Leveraging AI

286 | How to Automate Anything with Browser Agents & Zero Code with Chris Daigle

• Isar Meitis, Chris Daigle • Season 1 • Episode 286

Share episode

Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.

0:00 | 37:15

You learned how to prompt. Great. Now what?

Most business leaders have figured out how to get decent answers from ChatGPT or Claude. But there's a massive gap between writing good prompts and actually building things that run your business. The people closing that gap right now aren't developers. They're business people who figured out one thing: you don't need to code when your browser can do it for you.

In this session, Chris Daigle will open his actual setup — Claude Code paired with a browser agent — and build real solutions live. Not slides. Not theory. You'll watch him set up OAuth integrations, automate LinkedIn workflows, and tackle the kind of backend tasks that normally require a developer. All through a browser. All without writing a single line of code manually.

Chris calls this evolution "thinking in builds" — the next level beyond prompting. It's where you stop asking AI for answers and start asking it to do the work. And the tools to do it are shockingly accessible: a free browser agent and a $20 Claude subscription.

Chris Daigle is the founder of ChiefAIOfficer.com, where he helps mid-market executives and their teams develop AI strategy, implement AI across departments, and become AI-enabled businesses. He trains Chief AI Officers, keynotes at YPO and Vistage events, and has been deep in the agentic AI space since its earliest days. Chris brings the rare combination of strategic thinking and hands-on building.

In this session, you'll discover:
- How to pair Claude Code with a browser agent like Comet to build real workflows — step by step
- What "thinking in builds" means and why it's the skill that separates AI users from AI builders
- How to automate OAuth setups, API integrations, and other backend tasks without touching code
- Real examples of browser agent workflows you can copy and use immediately
- Why even seasoned AI professionals are underestimating what browser agents can do right now
- How to safely sandbox your AI agents so they don't destroy your production environment
- The exact copy-paste workflow Chris uses to go from idea to working solution in minutes

This is the session where prompting graduates to building. If you've been watching everyone talk about agents but haven't actually deployed one yourself, this is your starting point.

About Leveraging AI

If you’ve enjoyed or benefited from some of the insights of this episode, leave us a five-star review on your favorite podcast platform, and let us know what you learned, found helpful, or liked most about this show!

[00:00:00] Isar Meitis: Hello and welcome to another live episode of the Leveraging AI Podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, and advance your career. This is Isar Meitis, your [00:00:15] host, and in today's episode, we are going to dive into one of the coolest capabilities.

[00:00:21] AI gives us today, and that capability is actually a huge unlock to anybody who wants to start building slightly more [00:00:30] complex AI solutions than they're building today. So if you're just getting started on your journey of building advanced AI solutions, or even if you got started already and you're building a few things and you're doubling with it, you know that there are technical [00:00:45] aspects that you just have to figure out.

[00:00:47] These things can be setting up an OAuth two to whatever system or creating a project on Google Cloud to host whatever it is that you're trying to do, or setting up web hooks to different tools that you [00:01:00] want to connect to. And to be fair, I don't have a clue what an OO two means. I know roughly what is required in order to create a Google Cloud, uh, project, and I definitely do not know how to set up web hooks.

[00:01:13] But [00:01:15] I have done this multiple times, and the way I'm doing this is I'm allowing AI to do it for me. So if you're not a highly technical person, these things probably scare you. Like I don't, I don't know what that means and I don't wanna deal with it. But in many cases, once you start [00:01:30] building more advanced solutions, it becomes a necessity.

[00:01:33] The good news is today. Our guest, Chris Dele, is gonna show you exactly how to do this. He will take you step by step through the different things and how to use [00:01:45] AI and to be more specific, how to use an AI browser in order to set up literally any technical thing you need to set up in order for your AI automation and solution to work.

[00:01:56] Now, Chris is the founder and the CEO of [00:02:00] Chief AI Officer, and in the past three years or so, he has been helping individuals and teams and companies develop strategies and the tactics on how to implement AI successfully in their businesses. Now, [00:02:15] because of that, Chris has a very solid understanding in both the strategy.

[00:02:19] And the tactics, and this is why today's episode is gonna be a goldmine to show you exactly how to combine these two things together, the strategy around it, as well as the tactics and how to [00:02:30] make it work. And like I said, on things that are usually big showstoppers to people, to people who are not technical people.

[00:02:37] And this is why I'm very, very excited about this episode and I'm excited to welcome Chris to the show. Chris, welcome to leveraging ai. Thanks buddy. 

[00:02:47] Chris Daigle: Thank you so much for the, uh, honor and opportunity. So awesome. For those of you Yeah, for those of you listening, I just want to let you know, uh, I, ISAR was the first like AI person that I, I met in [00:03:00] my career.

