WEBVTT
00:00:00.880 --> 00:00:04.799
One of the most common questions I get is how I use AI every day.
00:00:04.959 --> 00:00:08.480
So on today's episode, I'm gonna tell you everything.
00:00:08.640 --> 00:00:19.120
And the answer to that question obviously has changed drastically over the years as quickly as the AI offerings themselves have changed, which is all the time.
00:00:19.280 --> 00:00:28.960
But I feel over the last few months at least, my usage has gotten consistent enough that I feel I can make this episode and not have it be obsolete in like two weeks.
00:00:29.199 --> 00:00:40.240
Because after using thousands of AI tools and modes over the years, you might be able to save yourself a few hundred hours and just copy some of my workflows and see what sticks.
00:00:40.399 --> 00:00:53.200
So on today's show, I'm going to give you a little behind the scenes on not only my nine most used AI tools and workflows, but also maybe some hot takes and trends on AI tool use in general along the way.
00:00:53.439 --> 00:01:02.880
So we're going to go inside everyday AI and go over my nine most used AI tools and workflows that power my day.
00:01:03.119 --> 00:01:04.640
All right, let's get into it.
00:01:04.719 --> 00:01:10.719
On today's show, here's what you're going to learn my nine most used AI tools and workflows.
00:01:10.799 --> 00:01:15.840
Uh, you're gonna know why I sometimes build my own AI tools, and I think you should too.
00:01:16.000 --> 00:01:23.200
And I'm gonna tell you why I'm obviously Codex pilled, yet still using Claude, Gemini, and other tools.
00:01:23.439 --> 00:01:24.719
All right, let's get into it.
00:01:24.879 --> 00:01:26.079
Welcome to Everyday AI.
00:01:26.239 --> 00:01:29.519
If you're new here, my name's Jordan and we do this every day.
00:01:29.599 --> 00:01:30.159
It's for you.
00:01:30.239 --> 00:01:38.079
It's your unedited, unscripted daily live stream podcast and free daily newsletter helping business leaders like you and me not just keep up, but get ahead.
00:01:38.239 --> 00:01:40.000
I tell you what works, what doesn't.
00:01:40.159 --> 00:01:44.640
You take that information, all those saved hours, and you grow your company and your career.
00:01:44.799 --> 00:01:46.560
So if that's what you're trying to do, sweet.
00:01:46.719 --> 00:01:47.359
Starts here.
00:01:47.439 --> 00:01:53.760
Make sure if you haven't already, please subscribe to the podcast and then go to our website at your everydayai.com.
00:01:53.840 --> 00:01:56.400
Uh, the website is also always in our show notes there.
00:01:56.560 --> 00:02:05.040
We're gonna be recapping the highlights from today's episode and giving you all the AI news and developments you need to know to stay ahead.
00:02:05.359 --> 00:02:08.159
All right, we'll see if this one sticks, right?
00:02:08.319 --> 00:02:08.879
Watch.
00:02:09.039 --> 00:02:11.280
Uh watch later today.
00:02:11.360 --> 00:02:12.479
Obviously, it's Thursday.
00:02:12.639 --> 00:02:14.240
Big releases always come out on Thursday.
00:02:14.319 --> 00:02:15.360
Watch everything change today.
00:02:15.520 --> 00:02:30.240
But um, I feel for the and honestly, for the first time in a very long time, uh, you know, my my usage in terms of uh AI tools has not completely changed, you know, in in three months, right?
00:02:30.319 --> 00:02:32.159
It's been fairly consistent.
00:02:32.400 --> 00:02:39.919
And some of those reasons is because I think there's, you know, one harness that will not be dethroned anytime soon.
00:02:40.080 --> 00:02:54.240
And kind of the move, you know, going from um, you know, AI that was mainly web-based uh to AI that lives on your desktop and agents that live on your desktop, I think it made the uh maybe the the models less important.
00:02:54.479 --> 00:03:03.120
I think it maybe made some of the modes, you know, like your deep research and your, you know, plugins and artifacts, all these things.
00:03:03.199 --> 00:03:05.599
I think it made those things a little less important.
00:03:05.840 --> 00:03:12.400
Um, and honestly, between the the models and the modes, I think there's actually a bit of parity.
00:03:12.560 --> 00:03:13.280
Um, right.
00:03:13.439 --> 00:03:17.919
Whereas maybe two years ago when a new model came out, it was such a big gap.
00:03:18.000 --> 00:03:19.919
It was like first place and second place.
00:03:20.080 --> 00:03:26.560
Now, uh at least recently, between OpenAI and Anthropic, it's usually one A and one B, and then they flip-flop, right?
00:03:26.639 --> 00:03:35.840
Um, but the harness itself, um, and this is why I think my my usage has been so consistent probably since February, um, has made all the difference.
00:03:36.000 --> 00:03:42.479
So before I go into my nine most used tools and workflows, a little precursor first.
00:03:42.639 --> 00:03:49.280
Speaking of the um the harness, I'm obviously codex pilled.
00:03:49.520 --> 00:03:53.360
If you've been listening to the show at all since February, I've been saying this.
00:03:53.520 --> 00:03:58.639
I've called it, I said Claude Code, it's it's gonna lose its lead, right?
00:03:58.800 --> 00:04:00.719
Uh, obviously, hats off to Anthropic.
00:04:00.960 --> 00:04:14.879
They really kicked off the agenc desktop era uh with Claude Code Desktop in December, followed up by Claude Cowork uh in January, but they've just been getting smoked and it's not even close in February.
00:04:15.039 --> 00:04:21.680
And you know, I always, I always will use the best overall tool no matter what, right?
00:04:21.839 --> 00:04:31.839
And you know, throughout the the years, I've had the most expensive plans to, you know, I was on the Perplexity$200 plan, you know, using their uh computer.
00:04:32.079 --> 00:04:37.839
I've I've been on the Google Ultra plan, I think when it was like$300 a month or whatever it used to be.
00:04:37.920 --> 00:04:44.000
Um, you know, I currently have a Claude uh, you know, 200 Max and an OpenAI 200 Max plan.
00:04:44.240 --> 00:04:45.759
So I've used them all, right?
00:04:45.839 --> 00:04:48.560
And I still use all of them to this day.
00:04:48.720 --> 00:04:53.680
Um, but the majority of my time now is really in codex.
00:04:54.079 --> 00:04:55.920
Um, it isn't a league of its own.
00:04:56.079 --> 00:05:05.199
I don't think um, you know, cursor uh will catch them, although I am glad that cursor added uh, you know, some simple Google connectors uh this week.
00:05:05.279 --> 00:05:07.120
I don't think Claude uh will catch.
00:05:07.439 --> 00:05:12.079
And also I want you to first think about your workflow.
00:05:12.240 --> 00:05:29.439
And the reason why I say those things is because I know our audience, you know, yes, there's obviously very technical people, there's builders who listen to this show, but for the most part, our audience is, you know, non-technical business leaders who are doing um, you know, non-technical work, right?
00:05:29.519 --> 00:05:32.000
So that's where my lens is coming through this.
00:05:32.160 --> 00:05:37.839
So, you know, if if you're just like as an example, software developer, maybe Claude Code is is best, right?
00:05:37.920 --> 00:05:39.519
Or maybe cursor is best.
00:05:39.680 --> 00:05:48.879
Um, but if you are someone that is, you know, not just 100% writing code, uh, codecs, like I said, in a league of its own.
00:05:49.040 --> 00:05:51.439
And I don't see it being caught anytime soon.
00:05:51.600 --> 00:05:56.720
Okay, so with that out of the way, I do want you to know that this is just based on my own workflows as well.
00:05:56.879 --> 00:05:59.680
Your usage is obviously going to vary and keep that in mind, right?
00:05:59.759 --> 00:06:01.519
So take that with a giant grain of salt.
00:06:01.600 --> 00:06:12.319
Uh, this isn't definitive, but I would say for the average non-technical AI user, like I'm saying, steal for my thousands of hours over the years of using all these tools.
00:06:12.560 --> 00:06:16.480
What I'm saying, sh, am I, you know, do I have a preference?
00:06:16.639 --> 00:06:17.120
Absolutely.
00:06:17.360 --> 00:06:18.720
Am I telling you the truth?
00:06:18.879 --> 00:06:19.279
Yes.
00:06:19.439 --> 00:06:19.759
All right.
00:06:19.839 --> 00:06:21.199
So just getting that out of the way.
00:06:21.360 --> 00:06:25.120
Also, another thing to keep in mind, my usage has really shifted.
00:06:25.199 --> 00:06:29.519
Uh, right, back in January, I was probably only 10% desktop, right?
00:06:29.600 --> 00:06:36.319
Because the only big desktop player at the time was uh, you know, cursor um and clawed code, right?
00:06:36.399 --> 00:06:40.319
So I was using clawed code about 10% of the time, and everything else was on the web.
00:06:40.480 --> 00:06:42.959
Obviously, today that's complete opposite.
00:06:43.040 --> 00:06:47.360
So today I'm like 90% using everything um on the desktop.
00:06:47.519 --> 00:06:55.519
So that's mainly codecs, but also using clawed code, clawed cod, uh, you know, cursor, anti-gravity, Gemini on the desktop, right?
00:06:55.600 --> 00:06:59.920
For the most part, I am desktop agenc harness through and through, right?
00:07:00.000 --> 00:07:02.879
Even for non-technical knowledge work, that's what I'm using.
00:07:03.040 --> 00:07:12.000
Um, but like I said, I'm really only using you know, Claude and Gemini desktop, anti-gravity cursor, so I understand them, right?
00:07:12.079 --> 00:07:13.279
So I have a comparison.
00:07:13.360 --> 00:07:20.319
And so when I tell you, yeah, codex slaps everyone else, that comes from facts, not just like a preference, right?
00:07:20.399 --> 00:07:23.519
So anytime there are new updates, I'm always using them, I'm always testing them.
00:07:23.759 --> 00:07:31.199
I'm, you know, doing some of my own uh, you know, internal benchmarks and use cases, so I know what's best for different types of work.
00:07:31.360 --> 00:07:40.319
Um, the the other thing to know is I am very bullish on agent control and agent co-working.
00:07:40.399 --> 00:07:42.399
And I'm gonna tell you what those things are, right?
00:07:42.480 --> 00:07:49.600
I'm I'm you know, kind of taking you behind the scenes here at everyday AI and in how I work and you know how we kind of run things.
00:07:49.839 --> 00:07:56.079
Um, but one thing to keep in mind is um not everyone can work like this either.
00:07:56.160 --> 00:08:00.160
Um, and I'm not saying that from a skills perspective because it's not difficult.
00:08:00.319 --> 00:08:03.360
I'm just saying from a data and permissions perspective, right?
00:08:03.519 --> 00:08:10.079
I am having agents literally running around the clock doing everything on my computer, full control, full YOLO mode.
00:08:10.160 --> 00:08:11.439
I know that's not for everyone, right?
00:08:11.519 --> 00:08:19.519
If you work at a big enterprise, even if you've gotten permission to use Claude Desktop or Codex, you may not be able to do a lot of these things.
00:08:19.680 --> 00:08:21.600
Um, so keep that in mind.
00:08:21.759 --> 00:08:31.279
But if you are a small business owner or if your company has taken off all restraints and you can just do whatever you want, well, let's let's have some fun.
00:08:31.439 --> 00:08:32.080
All right, here we go.
00:08:32.159 --> 00:08:33.600
I'm not gonna make you wait any longer.
00:08:33.759 --> 00:08:39.440
Here's my nine most used AI tools and workflows, and then we're gonna dive into each one individually, uh individually.
00:08:39.600 --> 00:08:43.759
So number one, I have my third shift stats agent.
00:08:43.919 --> 00:08:47.679
Uh, number two, I have my third shift comms triage.
00:08:47.840 --> 00:08:52.000
Uh, number three, I have my chat GPT sites to iMessage.
00:08:52.080 --> 00:08:54.080
Yeah, that one's a little uh specific.
00:08:54.320 --> 00:08:57.919
Number four, I have my parrot dictation app that I built.
00:08:58.000 --> 00:09:01.519
Uh number five, I have my episode planning research.
00:09:01.759 --> 00:09:04.080
Number six, my AI app design.
00:09:04.240 --> 00:09:10.320
Number seven, uh Gemini Notebook Study, also previously known as Notebook LM.
00:09:10.399 --> 00:09:12.559
So did a show on that uh yesterday.
00:09:12.720 --> 00:09:15.360
Uh, number eight, codex skill building.
00:09:15.440 --> 00:09:19.679
And number nine, remote chat GPT walk and talk.
00:09:19.840 --> 00:09:21.840
All right, let's get into it.
00:09:22.320 --> 00:09:26.159
Number one, third shift agents for stats.
00:09:26.320 --> 00:09:26.639
All right.
00:09:26.799 --> 00:09:29.360
First, let me describe what third shift agents are.
00:09:29.519 --> 00:09:32.720
Uh well, they're agents that work third shift, right?
00:09:32.799 --> 00:09:39.440
Uh, usually I'm up working fairly late, but let's just say my agents usually work about 11 to 5, right?
00:09:39.600 --> 00:09:40.639
Every single night.
00:09:40.720 --> 00:09:42.879
Uh, a lot of things are scheduled.
00:09:43.039 --> 00:09:52.639
Um, and then I will also usually give it my toughest problem or set of problems to codex um every single night, kind of before I go to bed.
00:09:52.799 --> 00:09:56.480
I'll use subagents, I'll use goal mode, I'll use plan mode.
00:09:56.639 --> 00:09:56.960
All right.
00:09:57.120 --> 00:10:02.159
And if you're wondering, like what the heck is all of that stuff, um, we did an episode.
00:10:02.240 --> 00:10:03.919
Let me bring up the number.
00:10:04.080 --> 00:10:06.480
Uh, let me bring up the number on that one.
00:10:06.559 --> 00:10:12.720
Uh, it was number, come on, there it is.
00:10:12.799 --> 00:10:24.799
Uh, episode 806, part of the start here series where we went over desktop agent lingo simplified, talking about goals, loops, plans, sub agents, and how those work in codex and clawed code.
00:10:24.879 --> 00:10:25.759
So go listen to that one.
00:10:25.840 --> 00:10:33.120
But essentially, uh, my probably most used um AI is not even me, right?
00:10:33.200 --> 00:10:34.080
I set these up.
00:10:34.240 --> 00:10:35.600
It happens third shift.
00:10:35.759 --> 00:10:38.399
My agents are working, you know, 11 to 5.
00:10:38.480 --> 00:10:40.639
Um, and then I wake up to things that are done.
00:10:40.799 --> 00:10:44.639
So let me tell you specifically what my third shift stats agents are.
00:10:44.799 --> 00:10:48.480
And again, I want you to think what just because I'm doing mine, right?
00:10:48.639 --> 00:10:52.559
Don't try to, you know, make my workflow fit your work.
00:10:52.799 --> 00:10:55.679
Instead, just see the path that I'm taking and apply it to yours.
00:10:55.840 --> 00:11:13.519
Okay, so essentially, inside, well, even on the web, but also on the desktop, uh, there's certain, you know, pieces of software or apps that you use that connect really nicely to ChatGPT, uh, Claude, Gemini, uh, Copilot, etc.
00:11:13.679 --> 00:11:15.200
And then there's some that don't.
00:11:15.360 --> 00:11:23.039
So for me, for everything that doesn't, right, it needs either computer use, browser use, or Chrome.
00:11:23.200 --> 00:11:28.080
Okay, so actually in Codecs and Chat GPT Work, which are literally the same thing, right?
00:11:28.159 --> 00:11:31.519
So I'm using just Codecs because it's just a little cleaner.
00:11:31.679 --> 00:11:34.960
Um, and I usually use Codecs, but you know, it's interchangeable.
00:11:35.039 --> 00:11:41.200
So FYI, when I'm saying Codex, I also mean ChatGPT Work, which if you go to ChatGPT and download it, that's what you're gonna get.
