Loading summary
Transcript56 lines
- [00:00]
A
Eventually you will get fired because AI will replace everyone at some point or we will find new ways to do our job.
- [00:07]
B
What are the things that a PM needs to know if they're going to go from PM to founder to really succeed?
- [00:13]
A
When we say that PMs are getting fired, I think it's important to clarify that it's the non technical PMs that are getting fired. The technical PMs are actually staying at those companies.
- [00:22]
B
Maybe my favorite voice online is Mengto. He has been publishing design guides for years on YouTube, on Twitter. I've been following him and he's going to break down for you as a product manager. What are the top use cases of these AI tools and more importantly, beyond the Surface guide of how to use them. How do I use them? Well, I think that people who are stuck in chatgpt haven't realized that this can connect to all of your existing apps if you're using it in Codex,
- [00:47]
A
Absolutely everything you can think of, you can imagine. Anything that fits your workflow can be done in Codex and you can now use computer use.
- [00:55]
B
Everybody is just cloud, cloud, cloud all the time.
- [00:58]
A
I'm not a big cloud user. I'm more of an OpenAI person. I'm all in on Codex and I've been using it every single day. They have this whole ecosystem around image 2.0. I think that every PM should know about this.
- [01:19]
B
Before we go any further, do me a favor and check that you are subscribed on YouTube and following on Apple and Spotify podcasts. And if you want to get access to amazing AI tools, check out my Bundle where if you become an annual subscriber to my newsletter, you get a full year free of the paid plans of Maupin, Arise, Relay App, Dovetail, Linear Magic Patterns, Deep Sky, Reforge, Build, Descript and Speechify. So be sure to check that out@buildle.akashg.com and now into today's episode. Meng, thank you so much for lending your expertise to the podcast and welcome.
- [01:54]
A
Thank you. And this is going to be a deep dive into Codex. I've been using this since day one, but also before Codex came out, just like four months ago. I've been, you know, building apps, you know, using agents and doing AI for a long time. So I'm going to be sharing with you all my secrets. This is going to be a unique perspective. A lot of PMs going to want to hear about this because it covers every single piece of the workflow from, you know, prompting, using what tools to use. If you only get out of this podcast, like what are the tools I'm supposed to use? Or what are some of the basic prompts? I think that's on a value. So I'm going to. But I'm going to do a deep dive. I'm going to show you all the demos, the images that I'm creating, the videos and you know, the HTML. It's going to be a deep dive.
- [02:44]
B
Amazing. That's what we like here. Try to going the layer deeper than the surface. So what are the best tools for AI design? You use them all right now, what are the ones you like the most?
- [02:55]
A
Yeah, so I'm basically all in on codecs right now. And I know a lot of people, they love cloud code. Some people still, they love cursor. I think cursor is amazing. I'm not saying that as a bad thing. I used to be a huge Cursor user before OpenAI came up with Codex, which basically changed the whole mindset around, you know, not just building, but also starting projects and starting chats around those projects. But also we have like openclaw, which recently completely take over the world, became the number one GitHub project of all time. So this is taking the world by storm and every single of these tools are like influencing each other to create the next best thing. And right now I feel like at the epicenter of everything, we have anthropic and then we have OpenAI with codecs.
- [03:49]
B
Amazing. I feel like sometimes I am a Claude code channel. So it's a breath of fresh air to see Codex. Can you fire it up? Can you show us how you use Codex and how to set it up so that it is used in the best possible way?
- [04:05]
A
Sure. All right, so obviously I'm going to be covering Codex, which for those who don't know is basically the ChatGPT, but 10x like one story or steroids, basically. So you can not just chat with an AI, but you can create slides, create HTMLs, create full websites, make your mobile apps, everything. And then one thing that I mentioned that you should definitely take out of this is you should use an AI browser. So the one that I'm using again from OpenAI is called Atlas. And basically what is really cool about this is for me, context is king. So anything that you have that is context is super useful. So you're browsing something, you want to ask a question, you have the ask button. And you can also let the AI agent take over your computer and just start using it. So, you know, at first I just Want to go over the tools? I think it's super important to give you an idea. So also Whisper Flow, which I'm sure a lot of people use it, I heard about it. Basically, instead of typing everything, you want to use your voice. And Whisperflow is the fastest one. It has the best, best accuracy. And you want to deal with dictionaries, words that are hard to use. So that's very good. For PMs, especially, you want to use something like Obsidian, because when you use something like Codex or cloud code, you're creating a ton of documents, tons of documents locally, especially on an open claw, kind of introduce that workflow where everything happens locally because you have a ton more context and the AI has a ton more power because it doesn't have to rely on an Internet connection or a private database somewhere, but everything on your computer is private. It's super, super powerful. And they also have this feature where, you know, it's kind of like a brain tree of the whole information, the whole context around every document that you have done so far, basically your whole life. So this is super important. Now what I use, I use my own tool. And I know a lot of people, a lot of people, including PMs, especially technical PMs, which I've always been a technical person, even as a designer. I'm like one of the first designers who started teaching designers to code. And that's a real story. I started my career almost like that. And basically, I build every single tool that I use, including my own video editor. I build my own SaaS project where I build websites from scratch and templates, which I have a ton of videos about. I build my own sort of design brainstorming tool using HTML. And as I mentioned before, I build my own video editor as well. And the reason why I do this is very simple because every human has a very unique set of needs. And in order to solve that, the only way is one, to experience those frustration and second, to go through the, the experience of solving those frustrations. And so you have a tool like Codex, which gives you all of these superpowers and you want to solve them. And therefore, you know, every time that I have like, let's say a podcast, I have a prep document that I, you know, I talk to my Codex and it creates all of this stuff. And so you can see, you know, like, it gives me the hooks, it gives me all the demos, you know, all the talking points, the research. And then we're going to get into, you know, creating charts, creating storyboard, you know, and the Proms to use them. And one thing I love is also generating avatars because, you know, a lot of people are loom users. For example, they go into meetings and they want to record themselves, like training something. Instead of having to go to these meetings, they record it privately and then they give it to their team. So having an avatar is super important. And nowadays we have AI that does all of this stuff. So again, you know, this is my entire workflow and this is what everything that we're going to cover. And like I said, I just wanted to start with this because if you're taking any value out of this podcast is all of these tools that I'm showing right now, just like Google them, downloading them is just enough to get a ton of value. And then I'm going to switch to the Codex. I'm going to start from scratch.