[00:03:00] I don't know if you remember when I was in Orlando, 

[00:03:02] Isar Meitis: I did reached, we 

[00:03:03] Chris Daigle: met face to face 

[00:03:04] Isar Meitis: in a nice restaurant in Orlando. Yeah, 

[00:03:06] Chris Daigle: yeah. Seasons 52, I guess it was. But anyway, so I agree. Um, we, we've got some, we've got some history. 

[00:03:12] Isar Meitis: Yes. Yes. Uh, so, so, yeah. You [00:03:15] know, you and I do very similar things. We help companies in, uh, slightly different ways, but, but to achieve the same goal, right?

[00:03:22] On how to become an AI first company and how to be, uh, grow a business around AI and how to remove [00:03:30] blockers from whatever you're doing right now by leveraging AI to do that. And that's why I think the topic we picked today is really, really awesome. Because I think a lot of people, whether they're solopreneurs or in big, large businesses, yeah, these are huge showstoppers.

[00:03:43] Like, I, I just don't know how to do [00:03:45] this thing. I don't even know what it means. And yes, you can go and watch 25 YouTube videos and try to follow them step by step. In many cases it will work, but it will take you three to four hours instead of letting AI do it in five minutes for you. 

[00:03:57] Chris Daigle: Yeah, for sure. Um, and I think that [00:04:00] it, it is important that this does apply to the solos who want to be building their own stuff or product or whatever, or the executive all the way up the, the chain that's like, I just don't like doing this part of my job.

[00:04:10] It'd be cool if I had an app or, uh, an automation that did this, right? So, [00:04:15] um, I'm not a technical person. Um, we don't define the role of a chief as a chief AI officer, as a technical person. I see it more as an operational person, right? So that's the lens that I'm sharing this with you. And we don't have a, a, we've got a small tech team, I guess, [00:04:30] for our own company.

[00:04:31] Uh, and we've created this culture of, of training people to be their own builders right now. Not for something that's necessarily gonna be attached to sensitive information or, uh, you know, products that we're selling, but to self-serve on [00:04:45] solutions when it comes to, um, this is a, a, a task in my job, or, you know, the contribution that I wanna make, the deliverable I wanna produce.

[00:04:53] Um, it would be cool if I, and maybe a GPT, don't cut it. Maybe a prop chain. Don't cut it, right? It's time to [00:05:00] create something. So one of the first experiments that I, I did with this that's gonna, um, result in, in this framework I'm gonna share with you today was we, uh, sponsor and speak at a lot of Vistage events.

[00:05:13] And if you're not familiar with Vistage, [00:05:15] it's like a local CEO peer group. Um, you know, people that take their, their businesses seriously enough to invest in their, you know, their peer group. And I, I'm very curious like, uh, on collecting data, what's going [00:05:30] on on the front lines of AI like that, that I know what, I know what Essar and, and I are up to, but we live in a bubble man.

[00:05:35] Like the stuff that we're thinking about and talking about, like, you think everybody else knows the stuff, but they don't. Um, so, you know, we started with a survey, [00:05:45] uh, a Google form, right? I mean, for an AI company that's, I guess it's a little like indie or whatever, but. Not the, not not on brand for how I wanted to, but it 

[00:05:55] Isar Meitis: works.

[00:05:56] It works. It's effective, 

[00:05:57] Chris Daigle: it's 

[00:05:57] Isar Meitis: free anywhere it works. 

[00:05:58] Chris Daigle: Yeah. And [00:06:00] as they say, version one is better than version none. Um, 

[00:06:03] Isar Meitis: agreed. 

[00:06:04] Chris Daigle: But I wanted to not just capture the information because then it's stored in a, a spreadsheet on a, you know, and I gotta go where, what drive folder was that in? And oh, I gotta share it with somebody else.

[00:06:13] And the, [00:06:15] the extraction of intelligence from the multiple entries was cumbersome. Yeah. So what I wanted to do was, but, and, and also like, it was like, thank you. At the end of the result, there was no real value for [00:06:30] the, the participant other than the just to, you know, participate in the survey and, and the survey of, of collecting the data.

[00:06:36] So I said, man, it'd be great if we had some sort of like a, an opportunity audit or a risk assessment or something where we could ask those same questions. But there was [00:06:45] logic behind it and there was, you know, uh. Based on all the choices that they made, that there was, um, a recommendation that was, you know, oh, that's pretty good.

[00:06:55] You know, lemme take that back to the team kind of thing. That they could get on the spot. Yeah. Okay. [00:07:00] I'm not building that in a Google form. Um, so, uh, I found initially one of the easiest places to build was Google AI Studio for me. Right? 

[00:07:10] Isar Meitis: Yep. 

[00:07:11] Chris Daigle: And do we do screen shares in this? Are we just talking through it today?