00:11:41.279 --> 00:11:47.039
So you can do these same things in ChatGPT Work, which is the desktop version of Chat GPT, uh, right.
00:11:47.200 --> 00:11:58.559
But there's three different ways that these agents can use your computer in instances where there's not a direct connection or where there's not an MCP or model context protocol server.
00:11:58.720 --> 00:12:02.240
Um, so in my case, right, we use Buzz Sprout.
00:12:02.639 --> 00:12:07.600
So that is, you know, the the the podcast, you know, thanks to you all that listen.
00:12:07.759 --> 00:12:11.039
Um, it's you know downloaded millions of times.
00:12:11.120 --> 00:12:16.559
And essentially, I didn't see this going in when I started the podcast because I'm like, no one's gonna listen.
00:12:16.639 --> 00:12:19.120
And apparently millions of people every year do.
00:12:19.200 --> 00:12:28.879
Um, and so there's just some stats that I really need that just aren't readily available by clicking export or by me going in and pulling up a couple screens on a couple monitors.
00:12:28.960 --> 00:12:40.399
Like I have to do usually about 30 or so minutes of work every single day, just pulling these metrics in, exporting certain things, and it is time consuming and I don't like doing it.
00:12:40.559 --> 00:12:43.759
So this is my uh third shift stats agent.
00:12:43.840 --> 00:12:46.240
So it does uh a lot of comparisons.
00:12:46.399 --> 00:12:48.960
Um, I have you know daily benchmarks, you know.
00:12:49.120 --> 00:12:59.039
So um, as an example, uh, you know, our Wednesdays, AI at Wednesdays, uh, you know, sorry, uh AI at work Wednesdays or working Wednesdays, you know, as we call them, right?
00:12:59.200 --> 00:13:09.120
I know that every single day, you know, Thursday at you know 9 a.m., that shows, you know, should have, like as an example, 11,500 downloads or something like that, right?
00:13:09.200 --> 00:13:13.440
So I know every day that it can go in there, it can see if that is the case.
00:13:13.519 --> 00:13:15.919
Uh it can go look at the last one from last Wednesday.
00:13:16.080 --> 00:13:17.759
Is it still getting a certain number?
00:13:17.919 --> 00:13:27.279
So I have all these kind of formulas that show me not only how popular a show is, but how does it do uh in its normal time slot or in its normal day slot versus others, right?
00:13:27.360 --> 00:13:30.720
For Tuesday and Thursday shows that maybe I don't have recurring shows on.
00:13:30.799 --> 00:13:47.679
Um, so I have all, you know, I had Codex make all these kind of formulas and it goes in, it pulls all these stats, you know, goes look at day day-by-day stats, which I can't export, uh, show me which, you know, shows are from two or three weeks ago are still maybe trending and you know, getting two or three X, what they should be getting at that point.
00:13:47.840 --> 00:13:50.799
So then I know that there's some evergreen appetite in that.
00:13:50.879 --> 00:13:58.960
And automatically I have a skill that if that happens, Codecs is gonna go start uh, you know, researching and find me more information on doing an updated show on that.
00:13:59.039 --> 00:14:00.720
So that's kind of my overnight agent.
00:14:00.799 --> 00:14:05.600
It also pulls information from our newsletter, uh, which we use Beehive.
00:14:05.840 --> 00:14:08.559
So there is a model context protocol server for that.
00:14:08.799 --> 00:14:11.679
But even with that, there are some things that I can't get in there.
00:14:11.840 --> 00:14:16.159
As an example, we run an A-B test on our newsletter every single day.
00:14:16.320 --> 00:14:19.360
In the M in the uh MCP, I can't get that.
00:14:19.440 --> 00:14:20.480
So I have to go in.
00:14:20.639 --> 00:14:26.480
It uses um uh for that, it uses browser control, uh, it goes in, clicks, and finds all those things.
00:14:26.559 --> 00:14:30.399
So I have so many of these tasks that I used to do like right two years ago.
00:14:30.480 --> 00:14:31.919
This is how I would start my day every day.
00:14:32.000 --> 00:14:37.120
Uh, you know, and if if I was very focused, I could get it done in, you know, maybe like an hour.
00:14:37.440 --> 00:14:42.320
Now it's you know, 30 seconds to overview something, which is great.
00:14:42.720 --> 00:14:43.840
One quick thing.
00:14:44.000 --> 00:14:50.320
Um, at least in codex, it's a little different in uh Cloud Code, but in Codex, it's a little better.
00:14:50.480 --> 00:14:52.799
So they have a built-in browser.
00:14:52.960 --> 00:15:03.600
Um, there is Chrome use, and then there's also um a Chrome extension, and those two obviously work hand in hand, and then computer use.
00:15:03.759 --> 00:15:16.320
So, you know, the browser, there's actually a file in uh kind of the Atlas browser was retired into uh Codex, but there's a full-fledged uh Chromium-based browser inside of Codex.
00:15:16.639 --> 00:15:23.039
So um, you know, for many of these things, I do them inside of the browser in Codex and I schedule them and they run overnight.
00:15:23.200 --> 00:15:32.960
Other other times, you know, it might it might need to use a um, as my second one here does, it might need to use Chrome because there's a Chrome extension involved.
00:15:33.039 --> 00:15:34.639
All right, so that's my first one.
00:15:34.960 --> 00:15:40.879
Um, but you know, essentially it just helps me do multiple things at once.
00:15:41.039 --> 00:15:42.639
I don't want to go and click around.
00:15:42.720 --> 00:15:46.639
I don't want to, you know, copy and paste information into spreadsheets.
00:15:46.799 --> 00:15:48.960
I don't want to be running formulas, right?
00:15:49.039 --> 00:15:53.759
I just wake up to an actionable briefing instead of spending my morning assembling one.
00:15:53.919 --> 00:15:54.240
All right.
00:15:54.320 --> 00:15:57.600
Number two, uh again, this is another third shift agent.
00:15:57.679 --> 00:15:59.200
This is my comms triage.
00:15:59.679 --> 00:16:01.759
This one, my gosh, this is helpful.
00:16:01.919 --> 00:16:02.159
All right.
00:16:02.240 --> 00:16:07.519
And one of the reasons is is I have, I don't know how or why.
00:16:07.759 --> 00:16:10.320
Um, I have a personal Gmail.
00:16:10.480 --> 00:16:16.000
Um, I have a Gmail account from my old company Accelerant Agency.
00:16:16.240 --> 00:16:22.399
I have a Gmail, and then I have two different Gmail accounts um for everyday AI.
00:16:22.559 --> 00:16:25.360
And for whatever reason, people find all of them.
00:16:25.440 --> 00:16:27.039
Maybe they're connected to LinkedIn.
00:16:27.120 --> 00:16:27.600
I don't know.
00:16:27.840 --> 00:16:29.279
I get spammed all the time, right?
00:16:29.360 --> 00:16:42.399
We get, I don't know, more than a thousand people each and every year, you know, pitching to be a guest on the show, people reaching out about spot uh sponsorships, partnerships, most of those I don't pay attention to, uh, you know, collaborations, whatever.
00:16:42.480 --> 00:16:45.840
Uh, so there's a lot of those, and then also LinkedIn, right?
00:16:46.080 --> 00:16:49.200
Um, this podcast goes out on LinkedIn every single day.
00:16:49.279 --> 00:16:50.960
Uh, so people message me all the time.
00:16:51.120 --> 00:16:54.159
Sometimes I ask people to message me ideas, those kind of things.
00:16:54.240 --> 00:16:56.320
Um, it's always me responding, right?
00:16:56.480 --> 00:16:59.039
But I do have agents go in and triage these things.
00:16:59.120 --> 00:17:14.000
So my second one is the uh codecs triaging all of those things and telling me what's important, what I need to get to, and then also giving me draft responses so I don't just have to sit at a blank stare email, right?
00:17:14.079 --> 00:17:18.160
Um, and usually, at least within codecs, I have these things set up within projects.
00:17:18.319 --> 00:17:27.599
So in each of these projects, um, you know, there's a markdown file that I can change very easily, update very easily, that give a set of directions to these things.
00:17:27.680 --> 00:17:29.519
So it can work with all my context.
00:17:29.599 --> 00:17:35.200
Uh, you know, I can give kind of custom instructions uh to each of these different uh, you know, projects.
00:17:35.279 --> 00:17:46.720
Uh, but this is good because, you know, in most um AI systems, you know, Gemini Claude, ChatGPT, um, Copilot, you can only really work with one email connected.
00:17:46.880 --> 00:17:48.480
Um, so this one's really helpful for me.
00:17:48.640 --> 00:17:56.160
The way that I pull this off is I, you know, just over time, I use the codex uh record and replay skill a lot.
00:17:56.319 --> 00:17:58.960
But um, even this one, it's it doesn't always work.
00:17:59.119 --> 00:18:01.359
So I've had to really refine it over the years.
00:18:01.519 --> 00:18:10.160
But essentially I have it launch Chrome profiles um and go to you know gmail.com uh for uh LinkedIn messages, right?
00:18:10.240 --> 00:18:13.599
I don't automate anything on LinkedIn because I don't want to get my LinkedIn banned.
00:18:13.680 --> 00:18:21.279
Uh so I do have a uh an extension in LinkedIn uh called um condo, essentially.
00:18:21.440 --> 00:18:25.519
So I have um it just syncs all my you know LinkedIn messages.
00:18:25.599 --> 00:18:26.880
It's a little quicker to go through.
00:18:26.960 --> 00:18:29.359
Uh the LinkedIn inbox is so slow.
00:18:29.519 --> 00:18:44.319
Um, so essentially I have a skill go in, it opens up a certain Chrome profile, it goes to LinkedIn.com, clicks on messages, that opens up a dedicated tab that has that Chrome extension that I need, which is why I do it through Chrome and not through the built-in browser.
00:18:44.400 --> 00:18:49.039
Uh, and then it can kind of go in, look at all my unreads, triage, find information there.
00:18:49.200 --> 00:18:50.799
So uh that's my second one.
00:18:50.880 --> 00:18:54.720
So essentially I can wake up every single day, I know every single stat, right?
00:18:54.799 --> 00:18:56.400
We put out a ton of content every day.
00:18:56.559 --> 00:19:02.880
We put so much effort into planning the shows, into how we deliver them, um, into the newsletter.
00:19:03.039 --> 00:19:08.880
And, you know, if I didn't have any guidance, I would just be guessing in the dark.
00:19:09.039 --> 00:19:09.599
Um, right.
00:19:09.680 --> 00:19:21.599
So it's great every day to have that in for my uh, you know, my my my third shift uh agents to have, you know, here's here's what performed well, um, you know, above average, below average.
00:19:21.680 --> 00:19:27.920
And then from a comms perspective, I don't have to go in and check, you know, four different emails and go into LinkedIn.
00:19:28.079 --> 00:19:29.440
It's all just there for me.
00:19:29.759 --> 00:19:30.400
All right.
00:19:30.880 --> 00:19:34.799
Next, uh ChatGPT sites to iMessage.
00:19:34.960 --> 00:19:35.359
All right.
00:19:35.519 --> 00:19:37.119
This one is great.
00:19:37.359 --> 00:19:42.559
Um, if you're not using Chat GPT sites, you are missing out.
00:19:42.720 --> 00:19:52.559
Um, Entropic has a similar um a similar uh kind of option called artifacts, and there's live artifacts.
00:19:52.720 --> 00:19:55.359
I think there's great use cases for live artifacts.
00:19:55.519 --> 00:20:10.480
The reason why I still prefer sites is it's a full, like lovable uh right, if you've used lovable, basically anything you can do inside like lovable or bolt or any of those uh kind of vibe coding, full, you know, almost like replit as well.
00:20:10.559 --> 00:20:12.400
That's what ChatGPT sites is.
00:20:12.559 --> 00:20:14.720
I still think it is criminally underrated.
00:20:14.799 --> 00:20:15.279
It is so good.
00:20:15.359 --> 00:20:19.599
So there's so many things that you can do inside ChatGPT sites that you can't do in Claude Artifacts, right?
00:20:19.759 --> 00:20:22.640
One of those things is just better permissions.
00:20:22.720 --> 00:20:28.480
So you can make things uh public, you can force login via ChatGPT, you can share things with your team.
00:20:28.559 --> 00:20:33.440
Uh not quite as robust um inside Claude Artifacts.
00:20:33.519 --> 00:20:43.839
Um, but what I love doing in this case is I have templates and skills that I've saved that make sites uh just really easy to use on my phone.
00:20:44.000 --> 00:20:47.200
So there's certain uh criteria, both from a design perspective.
00:20:47.440 --> 00:20:49.839
I always have it built in light and dark mode.
00:20:49.920 --> 00:20:57.680
Uh, I always have it build in uh a font where you can make it larger and smaller, and then I always have it built in uh kind of like a bookmark thing.
00:20:57.759 --> 00:21:06.480
So, you know, all these agents, when they do report these things to me, um, yes, it will be in line, but and oftentimes I just have them update a pre-existing site.
00:21:06.640 --> 00:21:09.759
And then what I do is I save those sites to my phone.
00:21:09.839 --> 00:21:13.359
So it's almost like I have agents updating these apps.
00:21:13.519 --> 00:21:16.880
The great thing about ChatGPT sites is it has databases.
00:21:16.960 --> 00:21:18.640
Um, it's like read write.
00:21:18.720 --> 00:21:26.400
So I can, you know, I have one that's like a little uh, you know, basic CRM, and I can, you know, just open my phone every morning, see what's new.
00:21:26.480 --> 00:21:27.359
I didn't do anything.
00:21:27.440 --> 00:21:37.279
It's just like literally I have agents, you know, grabbing all this information, running it through my personal context, updating the quote unquote apps or chat GPT sites that I use.
00:21:37.440 --> 00:21:42.480
Um, and then if it's a new one, it sends it to me through iMessage and it sends it to my phone, right?
00:21:42.559 --> 00:21:43.440
Uh, which is great.
00:21:43.519 --> 00:21:44.400
Yeah, people don't know.
00:21:44.480 --> 00:21:47.839
It's like that's a you know, it's actually a decent way, right?
00:21:48.000 --> 00:21:56.240
I just tell it to go check text messages from Jordan and I give it, you know, explicit, uh, you know, say, hey, it's okay to text Jordan, Jordan only.
00:21:56.480 --> 00:21:59.519
Um, it's actually one of my uh agent MD um.
00:22:00.480 --> 00:22:06.640
Uh, kind of instructions that go over all of my projects where it says, Hey, you can open iMessage and text Jordan, no one else.
00:22:06.799 --> 00:22:08.319
All right, so that's the other one.
00:22:08.400 --> 00:22:16.720
Uh, I love this because I just get that continually updated personal apps without having to, you know, rebuild or maintain them.
00:22:17.519 --> 00:22:18.160
All right.
00:22:18.400 --> 00:22:19.759
Uh, next one.
00:22:19.920 --> 00:22:24.880
I've never I've referenced this like once, but I've never really talked about Parrot.
00:22:25.279 --> 00:22:27.680
Okay, so this is uh one that I built.
00:22:27.759 --> 00:22:35.119
And let me just tell you why I built Parrot, um, why I think it's better than other alternatives and how I use it.
00:22:35.279 --> 00:22:37.680
Um, so Parrot is awesome.
00:22:37.839 --> 00:22:39.599
It's one of the first apps that I built.
00:22:39.759 --> 00:22:41.680
I use it literally every single day.
00:22:41.839 --> 00:22:48.880
Um, if you ever see me, you know, do screen recordings uh, you know, on Wednesday shows, a lot of times, you'll see a little green dot at the bottom.
00:22:48.960 --> 00:22:50.640
Sometimes that's parrot that's open.
00:22:50.799 --> 00:22:56.720
I usually try to like turn it off before I start in case I accidentally hit my dictation key, but a lot of times you'll see it on there.
