← The Growth Podcast
The Growth Podcast
PM's Guide to Claude - When to use Chat vs Cowork vs Code, with Pawel Huryn
01:32:40
Loading summary
Transcript107 lines
- [00:00]
A
There's no good reason to talk to Claude just over a normal web chat anymore.
- [00:04]
B
I don't use chat at all. I use it sporadically. Just if the window is open I can ask some questions like is this grammatically correct?
- [00:10]
A
Claude is way better at using PowerPoint than it was. There is no excuse to walk into a meeting with a bad presentation anymore. You Basically get a McKinsey level output in a minute or two.
- [00:19]
B
Cowork is not adjusted to working with codebases. As a product manager you will be working with codebases a lot.
- [00:25]
A
Pawel Hern is the number one AIPM voice in Europe with over 200,000 LinkedIn followers and over 100,000 thousand newsletter subscribers. And today he's going to break down everything you need to know to get the most out of Claude as a product manager. Pavel, you have spent more time in Cowork than almost anyone. You use it for a lot of your everyday day to day tasks even though you are a former engineer who could use Terminal just fine. So can you walk us through what a power user, what a master setup looks like in Cowork and how you
- [00:53]
B
use it in Cowork? We can organize work in projects or folders. So what you can see here Most people stay in chat forever. That's like using Photoshop only to crop photos. And today we are going to discuss Chat, which is part of the cloud desktop but also Cowork Cloud Code Dispatch which allows you to control remote sessions for Cowork and code web sessions and how to use them all to 10x your productivity.
- [01:19]
A
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 anal subscriber to my newsletter, you get a full year free of the paid plans of Mobin, 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. So Pavel is the guest behind our most popular episode ever with over 65,000 views. When he gave an impromptu complete course on AI product management, he did the NAN video which absolutely crushed with over 10,000 views. Before that he did a Discovery masterclass. Today he is back for a record fourth time to help you understand how to get the most out of your Claude Enterprise subscription. When to use Claude on the web when to use Cloud Cowork when to use Claude Code when to use Cloud Dispatch Pavel has tried all of the combinations of PM task versus tool and he's going to break down when you should use which tool for what and he is going to break down how you can create a self improving system that builds upon itself so that every time you do something the system gets better at doing that task. Pavel, welcome back to the podcast.
- [02:48]
B
Hi Kush, thanks for having me.
- [02:51]
A
I love getting your newsletter in my inbox. One of the most interesting things you've been writing about recently is how Anthropica has gone from a billion to 30 billion in 16 months. On the back of this insane shipping Velocity, you tracked 74 releases in 52 days, which is pretty mind blowing. Putting aside what's happening at Anthropic, what I want you to help us understand is what does this velocity say about the future direction of product management?
- [03:22]
B
So what I can say by observing Anthropic is that they are adjusting. Many companies, not just Anthropic, are adjusting their workflows to AI. So they do not use AI to replace steps in their processes, but to redesign their processes around what is currently possible. What I can see in many companies is that those roles so product manager, product marketing manager, designer and engineer are maybe not merging, but coming closer together. And many of the things that required a separate role, like maybe prototyping, maybe testing, writing, release notes, even designing an interface based on the design system. This is all being automated. And for a PM to thrive in this new environment and in those new workflows, product managers must understand technology. They must get comfortable with tools that previously were designed for engineers traditionally. So like the terminal, they also need to go outside their comfort zone and understand strategy, understand how they work drives revenue for the business, how it connects to business goals, product strategy, understand how it translates to revenue. The future is super PM or super individual contributor with maybe a PM focus, maybe engineering focus, but having skills from multiple areas, not just one. You cannot be a product manager who only interviews customers and creates items in the product backlog.
- [05:07]
A
Yeah, the nature of the role is shifting, but for my money, this is the most fun version of product management yet.
- [05:13]
B
Yeah, yeah, absolutely.
- [05:15]
A
In the 16 plus years I've been in this field, I've seen it evolve a lot. Which is one of its constants is that it's always evolving more than the average profession. And I think this version of it is the closest to the bare metal of the product, which I think is incredibly exciting. So for this future model of product management, I want to break down for everybody who watches this episode to the end, how to embrace it, how to actually redesign their processes from the ground up, like Anthropic, how to use the right tooling from Anthropic to behave like a next generation AI product manager. So that's the goal for this episode today we're going to break down for folks, you and I spend a good amount of time chatting on DMs and WhatsApp. And one of the craziest things you told me was that there is no good reason to use chat anymore. That is, there's no good reason to talk to Claude just over a normal web chat anymore. Can you break this down? Because this is going to surprise a lot of product managers listening.
- [06:18]
B
Yeah, like I personally I would lie if I told you that I don't use chat at all. I use it sporadically. Just if the window is open I can ask some questions like is this grammatically correct or something? Most of the time when starting a session you don't know what exactly you will need. And when you start a session in chat, there are certain restrictions that you will face sooner or later. Like you cannot continue. So let's imagine you have started your work, you are in the middle of the work and you have to need leave your desktop. You cannot continue. You can copy the entire chat history to another window and maybe start a remote session, but you cannot continue in this, in this window where, where the conversations happened. You cannot continue on mobile. There are restrictions related to what if you decide that now I want to code something, chat cannot, cannot do that and you want to create an HTML page, then export this HTML page to infographic and you need this infographic in your email. So once again you need to start a different session with a different context and explain what you have been discussing with chat. So for me it's easier just to start everything either in with cowork, with dispatch or with cloud code and then you can easily navigate between those interfaces. Does it make sense, Akash?
- [07:44]
A
Yeah, it does. So I've been building a lot of AI 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 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 Skills. 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 posting, but instead it hallucinated that they use React when the posting said Python. 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 Claude 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 in 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 pushed a 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 AR. Check it out. It's one of the top AI evals platforms used by all of the top AI teams for a reason. So let's make this more concrete though. Most PMs I talk to, they're finally on like a Claude Pro or Max or API enterprise subscription. And what they really need is a very clear mapping of if this, then that. You've mapped all of this out for us. Can you show us when should a product manager be using? Cowork versus dispatch versus code.
