write off my one, you know, little show here, kind of redeemed itself a little bit. Alright. So that is a wrap. I wanted to do a couple. I didn't want this to turn into an hour long show. So here's, here's the reality y'all.
Jordan Wilson [00:39:03]:
This is the future of work. It is demos over memos. All right. And, I think you, hopefully, if you saw this, you can understand the potential and why, you know, when I said a year ago that by the 2025, everyday non technical people are gonna be building themselves micro apps. They're gonna be building themselves little pieces of software. You saw me do it just by combining two simple things. Right? Custom instructions with any type of data or documents. And that's something that we can all do regardless of your role.
Jordan Wilson [00:39:38]:
If you sit in front of a computer for the majority of your day, if you are a knowledge worker on the internet, you can do what I just did. It's very simple. You don't have to know anything. All you gotta do, well, you gotta go share this show. Alright. So, I will send you over, the custom instructions. You might wanna tweak them a little bit yourself. You can read through them, but go repost this show on LinkedIn.
Jordan Wilson [00:40:00]:
Alright. So if if you are listening on the podcast, I always put the LinkedIn link for this very show. Alright? So like I said, go find episode six six fifty six sixty five on LinkedIn. Repost it. Give me, a couple hours, couple of days, and I'll send these custom instructions over to you, and you can get going right away. So that is it. That is putting AI to work on Wednesdays and the beginner's guide to how to visualize data with AI in chat, GPT, Gemini, and Claude. I hope this was helpful.
Jordan Wilson [00:40:29]:
If so, tell someone about it, then go to our website, youreverydayai.com. Thanks for tuning in. Hope to see you back tomorrow and everyday for more everyday AI. Thanks, y'all.