Full Tutorial: Build Your Personal Operating System with Claude Code | Teresa Torres

At the beginning of my day, I literally just write today, and we can see what it does. It generates my to-do list for today. It's going to go to Trello and see if anybody on my team has added any new Trello cards. And then it basically runs this Python script, and then you can see it's going to read my today MD, and it's going to update it, and you can see it popped up here. So this is a link to my research digest, my blog post. It's 9,000 words, and I wrote it in one and a half days. There is no way I would have done this myself. That is insane to me. Yeah, so I'm thinking about it. What do you think? Oh, I don't really like that. What if we try this other way? And then I do that throughout the whole construction of the blog post. It can just be like interview me about my business, and then it will ask you a bunch of questions, and then it will write a context file for you. This file we're looking at, this profile, I never wrote a word of it. Every time I have Claude add a context file, I say what index needs to be updated, and it just figures it out. And I say I'm just overwhelmed by all that stuff. What are your three tips to get started? Whenever you find yourself explaining context to Claude, stop and think about am I ever going to have to explain this context to Claude again. Okay, welcome, everyone. My guest today is Teresa Tours. Teresa is a legend in the PM field. She's author of Continuous Discovery Habits. But today we're going to talk about how Teresa uses Claude code for everything from writing to editing to task management to coding. Really excited to get her to give us a tour of her Claude code projects and show us how it's actually done. So welcome to Teresa. Thanks for having me. I'm excited to do this. Yeah. So, you know, I've also used Claude code quite a bit, but I'm super interested in seeing your high level workflows. So maybe you can give us a quick tour first. Yeah, let me share my screen. Okay, so what we're looking at is really simple. I have obsidian here on the left, and then if people aren't familiar with obsidian, it's just a note-taking tool that's based on the markdown. And then I have two terminal windows on the right. And the big thing that I use Claude code for, like I started using it coding, just like everybody else, most that's most people's entry into it. But I, what I really loved about Claude code with coding is it's almost like your pair programming with Claude. And I was like, wow, how do I pair with Claude on everything that I do? And so I started doing this for writing and for strategy and for literally all of the work that I do. This is my setup. This is my work obsidian vault. So I have an obsidian vault called work. In it, there's a bunch of subdirectories. One of them is LLM context, which I'll get into that. And then my notes, which is just any notes that I have. I have a research project that we can talk through. I have my task system. Worthy reads are like articles that I've saved. The other people wrote that I really like. And then my writing directory. And then you can see I have a Claude MD file here. And we can kind of go through all of this. But I'm going to start with tasks. So the way my task system works is I have folders for different things. So I have a folder for bugs. I have a folder for ideas. I have a folder for tasks. And every day I launch Claude inside my tasks folder. So you can see this top terminal window. I'm in tasks. I'm just going to launch Claude. And at the beginning of my day, I literally just write today. And we can see what it does. The first thing it's going to do is it's going to go to Trello. And see if anybody on my team has added any new Trello cards to my board. You can see good news. There's no new Trello cards. I've already run this today. But we'll just see what it looks like. And then it basically runs this Python script where it generates my to do list for today. So that's what we're looking at here in obsidian. It says Monday November 10th. I have one overdue item. I have a number of items that are due today. And then I have my in progress ideas that I'm working on. And this script just generated this file. Every task is a markdown file. So you can see in my tasks folder, I just have a whole bunch of tasks. Basically, this task that's overdue was due on Friday. You can see it's just I have to call the grooming place for my dog and schedule an appointment for her. And I didn't do that yet. And then all my other tasks like I have calls with a couple people today. I'm writing a Claude code safety article. I've got to add some images to it. All this stuff just shows up on my to do list every day based on what I put in my tasks. Got it. So the other tasks like the calls and stuff is coming from a calendar or is it coming from just your notes? It's tasks that I've created. And I'll show you. We're going to create a new task together. I'll show you what that looks like. So that's the first thing is when I run the today command. I do it every morning. It's basically looking through my tasks folder and looking for anything that's due today or anything that's overdue. And then it creates this today file for me. And it's just telling me what do I need to do today. And then I distinguish between tasks that have a due date and ideas that, you know, they're like more like projects that don't have a specific due date but they're things that I have going that are ongoing. So you can see like I have a podcast just now possible. That's like always in my in progress because