- [08:29]
B
Awesome. And while you're doing that, I wasn't totally clear on two things. One was how Obsidian plays in. Maybe I just missed the connection. And then the second was how an avatar helps you with loom videos.
- [08:43]
A
Okay, so I've never shown this to anyone outside of our team, but this is my codecs, my real codex. It's not a demo one. And these are all my projects. So for example, I have content and this is a project and all of these are local folders. And I just want to answer your questions first before we get into the step by step of getting started with Codex. Obviously at this point I assume that you already downloaded Codex. And the idea is that when you talk to AI, right, you ask a lot of changes or, you know, you want it to write documents or you want to fix issues, you want to fix and move pixels, and sometimes you want to plan YouTube videos and sometimes you want to, you know, draft, prepare a podcast. And what's happening here is that oftentimes it's going to generate these documents and these documents are like content md, right? And this is how you consume the content. And this is great. Codecs has everything. It's like an all in one apps. It can read your HTML, you can open your HTML, you can open your MD files, you can open the images, it's going to go into full screen, it can open your code changes and all that stuff. However, you have to understand that all of this stuff also exists on your computer. And you're not always going to go back to your Codex to find these documents. So you need a way to organize all of these documents somewhere. And this is where Obsidian comes in, because Codex, yes, it does a lot of this stuff. But Obsidian is going to allow you to organize your documents, your knowledge base and the brain tree. And, you know, you can always reference to the Obsidian content, which by the way, are basically just folders. And again, this is the superpower, that kind of open claw introduced to the world is that everything has to be local, everything has to exist on your computer first. And the rest is for all of these apps to digest that content. So, for example, you know, if you're talking about a coding project, well, you need HTML, you need React, you need, you know, a browser if it's an MD document, you need something like Obsidian that organize and read all of this stuff with beautiful imagery and stuff like that. Or the app that I build for myself for videos, for example. You need a separate app for organizing your videos because you're not going to do that here, and so on and so forth. So this is why, you know, we need these, these other apps. I hope that answers your question.
- [11:19]
B
Got it. And how does the avatar help with the loom videos?
- [11:24]
A
Right. Okay, so this is really interesting. I kind of dropped that knowledge. I understand that it's kind of like out of nowhere, but. But right now there's a huge shift into UGC content. Have you heard about UGC content?
- [11:39]
B
User generated content.
- [11:41]
A
Yes. So user generated content, where basically this is what everyone's doing. This is the new Marketing 2.0. Basically, people are tired of looking at companies and getting like corporate bureaucracy messages from them. Instead, they want people like you and me who have real human experience in an era of AI that feels like they're getting not only a ton of value, but also authenticity and a perspective that they can relate to. So having an AI avatar allows you to go from, oh, you know, today I have to put my, you know, I have to do my hair, I have to, you know, put on a nice shirt. You know, sometimes you don't feel like it. So having an AI avatar, which, by the way, you know, Sedance is really good at, or you know, hey, Gen, for example, is a really good AI model for that. Basically those they, you know, they can generate a clone of yourself, including your voice, and then you can just use that and type the stuff that you want your AI avatar to say while you do the screen sharing, which, by the way, what, you know, what this app that I'm building is about and just like put the two together and then you get your presentation, because everything is about presentation. So, you know, UGC is a presentation. It's just in the form of something you would post on Instagram or TikTok or Twitter and, you know, but if you're talking about in, I guess as a pm, you want to give the message to your team. So the best way to do that is you have to record yourself doing a screen recording, say stuff and then, you know, showing the slides. It's a lot more human.
- [13:27]
B
Nice. Amazing. Yeah. I think I've seen like some creators create like almost like photorealistic avatars. So I'm excited for that demo coming up.
- [13:35]
A
Yes. And with Image 2.0, everyone starts with Image 2.0. I'm going to get more into the details of it, but for now let's get into how to get started with codecs. So the first thing you want to do is to get into the plugins and the skills, right? The difference between a plugin and a skill is just how deeply integrated it is. Usually a plugin is more like it has, you know, the whole backend stuff and the whole integration more like a Figma plugin or Photoshop plugin where, you know, there's a whole team behind it, whether it's OpenAI or Slack or Chrome or Linear. So you want to definitely use. This is one of the most amazing thing is computer use. And we are, I would say we are in the middle of that journey. But eventually it's going to get so much better. But right now it's so good. It's able to work on your computer like it can open figma and start designing something on its own by using your own brow, your own mouse. Right. And that's so good because, you know, you've heard of mcp, you've heard of like cli. For those who don't know, CLI is when it goes to your command line and starts communicating with APIs. And MCP is when Figma, for example, introduced some sort of like a plugin. And then, you know, again, it's connecting to the AI agents and it does all of these tasks. But then you have computer use, which works on everything, right? It doesn't require someone to build something. It's going to just use your computer as a human would. So I would imagine eventually you're going to be able to do computer use and you have an AI agent that records on your computer and creates videos and presentation using your AI avatar. So that's just how powerful it is. But for now, I'm using computer use a ton for testing. So, for example, you know, a user has a problem, you're going to go through that flow and you're going to Use computer use for that. It's going to click here, go to these websites already login and then you know, go through that flow. Oh, we have this bug and then it fix it and so it reaches those pages and then it fix the bug. So computer use super, super important spreadsheets presentation Chrome similarly to computer use. But I would say that nowadays Codex has its own browser and so the AI is able to do everything by itself and oh, Gmail super important as well. So it's going to be able to, to go to your Gmail and it's going to be able to reply to your emails and it's going to be able to do a lot of cold reach which I know a lot of people do that. Now one side note about this is that I want to talk about trust