[00:07:14] Yeah, 

[00:07:14] Isar Meitis: a hundred percent. A [00:07:15] hundred percent. So I'll, I'll say two things before you jump into the screen. Share. Yeah. Uh, one for, uh, for those of you who are joining us live, first of all, thank you. There's a bunch of people Yes, both on LinkedIn and on, uh, and on the Zoom call. So if [00:07:30] first, introduce yourself, say where you're from, what are you trying to get outta this is so we have a better idea on who you are.

[00:07:34] And obviously if you have any questions to Chris or myself, please write them in the chat. I'm monitoring both the Zoom chat and the LinkedIn chat, so I, I'll be able to answer these questions or deliver the [00:07:45] right questions to Chris at the right time. Uh, if you're not here live, the question is why we do this every single Thursday with really amazing people like Chris, who share really amazing knowledge.

[00:07:54] And if you are not here, well, you can still listen to us on the, on the podcast or watch us on YouTube. Uh, but you [00:08:00] can't ask any questions. You can't, uh, engage in, in network with other people. And so come and join us. Uh, we do this every Thursday at noon Eastern time, and there's a link in the show notes.

[00:08:10] So if you're just listening to this after the fact, you can use the link to join us in future. [00:08:15] Episodes. Uh, the last thing that I will say, and then I'll give it back to Chris, is we are going to explain everything that's on the screen. So if you're not watching the screen right now because you're driving a car, walking the dog, washing the dishes, whatever it is that you're doing, when you are, uh, when you are, uh, [00:08:30] listening to this podcast, it's fine.

[00:08:31] We're still gonna explain everything that's on the screen. 

[00:08:34] Chris Daigle: Yep. And I'll second that endorsement. Like, I'm an AI professional. I'm, I'm busy, I know this stuff, but I listen to, to Issa's podcast, so 

[00:08:42] Isar Meitis: I appreciate that. Thank you. 

[00:08:43] Chris Daigle: Yeah, for sure. Man, [00:08:45] there's high signal, low noise in this environment. Okay, so I'm gonna share my screen and I'm gonna show you.

[00:08:50] What you're gonna see is, um, 

[00:08:52] essentially the, the, the front end of Google AI Studio. Um, I like, we're a Google, uh, workspace [00:09:00] business. So for us, this is, I mean, it's free, right? It's, well, yeah, we're paying for it somehow, but it's not like an extra charge or anything like that. So if you have a, a Google, uh, Gmail account or whatever, if your business runs on a Google workspace.

[00:09:13] You're not using this. [00:09:15] That's bananas. Okay. So what we see here is essentially the, the front page of, uh, Google AI Studio. And like most large language model or generative AI environments, it's got the dialogue box where I can put in my prompt, right? So very easy, and [00:09:30] it's got the, it almost looks like a custom GPT with the suggestions and all that kind of stuff, or maybe a gym more appropriate.

[00:09:38] So let me take you into some of the stuff that we've built. So, um, where are we? My apps, there [00:09:45] we go. So I'll run you through 

[00:09:47] Isar Meitis: an example. I'll say one thing, uh, yeah, just one thing before we dive in. So most people in the Google universe probably know Gemini, think about this as more of the geeky side of Gemini, right?

[00:09:59] So [00:10:00] you can do the same thing you can do in Gemini, you can do here, but you can do a lot more such as develop entire applications or analyze entire videos or do, uh, more detailed things than you can do in the regular Gemini. And the [00:10:15] only difference is that it actually uses the API, which means you're gonna pay for tokens versus in Gemini it's kinda like included in your membership.

[00:10:23] So that's the only difference. But you can do really advanced, cool, amazing stuff with a user interface that looks [00:10:30] like a regular chat. 

[00:10:31] Chris Daigle: Mm-hmm. So, um, for me, going back to that, that AI opportunity audit, let's call it, right? And just let's fast forward. The tool that we are using is now like. [00:10:45] A standard part of our sales process.

[00:10:48] Like, so it started with a Google form and a good idea. I had this idea that, you know, I wanted to be able to ingest the information from the people, use AI to process it like on the spot and give [00:11:00] them a recommendation, Hey, based on your answers looks like you could benefit from here, or hey, there's risk here, or whatever the case might be.

[00:11:06] Um, we've now turned that into a, uh, kind of like part of our, our discovery call where we run this. Um, so it wasn't just like a [00:11:15] cutesy vibe coded one-off kind of thing. It's, it's now got commercial application, but man, I've never coded anything. Um, you know, I had a hers, a cursor account maybe in September of 2024.

[00:11:27] And it was cool watching, like all the codes show up, but I [00:11:30] couldn't ever get anything to work. It was, um, it was a glimpse and I, I think if you're involved in ai, you don't get discouraged when something doesn't work because you know that like. It's just a matter of time before they, it, it's working [00:11:45] really, really well.