00:22:56.880 --> 00:23:04.880
So if you've used something like um Whisperflow or Super Whisper, there's all these you know platforms that you know they're good.
00:23:04.960 --> 00:23:08.880
Uh, but the cloud-based ones for me are just too slow, right?
00:23:08.960 --> 00:23:11.359
Even Whisperflow, I'd say, is the leader out there.
00:23:11.440 --> 00:23:13.920
It's too slow, it's not always accurate.
00:23:14.079 --> 00:23:17.920
Um, and there's just features that just don't fit my workflow.
00:23:18.000 --> 00:23:20.559
And there's features that I want that aren't there.
00:23:20.799 --> 00:23:24.160
So I essentially built my own version that I think is much better.
00:23:24.319 --> 00:23:28.400
Um, I built this with both uh Claude and with Codex.
00:23:28.880 --> 00:23:31.279
And it's essentially it runs locally.
00:23:31.359 --> 00:23:36.960
So there's nothing in the cloud, it's stored locally on my computer, and that makes it much faster, right?
00:23:37.039 --> 00:23:47.200
I encourage everyone if you want a fun little uh you know project to build and you're feeling somewhat ambitious, uh, you know, build a local uh dictation LLM.
00:23:47.279 --> 00:23:48.559
So yeah, you don't need internet.
00:23:48.799 --> 00:23:53.759
Um, you know, just tell ChatGPT exactly, or you know, codex or cloud code exactly what you're trying to do.
00:23:53.920 --> 00:24:02.720
Um, in this case, it, you know, finds the best text-to-speech uh or sorry, speech to text dictation model, you know, downloads it.
00:24:02.799 --> 00:24:04.960
Um, but yeah, like for me, why I use this.
00:24:05.119 --> 00:24:07.599
Well, number one, it's faster, there's no lag.
00:24:07.759 --> 00:24:10.319
So I do like whisper flow, but there's a lag.
00:24:10.400 --> 00:24:14.720
Um, and then I thought, like, why should I have to send all this to the cloud if I don't need to?
00:24:14.880 --> 00:24:23.359
Uh also codex has great transcription and you can actually, people don't know this, you can use it anywhere, not just in codex, but then the same thing.
00:24:23.519 --> 00:24:27.279
It like Whisperflow, you know, it's there's still a little bit of a lag.
00:24:27.440 --> 00:24:36.400
So when I'm I obviously talk a lot um and I dictate a lot, I don't want to wait a half second or a second for longer dictations.
00:24:36.559 --> 00:24:38.079
I need to go immediately.
00:24:38.160 --> 00:24:40.799
Um, but then I have all these other things that I built into it.
00:24:40.880 --> 00:24:55.359
So, as an example, um, I can type in any YouTube channel um and it's going to every single time that there's a new uh video, so you know, I can have the open AI, anthropic, right?
00:24:55.680 --> 00:25:12.079
Anything, any big company, you know, any other um, you know, AI YouTubers out there, you know, I don't have time to watch anything, but if I want to know what people are talking about, it is literally every single video that comes out, it's gonna automatically transcribe as long as I have the program open.
00:25:12.240 --> 00:25:21.039
And then I have a scheduled skill inside Codex that goes and it looks at all those transcriptions every single day and it just gives me a little brief.
00:25:21.119 --> 00:25:24.079
Here's what everyone on YouTube is talking about, right?
00:25:24.240 --> 00:25:27.599
I used to like three years ago, especially when I was getting started.
00:25:27.759 --> 00:25:31.440
I probably spent like 30 to 45 minutes every day on YouTube.
00:25:31.680 --> 00:25:34.400
Uh, you know, obviously watching at like 2.5x.
00:25:34.559 --> 00:25:36.160
I don't have time to do that anymore.
00:25:36.319 --> 00:25:38.240
Um, you know, it's it's distracting.
00:25:38.319 --> 00:25:39.119
I just don't have the time.
00:25:39.200 --> 00:25:42.240
So I'd much rather just get, you know, a sites report.
00:25:42.400 --> 00:25:43.680
Here's what everyone's talking about.
00:25:43.759 --> 00:25:45.200
Here's the bullet points, right?
00:25:45.279 --> 00:25:45.920
It's perfect.
00:25:46.079 --> 00:25:47.440
So that's uh parrot.
00:25:47.599 --> 00:25:51.519
It's probably my most used uh app that I built myself.
00:25:51.839 --> 00:25:52.400
All right.
00:25:52.640 --> 00:25:56.880
Uh next I have my daily episode planning deep research.
00:25:56.960 --> 00:25:57.279
All right.
00:25:57.440 --> 00:26:02.400
So this is one of the few things, if I'm being honest, that I still use Gemini for.
00:26:02.480 --> 00:26:05.279
Uh, but let me tell you a little bit on how this works.
00:26:05.440 --> 00:26:09.200
So again, this is running from Codecs because it's the only one that can handle this.
00:26:09.279 --> 00:26:15.119
Uh, but a lot of times I save uh Twitter posts uh on my phone, so I bookmark them, right?
00:26:15.200 --> 00:26:23.599
So if I'm walking from here to there, uh, you know, um whatever, at night, in the morning, you know, quick save things.
00:26:23.759 --> 00:26:27.039
Um, so I save a lot of posts on Twitter.
00:26:27.119 --> 00:26:28.640
Uh another signal, right?
00:26:28.720 --> 00:26:30.480
So it's all these signals that I'm looking at, right?
00:26:30.559 --> 00:26:31.519
Like, what are people talking about?
00:26:31.680 --> 00:26:32.240
What's breaking?
00:26:32.319 --> 00:26:33.039
What's trending?
00:26:33.200 --> 00:26:35.359
Similarly, the same thing on Beehive.
00:26:35.519 --> 00:26:37.200
So that is our email newsletter.
00:26:37.359 --> 00:26:44.480
Uh, so again, I know, like on our AI news section, if I put something in, you know, spot three, it should get this many clicks.
00:26:44.559 --> 00:26:49.920
If it gets above or below, I know that story either people don't care about or they care about it a lot.
00:26:50.559 --> 00:26:56.400
Um, and then um, so I essentially take those signals every single day.
00:26:56.559 --> 00:27:06.160
Um, Codex goes in, it opens a new browser instance, it goes to chatgbt.com, it goes to claw.ai, it takes all that information, right?
00:27:06.319 --> 00:27:10.640
Not just the save posts, um, right, but um, you know, replies.
00:27:10.720 --> 00:27:14.480
I have it kind of do a sentiment analysis on anything that I save.
00:27:14.559 --> 00:27:16.720
And then I have it take all of that information.
00:27:16.960 --> 00:27:20.400
Codex is the kind of uh the agent orchestrator, not me.
00:27:20.480 --> 00:27:21.200
Isn't that weird?
00:27:21.359 --> 00:27:27.680
I thought it'd be humans, the ones that were orchestrating agents, but for me, it's actually codex that's orchestrating agents more than I do.
00:27:27.839 --> 00:27:39.599
So it takes all of that information, um, it sends it to both uh ChatGPT, uh Deep Research, Claw Deep Research, and Gemini Deep Research, um, you know, to help me plan episodes.
00:27:39.680 --> 00:27:53.440
So essentially I say, you know, go find me, you know, five episodes, you know, go find all the information, you know, you choose whatever I bookmarked, whatever is, you know, well above the normal click-through rate um inside Beehive.
00:27:53.759 --> 00:27:56.960
Go, go do that in uh, you know, ChatGPT Claude Gemini.
00:27:57.200 --> 00:27:58.559
Uh, take all that information.
00:27:58.640 --> 00:28:03.119
And then I have another skill that helps me start bullet pointing and planning out different shows.
00:28:03.279 --> 00:28:03.759
All right.
00:28:04.079 --> 00:28:06.720
So now let's go to number six.
00:28:07.039 --> 00:28:11.519
This is uh kind of front-end design for vibe-coded apps.
00:28:11.680 --> 00:28:14.880
So I don't build as much as I'd like to, right?
00:28:15.039 --> 00:28:20.000
If I didn't have uh a daily podcast, I might build a little bit more, right?
00:28:20.079 --> 00:28:24.720
But I still, like I said, I have Parrot, uh, I have another one I built called Planadoro.
00:28:25.279 --> 00:28:27.359
Uh, I have what do I have open on my computer here?
00:28:27.519 --> 00:28:28.720
Codecs reset watcher.
00:28:28.880 --> 00:28:33.039
I have a lot of like just codex tools that I built that help me use codecs a little better, right?
00:28:33.119 --> 00:28:35.599
But I have all these things, but I don't want them to be ugly.
00:28:35.839 --> 00:28:39.839
So uh this is something if you spend a little bit of time on the front end, right?
00:28:39.920 --> 00:28:42.319
For even if it's a throwaway app, right?
00:28:42.400 --> 00:28:44.319
I build intentional throwaway apps.
00:28:44.480 --> 00:28:51.680
Um, you know, like I said, if I have a little project, I'll build a little Kanban, uh, you know, or I'll build a little app for a project that I'm working on.
00:28:52.079 --> 00:28:57.920
Um, so in those cases, it's like, well, it needs to look good uh because I'm not gonna build something and have it be ugly.
00:28:58.000 --> 00:29:00.079
So in that case, uh kind of three tools.
00:29:00.240 --> 00:29:04.799
This is just kind of like a three in one here, because I use them sometimes interchangeably, sometimes together.
00:29:04.960 --> 00:29:06.480
So that's clawed design.
00:29:06.559 --> 00:29:07.759
Uh love clawed design.
00:29:07.839 --> 00:29:10.640
It is, I think, probably their most unique product.
00:29:10.799 --> 00:29:15.119
Um, so I love using claw design, Google Stitch, and GPT image.
00:29:15.359 --> 00:29:20.400
So using a combination of those uh just to create uh different front ends, right?
00:29:20.480 --> 00:29:33.279
So usually I'll have a couple pieces of inspiration, either things I've previously designed or just designs that I really uh think are good, and I'll put them into, you know, claw design, Google Stitch or GPT image.
00:29:33.359 --> 00:29:37.200
I'll dictate what I'm trying to do, what I'm trying to build, um, and get different outputs.
00:29:37.359 --> 00:29:41.200
So claw design uh doesn't do visuals, but it does great, right?
00:29:41.440 --> 00:29:44.000
Mockups, it does great slides, etc.
00:29:44.319 --> 00:29:47.359
Uh Google Stitch does great at mock-ups, right?
00:29:47.440 --> 00:29:52.720
It also can use uh nano banana, so it can do images, uh, it can do website everything.
00:29:52.799 --> 00:29:56.400
And then GBT image um obviously can do that as well.
00:29:56.480 --> 00:30:01.119
Uh the thing I like really probably a little bit more Google Stitch than Claude.
00:30:01.200 --> 00:30:03.839
So, Claude, you can like export things to Claude code.
00:30:03.920 --> 00:30:08.000
It doesn't really work because in most instances it just sends HTML, which is not the best.
00:30:08.160 --> 00:30:16.160
Um, I actually like using Google Stitch for that because you can then export the entire code of what it builds uh to like Google AI Studio.
00:30:16.240 --> 00:30:18.559
Um, and then from there you can do pretty much anything with it.
00:30:18.640 --> 00:30:28.559
So this is just when I'm building front ends, whether it's for you know making changes, uh a design system for a new app, um, whatever it may be.
00:30:28.720 --> 00:30:31.680
Uh, these are the kind of my my three ones that I use.
00:30:32.079 --> 00:30:32.720
All right.
00:30:33.039 --> 00:30:36.720
Uh next, this is number seven, Gemini Notebook study.
00:30:36.880 --> 00:30:38.799
You all know I just did a show yesterday.
00:30:39.039 --> 00:30:45.359
I use what was formerly known as Notebook LM, uh now known as Gemini Notebook all the time.
00:30:45.599 --> 00:30:47.200
Almost every single day.
00:30:47.359 --> 00:30:50.400
Sometimes, depending on the day, I might spend multiple hours.
00:30:50.480 --> 00:30:51.039
Um, right.
00:30:51.200 --> 00:30:53.200
I like, even if I don't, this sounds bad.
00:30:53.359 --> 00:30:58.960
I don't always listen um or use everything that Gemini Notebook makes me.
00:30:59.039 --> 00:31:00.640
It just depends on if I have time.
00:31:00.799 --> 00:31:06.799
But for the most part, um, I'll have it making me multiple assets every single day.
00:31:07.039 --> 00:31:14.640
Um, so audio overviews, uh, custom, you know, slide decks, things like that based on well, anything.
00:31:14.799 --> 00:31:16.960
A lot of times it's around episode planning.
00:31:17.039 --> 00:31:20.000
Uh, I do actually put a ton of work into episode planning.
00:31:20.079 --> 00:31:22.240
Uh, ones like this, not as much, right?
00:31:22.319 --> 00:31:26.559
Uh, aside from my nice uh, you know, GPD image codex design slides here.
00:31:26.640 --> 00:31:29.759
Um, but I'm using Gemini Notebook all the time.
00:31:30.000 --> 00:31:34.720
Uh so kind of like um what I talked about earlier, how I do all these deep researches.
00:31:34.880 --> 00:31:45.519
Um, I have Codex go and take these signals uh from you know Twitter, from our newsletter, uh, run deep research on that kind of sentiment uh analysis.
00:31:45.680 --> 00:31:48.160
Um and then next I'll have a skill.
00:31:48.240 --> 00:31:56.880
So this is kind of like the combination or the continuation of that, where Codex pulls all that and it creates custom uh notebooks um for me.
00:31:57.119 --> 00:32:07.279
So yeah, um custom deep dives, audio deep dives, um uh reports, I mean infographics, especially if it's like I'm learning a new subject, right?
00:32:07.440 --> 00:32:10.559
Some sometimes I'm learning at the same rate as everyone else, right?
00:32:10.640 --> 00:32:17.279
Like when something new comes out, it's like you know, learning about you know, loops and subagents and all these other things, right?
00:32:17.359 --> 00:32:29.920
I'm obviously uh um experiencing them firsthand, but I'm also trying to learn about them as fast as possible, as you know, from from people who are, you know, more they uh who have more expertise than I do.
00:32:30.079 --> 00:32:33.519
So uh I love doing this inside Gemini Notebook.
00:32:33.599 --> 00:32:36.960
Um, it's not just for me, it's not just a content generation machine.
00:32:37.039 --> 00:32:45.920
Um, it is really interactive learning because I love my favorite one, is probably the uh audio overview that you can do the deep dive and then do interactive mode.
00:32:46.000 --> 00:32:50.960
Uh that's great because you can literally click like the join button and you can ask the two hosts questions.
00:32:51.119 --> 00:32:58.799
Um, so that's like really valuable before you know a major interview or a project where I just need a better understanding.
00:32:58.960 --> 00:33:06.880
Um, a lot of times if I'm doing a quote unquote bigger show, right, I'll first have the um the deep dive.
00:33:07.039 --> 00:33:09.759
Uh I guess two hosts do it.
00:33:09.839 --> 00:33:15.359
And then I'll listen and, you know, kind of drill them, like, hey, well, why'd you say this that way?
00:33:15.519 --> 00:33:18.079
Isn't this a better way to phrase that or frame that?
00:33:18.160 --> 00:33:19.759
And they might say yes and they might say no.
00:33:19.920 --> 00:33:24.559
So it's almost like sometimes I go through and I uh rehearse some shows.
00:33:24.720 --> 00:33:27.599
Um, I'd say I probably only do that like twice a month.
00:33:27.680 --> 00:33:32.799
Um, you know, when it's maybe something more challenging, something a little more new, a big interview, something like that.
00:33:32.960 --> 00:33:34.799
Um, then I'll go through and do it that way.
00:33:34.880 --> 00:33:36.640
But yeah, that is my number eight.