because you know, for, you know, at the beginning of the year we had openclaw and an openclaw took over the world for by storm. Now the biggest problem with OpenClaw at the time and I was a, you know, I wouldn't say a big. But I did it for like a month until I got into Codex. But the biggest problem with OpenClaw was security. A lot of people were worried, including myself, that if it reads my email someone can inject a prom and then start, you know, hacking my computer and getting all my, you know, OpenAI keys and stuff like that. And so, you know, there were no guardrails at the time but now it's a lot better and thanks to things like Codex you have something that is within a trusted channel which is Codex or OpenAI. And since they have a lot of accountability versus just an open source project, they can put all of these guardrails. It's going to ask you for permissions and all that stuff. Which is why I trust installing a Gmail plugin. I know it sounds. And nowadays I actually use it to send emails. For example, when there's a failed payment I would send sometimes send an email saying hey, you know, is there something wrong? But you know, for a lot of PMs could be like, oh, you know, someone reported an issue on Linear or something and you receive an email, you can reply right away with, you know, an auto reply but using AI instead, like an agent instead, which is a lot more smarter and stuff like that. So this could be super useful. Obviously Google Calendar would be really good. I'm not a super Calendar user at the moment. I'm also not a linear user by the way. And for me I actually use Discord and you know, Discord Because I'm, I'm very customer facing. So I use discord for everything, team chats and all that stuff. And AI can do pretty much everything. Now we're going to get into the skills. So skills is more like anyone can create a skill, including you. You should be creating your own skill. So it's a lot more hands on and it's a variety of stuff and small stuff such as prompting and image generation, or what model to use for image generation or video generation. Or if you're talking about design, for example, what are the design MDs that you should be always considering or what are the taste skills that you should always use whenever you design a landing page or a slide to make it 10x better looking and then you know, you have, yeah, front end stuff. For example, I'm building a Mac app and also an iOS app, which is what Dreamcut is on. So I use SwiftUI skills. Playwright is really good for taking screenshots. Netlify is really good for deploying your website because you're going to create all of these HTMLs and React project, but they need to be hosted somewhere. So something like Vercel or netlify, you just drag and drop your HTML or your REACT project and it's going to turn it into a URL and it's going to be hosted on an Internet and then you connect it to a custom domain name and then voila, you have your SaaS product or your landing page. So these are kind of like the skills that I have and I would highly recommend, you know, most of them, at least the one that I just mentioned. Copywriting, super good as well. So helps you write better for your, you know, your landing page, but also your documents. And then we're gonna get into the projects. But first of all, do you have any questions about where we are?
- [20:04]
B
How often are you updating your skills?
- [20:06]
A
I update them when I notice that there's a lack of understanding that my AI agents have. So for example, when I was building my SwiftUI apps, I was noticing, oh, it's missing some knowledge about performance and stuff like that. So I would go on the web and I would look for skill around performance about Mac Development or iOS Development, which by the way is super fun. If you're like a PM or a founder, you want to build something, start building apps. There's so many needs and there's so many ways to create an app around something. And you have so much power when you build an app for, let's say iOS or Android because you have access to all of these technologies that nobody are using on a app level. So that's why I think it's so fun. But obviously everyone knows how to build a website. So I would download the skills for building a website, but also like the taste skills for like front end development and design skills and CSS and tailwind skills. So other skills that I would recommend if you're building landing pages is for like you look at libraries like JSAP for animations or Lennis or Locomotive or you know, Barber. Like there's just so many of these, you know, I know I'm dropping a lot of names, I cannot cover them all, but you know, there's category of skills, there's categories of like, you know, things you should be using depending on what you're building, what you're generating. And then you have to study the AI models that are doing images, videos, you know, just AI agentic stuff, coding. It's, it's, it's a world of stuff and there's just so much to learn, which I hope just by dropping the name you're going to be doing some research on them and then you're going to be integrating them into your workflow.
- [22:01]
B
Awesome. I've been building a lot of AR products lately. My job search OS has 16 different agents, my newsletter has a recommendation engine and I kept running into the same problem. I'd ship something, it would work in my testing, and then I'd get messages from users saying it's hallucinating or picking the wrong tool. The issue wasn't the problem prompts or the tools, it was that I wasn't actually evaluating anything. I didn't have a way to see what my agent was actually doing. Step by step, every tool call, every decision. That's where Arise comes in. Let me show you. I'm going to open Claude Code and install Arise with just one command. NPX Skills. Add Arise. AI Arise Skill. Skill. Yes. Now, Claude code already knows how to instrument my agent. I tell it set up tracing to Arise and it automatically analyzes my code base, figures out where the LLM and tool calls are and adds instrumentation automatically. Now I can see everything. Every trace, every span, every decision. And more importantly, I can evaluate it. That's the shift trace what's happening, evaluate where it fails, then fix it. This trace right here, my resume feedback agent was supposed to pull the company's tech stack from the job post, but instead it hallucinated that they use React when the posting said Python. I never would have caught that without seeing the trace. And here's the part that blew my mind. I asked Claud Code to look at these traces and tell me what I should be evaluating. It came back with four eval criteria I hadn't written. Things like picking the right tool and staying grounded in the input. I wrote the evals, ran them, and found that my agent was making the same kind of mistake about 12% of the time. Claude Bush to fix, I reran the evals and it dropped to under 2%. That whole loop, trace, evaluate, fix took me about 20 minutes and now it runs automatically. If you're building AI products and not evaluating them, you're shipping blind. Try arise free@arise.com and get a year free a $1260 value with my bundle Arise. Check it out. It's one of the top AI evals platforms used by all of the top AI teams for a reason.