[00:11:45] So I was excited to see that stuff, but again, like I'm not a coder. I, I, I didn't, I was like, I'll, I'll get some use out of it. So with, um, Google AI Studio, I just kind of went in there and like, like with any of these [00:12:00] tools now, I guess I don't use lovable or base or any of those. I don't need to use 'em that often.

[00:12:04] Um, I just hold it what I wanted, kinda like a prompt, right? And I gave it, um, uh, a link to the, the Google form and that sort of thing. And so that started a process, an [00:12:15] iterative process of me and the, the brain, I guess Gemini 3.1 or whatever version we were using at the time, going back and forth in iteration.

[00:12:24] And I like best practice, hell no. But when I first got started I was like, oh, [00:12:30] make it do this. Oh, and make it do this. There was no PRD or if you're familiar with what that term means, there's no like product plan. It was just as I was going through it. I would encourage you to do the same thing, like eventually move to the professional stuff.

[00:12:44] But how you [00:12:45] learn about using these things is by using these things. And if there's some intimidation about, well, I don't know how to use it, just go in there and be dumb. Hey Jim, and I don't know what I'm doing, but I'd like to build an app that does. I have no, you do that. And, and what happens [00:13:00] is, you know, repetition is the mother of skill.

[00:13:02] You start to learn little bits here, a little bit. Oh, next time I'll do it this way. Oh, I should have asked for this, right? So I went through that process and, but where I kept getting stuck was, okay, great. I'm collecting [00:13:15] the information and I'm, I'm spitting out some info. But, and one of those ideas was, oh, let's send them a report.

[00:13:21] Seems pretty easy, right? Like, okay, we've already got the information on the screen. Let's send 'em a report. It's not, there was like a a, if I wanted it to be in PDF, it needed to be, [00:13:30] um, there was stuff that was happening like on, uh, fire, uh, whatever Google's database are firebase. And there was like all these things.

[00:13:38] We're Google developer tools, and I was just like, man, I cannot let you know this is I [00:13:45] I'm onto something here. I can't let that stop Now. Go try and find talent on Upwork that, that knows how to use these AI tools. I mean, everybody, everybody claims they do, but like, you know, Esau and I, we have a discerning palette when [00:14:00] it comes to talent on ai.

[00:14:01] So to find the right person on, on like Upwork or something like that ain't happening. I'm a startup. I'm not gonna be able to pay us based, you know, New York City develop, uh, vibe developer rates. So it was up to me [00:14:15] and, uh, one of my mentors a long time ago saying that I use all the time if it is to be, it's up to me.

[00:14:20] Right? So I had to take responsibility if I wanted this thing to, to present my company. Well, if I wanted to capture the information so that I could action it if I wanted to [00:14:30] make sure that the, the prospects that were on, you know, sales calls with us, were having a, an experience like an a wow experience, uh.

[00:14:38] I was gonna have to figure this out. And it was about that time that I started getting into, [00:14:45] uh, the Comet browser from Perplexity, um, chat. GBT has Atlas. I don't use Atlas much. I, you know, I'm pro user at or max or whatever it is, at chat GBT 200 a month. So like, I'm, I'm a power user of chat GBT, but I don't use [00:15:00] their Atlas browser.

[00:15:01] Um, so I was, I've been a big fan of perplexity for, you know, since the beginning. I've been teaching people about it since 2023 or whenever it came out, pretty much. So when the browser came out, I was particularly interested. Make sense. I could [00:15:15] do my little perplexity stuff on deck. I don't have to necessarily contact Switch and go here and forget stuff.

[00:15:20] But it was this thing right here, if you can see my screen, it was this assistant. Button up here. And if you're, if you're not looking at the screen, um, it's a [00:15:30] Chrome based browser, so it looks very familiar. All your plugins that you have in your, your Chrome or whatever, they work here 'cause it's Chrome based.

[00:15:38] But Perplexity is giving this browser away for free. And one of the things that comes with it is in the upper right hand corner, we'll call [00:15:45] it a browser agent, it's listed as an assistant because most people are like, if I were to go to a YouTube page right now, let's try that actually, just so you can see.

[00:15:55] It's more like, you know, speeding up the process. But if I go to assistant when [00:16:00] I'm on the, let's take a look at what up.

[00:16:05] Okay. So the instant or instantly it's, it's suggesting, do you want me to summarize this video? Extract key takeaways, scroll to the next interesting moment. Right. Helpful for sure. [00:16:15] But, um, if I wanted to do something, if I want to, I, if I want the perplexity browser to take over. My, uh, browser and perform actions for me.