it's reminding me to like make sure I schedule guests. And you can see here I have a single episode. This is my project for like getting that episode ready to be released. And then I have a task for social media. But this is really just my like remember to schedule guests kind of thing that's always in progress. And so what this does is it gives me a lot of flexibility. If I just have a random idea, I can just say it a cloud new idea and it will tell it what it is. It will create a markdown file. It'll put it in my ideas for. If it's a task, I can give it a due date and then it will show up on my on this like to do list. This is just called my today MD on the day that it's due. Should we try making maybe like a record podcast of Peter or something like some sort of task? Yeah. So we'll do a new task in just a second here. The other thing that's happening when I run this today command. It is I've built this research system. So I'm trying to keep up to date on like academic research that's related to my work. And so I built this system that searches a pre-print server and then Google Scholar every day. And it gives me a research report of what's relevant to my work. And that gets added to this today list. So you can see right here, it's not here yet. And it's because we haven't done that part. So it's running this slash command that's part of my research project. And now it's asking me oh it wants to go see if there's a research queue. So we're going to say yes to that. And then you'll see it's going to update this today list with any research for me to review. Q's empty. It's creating my research today MD. Got it. So this is just like searching some websites to find new research, right? Yep. And then you can see it's going to read my today MD and it's going to update it and you can see it popped up here. So this is a link to my research digest. So that's my today command and you can see it gives me a summary like this is what I just did. I created your today MD with the overdue task 10 tasks for in progress your research. Whatever. And then you can see it's also creating a this week view and a next week view. Got it. Okay. Yeah. Okay. So let's say I want to do a new task. We're actually going to write a blog post to that together. So I'm going to do new task right plan auto except cloud blog post. Do today draft outline with cloud. And basically this this task folder is set up with a cloud MD. So that cloud knows what to do with this. It knows to create a task. You can see it's using obsidian front matter and I've defined this whole system for cloud. So it knows to do this. It's defining as a task. It's putting the due date is today. It's tagging it for me. It's give basically giving me kind of a checklist. I'm actually not supposed to do this because it's kind of a crummy checklist. It's supposed to just take my notes. But pretty good. We're going to go with that. And then let's see if sometimes cloud is smart enough to put something due today on my today MD. It's not this time. So I'm going to say add to today MD got it. Okay. And then what that's going to do is it's just going to add that task. You can see it's here. So now I have my right plan auto except mode. What I love about this is I work out of the terminal most of the day and I keep this tasks terminal open all the time. So if like I think of something that I have to do or I have a random idea, I literally can just be like new idea blah blah blah and it's done. And then I can just go back to my work in my other window. And it's it's a lot faster than like opening a web browser, going to Trello, creating a new card, setting a two day, right? It's just it's super fast. And that's what I love about it. Got it. This episode is brought to you by Optimize Lee. The family in marketing usually isn't a lack of ideas. It's a lack of time. If your to-do list keeps getting away from you to take a look at Optimize the OPPO. An AI agent platform built specifically for marketing. With OPPO, you can use AI agents for SEO and geo recommendations, A/B testing, website analysis, and much more. OPPO knows your brand inside and out and plugs into your existing tools and data systems so that you can save time on labor-intensive feature testing reporting and more. See what it can take off your plate at optimize Lee dot com slash AI. Now back to your episode. The other thing I'll share is it allows me to do things like what are all my marketing ideas. And it's just going to go search my ideas folder for anything related to marketing. And so like whenever I'm working on a new project, I can just ask cloud, like, what are my tasks related to this or what are my, what are my idea, open ideas that are related to this? And it just goes out and finds them. And like Trello has search, but it's not the best, frankly. So I like this a lot too. So you have like ideas and memories and like ran a research snippets that you pulled. Yeah. So you can see like in my tax folder, I have bugs that have been filed, I have ideas. Import is for if I'm importing a bunch of stuff from Trello, I want to review it to make sure it imported correctly. My inbox is how I get stuff from my phone to my, to this whole system. Memories is like things. It's like little snippets that I want to remember. So we can kind of look at what's in here. I think this is safe. Like I have a affiliate link to the AI e-vails course that I always forget what it is. So it's literally just here's my affiliate link. This is a task. I don't know actually. Real real real quick. What do you mean by inbox? Like you send an email to yourself