- [24:05]
A
Okay, so now we're going to get into the projects. So I want you to think about Codex like a chatgpt, but on steroids. That's basically what it is. Everyone knows how to use ChatGPT. The first time that OpenAI introduced ChatGPT, everyone was like, wow, the future of UI is basically a chat. And I fully disagree with that, by the way. There's a ton of determinations, but there's also a ton of stuff that we're unlocking. And we've never seen more UI nowadays than we've ever seen in the past. But at the center of it all is the chat. So like I mentioned before, I was a huge cursor user. I was also into the nitty gritty of like using figma for design and using something like VS code for coding. And we have a whole new generation of people, especially PMs and people who've never done coding before, who are getting more and more technical because of AI, right? And for us, the technical people who have done this for like a decade, we are 10x the workflow. Basically the stuff that we've always dreamed of building before, now we can do it. Like for example, never in a million years I would think of building my own video editor, but yet here I am. So the PM who's never done technical stuff is now doing technical stuff. The one who's never done, like the teenagers who's never done an iOS app, now suddenly gets into coding and use Swift to build his app in a matter of days. And so yeah, this is where we are. And we started all of this with chat. So while nobody wants like all of these people, including myself, nowadays I haven't written a single line of code in the past six months. And I've heard a lot of engineers do that as well. So where are we right now if nobody's writing code? Right, so we're moving from VS Code and Figma into the chat box. Okay. So basically Cursor is also like VS Code, but with AI agents and even Cursor, they're moving away from the sort of like GitHub, centric files and folder centric into the chat based project. And the same way with cloud code as well. They're moving away from cloud code in the terminal, which is highly technical, into something like cloud cowork and cloud design. So you're seeing this shift into a more project based chat. And this is where we are right now with Codex and Codex has started this movement and then you also had, you know, like, also like the local base generation. So with all of this you have the projects and a project is basically just a folder. So now if you want to start a new project, you're going to click here. You can either start from scratch or using an existing folder. Now the folder can be anywhere on your computer. Okay? And keeping in mind that your AI nowadays can have full permission on anything on your computer. And in fact I have this little thing here, full access 24 7, because I trust it because it has guardrails. So what you want to do is you're going to start this project and you're going to go to your Downloads folder, right? Everyone knows what their downloads folders are. And then from the downloads folder you're going to create a project, a folder called Projects. And then in the projects folder, you're going to create a project, a folder for every single project that you're doing right now. And let me give you some example. So these are the apps that I'm building, but I also have content, which is for all the MD files and all the, you know, the text, the preparations, the video scripts. If you're a YouTube channel, for example, or if you're making presentations, you would create these markdown files. Okay? And then we also have a folder that you can put all your customer support stuff or the issue stuff, like you know, anything that the customer might have and you want to follow up, you also want to have something for your company. So if you have like, if you start your own company or you, you, you know, you have accounting, you want to create a folder for that. So you're going to put all of your invoices, all of your, you know, registry and documents and receipts, but also all Your company files, you know, all the context of your, the team that you work with, and so on and so forth. And then you might have a folder for skills that you're going to put all your skills into it so that you can use it for the next stuff. If you have kids, you might have a folder for school where you're going to put all of their, the kids assignments and their homeworks and you know, so that the AI has context, because you don't want to give AI too much context, otherwise it's going to cost too much tokens. That's why you want to have something like this. So I'm not going to get into the coding aspect, even though I think this is a hugely beneficial thing to do. You know, you create a new folder, you know, let's say you want to create an iOS app, then you start, you know, a new chat, for example, and you can use Whisper Flow, and you can start with the context. Usually you, you can ask questions, right? The first thing you want to do is the plan mode. So you're going to start with I want to plan this. So, you know, obviously it also took what I said, but you always want to start with I want to plan this. And the reason why is because you don't want to get into the coding yet, because you want to approve every single thing that you want to build first. And then you're going to be like, I want to build an app that scans QR code and sends automatically the content of that QR code to my email, for example. So then you have an app idea, right, and you want to plan it first. And by the way, I shouldn't put this in an existing folder, but I could just create one. Start from scratch and let's say QR project, and I'm going to save this and then I'm going to do this. So let's talk a little bit about the permissions. Okay, so you have the default permission. I think most people are going to start with this. Now, this is when you're a new user, you don't trust the AI yet. You know, your level of trust is like 0 to 100 at the beginning is more like 0. And then eventually you learn to trust. So default permission. And again, this depends on you whether you value speed and the token cost and all that stuff. You can start with standard and you can start with medium. And this depends on the level of difficulty that you think this project is going to take. So, for example, if you don't have a ton of tokens, you have like a $20 a month plan and you just want to experiment. You want to go with medium or low, right? But me, I'm a $200 plan because I use this every day. And one of the key reason that I'm actually using OpenAI is because they're far more generous in terms of tokens. I'm sure some of you of you already experienced that. Oh, you know, I'm already at my limits after five prompts on cloud design, for example. Well, that's the reason is because, like, first their models are super costly and last time I check, I don't think they have like a low, medium, high and extra high setting. And these are related to the token cost. So like I said, if you have like a $20 a month, you might want to use low. If you have like a $200 and you want you value accuracy over everything, everything else. And you do a lot of like you do a fleet of agent. I like to do like 20 agents running at once. Then you go with extra high because you can afford to wait on them. So this is a high difficulty one. So I'm gonna do this right here and I will set it to full access because I already trust it and you can see everything is happening locally. So I'm gonna start with that and then it's gonna start thinking and it's gonna come up with a plan. And while I'm doing this, I can also go to, I think a lot of people are gonna do this content, which is, for example, I want to create a slide for the stats that I have, like new users, how many new users have, what are the revenues that I'm doing every day for my projects. Dreamcut, aura, new form. And I want you to look into my downloads folder and in the download folder there's a projects folder. And you're going to find those projects folders right there. I want you to read those folders and I want you to look for the revenue stats and the new user stats, the conversion rate, etc. And then I want you to create a slide. So again, this is why I'm using Whisper Flow. Because when I'm using Whisper Flow, I can give a ton of context. And it also formats everything that I say in a super nice thing, like a really nice format. And you can see here while I'm doing this, it's already done. So now I have my build plan for my iOS app. Okay, so now I just need to read through this and kind of make sense of it. If I have any question about It I will ask a question. It's super important to ask the question. And when I'm done, I would say, okay, let's do it. But for now I'm going to say, okay, so architecture, we're going to need the QR scanner technology, we're going to need a backend secure. So the AI is really smart and 5.5 is considered the gold standard nowadays. So you have two of the best AI right now, which is 1 opus 4.7 and 2 GPT 5.5 at extra high. And so it's super good. And give it a try. Honestly, give it a try. I know you're going to get, you're going to build your dream app just from listening to this. And so yeah, it's giving me the plan, it gives me the MVP features. It gives me like, okay, this is the format that I'm going to get and this is the scan and this is the content. It's going to give me the URL I received the email safety features and so on and so forth. Okay, so this is great. And then I can start building or if I have a new question, for example, I can say, can we expand on the email and can we actually have an image, like maybe a screenshot of the QR code? So let's say the QR code goes to a website and let's say I want to use a technology that takes a screenshot of that website, what it looks like, and then send it to as part of the email. So obviously you want to start with a question, otherwise the AI might think that it's time to get into the coding. And like I said, you know, I'm just going you through like an exercise of a random app that just came came up like that. But this is what it looks like to build an app. Let's say you're a PM or you know, someone who's never done coding before. This is how I would start. And then for content, super important again, it's exploring all the files, Superpower running. It understands everything that I'm talking about. It understands that I have a downloads folder, it has a projects folder. I have Dreamcut New form. And it even understands all the sort of the names that I have that are not normal names, right? They're like specific names. And the same with generating your avatar or generating a slide. You know, for example, I can say, can you create a slides presentation in a, you know, keynote format? So it can even create like specific format. I should probably really, you know, I was talking during this for all of the stats around my last meeting with Akash. And you should also look into the document that I have in my content folder where I prepared the prep for the podcast. I want you to look at the content, and basically from all of that content, I want you to create a slides presentation in a keynote format. Let's plan this.