[00:16:28] It can do that. [00:16:30] Um, I'm not gonna give away some of my secrets, but like, for instance, oops, I hope nobody from LinkedIn is watching. But, so I, I, I use, um, and I had, you know, a couple hundred messages and my DM that I just, [00:16:45] I love, uh, LinkedIn. I love, you know, interacting on it. But the DM thing, I'm just, I'm bad at email, I'm bad at texts, I'm bad at dms.

[00:16:53] So I've, CR now created something to where, um, the perplexity browser will take over this particular tab [00:17:00] and it'll ex, it'll explore the messages that are coming in and, um, prioritize them based on opportunity and that sort of thing. Very helpful because otherwise I just wouldn't be able to do it. But now I take 30 seconds in the morning, give it, give it its instructions, and then off to work.

[00:17:14] [00:17:15] I go, um, by doing that sort of thing, it hit me. It was like, oh, wait a minute. I need the OAuth to, I need the pdf. Like engine tied into a, a hosted blah, blah, blah, blah, blah. Right? I [00:17:30] didn't even know what those things meant. I mean, I understood conceptually, but I didn't know all the stuff. And as Isar pointed out earlier, my options are perplex, you know, plex it, I guess take, go to perplexity.

[00:17:41] Hey perplexity, how do I do this? Right? I could get the instructions [00:17:45] from, uh, the, the AI studio. It was happy to give me those, Hey, give, give me those step by step. But even doing that, like the, the time just wasn't there. It was, it was, it ended up being projects that were like, lemme get, you know, 45 [00:18:00] minutes now, oh, I gotta do this call.

[00:18:01] Oh, uh, lemme try and get to it later and later and later and later. And it was just an open loop. And it wasn't because I wasn't clear on what I wanted. It wasn't because I, I didn't have something that was, you know, viable or marketable. It was those technical skills and I [00:18:15] didn't have the budget or the, uh, the staff, the team, the internal knowledge to be able to do those things.

[00:18:22] So it hit me. Hey, Gemini, or hey, AI Studio, I'm gonna be using the [00:18:30] Comet browser agent to do this for me. Can you give me these instructions in a way that I can copy and paste them to the browser agent and let it cook and the [00:18:45] entire technical world open up to me? I'm, I'm, I'm being a little hyperbolic.

[00:18:49] But, um, u using that it, it was able to set up the OAuth two and test it and all, all the things that I would've paid [00:19:00] a US based person, I don't know, maybe a hundred bucks an hour or more to do, maybe more if I could get their, get on their, you know, their clock or hours of my time. And since then, now anytime that I'm building something and I, and I don't build a, I say I don't build a lot, but I [00:19:15] probably build something every week.

[00:19:16] And for me, that's not a lot. But for. Others that might, and now my team is doing the same thing. Anybody who's on my team that, that has that idea, they already know how to do what we call think in ai, right? But now they're [00:19:30] thinking and builds because they have access. Everybody in the company uses, um, the comic browser here and the agent to help them build these things.

[00:19:39] And now with clients, we're building MVPs. Any of our Chief AI officers are now building MVPs [00:19:45] in a couple of hours. And before it was like, okay, get your requirements together, let's get it over to the dev team. And there was just this big lag time. I have set stuff up, set stuff up on CloudFlare. I have, uh, [00:20:00] you know, everything inside of the Google API environment.

[00:20:04] I, I have done it, I guess. I mean, I, I've led the doing of through these agents. And here's the beautiful part about using this is that, okay, I've got this tab [00:20:15] open. I wanna do something with, um. Uh, you know, I wanna do something with, with setting up a, a, a database so that I can store all of these answers and I can ship 'em out to people when they put in their email address.

[00:20:27] I can get, capture the opt-in and all that stuff, right? A [00:20:30] lot harder than it sounds when you're building from scratch. Um, but the, the gap between me having the idea and me being able to launch something because of this particular tool has, [00:20:45] uh, been compressed to a 30 minute session. No kidding. I mean, now again, am I saying that your first time out?

[00:20:52] Hell no. Like, I spent hours, and you will too. If you get into this stuff, the first few times it's hours and it's like, you know, [00:21:00] breaks or whatever, but it's enough. Even, even as a brand new user, there's enough confirmation from the, the device, from the models, from the tools that you're like, you know what, I, I could do this.

[00:21:12] Like, there's just a couple things that I didn't know, but now I know [00:21:15] them. Let me try again, and then you're gonna land it. Um. 

[00:21:19] Isar Meitis: Awesome. I I wanna pause you just for one second to add a few, a few things that I think are, first of all, this is fantastic, right? So just for those of you as a quick summary and recap, you get [00:21:30] to a point that there's a technical aspect in the process that you did not know how to do, and the AI in whatever tool you're using.

[00:21:36] Again, in this case we're talking about Google AI Studio, but this could have been clawed, this could have been anything else. And he tells you, oh, now you need to set up this thing. I'm like, I, I dunno what [00:21:45] this is, what Chris is doing. Say, okay, give me the instructions of exactly what needs to be done and what it needs to be set up to.