over the phone or yeah. So this, this is a little bit of a hack and I'm actually moving away from it. So I mentioned that I moved a bunch of stuff and it broke some things. But I was using Dropbox to sync my vaults. And I'm now moving to Obsidian Sync to sync my vaults. So the Obsidian Sync, I can use the iOS Obsidian app and I can just access all of this stuff from my phone. But when I was using Dropbox, I had to set up. This is like a iCloud linked folder so that I could add to it from my phone. And then it would automatically show up here. And then I could pull it into my task system. That was kind of a pain in the butt. So I moved from Dropbox to Obsidian Sync to make that easier. Got it. Okay. So basically Obsidian and Cloud Code runs your life right now. Yeah, yeah, pretty much Cloud Code and Obsidian run my life. All right. So let's go back to the writing the blog post. How is it going to help us write this blog post? Yeah. So I could do this. Let's do this. We're going to get rid of this dumb checklist that Cloud made because I don't like it. And we're just going to do like, okay, I'm going to talk through. I'm just going to like talk out loud. I plan out my blog post. So for context, I'm in the middle of writing this huge cloud code series for people that are non-technical. And it started with like, what is Cloud Code? Why is it different from Cloud in the browser? And the second post in the series was about like how to give Cloud a memory, which if you want to get into that, all my context files are also here in Obsidian. And then the third blog post that's coming out this Wednesday is about safety. So how to use Cloud Code safely. And then this one, we're going to start together as the fourth article. And this is where I'm going to get into like, doing projects with Cloud. And so I want to write a blog post where I talk about like plan mode, auto-except mode. And then I always want to use examples in my blog post that are related to product managers. And so like in this blog post, I might think like, let's talk through plan mode and auto-except mode if you were planning a new feature. So I'm starting to think about like, what's my example going to be in the blog post? And I have a AI product called the interview coach. This is a product where in my class where I teach how to conduct effective customer interviews, we do practice interviews with each other in class. And then the students can submit their transcripts and get like detailed feedback on how good of a job they did. And the thing with this product is it was built for my story-based interview coach or story-based interview class. And so the coach gives feedback on story-based interviews. And my new feature idea is, can I extend it to work with non-story-based interviews? So this is like a feature idea I have. And so in the blog post, there's a little meta. I'm going to use this feature idea to show how I would use plan mode and auto-except mode, right? So I'm going to, this is all I have. This is literally the state of this blog post. This is real. I have not written a single thing. And now I'm going to go over to this terminal window on the bottom and I'm going to launch Claude. And this is in the context of my writing vault. And so my writing vault has a Claude MD that talks about how I like to write and how I like to write with Claude. So it has different context than this tasks window. So like in my writing window, I can't type new task. It doesn't know anything about my task system. I have to do that in my tasks window. So we're going to do this. I don't know why it thinks it's a new folder, but we're going to ignore that for a minute. And then I'm going to say I want help creating an outline for a new blog post. I do this in plan mode. She's actually what the blog post is about. You can find my early thoughts in. Oh, see, I would not, this is a little weird. I would not do this in the task card. What I would do is I would come to writing. I would go to my Claude code series and I would do a new file. Let's do plan mode. And that did not go where I wanted it. So we're going to move it in plan mode. And I actually did not tell Claude enough information because it's not, it's going to look for plan mode in the current directory, but the plan mode is actually in Claude code. So we'll see what it comes back with. We'll see if it finds it. Okay. So basically, you have a cloud. Okay. So just real quick, you have a cloud md for your writing a vault that has a bunch of writing styles and like, you know, that kind of stuff, right? Yep. Is that got it? Yeah. So if you look at here on the left, like tasks is a thing, you can think about tasks is like a Claude project. I launched this instance of Claude in the context of tasks. And then I have a writing folder. And I launched this instance of Claude in the context of the writing folder. So the writing folder has different rules than the tasks folder. They each have their own Claude mds. So the Claude md for tasks explains how the task system works. It explains how tagging works. It explains how front matter in obsidian works. So when I just type new task, it knows exactly what to do with that. Whereas my writing folder doesn't have any of that context. It just knows it, like you can see here, I told it, I want to write a blog post. It found plan mode. It read it. Now it's asking me to read my style guide. And that's because my Claude md in my writing folder says before we do anything together, start by reading my writing style guide. Got it. Okay. So I'm going to go ahead and say, yes, it can do that. Do you ever just