- [37:20]
B
So even for a slide, planning is worthwhile.
- [37:24]
A
Yes, exactly. And this is cool with Whisperflow as well, you have a dictionary now, so it understood that your name was written this way, even though it's not. Like, I don't want to, obviously, you know best, but it's not a conventional name in terms of the way it's written, right?
- [37:41]
B
Yeah, exactly.
- [37:43]
A
So it was able to figure it out. Why? Because when I use Whispers Flow, it kind of, you know, I corrected and then the whisper flow understood that I corrected your name and then it remembered afterwards. And, you know, that's just the power of AI. It understands context and it's more proactive rather than always waiting for you to ask for something. So again, you know, here I'm asking for a very specific thing. And because I'm asking for like a Keynote file right now, the question is, is AI able to create a keynote file? Yes or no? And then you can ask that, you can explore those things. But most importantly, if the AI is not able to do that, then you can always say, are you able to create a Keynote file? If not, what if you use computer use to open Keynote and then go step by step into creating that presentation in Keynote. Right. And then while it's working, you have also the ability to queue new commands. Okay. And, you know, so here it gave me the plan because that's what I asked for, but also I can steer it and I can queue new tasks that I want to give. So you can see here, you know, let's see if it's able to. So deliverable key is required. I can try converting Keynote afterwards. The reliable format is DBT, which is kind of like, I think it's a PowerPoint presentation that keynote is able to open cleanly. And then it's kind of looking into this. And also you can sort of steer the conversation. So, for example, I can say something like, let me just restart this. What if we generate the image first as a slide in GPT 2.0 image first, let's create five of them. Let's use this taste skill and let me make sure that it looks good before we actually build the actual slides with layers. So here it did a problem with GPT2, but that's my fault. So I can always stop it. I can edit it and I can say image and then it inserts nicely into the text. It understands the context of the text. So obviously if I didn't correct it, it would just say GPT 2.0, which doesn't make any sense. It could be like an AI model. So understand these keywords is really key to knowing what to build and how to say it right, so that the AI doesn't make mistake on top of the fact that you're using the planning mode and you're also asking a question. So those are the three factors before you actually get into building and generating the images. And if you're blocked by something, the AI is going to ask you. So for example, maybe image 2.0 is not installed as a skill, but in this case, since we're using codecs, it should be fine. So let's look into the QR project. Here it says, okay, notes, Screenshot captured automatically by this using the scan. Let me see if I can ask, for example, what technology are you using for taking a screenshot? And okay, so here it says screenshot services like browserless and screenshot 1. Do you think that playwright would be a better technology for taking screenshots? Right. So this depends on your knowledge. I know that playwright is one of the best ways because I've been using it for Aura my other projects. So again, this is kind of like the gist of it and how I would do things. The last thing, the last bit of knowledge that I want to give you that I do like 90% of the time is, especially when you get into the nitty gritty when you're building a website, is you want to take screenshots of everything. Okay, because the AI, like an image is worth a thousand words. You can use, of course, whisper flow to talk and give a ton of context because the more context the better. And you don't want to type all of that context because you get lazy as human, you're limited by your speed and your thinking is way faster than your typing, if you think about it. So the second best thing is using your voice so you can talk way faster than your typing. And the third best, even better than that is taking a screenshot. Because taking a screenshot, you have this new, you know, you select, for example, the browser and then you have this new shortcut which is like command command, and then it takes the screenshot automatically of that browser that you had. Focus and look at that. It's really amazing. And this is just a new feature that was launched last week. And another new feature that was launched last week is the mobile. This is incredible. Okay, just to give you an idea of how incredible this is. When I go outside or I go commuting or, you know, I take a taxi, or I'm waiting for my food to be delivered to be served at the restaurant, I can open my Codex, which is connected to my computer, and I can go to each of these tasks that are being worked on. Okay? And just keep working on my project by just chatting. So the mobile, the Codex mobile sits in your ChatGPT app. Okay? All you need is your ChatGPT app and there's a little button that says Codex. You click on it, you connect it to your. To your Codex on your computer, and then you have access to all of these projects. Isn't that beautiful? Because then you can follow up with all of these chats and everything that you do and ask is being worked on your computer and not on your phone. And that's the magic.
- [44:18]
B
Does your computer need to be on for that?
- [44:20]
A
Yes. So there's a few options that you have to do in your settings. I'm not going to go into my settings just because I don't want to share the sensitive stuff, but you're going to go through like a workflow where you're giving permissions to, for example, keep my codecs on even though my screen is locked, and work on these things. So as you can see, you know, I'm working on slides. Okay. And it's taking it understood that I have a folder for content. And in my folder for content, I have a prep file around the, you know, around your podcast and, you know, we have stats, we have these beautiful slides. I'm also using the taste skill that gives me better design skills and better fonts and typography that looks like it was done by a senior designer. Now, that being said, of course it's going to make mistakes. So for example, sometimes it likes to cram a lot of information, a lot of lines, and it's not smart enough to know that it's not able to cram all of this stuff in a way that makes sense. So, for example, you can see it's trying to put, like, so many futures in a space that doesn't allow it to do, and that's where it struggles. So over time, you kind of understand how to deal with these things, with these pitfalls, and then you overcome it. And this is where you, as a human, you become better at, at kind of like making these micro Decisions in a split second. And then you say, oh, this is wrong. Right? Fix this. And you take screenshot for the context again, beautiful animation, right? Boom. And it just, you know, it does this beautiful animation, gives me the context, gives a screenshot of the image that you're talking about. You go to a website, you go to a slide. Boom. You do that, that shortcut, and it gives you the context, and so on and so forth. So the beauty of all of this, I want you to understand, is that all of this is happening all at once. When usually traditionally, if you think about 10 years ago, using Figma or using VS Code, you're limited by one task. You do one thing at a time. You do one project at a time. You have one cursor. What you need to understand nowadays is that you don't have to do that anymore. You have an army of agents. So when I say an agent, like this is an agent, this is an agent, this is an agent. And they're all working simultaneously. And on top of that, each of those agents can generate multiple designs at once or multiple documents at once. And then you're kind of cloning yourself, if you will. And the only task left is you as a product manager who is managing this fleet of agents to create your dream projects.