[00:21:51] And then he takes that instructions and he gives them to a browser-based AI tool that can take over the browser and then it can [00:22:00] actually do the thing. So it doesn't tell you what to do. And by the way, using perplexity a lot, it happens a lot like perplexity. The assistant in the browser said, oh, to do this, you need to do 1, 2, 3, 4, 5, 6, and no, no, no, no, no.

[00:22:13] You do this. Like, oh, okay. [00:22:15] And then he takes over the browser and actually goes and does the thing. Yeah. A few things about, uh, variations of this, or I'll say one thing that is a variation of this and the other is a, um. Is, [00:22:30] is the concept that I think people have to think through the variation of this. I build most of my stuff in Claude and, and by the way, same thing for Jim and I, but Claude has its own browser controller, so it's the same exact thing, but it's a Claude [00:22:45] extension.

[00:22:45] Yes, it opens on the side, but Claude Cowork and Claude Code. Know how to control it. What it saves me is copying and pasting the instructions or copying and pasting the results back to, in this particular [00:23:00] case, Google AI Studio. So I just work with cloud code or Cloud Cowork, and I say, Hey, you know what?

[00:23:05] Go and do this in the browser and then it on its own. We'll open the browser, do the thing, and figure out and set up everything. And when it gets stuck, it deals with it. I don't have [00:23:15] to copy stuff back because the, the brain of Claude Cowork that is aware of the bigger thing that I'm building knows what the required output it, and it goes back and forth with the browser and I don't even have to see the browser, which is fantastic.

[00:23:28] The only times you have to go [00:23:30] in is like popup screens that it doesn't have access to. Like if you need to log into something, okay, you need to log into your Google account. I don't, I can't do that. So these kind of things are the only things that require your attention, but then you just go to that browser page that's open by Claude and you go and [00:23:45] do the thing.

[00:23:45] So this is kinda like a, a cheat to get this even. Slightly less work. Yeah. The bigger thing here is I think the, the mindset, and I'll explain what I mean. We are humans [00:24:00] are the bottlenecks to most digital work today, period. Right? So if, if you need to do a process, whatever the process is, whether it's writing a proposal, analyzing information, creating a form for your customers, like all these kind of [00:24:15] things, you are the bottling.

[00:24:17] The more you can remove yourself further and further away from the doing, the better off you will be. You want to be the thinker, the ideator, the brain, [00:24:30] uh, and let AI do the thing. What does that connect to? Chris talked earlier about doing this the old school way, completely manual, not acceptable, not enough time in the day, not worth your time.[00:24:45]

[00:24:45] Second option is. I'm gonna wing it, which is what is suggested starting with, which I agree is a good starting point because you learn how this thing works. I'm gonna go step by step by step and try to figure this out together with ai. Step three, which you also mentioned is [00:25:00] A-P-R-D-A product requirements document.

[00:25:02] Having build a process where the AI interviews you about the whole thing. What are trying to build? What are the goals? Who's the target audience? Why is this required? What pain points does it solve for me? What kind of [00:25:15] technology needs to run on? Does it runs on phone, it runs on a Mac? Like what? What does it need a browser?

[00:25:20] Have it ask you all these questions, have it create a requirements document and then give it back to the ai. Say, okay, now [00:25:30] implement this. What happens then is you remove yourself from. 80% of the process, not a hundred percent. And that's a good thing. You want it to come back to you when it gets stuck, you want it come back to you when there's issues, you want it to come back to you when there's [00:25:45] decisions to be made.

[00:25:45] Like there's, there's things you wanna be involved in, but it now has a full spectrum of understanding of the different aspects, components, requirements, needs, goals, and you will do most of it on its own. So [00:26:00] now you removed yourself another step away from doing the doing, which means you can focus on more of the right stuff, which is thinking, developing, growing, uh, and so on.

[00:26:10] So even in the subtext of what Chris was saying, [00:26:15] there's a lot of really, really important stuff. 

[00:26:19] Chris Daigle: Yeah. Very cool. Um, so yeah, and for those listening, the way Issa just described, the way he's doing it better, better than what I'm doing. So, [00:26:30] um, but I'll tell you, um, it, you know, it's good to, to. To at least have gotten some, some reps with all the tools a hundred percent.

[00:26:41] So, you know which ones work, but there's no question that, [00:26:45] uh, Claude code plus cowork plus their browser extension. You know, I, I think it's because I started using Comet before the, the browser extension came out that I, I don't know if I'm set in my ways or whatever, but [00:27:00] I've got, uh, something that's workable.