ask it to just like, uh, skip all the permissions because it's kind of annoying to. Yeah. You know what? I have. So I just moved everything. Everything used to be in Dropbox. And I had all the permissions set up where my tasks could read and edit everything inside tasks and writing could read and everything inside writing. But because I just moved everything, those permissions aren't. I literally moved everything yesterday. Uh, and so I haven't copied over those permissions yet. I'm learning like when you move things in Clod, it kind of breaks things a little bit. Uh, so it's asking me which features do I want to focus on? I actually want to do both. Um, what's your intended audience for this post product? People knew to Claude should already know that. That's a little disappointing. Wait, so, so like, uh, is asking you questions because you prompted to ask questions? Ask me questions because it read this plan mode document. And it's now like trying to get more information from me to be helpful. Normally, I have a little bit more here, right? This isn't really enough for Claude to work with yet. But let's, let's see what Claude does. Yeah. See, it's trying to do too much right out of the gate. But let's see what it does. Now I understand the direction. Let me create an outline. Fine. It's already got a headline. Introduce plan mode and auto accept mode. What it is. When to use it, what you plan, what it is, the dangers. That's, that's great. Yeah. This is kind of nuts right? Like it kind of went crazy. Um, so I'm going to tell you I went crazy. Uh, it's kind of like, uh, when I use cloud code to like write a product spec, I always wanted to put the spec in MD files. I can delete a bunch of stuff because it tends to do too much. Yeah. So usually, to be honest, usually I have a little bit more. So let's, let's actually play with this draft a little bit. I would probably give Claude something like goals, help people new to cloud code, do bigger projects. Claude code. Uh, use planning a new feature as a product manager, as an example throughout. And then we could do, I can use my personal experience with expanding the interview coach. I'm going to ignore typos for now because cloud won't care. Um, and then, um, I'm going to do something like less about the features, these features, more about how to get Claude to do good work. And let's see if this helps. Got it. Let's see what it comes back with. So, okay, so after this, I'll, like, you're going to ask it to do all my research or what's the, I can do next. Yeah. So, you didn't see already it came back and it's like, oh, okay, I made too many assumptions. Yeah. And it's like, okay, now, like, now is this like the right direction. So now I might, now I would, I really want to do is ask Claude, like, you asked about research. We've got to come out of plan mode for this. Has anyone else written a blog post about this? And it'll go and it'll go search and see what other blog posts are out there. So I'll often do this. I'll often, like, before I sit down to write, I want to know what else has been out there. If somebody else has written this article for my audience, I'm not going to write it. I'm just going to, like, write a different article and just link to that article. Um, I want to make sure that I'm writing stuff that's unique. And then, now, sometimes someone may have written this blog post, like, in the context of coding, that's fine. Most of my audience isn't going to read that. And so, but I can read that article and learn from their experience and then translate it to product management. Um, so I always use Claude code to, like, do searches for me. The other thing I use it for while I'm writing is, like, I'll make a claim. And I'll be like, Oh, is that claim true? And then I'll ask Claude, like, can you do some academic research for me and see if there's evidence behind this? Like, is this really a true claim? Or is it just something that I randomly believe? So let's see what Claude came back with. So a lot of people have written about this. Of course, anthropic has written about it. They have great documentation. Most are written for developers, engineers. Yeah, perfect. I think people roll like technical stuff about plan, but not about this use case. Yeah. So then I might ask, like, okay, um, how do people search for this kind of content? What keywords from an SEO standpoint? Should I keep in mind? I almost never do this to start. I do this at the end, but we can do it to see how it does. Oh, that's very smart. I never asked this question from my blog post. That's important. Yeah. And again, it just goes off and does this thing. And I let it do this thing. And meanwhile, I'll be like, over here, noodling. I'm like, how am I going to structure this blog post? And like, this is really stuffed out. There's not really a blog post here, right? So I might start to think about an outline and be like, okay, well, the introduction needs to be strong hook around value of doing project work with cloud code. Then introduce like cloud modes, plan, auto accept, reference, safety article, walkthrough detailed example interview coach. So let's see what I came back with. So I've found it's really good at keyword research. Like really good at keyword research. I tend to do this after I've written the article because I really want to rent my articles for humans. But then I might tweak some words in my sub headers or my titles to like target higher volume keywords. What is it actually doing? Is this using Google searches here? Or is it actually doing some fancy stuff? Yeah, you can see it's