- [47:32]
B
Amazing. For that taste skill, is that one of the skills that OpenAI provides or did you create it? What does that look like? In order to generate slides of this quality?
- [47:41]
A
Sure. So I'm going to ask you a question because I don't want to switch between the browser and this window. So the taste skill I want you to go find on GitHub, there's this taste skill. You can also give me the list on the taste skill from a website, maybe go on Google and also go on GitHub, find the taste skill. So I'm going to do it super fast. Speed, fast. And I'm going to go maybe medium. This is not a hard difficulty. Should be faster. There's also Google. Sorry, OpenAI Spark. I'm not sure if they still have that. Yeah, I think this Codex Spark 5.3 they have. They don't have the. But this apparently is like almost instant. I can. Let me try that one. Actually, let me try just to compare it. I'm curious. I'm so used to using just like the other one. So let's just compare how fast it is. So find the taste skill. Okay, this one is obviously this, this did had like a little. Okay, it's, it's looking, it's fast, but there you go. Taste skill. It's from the design taste front end. You have different versions, it's. And then you have redesign skill, soft skill, output skill, brutalist skill and so on. There's also one for image gen which is for image generation. So the one that I'm using right now is GPT. And look at this one is already done and it did it in 25 seconds versus this one. It did it in 18 seconds. That's interesting. Maybe it's a GPT 5.5 thing. So GPT 5.5 is also faster than 5.3. So that's an interesting test. I did this at medium and it was faster than Spark. But again it could be also depending on what you're asking for. But again it links to the, to the GitHub project and it gives me all the skills. It's basically just a file.
- [49:39]
B
So you just picked up on this known file, you didn't have to modify it much. And we already get a pretty good slide out. But it sounds like you'd give that slide out but a couple iterations. Would you then ask it once it's done the imagen one to create a pptx or how do we close the loop on this presentation?
- [49:56]
A
Sure. So let's say again, it depends on your workflow and what tool you want and what is the last format that you want. So for example, I can say something like I really like the first slide. Can you do that in HTML? And I want you to use the best image to HTML generation vision possible. And I know you can do it because I know GPT 5.5 is one of the best. So this is one way to go about it. I really like the fourth slide and I want you to recreate it in figma. Maybe we can use computer use to open Figma and then try to recreate it. So that's another way. And can you use the FIGMA MCP to create the slide? Let's say slide number four. So again, these are for experimentation, but this is how I would close the loop. You have multiple options. I would definitely go with the HTML route just because the AI has really, really good code generation nowadays. If you're asking it to recreate something in Figma, it's going to take way longer and you might need to know Figma and you might need to install the MCP or you might even need to do it directly in figma. So you would maybe like download this as an image and then in Figma they already kind of figure out the workflow and you just drop the image and you ask the AI in Figma to recreate this in figma. But if you want to stay in Codex, which I think a lot of people would want to do that just because you don't want to have like 10, 20 subscriptions all at once, like Figma subscription, you know, all of these, like. So you want to keep sort of like the blast radius as low as possible. And yeah, that's what I would do. So it's going to generate the HTML and it's going to open it in a browser. So when it's done. But right now it's not done yet. So again, there's a number of ways. Again, can you also create it in PowerPoint using Keynote, the app? So it depends on your workflow, it depends what is the app that you use. But this is how I would do things.
- [52:13]
B
Okay, so Imagen is almost like a first draft which you can give it feedback, then you can export it using any of these four different prompts, of which it sounds like HTML is going
- [52:22]
A
to be the fastest, HTML is going to be the most controlled, the fastest. And it's all going to happen in Codex,
- [52:35]
B
probably the least tokens then too.
- [52:37]
A
Absolutely. So you have to understand also you can take that and turn that into a video. So for example, you can say something like, oh, I have a new idea. I want to turn those four slides into a video. Maybe you can use something like. What was the name? Well, Hyper Frames and I believe there's a new one. Maybe you can look into those. Let's plan this first. And basically the goal, and this is good that you give, the goal also is that the goal is that I want these four slides into a video that shows the slide one by one with maybe a fade transition and each slide have a five second. And maybe in that video we can sort of like do a transition of each bullet point, like one second each. So that's kind of how I would do it. But you know, there's just so many, so many ways. And this is the beauty of where we are today with agents, is that you're not limited to one tool. Like before, my whole life revolved around using Figma. And you know, of course now I could say the same about codecs, but in this case we're actually using Agent and the agent is not using only figma. Right. And the agent has access to the whole world of tools to create the goal that you want it to do. Right. And that's, I think that's really beautiful, 100%.
- [54:15]
B
I think that people who are stuck in ChatGPT haven't realized that this can connect to all of your existing apps.
- [54:22]
A
If you're using it in Codex, Absolutely everything you can think of, you can imagine. Anything that fits your workflow can be done in codecs and you can now use computer use. You can also do these screenshots that I highly recommend, and you can also do that on the go by using the codecs mobile.
- [54:42]
B
What's next after presentations?
- [54:44]
A
Yeah, I think we already had one hour, so I'm not sure how long you want to stretch it.
- [54:51]
B
Not too much. Just in case you had some stuff planned. I think you had like the avatars we talked a little bit about. If you want to talk about that, we can quickly go over it. It's up to you.