- [10:17]
B
So chat is like a chatbot, like ChatGPT. What various tools. So you type a question, it answers. Sometimes it can execute a simple script and for example, reply with spreadsheets, but other than that, nothing complex. So it can draft an email, it can pretend to be some person, summarize information. Very basic stuff. When it comes to cowork, it's about working with real files and executing workflows. So by Real files, I mean reorganize invoices on my desktop or create HTML infographic. Cork can also plan long running tasks. So for example, if completing a task requires taking five, six, seven or more steps, it can do that and it can then execute those steps one by one. It can also spawn sub agents, so some tasks can be executed in parallel. So for example, you want to write an email, you want to summarize your product strategy. Inside this email you also want to add some presentation as an attachment, but the presentation should be converted to PDF so it can start one agent to summarize strategy or whatever, another agent to create HTML infographic and then maybe convert it to PDF and another one to do something else. Maybe find person details in your in some CRM system and then all those agent agents finish the work. It can get the results, maybe reply some steps or adjust and finish the work. So those are real workflows, real identic workflows with the access to real files on your desktop. And code is the same, but it's coding. So except other than connecting to all those systems and working with real files, it can execute scripts on your real machine because Cowork runs in a virtual machine and code can execute scripts, can execute system commands on your laptop and it can also it is also adjusted to working with code bases. So it means it has different set of plugins, not adjusted to knowledge work, but adjusted to designing front end, working with databases, debugging and so on.
- [12:56]
A
A PM who's non technical, who's watching this is probably thinking code is scary. The IDE is scary. Can I just skip it?
- [13:04]
B
No, you can't. Because engineers are going to use code. And even though many features when talking about personal productivity, like working with files, analyzing information, even organizing self improving knowledge database, you can do that in Cork. You will not have the Explorer review which is about presenting the hierarchy of folders and files. But other than that, Cork can do almost everything. But there are certain features in Cloud that only cork has. So for example the code has, for example one example can be sub agents that you define in your solution. Cork cannot do that. It can call dynamic sub agents, but you cannot have those agentic Personas that you so for example researcher, for example an agent that tests your solution, an agent that creates release notes. You cannot have this structure in Cowork. And similarly there are also other features that are like code specific or working with code basis specific, like hooks that do not work in Cowork. So eventually as a product manager working with engineers, you will have to work with code.
- [14:27]
A
I can't emphasize this enough. As a product manager, you should be learning cloud code. You need to get over the initial sort of hump of this doesn't look great, but Cowork is super powerful and so Pavel, you have spent more time in Cowork than almost anyone. You use it for a lot of your everyday day to day tasks, even though you are a former engineer who could use Terminal just fine. So can you walk us through what a power user, what a master setup looks like in Cowork and how you use it
- [15:02]
B
in Cowork? First thing to understand that we can organize work in projects or folders. So what you can see here, here are some of the recent folders that I have been working in and also predefined projects that can have custom instructions. So one of those projects is Editor, which is my project that helps me with copywriting, research, generating infographics and other things related to content creation. But maybe we can first use it without it. So I will just select some random folder on my desktop. It's not entirely random because I prepared it before. Okay, so here is the folder with invoices. And yeah, after granting permissions, Cork can now access real files in this folder. And the files inside are just random invoices that I collected from two months. So like Atlassian invoices. I'm not sure if preview is relevant, but yeah, like different invoices, different receipts and so on. So what I can now ask it to do is to organize analyze PDF invoices in this folder and group them by month in folders like. John, Mar, June, etc. Yeah, the duplicate, the duplicate files, some of the files have duplicates, so it should figure out how to do that. The names might be different, but the content is the same.
- [17:25]
A
So now you guys are seeing immediately why Cowork pretty much always is preferable to chat. In this case, it's actually manipulating things in your file system.
- [17:36]
B
As we can see, it created a list of steps. So it needs to extract dates from PDF invoices, it needs to identify and remove duplicates. Maybe it will use a hash function. It needs to create manned folders, move files and verify that if everything is correct. What we can see is also the context. So context for this, because this is an agent context for this agent is this file CloudMD instructions. There are no special instructions inside, but if this file existed, that would be this CloudMD that everyone is talking about with like custom instructions when working in this folder. So the next time I could prepare an inbox and just drag and drop new invoices inside. And every time a new file appears, this process is repeated and the file is sent to the right subfolder. And it also dynamically loaded Skills, which are like procedures. Skills are activated based on the task that the agent currently is executing. So Skill has a description. And based on this description, an agent can decide that this skill is about working with PDFs. I'm working with PDFs, so let's see what is inside. And then it will read detailed instructions, detailed procedures of how to work with PDF files. And we call this progressive disclosure. So you can have dozens of hundreds maybe of skills and Cloud will read them. So Cloud will read the detailed instructions only when the skill description matches what you are trying to do. So in this case only one PDF was identified. What it did, it created four folders. We can see removed some duplicates and the names suggest that indeed those were duplicates. Let's see the folder. Okay. April, February, June, March. If I open January, then I have some invoice from January. This is not a secret. Maybe this one is. So let's try a different one. Yeah, like postmark. It is not a secret. I can present it. So it's February, is that correct? Yeah, it's an invoice from February and that's it. And I asked about PDF, but you can also see that it also processed images. Yeah, and this is some fuel invoice. Let me verify that it is correct. It's in Polish, but yeah, it's February. I hope you can see it. So it just understood that maybe Pavel didn't know that there are images inside. Let's move them to this folder. Too
- [20:57]
A
powerful. Not. Gemini is not the only thing that can read images these days. Claude can too.
- [21:03]
B
Yeah, no problem. What else it can do? So it can work with files. So we have presented that it can load skills, which are instructions. But Skill can also have scripts to be executed inside. Not necessarily. Cowork can also execute them inside a virtual machine. It can connect to external and local services. And the most popular format is MCP server. So it's like the USB for agents. And by MCP servers, I mean in Cloud they are called connectors. So we have connector for Google, for Google Drive, for Gmail, for Slack, and for dozens of other apps or hundreds of other apps. Some of those connectors of older MCP servers are provided by Anthropic and others. You can just download them and configure locally and talk to your apps. So for example, I can ask. Let Me demonstrate we are still in this folder. It doesn't matter. But how many unanswered emails I have.
- [22:28]
A
This is a go. I don't want to run this on my inbox live on the podcast.