just doing searches and looking for what's ranking well. Oh, is that what it's doing? Yeah, interesting. Okay. Yeah. Okay. So it's sort of my SEO researcher. Interesting. And then I could be like, I've started to stub out an outline in plan. Can you suggest alternative structures? There's not enough meat here. It's probably not going to do a very good job here. But yeah, um, we'll see what it does. And so I do this. This is literally how I write. I'm like doing all my thinking really rough. I'm going back and forth with Claude. I'll have questions like, what do I do? Like, how does this working Claude? Like, I think I know how auto accept mode works, right? But then I'll be writing a blog post about it. I'll be like, is that really right? And I literally will just pop over here and be like, Claude, is that are you allowed to do this in auto accept mode? Um, and so that's really nice too. And I know this is a little meta. I'm writing a blog post about Claude code. But Claude can actually answer questions about anything, right? So I could be writing a blog post about how product teams do customer interview analysis. And I can still ask Claude. In fact, I wrote a blog post about how about customer interview analysis with AI. And then when I was writing that article, I was constantly asking Claude to look at research for me, like academic research. Like, what do we know about what is lost when we rely on AI synthesis? What do we know? And a lot of that came from just asking Claude to do the research for me. Got it. This is very much two-screen kind of process. Yeah, that definitely using it as a thought partner and like a researcher. Yeah. And so you can see here now, Claude came back with like, here's some other ways to structure it. So we could do example, first structure, problem solution structure, journey structure, like your personal story. And you can see for each, it's kind of like giving me a rough outline. So what I like about this is like, when I write, I usually have a pretty fixed idea of what the structure is in my head. And Claude helps me explore alternatives. So it's like I'm comparing and contrasting in the context of writing, which before working with Claude, I would have literally never done that. And then the other thing that it really helps me with. And maybe I'll pull up my web browser to show this. Let me think about, actually, I think I can show it right here. The article that I'm publishing this coming Wednesday is on safety. So it's how do I teach beginners, Claude beginners, how to run an LLM safely on their computer. And you can see, I'll show you, it's organized by tier. So like, what's the risk of letting it read files. And then at the end of every section, I include what Claude is doing and how you know what it's doing. So like there's these tables of like this, just indicates if it's reading. There's like, because like I'm assuming most of my readers don't know Unix commands, right? So. Yeah, nice and terminal. Yeah. And there's no way I would have written this article. I'll show you at the bottom. Look at all these, look at what we cover. Like it's insane. This blog post is you know, you can see it's like 800 words. And I created this like quick reference commands table. This is like how Claude reads. This is how it searches beyond your current directory. This is how it searches the web. This is how it writes files. This is how it executes code. And like, this is an awesome reference now for people that have never used Claude code. Claude, like, see you. Yeah. I started to generate a list like you can see in my outline. Like, I started to generate a list of like commands. As I used Claude, like, oh, this stuff should go in my document. But as I worked with Claude, it taught me like, oh, I also use these other commands. And so this blog post is way more thorough than it would have been if I had just done it on my own. And then the other thing that I do is like, once I get to a complete outline, I actually start writing. And I still do all of my own writing. I want it to be in my voice. I personally like to write. And I have, I feel like I have a very specific cadence to my writing that like Claude just doesn't really get. It gets close, but not really. And so what I'll do is once I have a really detailed outline, I will write a section. And then as soon as I'm done with the section, I just pop over here. And I'll say like, Claude, I wrote the intro, give me feedback. And then Claude can see the same file I can see, right? So I don't have to cut and paste anything. And then Claude will give me feedback. And then it always finds typos. And it'll just be like, do I'm going to fix the typos? And I can just type yes. Why don't we try it? Can you get us to fix the typos right here? Like does it add in your file? Yeah. Can you fix the typos in my plan mode? Got it. Yeah. And it's just going to go and do it. So you can see here, it's showing me a dip of what it's fixing. I don't want it just fixing a random typos in my blog post as I write. So one thing I've taught Claude to do is when we review a section, first it tells me what's working well, then it tells me what could be better, what could be clear. It does a technical review. Am I saying anything that's technically wrong? And then the last thing it does is it lists the typos that it found. And it asks me if I want to fix those typos. And that's just sort of a safety check. Sometimes like I'm using a word that it thinks is a typo, but it's not. And so it allows me to quickly look down like this is kind of an example. This is one that told me after the fact