- [55:00]
A
Sure. So, but avatar is more like a personal thing. Okay. So, you know, just because I kind of tease everyone about the avatar thing and you had a question about it, so let's talk about it. So nowadays UGC content is a big deal. And I think that one of the things that you have to create the most is creating like a digital twin of yourself. So in order to create a digital twin, what you would do is that you would take the best headshots of yourself and you would drag and drop into this. Okay, but in my case, since it's kind of personal, I don't want to start dragging and dropping my portraits. I'm just going to ask. Yeah, okay. I want you to go into the content folder and I want you to look for the best pictures of me. And then from those best pictures, I want you to create an avatar, a digital twin of myself using GPT image 2.0. And I want different angles, different lighting in a studio setting, in an outside setting, me using my camera phone, you know, recording myself or me in my studio, or as a YouTuber or as a content creator, or me at the office, working on my. At my desk. So I want you to generate 10 images of me using GPT Image 2. So this is how I would do it. But normally you would just drag and drop the image right here, just the same way that you go to like, you know, here, and then you do the, this sort of the shortcut. So, and then what I would do next, once you have your avatar, I would say something like, okay, so I have these screen recordings that I did using either Screen Studio or Dreamcut. And then I want you to take those screen recording and put my avatar, and I want you to create a video script using a markdown file. And I want you to say those things using my digital twin to say those things that I have in my video script and next to the video presentations that I did or the image presentations that I did. And then I wanted you to use hyperframes to do all of that stuff into a one minute video. And I want the 16 by 9 content for YouTube, I want the 4x3 content with captions for X and I want the 9 by 16 content with my avatar at the bottom and then the screen recording at the top with a hook and that's going to be 9 by 16. Finalize at the end with a call to action that says something like drop a comment. I'm going to send you the whole workflow. That's how I would do it. And by the way, I put a lot of knowledge that I've been doing a lot recently. So this prompt is going to be so good for you guys. But yeah, this is how I would do it. And obviously it's not guaranteed that it's going to work. By the way, there's a lot of stuff. But if I have to imagine myself in six months of time, in a year's time, I would imagine that the AI will be able to do this perfectly. Which comes back to the point where creating you a digital twin is going to be amazing. I do want to drop a little FYI there. There's going to be a pushback on AI video generation and image generation where you don't want to deceive consumers. So doing a digital twin is fine as long as you're not creating yourself using a fake product or doing stuff that are not real. But you know, I would imagine that creating presentations is fine. And you know, you as a human has to validate the content to make sure that you're not deceiving anyone. But there will be a huge pushback because I'm starting to see a lot of these video generation using CDs that are creating like fake products. And a lot of people are gonna complain to the FCC and there's gonna be like, you know, a lot of bad stuff going on. But you know, there's also the good side of it, which is what I'm showing you guys right now is like, okay, I want to create a video presentation that I'm gonna send to my team and these are the talking points. This is my AI avatar because I don't want to do my hair, I don't want to, you know, you know, maybe it's. It's at night time, the lighting is horrible. So this is the best way to
- [59:48]
B
do it, should people be using Seed Dance for that video or is ChatGPT image fine?
- [59:54]
A
So ChatGPT doesn't have a video generation. They already discontinued like their video generation stuff. I would probably use Google Vo or Google Omni. But the number one thing that I would use, if you're focusing on presentation, I would use heygen. And heygen has a plethora of tools for lip syncing, for creating your avatar, creating your digital twin, specifically for the need of presentations. Now, Cdens is the best AI model for everything, including like filmmaking or it has the best understanding of like, let's say you, you want to ask for like a cap who does a vacuum in Tokyo. Well, Sea Dance is definitely going to do the best job at that.
- [60:44]
B
Okay, amazing. Last point I just wanted to cover off on in Codex is when how do you generate like divergent ideas for app design? Like we were talking about that QR email scanner. What's your workflow or the recommended workflow for PMs when they want to really investigate the design space of a product feature?
- [61:06]
A
Sure. So the first thing I would do, so I'm going to prompt. I think prompts is very useful to a lot of people. Okay, so I want you to open the app, I want you to open Xcode and I want you to run the app and then let me know if there are any permission issues. Let me know if I have to create an Apple account developer account, let me know if I have to log in. But at the end of the goal should be to open the app and to run the app on either my phone or on IO simulator so I can test the app. And then once you run the app, I want you to take a screenshot of every single part of the flow. So to give some example, we have the sign in, we have the payment flow, we have the editor flow, and so on. So, okay, so my Codex was opening Figma, so I had to focus back and yeah, and there you go. So this is how I would prompt it. And you know, at every step of the way you can ask for, you know, for Codex to take a screenshot of the app and to make you validate things and to kind of like ask you if the pixels are right or the designs are right. Now it's kind of hard for me to show you without getting into like the nitty gritty of all of these projects that I'm working on, which can be a bit sensitive. But you know, in this case, if I was in, like, if the app was already Built. Right. So for example, I don't know. Oh, PowerPoint presentation. Let me see if. Oh, okay. See, I'm constantly surprised by AI, right. It's able to open the PowerPoint presentation. Okay. And it create the PowerPoint presentation. So if you're already familiar with PowerPoint or Keynote, you already have a basic slide that looks better than what most PMs can do in term of design. Right. I'm not saying, you know, like it's better than the senior designer, but it's still better. But if you're only focus, if you forget about the design. Right. And you can always upgrade this with a taste skill. This is what you have. And I open it in codecs and I can like it's a PowerPoint file. I can also open it in keynote and edit things. So this is one example. Let me see if I have the HTML if it's ready. Yeah, it is ready. So let's review this. Okay, this is for review. I'm going to open it in a browser. Oh, this is the HTML review. I'm not sure where it doesn't have the ability to open in a browser, but I can always ask it if I'm not sure where. There you go, right? No, this is the image. Well, I can always go to the folder, but. So let me take a screenshot. I'm not sure why. So this is where I'm like, you know, can you open this HTML file for me and open it in codecs and I'm going to press Enter. I'm going to steer it right now because this takes priority and hopefully so it's really cool. So it's going to open it and while we're doing that. So let's see. Yeah, you know, it's really amazing and you guys don't see it, but it's opening my Xcode, it's building, you know, it's doing a lot of things that I don't want it to do because you know, these are not real projects. So I'm just going to stop it here.