- [22:34]
B
Do not reveal any personal information or emails. Yeah, let's just see. So it connected to my Gmail account. It can also draft emails and it can. This one cannot send. It can only create the drafts. But you can also connect a connector that can send emails for you.
- [23:04]
A
How do you process your email inbox today? Do you recommend most PMs do it with Claude?
- [23:10]
B
Yeah, I create all. All the responses. Yeah, this is my current configuration. So yeah, Cloud, the system that learns drafts replies, but it doesn't send them automatically. So I'm using this default connector that cannot send. And similarly on Slack, theoretically you can ask cloud to response automatically if you use this connector there is a footer sent by cloud so everyone can see it. Instead I ask it to draft replies and I verify them. In many cases someone asks about the URL. So no reason to find for this. To spend time looking for this. I just approve messages or edit them. I send it manually. So there is a button in the interface send. And after every session, cowork or code, depending on what interface I'm using, verifies my responses and tries to learn from them. So the next time it will get better.
- [24:19]
A
Love it.
- [24:22]
B
And that's basically it. So a big thing are those skills that you can either use predefined skills or skills from third party marketplaces like my marketplace. That's basically it when it comes to cowork.
- [24:45]
A
So can you show us the PM Skills Marketplace? This hit 1300 GitHub stars in 72 hours. So it's gone pretty viral.
- [24:55]
B
Yes, of course. So it's this one, it's P H U R Y N P M skills, PM skills. It's currently 10,000 GitHub stars. And what I have done is that I created a set of plugins. So a plugin is like a collection of skills and commands and for different domains like data analytics, execution, go to market microtissearch and you can load each of those plugins separately. Next, inside each plugin you have skills. So for example, if we open, let's say product discovery, inside there are, ah, there is a documentation. So there are analyze feature requests, brainstorm ideas, plan experiments, create metrics to track your feature and so on. And also I have defined workflows that aggregate more than one skill. So for example product discovery, this can be okay, this is a Better example. So discover it is from ideation. Then we map assumptions. Then we think about, we think about. So we analyze. Actually this description is not correct. So it analyzes customer needs. Then based on those needs it will map the opportunities and how important certain problems are for the customers and how satisfied they are with what they already have. Then it will ideate so how we can solve those problems. Map the assumptions related to value, usability, feasibility, viability, maybe some ethical considerations. And it will plan experiments to prove or disprove our assumptions. So this is like the entire product product discovery workflow in one command. How to use it. You can go to the home page and there is a script. But basically you can just take this URL go to Cloud open customize. Let me see personal plugins at the marketplace. Yeah, like yeah, this interface is really changing all the time. So it's. Let's see this one. But I think that owner repo doesn't work despite the description. So let's try this one. That's my gut feeling that this can work. Okay. And those are not mine. So yeah, we can see it here. So data analytics, execution, go to market, market research and so on. And if I click product discovery or product strategy. Yeah, maybe this one. Now it is added, installed and ready to use what is inside Analyze. Strategy. We have ansoft matrix pricing strategy. So now when I go to the chat, Let's start a new task in cowork. Help me design and theoretically I can count on skill being activated automatically. But if you want really be sure that the skill is activated.
- [29:02]
A
Product slash command which I do recommend.
- [29:05]
B
Yeah, it's. It's kind of messy and sometimes if cloud has general knowledge about a certain area like product strategy, it thinks it knows something. But you want to override this knowledge and without doing it explicitly, it can default to to the training data. So yeah, if you know that there is for Amazon 2.0, whatever it means. So it loaded the skill and now it will interview me to get more information. But it is all part of the skill. So what is the core concepts output format? Then it will create Product Strategy Canvas. By the way, based on my Product Strategy Canvas. When you type in Google Product Strategic Canvas it will be the one I created.
- [30:01]
A
Nice.
- [30:02]
B
So it looks like this. And of course there are those famous plugins that anthropic created GitHub repo with plugins and skills. The main plugin was legal. Hundreds of millions of dollars evaporated from from the stock market. That's because people understood how easy it is to Describe certain processes and automate them.
- [30:30]
A
Yeah, with a proper markdown file written by a subject matter expert these days, Opus 4.5 and Opus 4.6, they can really use the tools, whether it's PowerPoint or Excel or for PM's Notion or Google Docs, and they can operate it like a competent person if they have the right instructions. It's pretty crazy. So can you walk us through a couple of these skill files and how you constructed them and how somebody constructs a good skill file?
- [30:58]
B
Yeah, sure. So the skill is basically how to do something. So some procedure or a domain knowledge about doing something. So you don't really have to create those skills manually. You can describe this process to cowork or cloud code and ask it to create a skill. So basically, if you can teach graduates how to do something, just repeat the same to cloud and it will create a skill. That's the easiest way. We can of course look inside and I usually don't do that. So I just use the chat interface to talk to cloud. But yeah, it's not this repo, it's this one. So if we open for example product discovery skill, identify assumptions for an existing product, we have the SkillMD file and you can also have additional files in this folder. But basically the main file is Skill MD and the format is markdown. We can see the preview in GitHub, but if I switch to the code view, there is this intros, there is this section that agents read. So they do not load the entire skill. They load name and description and when to use the skill, what it is for. And as I said, when doing a specific work like use when stress testing a feature idea. So if the user will write in the chat that hey, I want to test this idea and assess the risk, the agent will see the skill, it will see the description, it will just trigger it, it will use it. Other than that, this is just a prompt, so it can have instructions. It can be general knowledge without step by step. But it can also be like step one, get information from place. A. Step B is formatted in a specific way. Step three is something, it's just a prompt. So in this case it is. Yeah, it's the context. So you are a devilish advocate. We are stress testing idea and there are those arguments. We have seen that Cloud, when working on strategy, asked me a few questions. So those are the arguments and then instructions what it should do step by step. And that's all. And by the way, this is if someone wants to learn more, either they can see it as a markdown file or if they keep talking to an agent the agent will suggest my articles about identifying assumptions. So this is marketing inside skills but relevant to what the person was trying to do. So all the knowledge is inside skill but then the agent will also have those articles in a short term memory.