that when we're doing our section by section review, it'll be like, here's what I want to change. And then I can just say yes, change it all or I can be like yes, change it all, but don't change this one. Got it. So I kind of still keep like safety guard rails on Claude before it just starts editing my blog posts. Interesting. It's interesting that you still, okay, so you still mounting right the actual blog posts from a detail online. You still write it. Yeah, I've experimented with letting Claude write stuff. I don't like the voice. And Claude knows a lot about my writing. Like I have my entire product talk archives in here. I have taken the time to develop a really good writing style guide. For me, good writing has a cadence that like you can hear. And that's the part of my writing. Like I just can't get Claude to get a 100% right. And then I also like to write to figure out what I think. And so like I don't want to outsource all of that to Claude because I want to force myself to do the thinking myself. Got it. I'm using Claude almost like a sparring partner. So like, here's all I'm thinking about it. What do you think? Yeah, it's like having a editor and a researcher and like, you know, just kind of they're sitting there with you, right? But like full time, right? It's not like I did everything and then you edited it. We're doing it very collaboratively. And then the other piece that I really like is that the way that I used to write, I used to write like a two to three thousand word blog post in like three or four days. And a reason why it would take so long is I would write a section and writing is exhausting, right? And so at the end of writing a section, I'd be like, I'm going to go check my email. And then I go get distracted for an hour. Then I come back and write another section. But when I'm writing with Claude, as soon as we finish the review of a section, Claude's always like, are you ready for phase two? And I'm like, yeah, okay, I guess I am ready for phase two. So just having Claude like poke me, I maintain momentum. And so I now, a lot of my blog posts are a lot more in depth. They're a lot more detailed. They're getting longer. Like you can see this blog post is pretty darn long. But you'll see there's there is literally no fluff. Like I challenge people, this article is coming out on November 12th. Go read it. You can tell me if you think there's any fluff in it. Like to me, this is just a very detailed guide for how to work with Claude safely. And I wrote all of this myself. It's 9,000 words. And I wrote it in one and a half days. Wow. Like that is insane to me. Okay, let me ask you like a few questions about this process. So, so you have one window open for writing. Do you just, do you ever clear the context or just keep going? And you let that's a really good, that's a really good question. When I'm working on an outline, like if when we're developing, so like in this writing exercise, we're developing an outline, I try to keep all of it in the context of the same conversation. Okay. There will be times like I'll keep an eye on whether or not it's going to want to compact the conversation. I always try to keep Claude from compacting. Like if it looks like that's getting close, what I'll do is I'll be like Claude, we're going to run out a context window. Let's write a summary of where we are that you can read in when I clear the context window. And the reason why I do that is I want oversight on how Claude is compacting the conversation. Whereas if you use the compact, like if you just let Claude use its own compact tool when you run out, I find that it loses a lot of context and detail that I don't want it to lose. So one thing that I've done, I don't always do this with writing, but I always like when I'm working on a project with Claude, in fact, that needs to go in this blog post. So I'm glad we're talking through this. I have Claude create this document called process notes. And as we're working, if it looks like we're getting towards the end of the compact, the context window, I'll stop and have Claude update process notes. And process notes is just a text file that's like, here's what we did in every session. So that I have a history of what we've done in the decisions that we've made. And then sometimes Claude like just loses stuff in the context window, I can be always be like, can you just search process notes? Like I feel like we already made this decision. And so this is a habit I've gotten into whenever I work with Claude on anything meaty. We're constantly co-creating process notes together. And I'm getting to the point where like I have a process for my process notes where I'm in a right sub agent that's my document or that Claude will just call to write those process notes when we're running out of context window. Okay, you've gone to like this is like inception. You have like processes as far. I mean, this is the hard part, right? Like when the context window fills up, bad things happen. Like I think you waste a lot of work. Claude loses details. Yeah, it gets dumber. Yeah. It just gets dumber. And so I feel like it's our job at least for now to like maintain this process so that when Claude resets and his memory gets wiped, it can pick up where you left off and you'll be fine. Anthropic has tried to build that in with that compact conversation feature, but it's not very good. So I like to I like to manage it myself a little bit more. Well, I think that's the thing with this like that's the thing with Claude code. It just like it's it's really kind of made for power users to be honest