00:33:36.799 --> 00:33:38.960
Uh number nine, or sorry, that was my number seven.
00:33:39.039 --> 00:33:41.440
So number eight is codex skill building.
00:33:41.599 --> 00:33:42.240
My gosh.
00:33:42.319 --> 00:33:44.240
Um, I'm big on skills.
00:33:44.559 --> 00:33:53.279
I think, you know, probably a year ago, or you know, even like December-ish, everyone was talking about lines of code, right?
00:33:53.440 --> 00:33:57.920
Or tokens, um, you know, as being like a heavy AI user.
00:33:58.079 --> 00:34:00.400
Um, I don't think that's a good metric, right?
00:34:00.559 --> 00:34:08.800
I think the number of times that you use a skill really shows if you're uh being an AI native person or not.
00:34:08.880 --> 00:34:10.239
So as an example, right?
00:34:10.400 --> 00:34:14.639
Um, I have 124 skills that I've used.
00:34:14.800 --> 00:34:19.039
Um, and I've used those skills, a total of uh I got these stats.
00:34:19.199 --> 00:34:22.000
This is just from within codex from just one of my accounts.
00:34:22.079 --> 00:34:25.679
Um, and I've used those skills 6,179 times.
00:34:25.760 --> 00:34:29.360
So I use skills obviously a lot, many times a day.
00:34:29.519 --> 00:34:30.159
Uh, you're right.
00:34:30.320 --> 00:34:34.559
And I break up these skills into multiple pieces and then create a plugin.
00:34:35.039 --> 00:34:35.199
All right.
00:34:35.280 --> 00:34:39.920
So if you don't know what a skill is, uh, it's just something that you repeatedly do over and over.
00:34:40.079 --> 00:34:43.440
And I want you to think of my codex use cases, right?
00:34:43.679 --> 00:34:55.119
Um, because I think a lot of people think of skills and they think of either just writing content a certain way, or they think of coding something, or they think of a design system that is in a skill, which is fine, right?
00:34:55.199 --> 00:35:11.199
The way I think of it, these skills um is taking a long multi-system, multi-app, multi-website task um, and breaking it down and turning each of those steps into a skill.
00:35:11.280 --> 00:35:16.239
Um, and then in codex, you can combine multiple of those skills and create a plugin, right?
00:35:16.320 --> 00:35:19.920
That's what I do for a lot of things that I run and then I schedule those things.
00:35:20.079 --> 00:35:20.320
Right.
00:35:20.400 --> 00:35:24.639
So let's say you go to, you know, heck, I'll give you one of mine, right?
00:35:24.719 --> 00:35:26.239
So you can go to StreamYard.
00:35:26.320 --> 00:35:30.159
That's what we um it's what we use for our live streaming.
00:35:30.239 --> 00:35:37.119
So you can go to StreamYard, download, uh, right, download this uh and then upload it into cast magic, right?
00:35:37.199 --> 00:35:39.280
So we do cast magic for transcriptions, right?
00:35:39.360 --> 00:35:40.880
That can be one skill, right?
00:35:40.960 --> 00:35:49.280
And then taking that, and you know, we take some of those um pieces from cast magic, you know, like bullet points of the show highlights, transcriptions, right?
00:35:49.440 --> 00:35:52.800
Then I can take that, copy and paste it into the back end of our website.
00:35:52.960 --> 00:35:54.079
That's another skill, right?
00:35:54.159 --> 00:35:58.880
So all these things that you do in succession, break them down into little pieces and save them as a skill.
00:35:59.039 --> 00:36:01.840
You can either do it after you do something, right?
00:36:02.000 --> 00:36:09.920
That's a huge, like essentially, whenever I do something quote unquote by hand, that's not a skill.
00:36:10.159 --> 00:36:12.239
I ask myself, am I gonna do this again?
00:36:12.480 --> 00:36:14.800
And chances are there's a decent chance that I might.
00:36:14.880 --> 00:36:19.039
So I create skills fairly, fairly frequently, right?
00:36:19.199 --> 00:36:21.519
Um, I've used 124 of them.
00:36:21.599 --> 00:36:27.039
Uh, I probably have a lot more that I don't use, but I've saved just in case.
00:36:27.199 --> 00:36:32.079
Um, you know, I actually have a skill that runs every single day that creates new skills.
00:36:32.239 --> 00:36:35.920
So I have a skill that goes through, it looks at all of my threads on codex.
00:36:36.000 --> 00:36:38.079
Again, something that Claude can't do.
00:36:38.239 --> 00:36:49.039
Um, looks at every single thread on Codex, and it's supposed to pull out and say, hey, these are things you're doing repeatedly, or um, this right here, you should turn into a skill, right?
00:36:49.199 --> 00:36:51.280
You went back and forth six or seven times.
00:36:51.519 --> 00:36:59.199
A lot of times, right, especially with this new technology, computer use was greatly improved with the new GPT-56 soul, right?
00:36:59.280 --> 00:37:06.159
But it sometimes makes your old skills faster, or you know, maybe certain things that worked a little better before works a little differently now.
00:37:06.320 --> 00:37:15.920
So, you know, it it's it's gonna, you know, when I'm doing new new projects or um trying to automate something new, um, a lot of times I have to go through a lot of back and forth.
00:37:16.000 --> 00:37:21.599
And that's whether it's you know, Claude, cursor, codex, anti-gravity gemini doesn't matter.
00:37:21.679 --> 00:37:22.960
That's just how it goes, right?
00:37:23.119 --> 00:37:27.760
But after you do that, that is your IP, right?
00:37:27.840 --> 00:37:29.519
That is your knowledge.
00:37:29.679 --> 00:37:34.480
And and the great thing about large language models now is well, just repeat it, right?
00:37:34.639 --> 00:37:35.280
That's the thing.
00:37:35.360 --> 00:37:43.599
People always think, like, okay, well, I'm just gonna do this every day and I'm just gonna use these models, and okay, and I'm gonna go and manually push the buttons.
00:37:43.760 --> 00:37:45.920
You gotta stop being a button pusher, all right?
00:37:46.079 --> 00:37:53.920
Go and push the buttons once, and then just have whether you're using Claude, Gemini Codecs, just say, hey, turn this into a skill, right?
00:37:54.000 --> 00:37:55.599
And it will, and it'll say the skill.
00:37:55.679 --> 00:37:59.519
Um, but yeah, you should be doing that as frequently as possible.
00:37:59.679 --> 00:38:14.880
All right, and then last but not least, uh, my gosh, um Chad GPT voice is insanely good.
00:38:15.840 --> 00:38:17.519
It is so so good.
00:38:17.679 --> 00:38:25.760
This is just another reason why I am confident like no one's gonna be touching the codex anytime soon.
00:38:25.920 --> 00:38:29.039
Um, it is so far, so far ahead.
00:38:29.199 --> 00:38:32.800
And if you haven't used Chat GPT voice, y'all, go go and look online.
00:38:32.960 --> 00:38:41.360
All the people that are, you know, normally even Claude fans and you know, bash, open AI, chat GPT, whatever, they will literally like go go find those people.
00:38:41.440 --> 00:38:42.400
You know those people.
00:38:42.559 --> 00:38:46.480
Uh everyone's just starting to talk about this like this week, right?
00:38:46.719 --> 00:38:48.239
Uh it is that good.
00:38:48.400 --> 00:38:48.800
It is.
00:38:48.960 --> 00:38:54.079
I did a show, I said this is the the next frontier of agentic work.
00:38:54.159 --> 00:38:56.559
Uh so if you don't know what it is, right?
00:38:56.800 --> 00:38:59.679
Uh I wish it was a little easier to get to in the app.
00:38:59.840 --> 00:39:09.360
So if you have the ChatGPT app, um, essentially you connect it once to the you know, either codecs or you know, ChatGPT work desktop app.
00:39:09.440 --> 00:39:16.800
Uh from there, on your ChatGPT mobile app, you open ChatGPT on the side panel, you click remote.
00:39:16.880 --> 00:39:19.920
Then there's a little button at the bottom, a little blue button.
00:39:20.000 --> 00:39:21.280
That's ChatGPT Live.
00:39:21.360 --> 00:39:26.480
So let me tell you what this is because you might say, like, oh, doesn't Quad have dispatch?
00:39:26.639 --> 00:39:28.239
Yeah, dispatch is terrible.
00:39:28.320 --> 00:39:34.480
Uh, it doesn't know any of your other threads, it only can work on one thread, and it can't really do anything, right?
00:39:34.559 --> 00:39:36.719
Aside from you can kind of chat back and forth.
00:39:36.800 --> 00:39:42.639
Uh, Chat GPT voice in remote, literally, you can control your entire computer.
00:39:43.599 --> 00:39:44.719
Anything, right?
00:39:44.800 --> 00:39:47.679
So I can be on my phone and I just did this this morning, right?
00:39:47.840 --> 00:39:51.519
I've been taking more walks recently since Chat GPT voice came out.
00:39:51.599 --> 00:39:52.079
It's amazing.
00:39:52.159 --> 00:39:53.039
Thank you, OpenAI.
00:39:53.119 --> 00:39:54.800
I'm actually getting steps now.
00:39:54.960 --> 00:39:55.519
Uh, right.
00:39:55.679 --> 00:40:00.079
Some days I'm like looking at my watch and I'm like, oh, I got like 800 steps today, right?
00:40:00.159 --> 00:40:06.079
Now it's like I got 13,000 today, uh, right, because I get work done walking, right?
00:40:06.159 --> 00:40:09.199
And hey, in Chicago, we don't we can't walk year out.
00:40:09.360 --> 00:40:17.679
So it's it's good now that I can go out and actually, you know, get some get some vitamin D, um, and in instead of sitting under the the fluorescent lights all day.
00:40:17.760 --> 00:40:23.840
But essentially, anything that you can do yourself on your computer, you can do it in ChatGPT voice.
00:40:24.000 --> 00:40:29.760
So I can literally say, you know, hey ChatGPT voice, uh look in my downloads folder.
00:40:29.840 --> 00:40:30.880
There's a new PowerPoint.
00:40:31.199 --> 00:40:33.280
Can you open that PowerPoint up?
00:40:33.519 --> 00:40:37.920
Um, and then I have a new image um inside Canva.
00:40:38.239 --> 00:40:40.480
Can you go download that and swap it out?
00:40:40.559 --> 00:40:42.639
Uh actually tell me what's on page three.
00:40:42.800 --> 00:40:43.840
What what's that image?
00:40:43.920 --> 00:40:44.079
Right.
00:40:44.159 --> 00:40:50.000
And it's gonna tell you, it's gonna literally, it's it's um, it's uh what's what's the word?
00:40:50.159 --> 00:40:51.119
Why do I keep forgetting?
00:40:51.199 --> 00:40:52.159
Uh duplex, right?
00:40:52.239 --> 00:40:53.440
Full duplex, right?
00:40:53.519 --> 00:40:58.960
So what that means is you can talk to it, you can interrupt it, it can interrupt you, it can talk and hear at the same time.
00:40:59.119 --> 00:41:02.400
But as it's talking to you, it has another model that works in the background.
00:41:02.559 --> 00:41:09.199
So, I mean, literally, I'm just just dictating, giving all these long, hard assignments, right?
00:41:09.360 --> 00:41:13.280
Hey, go go into go use this skill, right?
00:41:13.360 --> 00:41:16.159
Go go download this from this website.
00:41:16.239 --> 00:41:22.320
I'm logged in, uh, you know, upload it here, change this, tell me what's on this page, right?
00:41:22.400 --> 00:41:27.519
I am literally like like I'm on vacation and I have an intern sitting in front of my computer.
00:41:27.679 --> 00:41:29.360
That's literally what I'm doing, right?
00:41:29.440 --> 00:41:30.960
And that is what you can do.
00:41:31.119 --> 00:41:33.280
Um, it is amazing.
00:41:33.360 --> 00:41:36.559
And the great thing is it's different, which I know is confusing.
00:41:36.719 --> 00:41:40.960
It's a little different than the GPT live mode in the ChatGPT app.
00:41:41.039 --> 00:41:51.199
This is the most confusing thing because if you use that uh kind of voice mode inside normal ChatGPT, it can't access your connectors, it can't access your MCPs.
00:41:51.360 --> 00:41:53.280
Uh, right, that's the big difference.
00:41:53.360 --> 00:41:58.960
Uh, if you use Chat GPT voice mode via remote in the Chat GPT app, it can't.
00:41:59.039 --> 00:42:02.639
You can say, Hey, what are my most important emails?
00:42:02.800 --> 00:42:05.199
Okay, reply, say this, send.
00:42:05.280 --> 00:42:05.840
Uh, right.
00:42:05.920 --> 00:42:08.719
Like, hey, go, yeah, you know, whatever.
00:42:08.800 --> 00:42:11.119
You open my my my hub spot.
00:42:11.199 --> 00:42:13.119
Uh, you know, what leads have moved?
00:42:13.280 --> 00:42:14.000
Okay, right.
00:42:14.079 --> 00:42:18.079
Okay, go update this and then Slack, you know, my teammates, send them this.
00:42:18.159 --> 00:42:19.440
And it just does it all.
00:42:19.599 --> 00:42:24.639
You can literally do all your work in Chad GPT voice, as I'm starting to do.
00:42:24.880 --> 00:42:26.800
All right, so that's a wrap.
00:42:26.880 --> 00:42:27.840
That's my nine.
00:42:27.920 --> 00:42:29.440
I just gave you an inside look.
00:42:29.599 --> 00:42:33.440
Uh, yeah, I gave you a couple of hot takes there, but that's just the truth, right?
00:42:33.599 --> 00:42:36.239
Um, might this all change in a couple of weeks?
00:42:36.480 --> 00:42:37.519
It could, right?
00:42:37.679 --> 00:42:44.400
But honestly, I think um, at least for me, I don't see my workflow changing anytime soon.
00:42:44.639 --> 00:42:51.280
Um, and I think if if you've been stuck on the fence, um, just take take what I learned and run it through your own workflows, right?
00:42:51.440 --> 00:43:02.480
Run everything side by side through, you know, clawed code and codex and cursor, or you know, through you know, chat gpt.com, claw.ai, and gemini.google.com, right?
00:43:02.639 --> 00:43:03.519
Do it for yourself.
00:43:03.599 --> 00:43:09.760
But I want you to take maybe my workflows, these nine that I shared with you as a starting point.
00:43:09.920 --> 00:43:11.280
Some are more habits, right?
00:43:11.360 --> 00:43:13.199
Like turning things into skills.
00:43:13.360 --> 00:43:16.480
Uh, but some of them I think you should just be trying, right?
00:43:16.639 --> 00:43:22.719
Like, you know, try using the combination of claw design, um, you know, Google Stitch and GPT image.
00:43:22.800 --> 00:43:27.920
If you are trying to vibe code something, if you're trying to build a little app for yourself, your team, your company, right?
00:43:28.159 --> 00:43:32.719
Start there versus, you know, building it all and then saying, like, hey, this is ugly.
00:43:32.800 --> 00:43:33.599
Let's change some things.
00:43:33.679 --> 00:43:34.960
You're gonna save yourself so much time.
00:43:35.119 --> 00:43:37.039
So uh I hope this one is helpful.
00:43:37.199 --> 00:43:39.679
If you like this type of show, let me know.
00:43:39.840 --> 00:43:41.440
Maybe I'll do another one or two.
00:43:41.599 --> 00:43:48.400
Uh, but that is it inside everyday AI and my nine most used AI tools and workflows.
00:43:48.480 --> 00:43:54.480
If this is helpful, please subscribe to the podcast, then go to your evereverydayai.com, sign up for the free daily newsletter.
00:43:54.559 --> 00:43:55.199
Thanks for tuning in.
00:43:55.440 --> 00:43:57.840
See you back tomorrow and every day for more everyday AI.
00:43:57.920 --> 00:43:59.039
Thanks, y'all.