- [34:35]
A
I would tell everybody like iterating on your skills is one of the highest ROI activities I personally have done. So take hovels, skills is a baseline so at least you have a baseline. But then as you encounter some feedback for his skill give that feedback to Claude and say I want you to improve my assumption existing skill. Read our chat and see the feedback I gave you understand the root cause of what drove you to give output that I had to give feedback and rewrite the scale from first principles so that it doesn't make that mistake again. I have found this to be the single highest ROI activity I do. So I think once you get the initial skill you got to really iterate on it to really get the roi.
- [35:24]
B
I agree Akash, I don't know to memorize prompts. It's like in evals and you also have been writing about evals that you need when building some AI system or some AI pipeline you need to to see how the system performs in real life and then identify failure modes. And in this case you don't create evils but you can just give feedback to cloud say what was wrong, it will understand the context because it already has this context and what were your expectations and it will fix that and you test it again, test it again and eventually will eliminate like maybe 99% of the failures. So that's the only way. And you cannot just sit and use some magic technique to get it right on the first try. It doesn't work like that.
- [36:22]
A
So Pavel, now that people understand about self improving skills can you show us what our skill developed?
- [36:28]
B
So we already presented. I just asked to design product strategy and it loaded this built in so it loaded two skills. One skill was designing presentations and we should see it. Yeah pptx. So this is skilled by anthropic and another one was my skill about product strategy from my plugin and it used it to create this slide deck. We can see it directly in cowork, I can see it in Google Drive or display it here directly here. So we have product structure canvas for Amazon. We have the product vision, market segments like conscious customers, independent brands, relative costs so it adjusted colors, it figure out what the layout should be. This is not my branding. It's like Cork's Invention also icons and the difference between orange and green. This is interesting. So buyers have this. Whatever it means, it looks like something smart trade offs. So what we are not going to do so we have this focus on our strategy and the things that we want to say no to. So makes sense key metrics. So how we are going to track that our strategy is working like NPS order value, seller retention seems to make sense. North Star Star icon, guard line. It even suggested guard line metrics. So when we focus on our North Star how what should we monitor to make sure that our other areas do not degrade and carbon neutral delivery rate. This can have an effect on. Yeah, I'm not sure. Like public relations, our growth strategy. Why in different market segments and unit economics. Like this is pretty advanced and it's not a single layout. It's not just those are not just tables. It's diverse layouts, diverse icons, diverse. And it makes sense if I ask a graduate to do that. Like I'm not sure I got that in a few hours.
- [39:16]
A
Yeah. So there's two really mind blowing insights for everybody here. One, Claude is way better at using PowerPoint than it was a month or two ago. And so you need to look at this output and see like it can use PowerPoint to create great presentations. There is no excuse to walk into a meeting with a bad presentation anymore. And the second is that it used this skill specifically some of the things Pavel had defined in the skill around have a North Star metric, have guardrails and it has implemented those. And so that's why if you have a good skill, you can now create things. This is why people say RIP McKinsey.
- [39:50]
B
Right?
- [39:51]
A
You basically get a McKinsey level output in a minute or two.
- [39:55]
B
Yeah, and I have defined 60 something skills. But you can define how you can find how hundreds of skills or thousands of skills defined by others. I would only recommend you to verify every skill that is not defined by anthropic and make sure that it really fits your specific scenario, a specific use case. But other than that, the knowledge is there are many free repositories. I can also share those links with Akash.
- [40:25]
A
So we'll include those in our newsletters when we talk about this podcast so that you guys get all of those. Be sure to subscribe to both. That's the Cowork segment. So you guys just got the wow moment. Cowork can generate amazing presentations for you. We showed you how Cowork can organize your file system for you. Now talk to us about Claude Code Pavel, why Does a PM even need cloud code at this point? They think, oh, Cowork is good enough.
- [40:50]
B
Cowork is not adjusted to working with codebase. And as a product manager you will be working with codebases a lot. And also if you are building complex systems that involve multiple files, then this view that what we see in Cowork is not adjusted to it. So for example, if I want to find this presentation, I can click show in folder and it is somewhere probably in our. Yeah, we've been working with this invoices folder. So it placed it there. But imagine I have like 100 files or a few hundred files, like different invoices, different contractors, contracts, maybe some article drafts, some marketing strategies, pictures, brand guide and so on. So those files will be organized in some hierarchy and you cannot browse them from here. You can just drag and drop or select single files like just by browsing your local folder or browsing Google Drive. But there is no way to easily work with with those large code bases. One example, but also a list of contractors, a list of invoices, like a lot of graphical files, some templates, you need to upload them, find those files, upload them here. And once the agent delivers something, you need to find that in the folder or save it to the folder. So even though this is my real folder, I still need to find the same file to do something with it. So especially in case of code bases, you need this view in which you see folders, you can expand folders and you can see what is inside. So for example, I have infographics folder and inside infographics folder I have. Cloud code pricing. And inside cloud code pricing I have some files generated by cloud. So let's see it in. I will just view it here. So this is not the best picture that it generated. Yeah, but this was published today in my newsletter and also generated by cloud. Another one can be this picture with Calendar that went viral. This was also generated by cloud, not by me. So this one, this one is so good.
- [44:02]
A
So a lot of people, they struggle with getting faces and images and logos. So you've gotten the anthropic logo and you've gotten those eight people's faces. Also you've actually gotten the data from Twitter. So can you show us all three components of how you did that?
- [44:19]
B
Yeah, I think I need to explain how my system works and how it is organized to do that. Otherwise it would be I can repeat the process, but to explain how it works, I need to just to explain in the system. So recently Karpathi presented this system in which you use LLMs to build a personal wiki or knowledge base for humans. So you upload some information, give them give random articles on random attachments to to an agent documents and agent organize them and then you can browse those files, browse those information and how different facts are connected. I've been doing it since February 2026 and instead of building the second brain for myself, I started building second brain for my agents. So I'm the curator of the information and what I do is I send articles, I send infographics that I find on social media. I can also ask hey, let's analyze the last 10 posts by Akash above 200 reactions. What why they worked Voice, hooks, emotions.
- [46:13]
A
And a lot of people struggle with editing their terminal prompts. You were using the to do that, right?