[00:27:02] Isar Meitis: No, it's, it's working amazingly well. By the way, I started exactly like you, I started with Comet. I will say one more thing about, about the perplexity universe, perplexity, computer controller, whatever they call it, I think it's just called computer. 

[00:27:14] Chris Daigle: [00:27:15] Computer, 

[00:27:15] Isar Meitis: uh, allows you to do. Incredible things. Very, very similar to what I just said too about Claude because A, it now has the brains of like 10 or 12 different AI models.

[00:27:28] Yeah. So think about Claude [00:27:30] code, but with 12 models running behind the scenes and it picks the right things for the right stuff, and it has browser control and it has control over more or less anything on your computer. So it is another way to [00:27:45] get to achieve what I described, if you like, the perplexity universe, which is really, really good.

[00:27:49] Mm-hmm. Like I have nothing against perplexity. Uh, just like, just like you said, I, I kinda like planted my flag for now on the Claude Universe. Yeah. And when I say for now, that may change next week if [00:28:00] something more interesting, more relevant or more useful will come out. But for now, I mean that universe.

[00:28:05] But, but there is a almost identical process in their perplexity universe with their computer use, uh, solution. 

[00:28:14] Chris Daigle: [00:28:15] Yeah. So, you know, I guess, I guess the, the TLDR of that story is that as somebody who's not a technical individual, um, you don't need to be, if you can write a [00:28:30] sentence right, or have, ask AI to write the sentence for you, then you can do these things leveraging this, these EnTec browsers or the plugins, like the, 'cause I guess Manis has got a plugin.

[00:28:42] If you're a Manis junkie, um, [00:28:45] uh, open Clause got a plugin for browser control. Yeah. Yeah. Um, so this, this is a thing. So if you're, if you consider yourself a, you know, an AI power user or, or an effective user, and you're not. And you're just using, maybe you say, [00:29:00] oh, I use Atlas, or I use, you know, the, the extension.

[00:29:03] But you're using it for the basics and you're not, not necessarily really putting it to work for an expertise that you don't possess. Um, there's still, you still got a little more runway before you can, [00:29:15] uh, truly, I, I would suggest call yourself a, an expert. Not, not to to slight anybody, it's just, but once expanded from, listen, like, your mind is not gonna be able to contract to its original state.

[00:29:25] You're hearing this stuff now. So it's, it's, it's now on you to go, okay, [00:29:30] do I get back out of my comfort zone and go figure out a new tool? But the answer is yes, as like with any of these tools, the learning curve is designed to be fast, right? Like generative AI is, is my children literally can use it, right?

[00:29:44] Like, that's [00:29:45] the design behind this stuff. So. As somebody who is listening to this, you're looking for opportunities to shave more time off of your, you know, your production efforts. And this is an area [00:30:00] where I would suggest that I use it, like I pay the, whatever the hell perplexity charges for their top tier because exclusively because of I was running out of that agentic, like I was just power using the hell out of it.

[00:30:13] And I'm [00:30:15] not the technical guy. There's probably smarter ways to do all of this stuff, but, you know, trying to over-engineer your, your AI use is not a recommended practice. I would suggest just get in there and like, like, like me and [00:30:30] just I'm okay being dumb. Hey, never done this before. What tools should I use?

[00:30:34] How can you help me? And the, the point that Isar made earlier is like, it'll say, oh, do this. The key phrase is you type. Can you do it for me? And it's [00:30:45] like, oh, sure, let me get to work. Um, but the cool thing about that is about using this, whether it's the research side or, or it's, it's actually pushing the buttons and doing the technical stuff for you.

[00:30:57] That happens in one browser tab. You open up [00:31:00] another browser tab and you can have another thing happening and another thing happening and another thing happening. So it's, it, it really, the limitation is gonna be your, your cognitive processing shifting from linear [00:31:15] to, uh, almost like hub and spoke with you being the, the hub.

[00:31:19] And I need this done and I need that done and I need that done. And when that's done and need that done, that would be as compared to, okay, here's my checklist, step one, step two, step three. [00:31:30] So, uh, just, but once you start thinking in that manner, all of these. Tools that, like stacking them and figuring out like, when do I use it?

[00:31:41] And I mean, even as a, a quote unquote AI expert, right? Still [00:31:45] there's, there's times where I'm like, why am I doing this manually? There's, there's, you know, in my case, 53 years of programming that has happened to where my muscle memory is not to think in ai. It's not to, I mean, it's become that way, but it's not to, you know, Hey, how can an agent do me?

[00:31:59] I [00:32:00] mean, like, how can an agent help out with, how can multiple agents help out with multiple tasks simultaneously? So it is, um, uh, uh, uh, I guess a, a learning curve a bit, but it's a fun learning curve for sure. 

[00:32:13] Isar Meitis: A hundred percent. I, I, [00:32:15] I wanna piggyback on two things you said. One, you said skills you don't possess.