00:00:00.880 --> 00:00:04.799
One of the most common questions I get is how I use AI every day.
00:00:04.959 --> 00:00:08.480
So on today's episode, I'm gonna tell you everything.
00:00:08.640 --> 00:00:19.120
And the answer to that question obviously has changed drastically over the years as quickly as the AI offerings themselves have changed, which is all the time.
00:00:19.280 --> 00:00:28.960
But I feel over the last few months at least, my usage has gotten consistent enough that I feel I can make this episode and not have it be obsolete in like two weeks.
00:00:29.199 --> 00:00:40.240
Because after using thousands of AI tools and modes over the years, you might be able to save yourself a few hundred hours and just copy some of my workflows and see what sticks.
00:00:40.399 --> 00:00:53.200
So on today's show, I'm going to give you a little behind the scenes on not only my nine most used AI tools and workflows, but also maybe some hot takes and trends on AI tool use in general along the way.
00:00:53.439 --> 00:01:02.880
So we're going to go inside everyday AI and go over my nine most used AI tools and workflows that power my day.
00:01:03.119 --> 00:01:04.640
All right, let's get into it.
00:01:04.719 --> 00:01:10.719
On today's show, here's what you're going to learn my nine most used AI tools and workflows.
00:01:10.799 --> 00:01:15.840
Uh, you're gonna know why I sometimes build my own AI tools, and I think you should too.
00:01:16.000 --> 00:01:23.200
And I'm gonna tell you why I'm obviously Codex pilled, yet still using Claude, Gemini, and other tools.
00:01:23.439 --> 00:01:24.719
All right, let's get into it.
00:01:24.879 --> 00:01:26.079
Welcome to Everyday AI.
00:01:26.239 --> 00:01:29.519
If you're new here, my name's Jordan and we do this every day.
00:01:29.599 --> 00:01:30.159
It's for you.
00:01:30.239 --> 00:01:38.079
It's your unedited, unscripted daily live stream podcast and free daily newsletter helping business leaders like you and me not just keep up, but get ahead.
00:01:38.239 --> 00:01:40.000
I tell you what works, what doesn't.
00:01:40.159 --> 00:01:44.640
You take that information, all those saved hours, and you grow your company and your career.
00:01:44.799 --> 00:01:46.560
So if that's what you're trying to do, sweet.
00:01:46.719 --> 00:01:47.359
Starts here.
00:01:47.439 --> 00:01:53.760
Make sure if you haven't already, please subscribe to the podcast and then go to our website at your everydayai.com.
00:01:53.840 --> 00:01:56.400
Uh, the website is also always in our show notes there.
00:01:56.560 --> 00:02:05.040
We're gonna be recapping the highlights from today's episode and giving you all the AI news and developments you need to know to stay ahead.
00:02:05.359 --> 00:02:08.159
All right, we'll see if this one sticks, right?
00:02:08.319 --> 00:02:08.879
Watch.
00:02:09.039 --> 00:02:11.280
Uh watch later today.
00:02:11.360 --> 00:02:12.479
Obviously, it's Thursday.
00:02:12.639 --> 00:02:14.240
Big releases always come out on Thursday.
00:02:14.319 --> 00:02:15.360
Watch everything change today.
00:02:15.520 --> 00:02:30.240
But um, I feel for the and honestly, for the first time in a very long time, uh, you know, my my usage in terms of uh AI tools has not completely changed, you know, in in three months, right?
00:02:30.319 --> 00:02:32.159
It's been fairly consistent.
00:02:32.400 --> 00:02:39.919
And some of those reasons is because I think there's, you know, one harness that will not be dethroned anytime soon.
00:02:40.080 --> 00:02:54.240
And kind of the move, you know, going from um, you know, AI that was mainly web-based uh to AI that lives on your desktop and agents that live on your desktop, I think it made the uh maybe the the models less important.
00:02:54.479 --> 00:03:03.120
I think it maybe made some of the modes, you know, like your deep research and your, you know, plugins and artifacts, all these things.
00:03:03.199 --> 00:03:05.599
I think it made those things a little less important.
00:03:05.840 --> 00:03:12.400
Um, and honestly, between the the models and the modes, I think there's actually a bit of parity.
00:03:12.560 --> 00:03:13.280
Um, right.
00:03:13.439 --> 00:03:17.919
Whereas maybe two years ago when a new model came out, it was such a big gap.
00:03:18.000 --> 00:03:19.919
It was like first place and second place.
00:03:20.080 --> 00:03:26.560
Now, uh at least recently, between OpenAI and Anthropic, it's usually one A and one B, and then they flip-flop, right?
00:03:26.639 --> 00:03:35.840
Um, but the harness itself, um, and this is why I think my my usage has been so consistent probably since February, um, has made all the difference.
00:03:36.000 --> 00:03:42.479
So before I go into my nine most used tools and workflows, a little precursor first.
00:03:42.639 --> 00:03:49.280
Speaking of the um the harness, I'm obviously codex pilled.
00:03:49.520 --> 00:03:53.360
If you've been listening to the show at all since February, I've been saying this.
00:03:53.520 --> 00:03:58.639
I've called it, I said Claude Code, it's it's gonna lose its lead, right?
00:03:58.800 --> 00:04:00.719
Uh, obviously, hats off to Anthropic.
00:04:00.960 --> 00:04:14.879
They really kicked off the agenc desktop era uh with Claude Code Desktop in December, followed up by Claude Cowork uh in January, but they've just been getting smoked and it's not even close in February.
00:04:15.039 --> 00:04:21.680
And you know, I always, I always will use the best overall tool no matter what, right?
00:04:21.839 --> 00:04:31.839
And you know, throughout the the years, I've had the most expensive plans to, you know, I was on the Perplexity$200 plan, you know, using their uh computer.
00:04:32.079 --> 00:04:37.839
I've I've been on the Google Ultra plan, I think when it was like$300 a month or whatever it used to be.
00:04:37.920 --> 00:04:44.000
Um, you know, I currently have a Claude uh, you know, 200 Max and an OpenAI 200 Max plan.
00:04:44.240 --> 00:04:45.759
So I've used them all, right?
00:04:45.839 --> 00:04:48.560
And I still use all of them to this day.
00:04:48.720 --> 00:04:53.680
Um, but the majority of my time now is really in codex.
00:04:54.079 --> 00:04:55.920
Um, it isn't a league of its own.
00:04:56.079 --> 00:05:05.199
I don't think um, you know, cursor uh will catch them, although I am glad that cursor added uh, you know, some simple Google connectors uh this week.
00:05:05.279 --> 00:05:07.120
I don't think Claude uh will catch.
00:05:07.439 --> 00:05:12.079
And also I want you to first think about your workflow.
00:05:12.240 --> 00:05:29.439
And the reason why I say those things is because I know our audience, you know, yes, there's obviously very technical people, there's builders who listen to this show, but for the most part, our audience is, you know, non-technical business leaders who are doing um, you know, non-technical work, right?
00:05:29.519 --> 00:05:32.000
So that's where my lens is coming through this.
00:05:32.160 --> 00:05:37.839
So, you know, if if you're just like as an example, software developer, maybe Claude Code is is best, right?
00:05:37.920 --> 00:05:39.519
Or maybe cursor is best.
00:05:39.680 --> 00:05:48.879
Um, but if you are someone that is, you know, not just 100% writing code, uh, codecs, like I said, in a league of its own.
00:05:49.040 --> 00:05:51.439
And I don't see it being caught anytime soon.
00:05:51.600 --> 00:05:56.720
Okay, so with that out of the way, I do want you to know that this is just based on my own workflows as well.
00:05:56.879 --> 00:05:59.680
Your usage is obviously going to vary and keep that in mind, right?
00:05:59.759 --> 00:06:01.519
So take that with a giant grain of salt.
00:06:01.600 --> 00:06:12.319
Uh, this isn't definitive, but I would say for the average non-technical AI user, like I'm saying, steal for my thousands of hours over the years of using all these tools.
00:06:12.560 --> 00:06:16.480
What I'm saying, sh, am I, you know, do I have a preference?
00:06:16.639 --> 00:06:17.120
Absolutely.
00:06:17.360 --> 00:06:18.720
Am I telling you the truth?
00:06:18.879 --> 00:06:19.279
Yes.
00:06:19.439 --> 00:06:19.759
All right.
00:06:19.839 --> 00:06:21.199
So just getting that out of the way.
00:06:21.360 --> 00:06:25.120
Also, another thing to keep in mind, my usage has really shifted.
00:06:25.199 --> 00:06:29.519
Uh, right, back in January, I was probably only 10% desktop, right?
00:06:29.600 --> 00:06:36.319
Because the only big desktop player at the time was uh, you know, cursor um and clawed code, right?
00:06:36.399 --> 00:06:40.319
So I was using clawed code about 10% of the time, and everything else was on the web.
00:06:40.480 --> 00:06:42.959
Obviously, today that's complete opposite.
00:06:43.040 --> 00:06:47.360
So today I'm like 90% using everything um on the desktop.
00:06:47.519 --> 00:06:55.519
So that's mainly codecs, but also using clawed code, clawed cod, uh, you know, cursor, anti-gravity, Gemini on the desktop, right?
00:06:55.600 --> 00:06:59.920
For the most part, I am desktop agenc harness through and through, right?
00:07:00.000 --> 00:07:02.879
Even for non-technical knowledge work, that's what I'm using.
00:07:03.040 --> 00:07:12.000
Um, but like I said, I'm really only using you know, Claude and Gemini desktop, anti-gravity cursor, so I understand them, right?
00:07:12.079 --> 00:07:13.279
So I have a comparison.
00:07:13.360 --> 00:07:20.319
And so when I tell you, yeah, codex slaps everyone else, that comes from facts, not just like a preference, right?
00:07:20.399 --> 00:07:23.519
So anytime there are new updates, I'm always using them, I'm always testing them.
00:07:23.759 --> 00:07:31.199
I'm, you know, doing some of my own uh, you know, internal benchmarks and use cases, so I know what's best for different types of work.
00:07:31.360 --> 00:07:40.319
Um, the the other thing to know is I am very bullish on agent control and agent co-working.
00:07:40.399 --> 00:07:42.399
And I'm gonna tell you what those things are, right?
00:07:42.480 --> 00:07:49.600
I'm I'm you know, kind of taking you behind the scenes here at everyday AI and in how I work and you know how we kind of run things.
00:07:49.839 --> 00:07:56.079
Um, but one thing to keep in mind is um not everyone can work like this either.
00:07:56.160 --> 00:08:00.160
Um, and I'm not saying that from a skills perspective because it's not difficult.
00:08:00.319 --> 00:08:03.360
I'm just saying from a data and permissions perspective, right?
00:08:03.519 --> 00:08:10.079
I am having agents literally running around the clock doing everything on my computer, full control, full YOLO mode.
00:08:10.160 --> 00:08:11.439
I know that's not for everyone, right?
00:08:11.519 --> 00:08:19.519
If you work at a big enterprise, even if you've gotten permission to use Claude Desktop or Codex, you may not be able to do a lot of these things.
00:08:19.680 --> 00:08:21.600
Um, so keep that in mind.
00:08:21.759 --> 00:08:31.279
But if you are a small business owner or if your company has taken off all restraints and you can just do whatever you want, well, let's let's have some fun.
00:08:31.439 --> 00:08:32.080
All right, here we go.
00:08:32.159 --> 00:08:33.600
I'm not gonna make you wait any longer.
00:08:33.759 --> 00:08:39.440
Here's my nine most used AI tools and workflows, and then we're gonna dive into each one individually, uh individually.
00:08:39.600 --> 00:08:43.759
So number one, I have my third shift stats agent.
00:08:43.919 --> 00:08:47.679
Uh, number two, I have my third shift comms triage.
00:08:47.840 --> 00:08:52.000
Uh, number three, I have my chat GPT sites to iMessage.
00:08:52.080 --> 00:08:54.080
Yeah, that one's a little uh specific.
00:08:54.320 --> 00:08:57.919
Number four, I have my parrot dictation app that I built.
00:08:58.000 --> 00:09:01.519
Uh number five, I have my episode planning research.
00:09:01.759 --> 00:09:04.080
Number six, my AI app design.
00:09:04.240 --> 00:09:10.320
Number seven, uh Gemini Notebook Study, also previously known as Notebook LM.
00:09:10.399 --> 00:09:12.559
So did a show on that uh yesterday.
00:09:12.720 --> 00:09:15.360
Uh, number eight, codex skill building.
00:09:15.440 --> 00:09:19.679
And number nine, remote chat GPT walk and talk.
00:09:19.840 --> 00:09:21.840
All right, let's get into it.
00:09:22.320 --> 00:09:26.159
Number one, third shift agents for stats.
00:09:26.320 --> 00:09:26.639
All right.
00:09:26.799 --> 00:09:29.360
First, let me describe what third shift agents are.
00:09:29.519 --> 00:09:32.720
Uh well, they're agents that work third shift, right?
00:09:32.799 --> 00:09:39.440
Uh, usually I'm up working fairly late, but let's just say my agents usually work about 11 to 5, right?
00:09:39.600 --> 00:09:40.639
Every single night.
00:09:40.720 --> 00:09:42.879
Uh, a lot of things are scheduled.
00:09:43.039 --> 00:09:52.639
Um, and then I will also usually give it my toughest problem or set of problems to codex um every single night, kind of before I go to bed.
00:09:52.799 --> 00:09:56.480
I'll use subagents, I'll use goal mode, I'll use plan mode.
00:09:56.639 --> 00:09:56.960
All right.
00:09:57.120 --> 00:10:02.159
And if you're wondering, like what the heck is all of that stuff, um, we did an episode.
00:10:02.240 --> 00:10:03.919
Let me bring up the number.
00:10:04.080 --> 00:10:06.480
Uh, let me bring up the number on that one.
00:10:06.559 --> 00:10:12.720
Uh, it was number, come on, there it is.
00:10:12.799 --> 00:10:24.799
Uh, episode 806, part of the start here series where we went over desktop agent lingo simplified, talking about goals, loops, plans, sub agents, and how those work in codex and clawed code.
00:10:24.879 --> 00:10:25.759
So go listen to that one.
00:10:25.840 --> 00:10:33.120
But essentially, uh, my probably most used um AI is not even me, right?
00:10:33.200 --> 00:10:34.080
I set these up.
00:10:34.240 --> 00:10:35.600
It happens third shift.
00:10:35.759 --> 00:10:38.399
My agents are working, you know, 11 to 5.
00:10:38.480 --> 00:10:40.639
Um, and then I wake up to things that are done.
00:10:40.799 --> 00:10:44.639
So let me tell you specifically what my third shift stats agents are.
00:10:44.799 --> 00:10:48.480
And again, I want you to think what just because I'm doing mine, right?
00:10:48.639 --> 00:10:52.559
Don't try to, you know, make my workflow fit your work.
00:10:52.799 --> 00:10:55.679
Instead, just see the path that I'm taking and apply it to yours.
00:10:55.840 --> 00:11:13.519
Okay, so essentially, inside, well, even on the web, but also on the desktop, uh, there's certain, you know, pieces of software or apps that you use that connect really nicely to ChatGPT, uh, Claude, Gemini, uh, Copilot, etc.
00:11:13.679 --> 00:11:15.200
And then there's some that don't.
00:11:15.360 --> 00:11:23.039
So for me, for everything that doesn't, right, it needs either computer use, browser use, or Chrome.
00:11:23.200 --> 00:11:28.080
Okay, so actually in Codecs and Chat GPT Work, which are literally the same thing, right?
00:11:28.159 --> 00:11:31.519
So I'm using just Codecs because it's just a little cleaner.
00:11:31.679 --> 00:11:34.960
Um, and I usually use Codecs, but you know, it's interchangeable.
00:11:35.039 --> 00:11:41.200
So FYI, when I'm saying Codex, I also mean ChatGPT Work, which if you go to ChatGPT and download it, that's what you're gonna get.