- [46:19]
B
Yeah. There is the second way to use cloud code. I'm using CLI inside Visual Studio code but you can also use Visual Studio extension. They are both similar and they are not super user friendly. In February I started making screenshots on social media and I just I was giving different types of information to my agents. So back then it was cowork and I asked what made this post or what made this infographic work and then the coworker replied with some information. In some cases it knew the answer so I was able to note it. In other cases it replied with a hypothesis. So this worked probably because something
- [47:20]
A
I
- [47:20]
B
decided that instead of noting this myself, I will ask an agent hey, build a knowledge database and can you please every time I give you some article or infographic organize it by domain. So in this case the domain is social media. So this can be X, it can be LinkedIn, it can be substack and then write the rules for which you have a lot of information. If you see the repeating patterns save this pattern as a rule and if you are not sure save it as a hypothesis that you can later prove by analyzing more data. So what we have ended up with is this knowledge database and I have yeah for example sound bytes. So what creators use to core patterns that work across platforms based on data. What are the core techniques like interpretation layer uncomfortable closed credibility before claim and this is confirmed across multiple many platforms, all platforms and all creators and all successful posts. How to what is the word choice like list of hypothesis across platform specific to index rejected. So also things that we have been considering in the past but now we know they are not correct. Like let's say on cross platform this is. Yeah achievement as as proof hooks outperform achievement as point hooks or emotional diversification correlates with higher average engagement. Those are not hypothesis I formulated. I have not even seen them. I'm seeing it for the first time this one the number is 46 and it's like not even of the file. So it extracts this information and yeah, every time it analyzes more posts, more graphics it tries to confirm or reject those hypothesis. And yeah, at the end of the day I have information how to write the files beliefs for X what are the hooks that work on X, what are the accounts that we monitor, what are the rules, hard rules like probably more technical ones and some templates that we know we have tested and we know that this template will work. This doesn't mean that it writes for me. I previously demonstrated in the newsletter that like the conversation that I suggest ideas or suggest takes so like raw knowledge and raw opinion what I think about a specific news. But then cloud adjusts the format, adjust the style, adjust the hook to the information to the platform and yeah what I'm trying to say to make it resonate with others about your okay, about your posts, I'm not sure why
- [50:52]
A
so is the X API free that you've hooked into or how did you Are you paying for it? I've not. I haven't seen somebody connect into it before.
- [50:59]
B
Yeah, I am paying for X API so in in many cases you can fetch posts for free. Like it's this fx, Twitter, something like that. I'm not sure why we are seeing errors. Usually it is not the case.
- [51:18]
A
So this Yep, I saw API fx, Twitter.
- [51:22]
B
Yeah, so this one is free but it is limited. It doesn't always work. So just to save costs the agent tries to use it by default. If it doesn't work, it uses this custom tool that we developed together. Like I just gave it documentation of the Twitter API and it created the tool for itself. So it wraps this API to something that is easy to use.
- [51:51]
A
Nice.
- [51:53]
B
Okay, I'm not sure one for mua. Let me see what it told about you. Pure analyst voice radical topic diversity. He doesn't need to stay in pm. He can surf whatever wave is biggest on any given day because the mechanism reveal pattern transferred to food science, neuroscience physics. Okay, that's the his top 10 has two tech posts and eight random curiosity posts. That's the opposite of favolain strategy. The question isn't whether to copy some hypothesis. You already have it documented. The question is whether the mechanism reveal voice can work within your lenses Eye architecture, agent design, PM tooling at the same scale. Like we have many of those conversations with cloud code and coworker. Yeah, just to demonstrate. And similarly, I feed it with infographics and it tries to extract some patterns that catch the attention or work in other creators. We select infographics that are easy to codify as HTML and when they are easy to codify, then we design. We extract components that we can reuse. And then it uses the growing library of components to design infographics for. Does it make sense?
- [53:32]
A
Yeah, it does. The last component is how do you personally did it fetch the profile pictures of Boris and Tariq and this one?
- [53:44]
B
Yeah, but it was like a custom query, like to. I'm not sure where it was. It was ad hoc. Ad hoc. Maybe article, maybe something else. Let me see. Calendar? No. Assets? No. Maybe Drafts? No, it was like a temporary artifact. They asked it to create a script and go through first find. So I knew the free anthropic accounts. So then I asked it to analyze their recent posts and reposts and I assumed that they will eventually retweet every other cloud quote team member. Then it analyzed which team members used we or we just released or my team just released. If it was unsure, it verified the comments. So that. Yeah, just to make sure that the person was anthropic employee. And then yeah, it went through like 15 people from anthropic mapping for every feature mapping. Who first wrote about it for those people, we got pictures also from Twitter from X and then we iterated several times on how to visualize it. So that was the final result. But this is just like done by cloud code. This particularly this one was done by cloud code. And this is HTML based on the research. And the most difficult part was the research. So just getting all this information from
- [55:36]
A
Twitter, yes, it was difficult, but in the end you were just, you were talking to Claude code over hours in natural language. So it's not impossible for other people to do.
- [55:48]
B
Yeah, I do not code at all. I don't write any code. I don't even review the code. If I want to know how something works, I just ask questions in the chat window.
- [56:02]
A
So how do you make this system self improving and what are the tips and tricks that people need to know around Claude MD files and folder structure to make their system really sing?