- [65:01]
B
Amazing, guys. So we just walked through some of the most important PM use cases for you in design. Right? Building app designs using real screenshots to iterate and improve on those app designs. Building slides and charts with your real data and as you saw, minimally directing where to even pull that data from. It has full permissions because you toggled on for permissions. And this is how you really increase your leverage as a product manager. Another question I had for you, Meng, and we were talking about this pre call was around this topic of PM's potentially shifting out of product management right now. Last week we saw 10% of men I get laid off. A couple weeks before we saw similar numbers at Oracle. The market is starting to get flooded with PMs and a lot of these people, they're being forced out of a job, they're looking at the world and they're saying, whoa, maybe I should be building an AI app of my own. What are the things that a PM needs to know if they're going to go from PM to founder to really succeed?
- [66:12]
A
Right, So I just want to clarify something. When we say that PMs are getting fired, I think it's important to clarify that it's the non technical PMs that are getting fired. The technical PMs are actually staying at those companies. And this gives us a very important message, which is that as a pm, you need to get more technical. And when we say technical, it doesn't mean that you're going to write the line of code. Like I mentioned before, I haven't written a single line of code in the past six months. Technical is this, this is what I mean by technical. You're no longer the bureaucracy player, the politics player in the company. Nobody needs that anymore because AI can kind of juggle around that. Your job is basically to understand all of the jargon. So what is the best AI model? When someone who's more technical than you, who's working on those projects, when they talk about GPT2 Image 2.0, you know what it is? So those PM who have these superpowers and who have all of this knowledge base and who has all of this workflow, they, they will be the one who will be staying and they will be the one that will be transitioning to a new role. And for those who got fired, by the way, I'm sorry, but you will probably transition into a new role that is more technical and then your job will be safe. But beyond that, right? Let's say you transition to that new role, you also have a window to, for me, a far better role than any of those working at the big company. Because these big companies, they don't have feelings for you, right? When they need you, they hire you. When they don't need you, they fire you. But what if you're your own boss, right? So I think, you know, for now this is what I do and I manage a team of six people and basically I have built these products. They're making well over a million a year and I can afford a team, I can afford to pay my tokens, which is amazing because I love doing what I'm doing and I want to keep doing that. So you will pro. The end goal, the end game, is probably that you starting your own company. Because AI, you don't need to be scared of starting a company anymore because AI can take care of all the paperwork for you, all the accounting for you, all the boring stuff, the janitor stuff, the stuff that you were always scared of doing, and even the marketing stuff, it can do a lot of that stuff for you. So at the end of the day, the last 10% or the last 8% is you kind of being, you know, orchestrating everything. So you're the one who does the quality assurance. You're the one who, you know, makes sure that the plan that you give to AI makes sense. You're the one who has the moat. So you know best. Because like any business rule is that you have to be the one who knows this topic the best, otherwise you don't have any leverage. So when you have this knowledge, but whether it's around coffee design, pm lawyer stuff, you should utilize that and then let AI be your amplifier, magnifier so that you can quickly make these micro decisions and you can deploy a fleet of agents. I think that's the end game. But I think for now you are probably, let's say either you got fired and you have to transition to a more technical role, or you're already technical and you didn't get fired, which is amazing. But eventually you will get fired because AI will replace everyone at some point, or we will find new ways to do our job in which AI cannot fire us. But it's a cat and mouse chase. But eventually if you solve that sort of a formula, and there's, by the way, a formula for everything, there's a recipe for everything. This is what I kind of learned nowadays. For everything, there's a formula. So whether it's like a YouTube channel, there's a formula to go viral, or whether it's like an X post, there's a formula to go viral. Instagram, TikTok. And you can look at my Instagram, you can look at my LinkedIn and all that stuff. I have viral posts and all those things. So I have kind of everyone's still learning. I'm not saying I'm like, you know, I know everything. I'm not saying that at all. I'm just saying that I have done, you know, a viral post on each of them. And my point is that there is A formula for all of those things. And there's also a formula which is for the end game to start a business. And that formula is you being the best at your job and you deploying your fleet of agents and you utilizing that last 8% of a human taste to orchestrate all the tasks and make sure that the quality is always higher than the baseline. But to understand, you have to understand that baseline is getting higher because of AI, but also the ceiling of quality is also getting higher. So your job is always to get to. If this is a five star, which is by the way is a podcast I listen from the CEO of Airbnb, you want to get to 11 star, but at the minimum should be the 5 star. And then you have to imagine what is 6 star, 7 star, 8 star, 9 star, 10 11. And then your job is to always be above the five star, six star or seven star and to think about the future, which is the 11 star.
- [72:25]
B
Wow, what a persuasive argument for tripling down on your product management skillset, product strategy, vision, delivering a 6, 7 star, 11 star, eventually experience. That is pretty much the future for all of our roles. Meng, you have brought it down for us in an amazing way. If people want to learn more from you or connect with you online, where should they go?
- [72:48]
A
Sure, you can go to X Mengto, you can also LinkedIn, Instagram. I'm starting my TikTok channel so it's also Mengto. I believe you can also find the products that I build and just check like these are the stuff that I vibe coded and I'm using AI to create all of these things. You can check for yourself the level of quality that it is. And keeping in mind that each of these products have way over 10,000 prompts each. So do not give up on the first prompt. But yeah, you know Aura, Nuform, Dreamcut, I'm gonna keep building products, I'm gonna keep learning these formula and I hope you will too.
- [73:32]
B
All right, we're gonna link all his socials or a Nuform Indrika down below. Subscribe to his YouTube channel. Follow him on all platforms. Meng, thank you very much.
- [73:41]
A
Thank you so much for listening and thank you for inviting me to this podcast. Thank you. This honor.
- [73:46]
B
My pleasure. Bye everyone. I hope you enjoyed that episode. If you could take a moment to double check that you have followed on Apple and Spotify podcasts, subscribed on YouTube, left a rating or review on Apple or Spotify and commented on YouTube. All these things will help the algorithm distribute the show to more and more people. As we distribute the show to more people, we can grow the show, improve the quality of the content and the production to get you better insights to stay ahead in your career. Finally, do check out my bundle@bundle.akashg.com to get access to nine AI products for an entire year for free. This includes Dovetail, Mobin, Linear, Reforge, Build, descript, and many other amazing tools that will help you as an AI product manager or builder succeed. I'll see you in the next episode.