00:11:41.279 --> 00:11:47.039
So you can do these same things in ChatGPT Work, which is the desktop version of Chat GPT, uh, right.
00:11:47.200 --> 00:11:58.559
But there's three different ways that these agents can use your computer in instances where there's not a direct connection or where there's not an MCP or model context protocol server.
00:11:58.720 --> 00:12:02.240
Um, so in my case, right, we use Buzz Sprout.
00:12:02.639 --> 00:12:07.600
So that is, you know, the the the podcast, you know, thanks to you all that listen.
00:12:07.759 --> 00:12:11.039
Um, it's you know downloaded millions of times.
00:12:11.120 --> 00:12:16.559
And essentially, I didn't see this going in when I started the podcast because I'm like, no one's gonna listen.
00:12:16.639 --> 00:12:19.120
And apparently millions of people every year do.
00:12:19.200 --> 00:12:28.879
Um, and so there's just some stats that I really need that just aren't readily available by clicking export or by me going in and pulling up a couple screens on a couple monitors.
00:12:28.960 --> 00:12:40.399
Like I have to do usually about 30 or so minutes of work every single day, just pulling these metrics in, exporting certain things, and it is time consuming and I don't like doing it.
00:12:40.559 --> 00:12:43.759
So this is my uh third shift stats agent.
00:12:43.840 --> 00:12:46.240
So it does uh a lot of comparisons.
00:12:46.399 --> 00:12:48.960
Um, I have you know daily benchmarks, you know.
00:12:49.120 --> 00:12:59.039
So um, as an example, uh, you know, our Wednesdays, AI at Wednesdays, uh, you know, sorry, uh AI at work Wednesdays or working Wednesdays, you know, as we call them, right?
00:12:59.200 --> 00:13:09.120
I know that every single day, you know, Thursday at you know 9 a.m., that shows, you know, should have, like as an example, 11,500 downloads or something like that, right?
00:13:09.200 --> 00:13:13.440
So I know every day that it can go in there, it can see if that is the case.
00:13:13.519 --> 00:13:15.919
Uh it can go look at the last one from last Wednesday.
00:13:16.080 --> 00:13:17.759
Is it still getting a certain number?
00:13:17.919 --> 00:13:27.279
So I have all these kind of formulas that show me not only how popular a show is, but how does it do uh in its normal time slot or in its normal day slot versus others, right?
00:13:27.360 --> 00:13:30.720
For Tuesday and Thursday shows that maybe I don't have recurring shows on.
00:13:30.799 --> 00:13:47.679
Um, so I have all, you know, I had Codex make all these kind of formulas and it goes in, it pulls all these stats, you know, goes look at day day-by-day stats, which I can't export, uh, show me which, you know, shows are from two or three weeks ago are still maybe trending and you know, getting two or three X, what they should be getting at that point.
00:13:47.840 --> 00:13:50.799
So then I know that there's some evergreen appetite in that.
00:13:50.879 --> 00:13:58.960
And automatically I have a skill that if that happens, Codecs is gonna go start uh, you know, researching and find me more information on doing an updated show on that.
00:13:59.039 --> 00:14:00.720
So that's kind of my overnight agent.
00:14:00.799 --> 00:14:05.600
It also pulls information from our newsletter, uh, which we use Beehive.
00:14:05.840 --> 00:14:08.559
So there is a model context protocol server for that.
00:14:08.799 --> 00:14:11.679
But even with that, there are some things that I can't get in there.
00:14:11.840 --> 00:14:16.159
As an example, we run an A-B test on our newsletter every single day.
00:14:16.320 --> 00:14:19.360
In the M in the uh MCP, I can't get that.
00:14:19.440 --> 00:14:20.480
So I have to go in.
00:14:20.639 --> 00:14:26.480
It uses um uh for that, it uses browser control, uh, it goes in, clicks, and finds all those things.
00:14:26.559 --> 00:14:30.399
So I have so many of these tasks that I used to do like right two years ago.
00:14:30.480 --> 00:14:31.919
This is how I would start my day every day.
00:14:32.000 --> 00:14:37.120
Uh, you know, and if if I was very focused, I could get it done in, you know, maybe like an hour.
00:14:37.440 --> 00:14:42.320
Now it's you know, 30 seconds to overview something, which is great.
00:14:42.720 --> 00:14:43.840
One quick thing.
00:14:44.000 --> 00:14:50.320
Um, at least in codex, it's a little different in uh Cloud Code, but in Codex, it's a little better.
00:14:50.480 --> 00:14:52.799
So they have a built-in browser.
00:14:52.960 --> 00:15:03.600
Um, there is Chrome use, and then there's also um a Chrome extension, and those two obviously work hand in hand, and then computer use.
00:15:03.759 --> 00:15:16.320
So, you know, the browser, there's actually a file in uh kind of the Atlas browser was retired into uh Codex, but there's a full-fledged uh Chromium-based browser inside of Codex.
00:15:16.639 --> 00:15:23.039
So um, you know, for many of these things, I do them inside of the browser in Codex and I schedule them and they run overnight.
00:15:23.200 --> 00:15:32.960
Other other times, you know, it might it might need to use a um, as my second one here does, it might need to use Chrome because there's a Chrome extension involved.
00:15:33.039 --> 00:15:34.639
All right, so that's my first one.
00:15:34.960 --> 00:15:40.879
Um, but you know, essentially it just helps me do multiple things at once.
00:15:41.039 --> 00:15:42.639
I don't want to go and click around.
00:15:42.720 --> 00:15:46.639
I don't want to, you know, copy and paste information into spreadsheets.
00:15:46.799 --> 00:15:48.960
I don't want to be running formulas, right?
00:15:49.039 --> 00:15:53.759
I just wake up to an actionable briefing instead of spending my morning assembling one.
00:15:53.919 --> 00:15:54.240
All right.
00:15:54.320 --> 00:15:57.600
Number two, uh again, this is another third shift agent.
00:15:57.679 --> 00:15:59.200
This is my comms triage.
00:15:59.679 --> 00:16:01.759
This one, my gosh, this is helpful.
00:16:01.919 --> 00:16:02.159
All right.
00:16:02.240 --> 00:16:07.519
And one of the reasons is is I have, I don't know how or why.
00:16:07.759 --> 00:16:10.320
Um, I have a personal Gmail.
00:16:10.480 --> 00:16:16.000
Um, I have a Gmail account from my old company Accelerant Agency.
00:16:16.240 --> 00:16:22.399
I have a Gmail, and then I have two different Gmail accounts um for everyday AI.
00:16:22.559 --> 00:16:25.360
And for whatever reason, people find all of them.
00:16:25.440 --> 00:16:27.039
Maybe they're connected to LinkedIn.
00:16:27.120 --> 00:16:27.600
I don't know.
00:16:27.840 --> 00:16:29.279
I get spammed all the time, right?
00:16:29.360 --> 00:16:42.399
We get, I don't know, more than a thousand people each and every year, you know, pitching to be a guest on the show, people reaching out about spot uh sponsorships, partnerships, most of those I don't pay attention to, uh, you know, collaborations, whatever.
00:16:42.480 --> 00:16:45.840
Uh, so there's a lot of those, and then also LinkedIn, right?
00:16:46.080 --> 00:16:49.200
Um, this podcast goes out on LinkedIn every single day.
00:16:49.279 --> 00:16:50.960
Uh, so people message me all the time.
00:16:51.120 --> 00:16:54.159
Sometimes I ask people to message me ideas, those kind of things.
00:16:54.240 --> 00:16:56.320
Um, it's always me responding, right?
00:16:56.480 --> 00:16:59.039
But I do have agents go in and triage these things.
00:16:59.120 --> 00:17:14.000
So my second one is the uh codecs triaging all of those things and telling me what's important, what I need to get to, and then also giving me draft responses so I don't just have to sit at a blank stare email, right?
00:17:14.079 --> 00:17:18.160
Um, and usually, at least within codecs, I have these things set up within projects.
00:17:18.319 --> 00:17:27.599
So in each of these projects, um, you know, there's a markdown file that I can change very easily, update very easily, that give a set of directions to these things.
00:17:27.680 --> 00:17:29.519
So it can work with all my context.
00:17:29.599 --> 00:17:35.200
Uh, you know, I can give kind of custom instructions uh to each of these different uh, you know, projects.
00:17:35.279 --> 00:17:46.720
Uh, but this is good because, you know, in most um AI systems, you know, Gemini Claude, ChatGPT, um, Copilot, you can only really work with one email connected.
00:17:46.880 --> 00:17:48.480
Um, so this one's really helpful for me.
00:17:48.640 --> 00:17:56.160
The way that I pull this off is I, you know, just over time, I use the codex uh record and replay skill a lot.
00:17:56.319 --> 00:17:58.960
But um, even this one, it's it doesn't always work.
00:17:59.119 --> 00:18:01.359
So I've had to really refine it over the years.
00:18:01.519 --> 00:18:10.160
But essentially I have it launch Chrome profiles um and go to you know gmail.com uh for uh LinkedIn messages, right?
00:18:10.240 --> 00:18:13.599
I don't automate anything on LinkedIn because I don't want to get my LinkedIn banned.
00:18:13.680 --> 00:18:21.279
Uh so I do have a uh an extension in LinkedIn uh called um condo, essentially.
00:18:21.440 --> 00:18:25.519
So I have um it just syncs all my you know LinkedIn messages.
00:18:25.599 --> 00:18:26.880
It's a little quicker to go through.
00:18:26.960 --> 00:18:29.359
Uh the LinkedIn inbox is so slow.
00:18:29.519 --> 00:18:44.319
Um, so essentially I have a skill go in, it opens up a certain Chrome profile, it goes to LinkedIn.com, clicks on messages, that opens up a dedicated tab that has that Chrome extension that I need, which is why I do it through Chrome and not through the built-in browser.
00:18:44.400 --> 00:18:49.039
Uh, and then it can kind of go in, look at all my unreads, triage, find information there.
00:18:49.200 --> 00:18:50.799
So uh that's my second one.
00:18:50.880 --> 00:18:54.720
So essentially I can wake up every single day, I know every single stat, right?
00:18:54.799 --> 00:18:56.400
We put out a ton of content every day.
00:18:56.559 --> 00:19:02.880
We put so much effort into planning the shows, into how we deliver them, um, into the newsletter.
00:19:03.039 --> 00:19:08.880
And, you know, if I didn't have any guidance, I would just be guessing in the dark.
00:19:09.039 --> 00:19:09.599
Um, right.
00:19:09.680 --> 00:19:21.599
So it's great every day to have that in for my uh, you know, my my my third shift uh agents to have, you know, here's here's what performed well, um, you know, above average, below average.
00:19:21.680 --> 00:19:27.920
And then from a comms perspective, I don't have to go in and check, you know, four different emails and go into LinkedIn.
00:19:28.079 --> 00:19:29.440
It's all just there for me.
00:19:29.759 --> 00:19:30.400
All right.
00:19:30.880 --> 00:19:34.799
Next, uh ChatGPT sites to iMessage.
00:19:34.960 --> 00:19:35.359
All right.
00:19:35.519 --> 00:19:37.119
This one is great.
00:19:37.359 --> 00:19:42.559
Um, if you're not using Chat GPT sites, you are missing out.
00:19:42.720 --> 00:19:52.559
Um, Entropic has a similar um a similar uh kind of option called artifacts, and there's live artifacts.
00:19:52.720 --> 00:19:55.359
I think there's great use cases for live artifacts.
00:19:55.519 --> 00:20:10.480
The reason why I still prefer sites is it's a full, like lovable uh right, if you've used lovable, basically anything you can do inside like lovable or bolt or any of those uh kind of vibe coding, full, you know, almost like replit as well.
00:20:10.559 --> 00:20:12.400
That's what ChatGPT sites is.
00:20:12.559 --> 00:20:14.720
I still think it is criminally underrated.
00:20:14.799 --> 00:20:15.279
It is so good.
00:20:15.359 --> 00:20:19.599
So there's so many things that you can do inside ChatGPT sites that you can't do in Claude Artifacts, right?
00:20:19.759 --> 00:20:22.640
One of those things is just better permissions.
00:20:22.720 --> 00:20:28.480
So you can make things uh public, you can force login via ChatGPT, you can share things with your team.
00:20:28.559 --> 00:20:33.440
Uh not quite as robust um inside Claude Artifacts.
00:20:33.519 --> 00:20:43.839
Um, but what I love doing in this case is I have templates and skills that I've saved that make sites uh just really easy to use on my phone.
00:20:44.000 --> 00:20:47.200
So there's certain uh criteria, both from a design perspective.
00:20:47.440 --> 00:20:49.839
I always have it built in light and dark mode.
00:20:49.920 --> 00:20:57.680
Uh, I always have it build in uh a font where you can make it larger and smaller, and then I always have it built in uh kind of like a bookmark thing.
00:20:57.759 --> 00:21:06.480
So, you know, all these agents, when they do report these things to me, um, yes, it will be in line, but and oftentimes I just have them update a pre-existing site.
00:21:06.640 --> 00:21:09.759
And then what I do is I save those sites to my phone.
00:21:09.839 --> 00:21:13.359
So it's almost like I have agents updating these apps.
00:21:13.519 --> 00:21:16.880
The great thing about ChatGPT sites is it has databases.
00:21:16.960 --> 00:21:18.640
Um, it's like read write.
00:21:18.720 --> 00:21:26.400
So I can, you know, I have one that's like a little uh, you know, basic CRM, and I can, you know, just open my phone every morning, see what's new.
00:21:26.480 --> 00:21:27.359
I didn't do anything.
00:21:27.440 --> 00:21:37.279
It's just like literally I have agents, you know, grabbing all this information, running it through my personal context, updating the quote unquote apps or chat GPT sites that I use.
00:21:37.440 --> 00:21:42.480
Um, and then if it's a new one, it sends it to me through iMessage and it sends it to my phone, right?
00:21:42.559 --> 00:21:43.440
Uh, which is great.
00:21:43.519 --> 00:21:44.400
Yeah, people don't know.
00:21:44.480 --> 00:21:47.839
It's like that's a you know, it's actually a decent way, right?
00:21:48.000 --> 00:21:56.240
I just tell it to go check text messages from Jordan and I give it, you know, explicit, uh, you know, say, hey, it's okay to text Jordan, Jordan only.
00:21:56.480 --> 00:21:59.519
Um, it's actually one of my uh agent MD um.
00:22:00.480 --> 00:22:06.640
Uh, kind of instructions that go over all of my projects where it says, Hey, you can open iMessage and text Jordan, no one else.
00:22:06.799 --> 00:22:08.319
All right, so that's the other one.
00:22:08.400 --> 00:22:16.720
Uh, I love this because I just get that continually updated personal apps without having to, you know, rebuild or maintain them.
00:22:17.519 --> 00:22:18.160
All right.
00:22:18.400 --> 00:22:19.759
Uh, next one.
00:22:19.920 --> 00:22:24.880
I've never I've referenced this like once, but I've never really talked about Parrot.
00:22:25.279 --> 00:22:27.680
Okay, so this is uh one that I built.
00:22:27.759 --> 00:22:35.119
And let me just tell you why I built Parrot, um, why I think it's better than other alternatives and how I use it.
00:22:35.279 --> 00:22:37.680
Um, so Parrot is awesome.
00:22:37.839 --> 00:22:39.599
It's one of the first apps that I built.
00:22:39.759 --> 00:22:41.680
I use it literally every single day.
00:22:41.839 --> 00:22:48.880
Um, if you ever see me, you know, do screen recordings uh, you know, on Wednesday shows, a lot of times, you'll see a little green dot at the bottom.
00:22:48.960 --> 00:22:50.640
Sometimes that's parrot that's open.
00:22:50.799 --> 00:22:56.720
I usually try to like turn it off before I start in case I accidentally hit my dictation key, but a lot of times you'll see it on there.