like we really want to personalize everything. Like it's not super. It's not super intuitive to use if you're a complete beginner, but you have like going to the rabbit hole and I guess more and more powerful. You know what I like about it though for product people is that like using Claude code right now and especially pushing the boundaries with Claude code is living on the edge of what's possible today. And I feel like if we're going to build with AI like as product people if we're going to build AI into our products, like we should be living on that edge. And so like even just the stuff we talked about with context windows, I wouldn't have learned to any of that if I hadn't been in Claude code all day every day. And so now when I go work on like my AI product when I'm working on my interview coach, I have like a depth of experience of understanding how to manage a context window, but there's no way I would have developed otherwise. And so like yeah, like in the long run, is this how we're going to work with LLMs? Probably not. Like they'll be tooling around it and the labs will get better at managing the context for us. But like as product people, we can't wait for that. We're building AI into our products today. So I feel like we have to be living on that edge so we can build our products on the edge as well. Yeah, you got to go on the edge, you got to learn the latest info. Yeah. So that's kind of I just want to kind of talk about the context window thing a little bit more. So you know, so so context is like everything for how effective these LLMs have worked, right? So I just want to talk about the three, the three layers of context that you talked about in your previous blog post. Yeah. And you don't have to maybe share your cloud that MD file, but maybe like talk about maybe start with the highest layer and talk about what you're playing there. And then it kind of like, you know, yeah. So I actually have that article right here. Yeah. Let's see. Let's see what state it's in. So this article is life. You can find it a product. Talk that over. And in this article, I just talk about like the opening hook is this story about how I just got sick of trying to get cloud and chat GPT to like be reliably good. And I realized that like one of the challenges is that in order for cloud to be good, it needs to know all about me and my business. And needs to know that I'm a product discovery coach. It needs to know that I write at product talk. It needs to know that my audience is cross functional product teams. It needs to know that I have a course business and what all those products are. It even needs to know things like who I work with, right? In order for me to say like not only in my task window, I can add tasks to my to do list, but I can also say create a Trello card on Walena's board. And Walena is my admin, right? And so I can be like create a tree or I can even better. I can create a task file in my system in Markdown. And then say create a Trello card on Walena's board using this task. So it's like in my system, I'm creating a task for Walena. And then Claude goes and pushes it to her Trello board. But that only works if Claude has the context like who's Walena and what's a Trello board? And like what's a task, right? Yeah. So in order to get this like I wrote some pretty lazy stuff, new task, blah, blah, blah. Like in order for that to work, Claude has to have this view that we're looking at, doesn't have images. But I just explained this idea that every conversation starts from scratch. We have to create memory memory as three layers. You asked about three layers. The first one is my global preferences. Let me actually pop over to the web because I can show some of my Claudem D files pretty safely. So this is my global Claudem D, the start of it. Yeah. I can zoom in a little bit. Perfect. Yeah. This top section I write about in the blog post is just a little thing I learned. Is that like, I don't write my Claudem Ds anymore whenever I'm working with Claude. When we're done working, I say, Claude, what did you learn about working with me? Like what should we add to the Claudem D? So this goes smoother next time. And that's been awesome because I don't have to maintain this file anymore. Claude does. But you can see I've just defined some personal preferences. I always want to plan before Claude does anything. I never let Claude just do stuff. And I do plan at multiple levels. You could solve that with the blog post. I start with just really rough thoughts. We work our way to outline. Once I have that outline, we start writing. So there's just this file is across all my projects. Coding, writing, tasks, everything. I just want Claude to know like this is what I like. And it's not very long. This file doesn't go much further behind. But beyond this, it's pretty short. I just have a little section on what how I prefer to get feedback from Claude. And it's really simple. And this lives, you can see here, it lives in my local user directory. So on my Mac, it's like tilde/titoris and then dot Claude. Claude MD. Yeah. Do you put like Tories as a protocol? And like, you know, here's my business and all I care here. No, I don't put any of that here because this file is going to get loaded in the context window every single time you use Claude. So you only want to put stuff in here that you always want it to follow. And so like if I'm using Claude to like brainstorm Christmas gifts for my husband, Claude does not need to know about product talk. So I don't want that here, right? But no matter what. Yeah, this is literally global. So