- [56:15]
B
Okay, so first a lot of people. So people are discussing cloud MD file that you can put your instructions there. The problem with CloudMD is that if you put all the instructions inside, it will grow, maybe not exponentially, but it will keep growing. And Growing and growing and eventually it will consume a lot of your of your context window. And every time you ask a simple prompt in your project, all this CloudMD context will be included. It is part of your prompt. So a smarter approach is to organize your knowledge in files dedicated to specific domains and let me demonstrate mine. So I have cloudmdash so I have this main Cloud md. So the only goal of Cloud MD is to explain what this project is about. It doesn't have detailed instructions or detailed information about like good practices or bad practices of what to avoid, what to do. More often all this information is inside in other files and the only way A goal of CloudMD is to to give those instructions how to find the knowledge and what to do with the new knowledge. So project structure, this is just what we can see on the left side so I can skip that. Like there are tools, there are scripts, just so the agent knows without scanning the repo. Another one is where things live. So this is similar and by the way this was also created by Cloud. I didn't wrote this so I just discussed in the chat how we organize things and cloud writes instructions for itself. Who I am like basic information and the knowledge system. This is the most important part. So this is the self organizing system where I have index of all files like X files, LinkedIn files, substack files, substack notes, files, voice, archetypes, craft. So those are, this is general knowledge across platforms and then for every platform when different elements live. And now there are also workflows that the system should follow. So how to fetch data for Twitter, how to work with LinkedIn posts, how to link with, work with substack. The most important part is when asked to study and analyze. So every time I give it some posts like let's study the last 100 posts or I like this one, let's analyze what made it work. It knows what tools to use, so it will extract hook pattern structure, sound bytes and engagement metrics only if I request visual analysis, it will also analyze the attached graphic. This is to save tokens So I don't analyze the graphics every time I analyze the post, check against the existing patterns and false beliefs and then if there is an existing hypothesis, it will update the existing hypothesis with the new evidence. If there is an existing hypothesis but we see that the specific post didn't work, we can demote the hypothesis that the hypothesis is less likely or it will become rejected. Yeah, and it will happen to the post that was analyzed to the to the database. So I think we may need to simplify this. But basically it gets information about posts and it tries to decompose this knowledge and organize this knowledge itself into rules, into hypothesis and yeah, like other elements like structure, hooks, sound bytes, engagement metrics and so on. So the system learns itself without me telling it why the specific piece of content worked. The cloud does it itself. And the next time I have an idea or I express opinion about something that the other person tweeted, then I can say I like this. But I think this, this is connected to another idea or for example like Carpathi post, but it will degrade over time. And by the way, you don't need Obsidian if the user is not a person because we are building a knowledge base for agents and yeah, how can we retweet that? Or maybe I can add some additional details and then Claudit will suggest if we use my ideas, it's will it will use my take but it will format it in a way that resonates.
- [61:35]
A
So this is very content focused. Yeah, A PM watching this might say this is kind of content focused. What's in this for me? And I don't write code. So what is the minimum viable setup for a product manager and how they
- [61:50]
B
should be setting this up site improving system? That's. Yeah, I have recently shared that and let me demonstrate it. So I have actually I have a poster for this. So how to create a knowledge system that learns itself. And the prompt is very simple so you don't have to build everything I did. You can start with just this prompt. So before starting a new task, review existing rules and hypothesis for this domain, then apply rules by default. So for example, if we know that so basically this is the most important part that you need to paste to your cloud nd and this is not content specific so that whatever cloud does something in in a specific domain, like testing software, like writing marketing materials, maybe writing release notes, it should review the rules and hypotheses from this domain and it should apply the rules that were confirmed to its work. So for example, how a good test case, how good user stories formatted, or how the acceptance criteria should be written or what are the good examples of release notes or customer offer. Whatever you do, what are the good examples of something and what are the bad examples of something and it will try to extract the rules and then when you ask it to perform a task like hey, you saw the 10 good examples to bad examples, then let's try to create another offer for this new customer. It will review the existing rules and hypothesis because you didn't write reasoned. What are the good rules and bad rules? What are the hypothesis from the data that it has seen? And it will also keep learning. So every time you give it new information, it will update its knowledge, it will update the hypothesis. It can also ask you questions if this is something that, where you can give agent a feedback and basically it keeps learning, keeps adding knowledge and the knowledge is organized by the domain. So pricing, so marketing, testing, quality strategy.
- [64:28]
A
Yeah so you want to create that knowledge with an index and MD that has a router and in your cloud MD you want to give it this prompt so that it's self improving, it
- [64:37]
B
will figure out what to do. And every time it, it's, every time you ask it to do something, it will use the existing knowledge that is growing. And every time it sees new information with the context. Like when I quote a tweet, the tweet has some metrics like this tweet worked or didn't work or how many people liked it. But maybe you can feed it with the offers that worked or with. Resumes of successful candidates and it will start generating those rules. And the next time you will get a candidate you can ask Cloud, hey, is this a good candidate?
- [65:21]
A
Love it. So one of the things that you've written about that I haven't seen a lot of people write about and maybe you can show us is the Chrome mcp. When and how should we be using that?
- [65:30]
B
I don't use Chrome MCP anymore. And the reason is that I've been testing different approaches and Chrome mcp, it's basically MCP that controls your brain browser. It works well probably similarly to Cloud in Chrome, which is anthropic extension that you can use. Like this guy here, you can ask to do something or you can also call it from. You can schedule tasks here or you can call to cowork and cowork will call this Cloud in Chrome. The problem with those extensions is that they rely heavily on taking screenshots and screenshots mean a lot of tokens. And if you have some tasks that you want to repeat regularly or complex processes, you can easily consume like $100 in an hour, especially with opus. So what I do instead is I use. Let me check but I think my agents right now use Agent Def. So what Agent browser does by Vercel Labs, this is the most reliable according like in my tests, it also uses the real browser, but it can do that in a headless mode and it explains the structure of the page to the agent without presenting the entire HTML So it is token efficient. So the agent doesn't have to see HTML and doesn't have to interpret HTML but can take actions. So it will see buttons with specific IDs even if the original button didn't have ID. So this is real browser, real rendering. It can execute JavaScript if needed. It waits for rendering, which is important. So if this is a single page application or there are some additional resources that load a few seconds later, it will wait for it. And yeah, it presents this page to an agent without taking screenshots. So the agent can see the text, it can see layout, can see different components, the content. It can say hey agent browser, click this button. But it doesn't have to interact with parse or interact with HTML itself. It is very simple, simple protocol. It's not an mcp, it's a CLI tool.
- [68:24]
A
Very cool. Use Agent browser from Vercel instead of Chrome mcp. And what do you use it for exactly? Like what is the use case that a PM should think about?
- [68:32]
B
This is when like everything where you don't have an API to get data from external system. So for example, if I want to get data from LinkedIn, of course I can fire Chrome MCP or trigger Cloud in Chrome, but it will start taking screenshots every half a second or every second. So it's like crazy token consumption. And it is also visible in most cases on your screen. So it's not something that you would like to see. And with this I can just ask it to hey, go to LinkedIn, check my inbox or analyze the top last posts by Akash and see the comments. Something like that. So maybe more enterprise use case will be accessing some legacy software without API or without McP servers. Maybe SAP, maybe some old CRM system the agent can access just by using web browser.