00:22:56.880 --> 00:23:04.880
So if you've used something like um Whisperflow or Super Whisper, there's all these you know platforms that you know they're good.
00:23:04.960 --> 00:23:08.880
Uh, but the cloud-based ones for me are just too slow, right?
00:23:08.960 --> 00:23:11.359
Even Whisperflow, I'd say, is the leader out there.
00:23:11.440 --> 00:23:13.920
It's too slow, it's not always accurate.
00:23:14.079 --> 00:23:17.920
Um, and there's just features that just don't fit my workflow.
00:23:18.000 --> 00:23:20.559
And there's features that I want that aren't there.
00:23:20.799 --> 00:23:24.160
So I essentially built my own version that I think is much better.
00:23:24.319 --> 00:23:28.400
Um, I built this with both uh Claude and with Codex.
00:23:28.880 --> 00:23:31.279
And it's essentially it runs locally.
00:23:31.359 --> 00:23:36.960
So there's nothing in the cloud, it's stored locally on my computer, and that makes it much faster, right?
00:23:37.039 --> 00:23:47.200
I encourage everyone if you want a fun little uh you know project to build and you're feeling somewhat ambitious, uh, you know, build a local uh dictation LLM.
00:23:47.279 --> 00:23:48.559
So yeah, you don't need internet.
00:23:48.799 --> 00:23:53.759
Um, you know, just tell ChatGPT exactly, or you know, codex or cloud code exactly what you're trying to do.
00:23:53.920 --> 00:24:02.720
Um, in this case, it, you know, finds the best text-to-speech uh or sorry, speech to text dictation model, you know, downloads it.
00:24:02.799 --> 00:24:04.960
Um, but yeah, like for me, why I use this.
00:24:05.119 --> 00:24:07.599
Well, number one, it's faster, there's no lag.
00:24:07.759 --> 00:24:10.319
So I do like whisper flow, but there's a lag.
00:24:10.400 --> 00:24:14.720
Um, and then I thought, like, why should I have to send all this to the cloud if I don't need to?
00:24:14.880 --> 00:24:23.359
Uh also codex has great transcription and you can actually, people don't know this, you can use it anywhere, not just in codex, but then the same thing.
00:24:23.519 --> 00:24:27.279
It like Whisperflow, you know, it's there's still a little bit of a lag.
00:24:27.440 --> 00:24:36.400
So when I'm I obviously talk a lot um and I dictate a lot, I don't want to wait a half second or a second for longer dictations.
00:24:36.559 --> 00:24:38.079
I need to go immediately.
00:24:38.160 --> 00:24:40.799
Um, but then I have all these other things that I built into it.
00:24:40.880 --> 00:24:55.359
So, as an example, um, I can type in any YouTube channel um and it's going to every single time that there's a new uh video, so you know, I can have the open AI, anthropic, right?
00:24:55.680 --> 00:25:12.079
Anything, any big company, you know, any other um, you know, AI YouTubers out there, you know, I don't have time to watch anything, but if I want to know what people are talking about, it is literally every single video that comes out, it's gonna automatically transcribe as long as I have the program open.
00:25:12.240 --> 00:25:21.039
And then I have a scheduled skill inside Codex that goes and it looks at all those transcriptions every single day and it just gives me a little brief.
00:25:21.119 --> 00:25:24.079
Here's what everyone on YouTube is talking about, right?
00:25:24.240 --> 00:25:27.599
I used to like three years ago, especially when I was getting started.
00:25:27.759 --> 00:25:31.440
I probably spent like 30 to 45 minutes every day on YouTube.
00:25:31.680 --> 00:25:34.400
Uh, you know, obviously watching at like 2.5x.
00:25:34.559 --> 00:25:36.160
I don't have time to do that anymore.
00:25:36.319 --> 00:25:38.240
Um, you know, it's it's distracting.
00:25:38.319 --> 00:25:39.119
I just don't have the time.
00:25:39.200 --> 00:25:42.240
So I'd much rather just get, you know, a sites report.
00:25:42.400 --> 00:25:43.680
Here's what everyone's talking about.
00:25:43.759 --> 00:25:45.200
Here's the bullet points, right?
00:25:45.279 --> 00:25:45.920
It's perfect.
00:25:46.079 --> 00:25:47.440
So that's uh parrot.
00:25:47.599 --> 00:25:51.519
It's probably my most used uh app that I built myself.
00:25:51.839 --> 00:25:52.400
All right.
00:25:52.640 --> 00:25:56.880
Uh next I have my daily episode planning deep research.
00:25:56.960 --> 00:25:57.279
All right.
00:25:57.440 --> 00:26:02.400
So this is one of the few things, if I'm being honest, that I still use Gemini for.
00:26:02.480 --> 00:26:05.279
Uh, but let me tell you a little bit on how this works.
00:26:05.440 --> 00:26:09.200
So again, this is running from Codecs because it's the only one that can handle this.
00:26:09.279 --> 00:26:15.119
Uh, but a lot of times I save uh Twitter posts uh on my phone, so I bookmark them, right?
00:26:15.200 --> 00:26:23.599
So if I'm walking from here to there, uh, you know, um whatever, at night, in the morning, you know, quick save things.
00:26:23.759 --> 00:26:27.039
Um, so I save a lot of posts on Twitter.
00:26:27.119 --> 00:26:28.640
Uh another signal, right?
00:26:28.720 --> 00:26:30.480
So it's all these signals that I'm looking at, right?
00:26:30.559 --> 00:26:31.519
Like, what are people talking about?
00:26:31.680 --> 00:26:32.240
What's breaking?
00:26:32.319 --> 00:26:33.039
What's trending?
00:26:33.200 --> 00:26:35.359
Similarly, the same thing on Beehive.
00:26:35.519 --> 00:26:37.200
So that is our email newsletter.
00:26:37.359 --> 00:26:44.480
Uh, so again, I know, like on our AI news section, if I put something in, you know, spot three, it should get this many clicks.
00:26:44.559 --> 00:26:49.920
If it gets above or below, I know that story either people don't care about or they care about it a lot.
00:26:50.559 --> 00:26:56.400
Um, and then um, so I essentially take those signals every single day.
00:26:56.559 --> 00:27:06.160
Um, Codex goes in, it opens a new browser instance, it goes to chatgbt.com, it goes to claw.ai, it takes all that information, right?
00:27:06.319 --> 00:27:10.640
Not just the save posts, um, right, but um, you know, replies.
00:27:10.720 --> 00:27:14.480
I have it kind of do a sentiment analysis on anything that I save.
00:27:14.559 --> 00:27:16.720
And then I have it take all of that information.
00:27:16.960 --> 00:27:20.400
Codex is the kind of uh the agent orchestrator, not me.
00:27:20.480 --> 00:27:21.200
Isn't that weird?
00:27:21.359 --> 00:27:27.680
I thought it'd be humans, the ones that were orchestrating agents, but for me, it's actually codex that's orchestrating agents more than I do.
00:27:27.839 --> 00:27:39.599
So it takes all of that information, um, it sends it to both uh ChatGPT, uh Deep Research, Claw Deep Research, and Gemini Deep Research, um, you know, to help me plan episodes.
00:27:39.680 --> 00:27:53.440
So essentially I say, you know, go find me, you know, five episodes, you know, go find all the information, you know, you choose whatever I bookmarked, whatever is, you know, well above the normal click-through rate um inside Beehive.
00:27:53.759 --> 00:27:56.960
Go, go do that in uh, you know, ChatGPT Claude Gemini.
00:27:57.200 --> 00:27:58.559
Uh, take all that information.
00:27:58.640 --> 00:28:03.119
And then I have another skill that helps me start bullet pointing and planning out different shows.
00:28:03.279 --> 00:28:03.759
All right.
00:28:04.079 --> 00:28:06.720
So now let's go to number six.
00:28:07.039 --> 00:28:11.519
This is uh kind of front-end design for vibe-coded apps.
00:28:11.680 --> 00:28:14.880
So I don't build as much as I'd like to, right?
00:28:15.039 --> 00:28:20.000
If I didn't have uh a daily podcast, I might build a little bit more, right?
00:28:20.079 --> 00:28:24.720
But I still, like I said, I have Parrot, uh, I have another one I built called Planadoro.
00:28:25.279 --> 00:28:27.359
Uh, I have what do I have open on my computer here?
00:28:27.519 --> 00:28:28.720
Codecs reset watcher.
00:28:28.880 --> 00:28:33.039
I have a lot of like just codex tools that I built that help me use codecs a little better, right?
00:28:33.119 --> 00:28:35.599
But I have all these things, but I don't want them to be ugly.
00:28:35.839 --> 00:28:39.839
So uh this is something if you spend a little bit of time on the front end, right?
00:28:39.920 --> 00:28:42.319
For even if it's a throwaway app, right?
00:28:42.400 --> 00:28:44.319
I build intentional throwaway apps.
00:28:44.480 --> 00:28:51.680
Um, you know, like I said, if I have a little project, I'll build a little Kanban, uh, you know, or I'll build a little app for a project that I'm working on.
00:28:52.079 --> 00:28:57.920
Um, so in those cases, it's like, well, it needs to look good uh because I'm not gonna build something and have it be ugly.
00:28:58.000 --> 00:29:00.079
So in that case, uh kind of three tools.
00:29:00.240 --> 00:29:04.799
This is just kind of like a three in one here, because I use them sometimes interchangeably, sometimes together.
00:29:04.960 --> 00:29:06.480
So that's clawed design.
00:29:06.559 --> 00:29:07.759
Uh love clawed design.
00:29:07.839 --> 00:29:10.640
It is, I think, probably their most unique product.
00:29:10.799 --> 00:29:15.119
Um, so I love using claw design, Google Stitch, and GPT image.
00:29:15.359 --> 00:29:20.400
So using a combination of those uh just to create uh different front ends, right?
00:29:20.480 --> 00:29:33.279
So usually I'll have a couple pieces of inspiration, either things I've previously designed or just designs that I really uh think are good, and I'll put them into, you know, claw design, Google Stitch or GPT image.
00:29:33.359 --> 00:29:37.200
I'll dictate what I'm trying to do, what I'm trying to build, um, and get different outputs.
00:29:37.359 --> 00:29:41.200
So claw design uh doesn't do visuals, but it does great, right?
00:29:41.440 --> 00:29:44.000
Mockups, it does great slides, etc.
00:29:44.319 --> 00:29:47.359
Uh Google Stitch does great at mock-ups, right?
00:29:47.440 --> 00:29:52.720
It also can use uh nano banana, so it can do images, uh, it can do website everything.
00:29:52.799 --> 00:29:56.400
And then GBT image um obviously can do that as well.
00:29:56.480 --> 00:30:01.119
Uh the thing I like really probably a little bit more Google Stitch than Claude.
00:30:01.200 --> 00:30:03.839
So, Claude, you can like export things to Claude code.
00:30:03.920 --> 00:30:08.000
It doesn't really work because in most instances it just sends HTML, which is not the best.
00:30:08.160 --> 00:30:16.160
Um, I actually like using Google Stitch for that because you can then export the entire code of what it builds uh to like Google AI Studio.
00:30:16.240 --> 00:30:18.559
Um, and then from there you can do pretty much anything with it.
00:30:18.640 --> 00:30:28.559
So this is just when I'm building front ends, whether it's for you know making changes, uh a design system for a new app, um, whatever it may be.
00:30:28.720 --> 00:30:31.680
Uh, these are the kind of my my three ones that I use.
00:30:32.079 --> 00:30:32.720
All right.
00:30:33.039 --> 00:30:36.720
Uh next, this is number seven, Gemini Notebook study.
00:30:36.880 --> 00:30:38.799
You all know I just did a show yesterday.
00:30:39.039 --> 00:30:45.359
I use what was formerly known as Notebook LM, uh now known as Gemini Notebook all the time.
00:30:45.599 --> 00:30:47.200
Almost every single day.
00:30:47.359 --> 00:30:50.400
Sometimes, depending on the day, I might spend multiple hours.
00:30:50.480 --> 00:30:51.039
Um, right.
00:30:51.200 --> 00:30:53.200
I like, even if I don't, this sounds bad.
00:30:53.359 --> 00:30:58.960
I don't always listen um or use everything that Gemini Notebook makes me.
00:30:59.039 --> 00:31:00.640
It just depends on if I have time.
00:31:00.799 --> 00:31:06.799
But for the most part, um, I'll have it making me multiple assets every single day.
00:31:07.039 --> 00:31:14.640
Um, so audio overviews, uh, custom, you know, slide decks, things like that based on well, anything.
00:31:14.799 --> 00:31:16.960
A lot of times it's around episode planning.
00:31:17.039 --> 00:31:20.000
Uh, I do actually put a ton of work into episode planning.
00:31:20.079 --> 00:31:22.240
Uh, ones like this, not as much, right?
00:31:22.319 --> 00:31:26.559
Uh, aside from my nice uh, you know, GPD image codex design slides here.
00:31:26.640 --> 00:31:29.759
Um, but I'm using Gemini Notebook all the time.
00:31:30.000 --> 00:31:34.720
Uh so kind of like um what I talked about earlier, how I do all these deep researches.
00:31:34.880 --> 00:31:45.519
Um, I have Codex go and take these signals uh from you know Twitter, from our newsletter, uh, run deep research on that kind of sentiment uh analysis.
00:31:45.680 --> 00:31:48.160
Um and then next I'll have a skill.
00:31:48.240 --> 00:31:56.880
So this is kind of like the combination or the continuation of that, where Codex pulls all that and it creates custom uh notebooks um for me.
00:31:57.119 --> 00:32:07.279
So yeah, um custom deep dives, audio deep dives, um uh reports, I mean infographics, especially if it's like I'm learning a new subject, right?
00:32:07.440 --> 00:32:10.559
Some sometimes I'm learning at the same rate as everyone else, right?
00:32:10.640 --> 00:32:17.279
Like when something new comes out, it's like you know, learning about you know, loops and subagents and all these other things, right?
00:32:17.359 --> 00:32:29.920
I'm obviously uh um experiencing them firsthand, but I'm also trying to learn about them as fast as possible, as you know, from from people who are, you know, more they uh who have more expertise than I do.
00:32:30.079 --> 00:32:33.519
So uh I love doing this inside Gemini Notebook.
00:32:33.599 --> 00:32:36.960
Um, it's not just for me, it's not just a content generation machine.
00:32:37.039 --> 00:32:45.920
Um, it is really interactive learning because I love my favorite one, is probably the uh audio overview that you can do the deep dive and then do interactive mode.
00:32:46.000 --> 00:32:50.960
Uh that's great because you can literally click like the join button and you can ask the two hosts questions.
00:32:51.119 --> 00:32:58.799
Um, so that's like really valuable before you know a major interview or a project where I just need a better understanding.
00:32:58.960 --> 00:33:06.880
Um, a lot of times if I'm doing a quote unquote bigger show, right, I'll first have the um the deep dive.
00:33:07.039 --> 00:33:09.759
Uh I guess two hosts do it.
00:33:09.839 --> 00:33:15.359
And then I'll listen and, you know, kind of drill them, like, hey, well, why'd you say this that way?
00:33:15.519 --> 00:33:18.079
Isn't this a better way to phrase that or frame that?
00:33:18.160 --> 00:33:19.759
And they might say yes and they might say no.
00:33:19.920 --> 00:33:24.559
So it's almost like sometimes I go through and I uh rehearse some shows.
00:33:24.720 --> 00:33:27.599
Um, I'd say I probably only do that like twice a month.
00:33:27.680 --> 00:33:32.799
Um, you know, when it's maybe something more challenging, something a little more new, a big interview, something like that.
00:33:32.960 --> 00:33:34.799
Um, then I'll go through and do it that way.
00:33:34.880 --> 00:33:36.640
But yeah, that is my number eight.