[00:32:21] Uh, we start, everybody that starts with AI starts with, how can I make what I'm doing today more efficient? [00:32:30] Which is awesome. It's great. It makes you more efficient. You, your team, your company, whatever the case may be. The real unlock, the real value, the bigger ROI comes from doing things you cannot do today, either you yourself, your team, your, your [00:32:45] department, your company, right?

[00:32:46] This is where the bigger unlocks come. Like if you can do three x what you're doing right now, including things you've never had the skills to do, you can make more money with the same amount of resources. This is where it gets really interesting, [00:33:00] right? It's, it's not by, oh, I can, I can now write a document faster is I can now set up a system that uses a cloud, a Google Cloud project with OAuth two that connects to these three APIs to do this thing.

[00:33:13] I don't have a freaking clue what [00:33:15] OAuth means. I don't know how to set up an account and I dunno what an API is, but I know that all these things, the AI told me if I had them, I can do this other thing that I really want as an outcome. And now you can do that. So I, I, I [00:33:30] love the way you phrased it, like skills they don't possess.

[00:33:32] This is, this is the, the biggest thing is, is, is that the second thing that you said in the end that I really agree with is you have to start thinking in a [00:33:45] parallel manner, which the human brain is not geared to do. Yeah. 'cause historically, whenever needed to, and you need to become better and better in context.

[00:33:54] Shifting I run at any given moment, literally any given moment, [00:34:00] five to seven different projects at the same time all the time. Always. And knowing what you did in which project, what was the last thing that happened? Skimming through what the AI said, making a quick decision on what needs to be the next [00:34:15] step.

[00:34:15] So you can switch, switch to the other six or seven. Is, is a skill that we all will develop. Yes. The sooner you develop that, the more effective you become. Because if you are paying and, and you know, Chris is saying [00:34:30] he's max on, on his plans, I'm the same way, right? Like, whatever the tools that I'm using, whatever the top tier, I'm gonna go there.

[00:34:37] Not because I'm, I'm not showing off because on the tier below that I get stuck around 2:00 PM and then it says, we come back tomorrow. And that's not [00:34:45] acceptable from my perspective. And so I will pay the $200 a month not to get stuck at 2:00 PM on the things that I'm doing. So I can run six or seven projects in parallel at any given moment.

[00:34:57] Now that means that I need to [00:35:00] use that and to use that, I need to be able to shift back and forth and back and forth very, very quickly. And I did not know how to do this. Three and a half months ago I taught myself and now it's second nature. I don't even think about it. And so it's, these things start with [00:35:15] two.

[00:35:15] So with two things running in parallel and, and jump back and forth, and then three and then four. And then you'll, you'll get to the point where, where there's diminishing returns. So like, okay, if I go beyond and I know that my number is like six or seven, if I go beyond that, then I, I, I don't actually, [00:35:30] I leave a lot of stuff not actually running and doing anything.

[00:35:33] Chris Daigle: Yeah. 

[00:35:33] Isar Meitis: And I'm not focused enough on the things that I'm doing. So that's kinda like my limit. Maybe yours is 20, maybe yours is three, but you will figure it out as you try to do this more and more. Chris, this was fantastic, as I [00:35:45] said, both, both on the tactical side on how to do things, as well as a lot of really important concepts.

[00:35:50] If people want to follow you, work with you, learn from you, connect with you, uh, listen to your podcast, you have a podcast as well. Yeah. What are the best ways [00:36:00] to do that 

[00:36:01] Chris Daigle: podcast, episode 100 is coming out in a couple weeks. Um, it's called Using AI at Work. Um. Love to have you, uh, take a listen. Um, and then as far as at Chief AI Officer, we have a very active community.

[00:36:13] It's free, it's full of [00:36:15] a few thousand non-technical business professionals who are, you know, serious about the application of AI and the, the, the, what does it mean for techno, for the society, and how do I make more money with it all the conversation that's happening there. [00:36:30] And it's free, it's chief ai officer.com/community.

[00:36:33] So we'd love to see you there as well. And Isar, thank you so much for the opportunity. I know your audience is, uh, they're not like, it's a good, good audience, smart people. 

[00:36:43] Isar Meitis: Awesome. Thank you so [00:36:45] much. Thanks everybody who joined us, uh, live. And, uh, both on LinkedIn and on the Zoom. I appreciate all of you. I know you have other stuff you can do on the Thursday, uh, early afternoon or, or whatever time it is for you.

[00:36:58] I know there's, uh, at least a [00:37:00] few people joining from Europe, uh, every time. And so, uh, thank you all for joining us. Thanks Chris for again, thanks everybody. Fantastic episode. Have a great day, everyone. 

[00:37:10] ​

Head Shot

Isar Meitis

Host