- [69:46]
A
This is pretty epic. So as a PM you need to hook your claude code into absolutely everything and you should use Agent browser for the stuff where you don't have an MCP CLI API to hikinto. Now I want to move into remote work. Anthropic shipped four remote services in recent months. Web Sessions, Remote Control, Dispatch and Channels. You use all four of these remote methods. Walk us through how you actually combine them for the same project and when a PM should use which okay, so
- [70:19]
B
the one issue with Anthropic is that those surfaces overlap and I don't use them in the same proportions. So I have tested channels, I have abandoned channels because I didn't see value. Like having this telegram interface because I have Cloud. I have a dedicated cloud app where I can do everything. Okay, but starting with maybe, let's start with dispatch. So dispatch is a new tab that appeared in the desktop app and also on your phone. And this is exactly the same. So here. Okay, I'm not sure what it is. So this patch is like this single, single interface in which you can interact with cloud code and cowork. It is displayed under cowork. It is a bit confusing. It is a completely different product. It's like walkie talkie. So it can start multiple background tasks and every time the task is completed it will report back what is the status. So for example, create an infographic in anthropic style for the following text and let me find something following text. And the text will be about Bolt and Windsurf and it's probably your work in anthropic style for the following text. And this will be LinkedIn resolution. Then I can ask it to hey, how many emails in the last two hours did I receive? No names, no personal data. It doesn't have to start the previous task, it will just start another one. And if we open the recents I will show them. We should see that it delegates them to, it should delegate them to other threads. Three emails in the last couple of hours, so maybe it did it directly. And let's go to code. Ah, analyze Akash posts. Normally it would delegate those tasks to sub agents and you will see them as dispatch tasks in the left panel. So you can start multiple agents and to use a single interface to communicate with all of them. And I can take my phone, open the, let me open the cloud app and I will try to demonstrate. Demonstrate that. But first I will ask it, are you there? I'm not sure this will be visible but like I have the same interface here.
- [74:16]
A
Yep, I can see it. And so you can basically talk to it on web and mobile now. And so there's really no excuse. You're out on a walk, you're at a meeting, whatever it might be, you're at a conference. Conference you can have your agents running for you. Yeah, and what about code web sessions? You said you use those roughly 60% of the time and dispatch 40%.
- [74:36]
B
Yeah, I don't remember the exact stats. Like I really use all three surfaces and this proportions differ from day to day. But most of the time I use dispatch and web sessions, maybe like 70% together. Then 5% chat sometimes and the rest is cloud code. And the reason I use dispatch so much is that I just don't work with my laptop, I go for shopping, I go somewhere with my kid, and I just dispatch tasks. I already explained that I don't code. I don't. I just provide feedback, text feedback in the chat. And then cowork dispatch presents me the results. I look at the results, I dispatch another task, and then I can continue what I was doing. So, yeah, it really transformed my ways, my days.
- [75:41]
A
Amazing.
- [75:42]
B
Yeah. We have not covered web sessions, so web sessions are something different. So here in cowork, in dispatch, depending on the task that you give it, it can either dispatch task to cowork. Like I asked about last three tweets, and you see there is a dispatch thread here. So this is something where I do not have to interact with it. It's dispatch talking to this agent, but it is visible for humans. And similarly, I can also dispatch some coding tasks from dispatch and it will implement that and report back. Oh, it even created a graphic for your post, like, let's say a prototyping graphic.
- [76:31]
A
Ooh, I want to see it
- [76:35]
B
open. Like, whoa.
- [76:39]
A
Pretty good.
- [76:40]
B
Yeah. Sometimes you need a few iterations, but it is not the. The worst point to start.
- [76:47]
A
Very cool.
- [76:51]
B
Okay, so this is this dispatch, so you can think of dispatch. Normally you don't use it on. On your desktop, you have this single chat, single interface that you use on mobile.
- [77:06]
A
But
- [77:08]
B
sometimes. But for dispatch to work, your computer must be online. And sometimes this is not the case, and sometimes there is a problem and it stops working. Or sometimes you have so many parallel threads that is difficult to manage them from a single chat. Interact. There are no tabs here on your phone, you will see just one big stream of messages. You cannot organize them. So when I do a more complex work, I switch to this code task. And this is. You can think of it as visual Studio code. And cloud code is just in the cloud, so it is hosted by Entropy. So it's. Yeah, it's just a list of sessions where I can select a specific folder. Either my local folder or folder in GitHub, like my editor project, it is synced with GitHub. So all those files or knowledge files, hypothesis, sound bytes, hooks, this is all synced with my private GitHub repository. Even when my laptop is offline, I can go here from my mobile phone and ask it some question. And it will work in the cloud without any device.
- [78:42]
A
Yep. And this is actually a more secure way to run stuff, guys, because it's in anthropics servers. So I highly, highly, highly recommend everything you build, all your operating systems, you put them into GitHub, you point them via code web sessions and you work with stuff here. You can also the coolest thing as we just showed with dispatch is you can start a chat here, start something here on your desktop, then you can go to your phone and so it's like you can be working 247 with us.
- [79:11]
B
Yeah, that's correct. And I don't work internally 247 but like I feel that my life is now much more work is much, much better integrated with life. So I don't have to have these blocks dedicated to work. I can go on a shopping and yeah, maybe when, when shopping this person task and then check 10 minutes later when I have a graphic, provide some feedback and then continue what what I was doing. So this is really transforming. And when you need a better organization or when you know that you want to focus on coding like my Acredia IO platform, then I switch to code. And I also do it primarily on mobile. And yeah, like in some cases I also use Cowork and Visual Studio code. But primarily this is remote. Most of the work is remote work.
- [80:11]
A
This is epic, guys. So hopefully you can understand how your life will change once you set all this up. I want to draw out some key lessons, Pavel, from all of the hundreds of hours you've now put into these things. Starting with what's the biggest mistake PMs make when setting up Claude?
- [80:26]
B
Yeah, I think that the biggest mistake would be to prompt it every time from scratch. Instead of using cloud, I force myself to organize knowledge and this is very difficult to me when writing articles, but cloud can do it without effort. So instead of collecting prompts and figuring out how to do something, it's much easier to just to build a system where cloud can learn from its mistakes and either from your feedback or from data, it can figure out, hypothesize and figure out the better ways to the work. Yeah, not doing that, not organizing your knowledge, not learning from mistakes and just having everything in your head. And yeah, this is the biggest mistake the PM can make. Just hoping that you can learn the better prompts. There is too much data to analyze.