00:33:36.799 --> 00:33:38.960
Uh number nine, or sorry, that was my number seven.
00:33:39.039 --> 00:33:41.440
So number eight is codex skill building.
00:33:41.599 --> 00:33:42.240
My gosh.
00:33:42.319 --> 00:33:44.240
Um, I'm big on skills.
00:33:44.559 --> 00:33:53.279
I think, you know, probably a year ago, or you know, even like December-ish, everyone was talking about lines of code, right?
00:33:53.440 --> 00:33:57.920
Or tokens, um, you know, as being like a heavy AI user.
00:33:58.079 --> 00:34:00.400
Um, I don't think that's a good metric, right?
00:34:00.559 --> 00:34:08.800
I think the number of times that you use a skill really shows if you're uh being an AI native person or not.
00:34:08.880 --> 00:34:10.239
So as an example, right?
00:34:10.400 --> 00:34:14.639
Um, I have 124 skills that I've used.
00:34:14.800 --> 00:34:19.039
Um, and I've used those skills, a total of uh I got these stats.
00:34:19.199 --> 00:34:22.000
This is just from within codex from just one of my accounts.
00:34:22.079 --> 00:34:25.679
Um, and I've used those skills 6,179 times.
00:34:25.760 --> 00:34:29.360
So I use skills obviously a lot, many times a day.
00:34:29.519 --> 00:34:30.159
Uh, you're right.
00:34:30.320 --> 00:34:34.559
And I break up these skills into multiple pieces and then create a plugin.
00:34:35.039 --> 00:34:35.199
All right.
00:34:35.280 --> 00:34:39.920
So if you don't know what a skill is, uh, it's just something that you repeatedly do over and over.
00:34:40.079 --> 00:34:43.440
And I want you to think of my codex use cases, right?
00:34:43.679 --> 00:34:55.119
Um, because I think a lot of people think of skills and they think of either just writing content a certain way, or they think of coding something, or they think of a design system that is in a skill, which is fine, right?
00:34:55.199 --> 00:35:11.199
The way I think of it, these skills um is taking a long multi-system, multi-app, multi-website task um, and breaking it down and turning each of those steps into a skill.
00:35:11.280 --> 00:35:16.239
Um, and then in codex, you can combine multiple of those skills and create a plugin, right?
00:35:16.320 --> 00:35:19.920
That's what I do for a lot of things that I run and then I schedule those things.
00:35:20.079 --> 00:35:20.320
Right.
00:35:20.400 --> 00:35:24.639
So let's say you go to, you know, heck, I'll give you one of mine, right?
00:35:24.719 --> 00:35:26.239
So you can go to StreamYard.
00:35:26.320 --> 00:35:30.159
That's what we um it's what we use for our live streaming.
00:35:30.239 --> 00:35:37.119
So you can go to StreamYard, download, uh, right, download this uh and then upload it into cast magic, right?
00:35:37.199 --> 00:35:39.280
So we do cast magic for transcriptions, right?
00:35:39.360 --> 00:35:40.880
That can be one skill, right?
00:35:40.960 --> 00:35:49.280
And then taking that, and you know, we take some of those um pieces from cast magic, you know, like bullet points of the show highlights, transcriptions, right?
00:35:49.440 --> 00:35:52.800
Then I can take that, copy and paste it into the back end of our website.
00:35:52.960 --> 00:35:54.079
That's another skill, right?
00:35:54.159 --> 00:35:58.880
So all these things that you do in succession, break them down into little pieces and save them as a skill.
00:35:59.039 --> 00:36:01.840
You can either do it after you do something, right?
00:36:02.000 --> 00:36:09.920
That's a huge, like essentially, whenever I do something quote unquote by hand, that's not a skill.
00:36:10.159 --> 00:36:12.239
I ask myself, am I gonna do this again?
00:36:12.480 --> 00:36:14.800
And chances are there's a decent chance that I might.
00:36:14.880 --> 00:36:19.039
So I create skills fairly, fairly frequently, right?
00:36:19.199 --> 00:36:21.519
Um, I've used 124 of them.
00:36:21.599 --> 00:36:27.039
Uh, I probably have a lot more that I don't use, but I've saved just in case.
00:36:27.199 --> 00:36:32.079
Um, you know, I actually have a skill that runs every single day that creates new skills.
00:36:32.239 --> 00:36:35.920
So I have a skill that goes through, it looks at all of my threads on codex.
00:36:36.000 --> 00:36:38.079
Again, something that Claude can't do.
00:36:38.239 --> 00:36:49.039
Um, looks at every single thread on Codex, and it's supposed to pull out and say, hey, these are things you're doing repeatedly, or um, this right here, you should turn into a skill, right?
00:36:49.199 --> 00:36:51.280
You went back and forth six or seven times.
00:36:51.519 --> 00:36:59.199
A lot of times, right, especially with this new technology, computer use was greatly improved with the new GPT-56 soul, right?
00:36:59.280 --> 00:37:06.159
But it sometimes makes your old skills faster, or you know, maybe certain things that worked a little better before works a little differently now.
00:37:06.320 --> 00:37:15.920
So, you know, it it's it's gonna, you know, when I'm doing new new projects or um trying to automate something new, um, a lot of times I have to go through a lot of back and forth.
00:37:16.000 --> 00:37:21.599
And that's whether it's you know, Claude, cursor, codex, anti-gravity gemini doesn't matter.
00:37:21.679 --> 00:37:22.960
That's just how it goes, right?
00:37:23.119 --> 00:37:27.760
But after you do that, that is your IP, right?
00:37:27.840 --> 00:37:29.519
That is your knowledge.
00:37:29.679 --> 00:37:34.480
And and the great thing about large language models now is well, just repeat it, right?
00:37:34.639 --> 00:37:35.280
That's the thing.
00:37:35.360 --> 00:37:43.599
People always think, like, okay, well, I'm just gonna do this every day and I'm just gonna use these models, and okay, and I'm gonna go and manually push the buttons.
00:37:43.760 --> 00:37:45.920
You gotta stop being a button pusher, all right?
00:37:46.079 --> 00:37:53.920
Go and push the buttons once, and then just have whether you're using Claude, Gemini Codecs, just say, hey, turn this into a skill, right?
00:37:54.000 --> 00:37:55.599
And it will, and it'll say the skill.
00:37:55.679 --> 00:37:59.519
Um, but yeah, you should be doing that as frequently as possible.
00:37:59.679 --> 00:38:14.880
All right, and then last but not least, uh, my gosh, um Chad GPT voice is insanely good.
00:38:15.840 --> 00:38:17.519
It is so so good.
00:38:17.679 --> 00:38:25.760
This is just another reason why I am confident like no one's gonna be touching the codex anytime soon.
00:38:25.920 --> 00:38:29.039
Um, it is so far, so far ahead.
00:38:29.199 --> 00:38:32.800
And if you haven't used Chat GPT voice, y'all, go go and look online.
00:38:32.960 --> 00:38:41.360
All the people that are, you know, normally even Claude fans and you know, bash, open AI, chat GPT, whatever, they will literally like go go find those people.
00:38:41.440 --> 00:38:42.400
You know those people.
00:38:42.559 --> 00:38:46.480
Uh everyone's just starting to talk about this like this week, right?
00:38:46.719 --> 00:38:48.239
Uh it is that good.
00:38:48.400 --> 00:38:48.800
It is.
00:38:48.960 --> 00:38:54.079
I did a show, I said this is the the next frontier of agentic work.
00:38:54.159 --> 00:38:56.559
Uh so if you don't know what it is, right?
00:38:56.800 --> 00:38:59.679
Uh I wish it was a little easier to get to in the app.
00:38:59.840 --> 00:39:09.360
So if you have the ChatGPT app, um, essentially you connect it once to the you know, either codecs or you know, ChatGPT work desktop app.
00:39:09.440 --> 00:39:16.800
Uh from there, on your ChatGPT mobile app, you open ChatGPT on the side panel, you click remote.
00:39:16.880 --> 00:39:19.920
Then there's a little button at the bottom, a little blue button.
00:39:20.000 --> 00:39:21.280
That's ChatGPT Live.
00:39:21.360 --> 00:39:26.480
So let me tell you what this is because you might say, like, oh, doesn't Quad have dispatch?
00:39:26.639 --> 00:39:28.239
Yeah, dispatch is terrible.
00:39:28.320 --> 00:39:34.480
Uh, it doesn't know any of your other threads, it only can work on one thread, and it can't really do anything, right?
00:39:34.559 --> 00:39:36.719
Aside from you can kind of chat back and forth.
00:39:36.800 --> 00:39:42.639
Uh, Chat GPT voice in remote, literally, you can control your entire computer.
00:39:43.599 --> 00:39:44.719
Anything, right?
00:39:44.800 --> 00:39:47.679
So I can be on my phone and I just did this this morning, right?
00:39:47.840 --> 00:39:51.519
I've been taking more walks recently since Chat GPT voice came out.
00:39:51.599 --> 00:39:52.079
It's amazing.
00:39:52.159 --> 00:39:53.039
Thank you, OpenAI.
00:39:53.119 --> 00:39:54.800
I'm actually getting steps now.
00:39:54.960 --> 00:39:55.519
Uh, right.
00:39:55.679 --> 00:40:00.079
Some days I'm like looking at my watch and I'm like, oh, I got like 800 steps today, right?
00:40:00.159 --> 00:40:06.079
Now it's like I got 13,000 today, uh, right, because I get work done walking, right?
00:40:06.159 --> 00:40:09.199
And hey, in Chicago, we don't we can't walk year out.
00:40:09.360 --> 00:40:17.679
So it's it's good now that I can go out and actually, you know, get some get some vitamin D, um, and in instead of sitting under the the fluorescent lights all day.
00:40:17.760 --> 00:40:23.840
But essentially, anything that you can do yourself on your computer, you can do it in ChatGPT voice.
00:40:24.000 --> 00:40:29.760
So I can literally say, you know, hey ChatGPT voice, uh look in my downloads folder.
00:40:29.840 --> 00:40:30.880
There's a new PowerPoint.
00:40:31.199 --> 00:40:33.280
Can you open that PowerPoint up?
00:40:33.519 --> 00:40:37.920
Um, and then I have a new image um inside Canva.
00:40:38.239 --> 00:40:40.480
Can you go download that and swap it out?
00:40:40.559 --> 00:40:42.639
Uh actually tell me what's on page three.
00:40:42.800 --> 00:40:43.840
What what's that image?
00:40:43.920 --> 00:40:44.079
Right.
00:40:44.159 --> 00:40:50.000
And it's gonna tell you, it's gonna literally, it's it's um, it's uh what's what's the word?
00:40:50.159 --> 00:40:51.119
Why do I keep forgetting?
00:40:51.199 --> 00:40:52.159
Uh duplex, right?
00:40:52.239 --> 00:40:53.440
Full duplex, right?
00:40:53.519 --> 00:40:58.960
So what that means is you can talk to it, you can interrupt it, it can interrupt you, it can talk and hear at the same time.
00:40:59.119 --> 00:41:02.400
But as it's talking to you, it has another model that works in the background.
00:41:02.559 --> 00:41:09.199
So, I mean, literally, I'm just just dictating, giving all these long, hard assignments, right?
00:41:09.360 --> 00:41:13.280
Hey, go go into go use this skill, right?
00:41:13.360 --> 00:41:16.159
Go go download this from this website.
00:41:16.239 --> 00:41:22.320
I'm logged in, uh, you know, upload it here, change this, tell me what's on this page, right?
00:41:22.400 --> 00:41:27.519
I am literally like like I'm on vacation and I have an intern sitting in front of my computer.
00:41:27.679 --> 00:41:29.360
That's literally what I'm doing, right?
00:41:29.440 --> 00:41:30.960
And that is what you can do.
00:41:31.119 --> 00:41:33.280
Um, it is amazing.
00:41:33.360 --> 00:41:36.559
And the great thing is it's different, which I know is confusing.
00:41:36.719 --> 00:41:40.960
It's a little different than the GPT live mode in the ChatGPT app.
00:41:41.039 --> 00:41:51.199
This is the most confusing thing because if you use that uh kind of voice mode inside normal ChatGPT, it can't access your connectors, it can't access your MCPs.
00:41:51.360 --> 00:41:53.280
Uh, right, that's the big difference.
00:41:53.360 --> 00:41:58.960
Uh, if you use Chat GPT voice mode via remote in the Chat GPT app, it can't.
00:41:59.039 --> 00:42:02.639
You can say, Hey, what are my most important emails?
00:42:02.800 --> 00:42:05.199
Okay, reply, say this, send.
00:42:05.280 --> 00:42:05.840
Uh, right.
00:42:05.920 --> 00:42:08.719
Like, hey, go, yeah, you know, whatever.
00:42:08.800 --> 00:42:11.119
You open my my my hub spot.
00:42:11.199 --> 00:42:13.119
Uh, you know, what leads have moved?
00:42:13.280 --> 00:42:14.000
Okay, right.
00:42:14.079 --> 00:42:18.079
Okay, go update this and then Slack, you know, my teammates, send them this.
00:42:18.159 --> 00:42:19.440
And it just does it all.
00:42:19.599 --> 00:42:24.639
You can literally do all your work in Chad GPT voice, as I'm starting to do.
00:42:24.880 --> 00:42:26.800
All right, so that's a wrap.
00:42:26.880 --> 00:42:27.840
That's my nine.
00:42:27.920 --> 00:42:29.440
I just gave you an inside look.
00:42:29.599 --> 00:42:33.440
Uh, yeah, I gave you a couple of hot takes there, but that's just the truth, right?
00:42:33.599 --> 00:42:36.239
Um, might this all change in a couple of weeks?
00:42:36.480 --> 00:42:37.519
It could, right?
00:42:37.679 --> 00:42:44.400
But honestly, I think um, at least for me, I don't see my workflow changing anytime soon.
00:42:44.639 --> 00:42:51.280
Um, and I think if if you've been stuck on the fence, um, just take take what I learned and run it through your own workflows, right?
00:42:51.440 --> 00:43:02.480
Run everything side by side through, you know, clawed code and codex and cursor, or you know, through you know, chat gpt.com, claw.ai, and gemini.google.com, right?
00:43:02.639 --> 00:43:03.519
Do it for yourself.
00:43:03.599 --> 00:43:09.760
But I want you to take maybe my workflows, these nine that I shared with you as a starting point.
00:43:09.920 --> 00:43:11.280
Some are more habits, right?
00:43:11.360 --> 00:43:13.199
Like turning things into skills.
00:43:13.360 --> 00:43:16.480
Uh, but some of them I think you should just be trying, right?
00:43:16.639 --> 00:43:22.719
Like, you know, try using the combination of claw design, um, you know, Google Stitch and GPT image.
00:43:22.800 --> 00:43:27.920
If you are trying to vibe code something, if you're trying to build a little app for yourself, your team, your company, right?
00:43:28.159 --> 00:43:32.719
Start there versus, you know, building it all and then saying, like, hey, this is ugly.
00:43:32.800 --> 00:43:33.599
Let's change some things.
00:43:33.679 --> 00:43:34.960
You're gonna save yourself so much time.
00:43:35.119 --> 00:43:37.039
So uh I hope this one is helpful.
00:43:37.199 --> 00:43:39.679
If you like this type of show, let me know.
00:43:39.840 --> 00:43:41.440
Maybe I'll do another one or two.
00:43:41.599 --> 00:43:48.400
Uh, but that is it inside everyday AI and my nine most used AI tools and workflows.
00:43:48.480 --> 00:43:54.480
If this is helpful, please subscribe to the podcast, then go to your evereverydayai.com, sign up for the free daily newsletter.
00:43:54.559 --> 00:43:55.199
Thanks for tuning in.
00:43:55.440 --> 00:43:57.840
See you back tomorrow and every day for more everyday AI.
00:43:57.920 --> 00:43:59.039
Thanks, y'all.