- [81:26]
A
Cowork versus Claude code. If a PM only had a little bit of time to learn one, which one should should they choose and why?
- [81:32]
B
This is not an alternative. I would start with Cowork because everything you will learn in cowork will help you better understand code. I use the same repo from Cowork and from cloud code. So for example, I already presented that, but once again I can select this editor project Maybe let's remove this one and it has CloudMD. It will see the same files. It will. So this, this is CloudMD that I presented in Visual Studio. It will see the same files, the same structure. So I can ask it to analyze tweets here in this interface I can do it on my mob in the using dispatch, I can do it in web session, web cloud session. I can do it in Visual Studio. This is all connected to the same repo. I will start with Cowork because this interface is more simple. You don't have to get used to Explorer and Terminal. It's more user friendly. You can see files, you can open those files directly here without plugins, without how to display markdown or how to to display HTML. If you see HTML here, you click HTML and it will show you HTML. And in Visual Studio there are certain tricks that you must learn. So I would start with Cowork and just understanding how to work with agents, how to aggregate this knowledge, how to define your workflows and then once you feel comfortable with Cowork then add this Terminal aspect. But in my opinion that this is more effective, should be more effective for many people than trying to learn cloud without experiencing cowork before.
- [83:31]
A
What's your hot take on where AIPMs are headed? What does a PM's daily workflow look like in 12 months?
- [83:37]
B
I doubt that in 12 months the role will disappear or something. But yeah, we are heading into like super individual contributor PM and then CPO CEO at the top. So I imagine that most of the time you will be working with agents, orchestrating multiple like multiple agents at the same time, switching the context. It will not be easier. The work might be even more demanding. But at the same time you will focus on. There will be less trivial things because those can be automated like writing tickets or debugging something, preparing a presentation. Those are the things that should be automated. And eventually people who develop skills from multiple areas. So like P shaped or even broader shaped that understand marketing, understand strategy, understand technology, understand products, can talk to customers and understand enough to delegate the work and assess the results.
- [84:52]
A
What's overhyped versus underhyped in the cloud
- [84:54]
B
ecosystem Right now I get the impression that people still have had not realized what agents can do, especially with the right harness and with the right systems around them. I just started experimenting with that. Like I've been working with cloud and with agents for two years or more, but I just started like investing heavily in automation and hardness myself and I know that I can be much more effective. I Doubt there is something that is like there is not enough hype so
- [85:31]
A
everything is underhyped right now. Guys in the Claude ecosystem, go learn what we've showed you right now. Final question for you Pavel, your N8N episode, it did really well. Is N8N over? I mean should everything just be done in cloud code now?
- [85:47]
B
No, Nan is still relevant. There are two types of. There are two types of automation. One automation is when you automate things for yourself like I want to analyze 100 tweets or I want to draft a response to customer email. Then you have this person automation and you can use cloud code for it. Also we can automate specific processes inside your code base like code review or release notes or front end design and have those sub agents, that's fine but when you want to automate production processes, The logic that I presented this is part of the prompt and then the agent can respect, may not respect it. All we do is edit text files within Harness that was defined by anthropic. We cannot tell the agent that hey, if anthropic API fails, try three times or for this you should always use this tool before. You should always verify that customer email exists before doing something or that customer has access to this data. We just create text files and we hope that agents will follow our instructions more or less. Like you can add hooks, you can add some. There are some exceptions from this rule but overall we rely on anthropic hardness interpreting our text files. This doesn't scale, this is not secure enough and this is not effective enough for production processes. So if I want to design a system that replies to customer tickets or maybe chats with the customer, I want to have a hard guidelines, not prompts that the customer cannot access data of another customer for example or that cannot delay data or if you want to send an email then yeah, like copy a file that has 1 gigabyte from 1 place to another. We don't want the agent to do that or maybe even we don't want agent to look at this data. It should be handled by the code. So Akash, I'm not sure you remember that we built an agent in three versions and why one was fully autonomous and we started with the least autonomous one where most of the process was code and there was one LLM call. Then we built a hybrid scenario and then the last version was fully autonomous and in production everything that doesn't have to be autonomous shouldn't be autonomous. So we should have code, we should have conditions, we should have guard lies. If there is a process that should be followed. It should be code and maybe in this process there are some LLM calls or agents inside. So this is, this is more difficult to implement, but it is much more cost effective and much more safe than relying on agents. Respecting instructions.
- [89:10]
A
So when it comes to the takeaway from our Nadan episode, as we showed you guys, you want to actually be like less vague. And with these anthropic based Claude code systems right now there's a lot of room for interpretation, less controls. If you're going to build a true production grade automation for your company, you're still going to be using N8N. You're going to be defining as much as you can some of those hard rules Pavel talked about. Did I summarize it correctly?
- [89:35]
B
Yes. And you can also use Entropic API to define agents in code, but that's a separate story. And you can use Entropic API to define your workflows in code, but this is not the same as organizing text files so that the agent follows the instructions. We can also code our workflows with anthropic API or OpenAI agentic API or other APIs. The simplest way for a person that doesn't code is is using Canadian.
- [90:17]
A
Makes sense. All right guys, we have walked you through the AIPmtool universe in today's episode. If you haven't yet, be sure to subscribe to Pavel's newsletter. He has an upcoming Cloudathon starting May 9th which you may want to participate in. Check out our other episodes if you want to learn more about AI product management, N8N or customer discovery on my 9th.
- [90:42]
B
So in a month we are starting Buildathon Cloudathon with Cloud and the previous edition it was 250 students. We were building real products with Nan and with lovable and this time we will focus on cloud code and nan@triggerdev to build real agentic workflows. So yeah, I encourage you to check the program. There are only 60 places in total hotel and you can also see the gallery of the real things that our builders have shipped. So this is not the theory. There are a few dozens of solutions that are available to browse in the gallery and you can vote for your favorites and also understand how they were built, what is the architecture and yeah even download some documents. So all this is public and the next class starts next month.
- [91:40]
A
Alrighty Pavel, thank you so much for being on the pod.
- [91:42]
B
Thank you Akash, it was a pleasure.
- [91:45]
A
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.