you want to keep it short. It's going to go in every single context window. And like I ask Claude a lot of the time, can my dog eat this food? Like Claude doesn't need to know about product talk for those stupid queries, right? So like what's really important is you have to keep the context window as clean as possible, right? And so this literally is just my global rules. But you'll see later, if we just scroll down, I have project specific instructions. So this is actually my writing Claude MD. And in my writing Claude MD, I have like it says at the start of each section, read my writing style guide. This is actually old, I move things out of Dropbox. But if you remember, if I go back to the terminal, which is hard to do with this sharing thing here, when I ran, sorry, here when I said let's work on a blog post together, the very first thing Claude did was it went and read my writing style guide. That's right. Yeah. And it's somewhere in here. Yeah. And that's because here it says at the start of every session, read the writing style guide. And then this is where I get into my rules about writing. So Claude is a thought partner, not a writer, you're acting as an editor, you can do some research and development. And this document is also not very long. It's really just telling Claude, this is how we write together. Okay. One thing that is in my global Claude MD, which I don't, let's see if I have a screenshot of it somewhere, is this idea of context. So I have my, I have my context files defined. So I've created little markdown files and the key is there little. So I have a lot of them because I want to, I want to mix and match them so that I can tell Claude which files matter for the task at hand. And it doesn't have to read all of my context every time. So I have a business profile that just is like, this is what my business does. Here's where you can find my product descriptions. Here's where you can find my marketing channels. Here's where you can learn about my team. I can show you that one. But it basically is telling Claude where to find more details in all these files. And so I think this blog post has a screenshot of that. Yeah. So this is my global Claude MD. We already looked at this top part. You can see at the bottom, I'm telling it. Here's where you can find reference context files. And I basically tell it specifically, only use these files if they're relevant to what I'm asking you about. So if I'm asking about something related to my business, go look at my business profile. And if I'm asking you something personal, go look at my personal profile. And then you can, okay, this makes sense. So you don't have to load all the shit into the default context. Yeah. So you don't crop product context. Exactly. So like if I ask it, I have a product file all about my story based customer interview course. So if I ask it, like, Hey, let's work on the landing page for my story based customer interview course. It already knows where to find details about this course. It already knows details about my company. It already knows details about my target audience. I don't have to tell any of that stuff. And it's because I've given an index of context files. So it can just go pull in the relevant stuff. Wow. Okay. But don't you feel like it's going to be like too many files to manage or like I guess you just make Claude up figure context files, right? Yeah. So I do. In this article, I talk about this, by the way, this article has a really fun use case of like how to use Claude to do a competitive analysis. So you can see here I'm having Claude like, this isn't for me. I used 11 labs as if that was my company. And it's generating like, let's see if I can find it. I don't know if I'm going to find it. But here's the goal. Like the key is to give Claude just enough to go find what it needs when it needs it. And part of this article is about like, okay, well, how do I maintain all this stuff? Like I have a ton of files now. How do I keep it current? And so what I do is I have this section about like, okay, how do I keep it up to date? The way we're going to keep it up to date is at the end of every session with Claude, I literally say, what did you learn about me that we should add to a context file? And then we have a conversation about where to add it. Should it go into Claude MD? Should it go in one of these LM context files? Like, what's the right place? And then I'm working with Claude to make sure like, Claude wants to jam everything into your Claude MD. You don't want that. That's getting loaded in every conversation. So I work with Claude to be like, hey, it seems like that should go in my marketing channels file. Why don't we add that there? So I think about it as like information about me and my business goes in a context file. Whereas my working preferences, like, this is how me and Claude work together goes in a Claude MD. So basically, yeah, this is really important tip. Like after every conversation, you ask Claude, how can you make the context better? And you have all your context in the LM context folder with a bunch of subfolds and files. Yeah. Wait, so how much are you playing this Claude employees? They sound pretty useful. How much are you paying? Yeah. Yeah. Yeah. I'm on the $100 a month plan. Okay. So you can see, I'll show you here in a city and you can see all my context files. So like for my business, I have a target audience file, a marketing profile, a list of my differentiators, my company overview, my business model. I didn't like sit down and create this all one day. That would have been tedious and horrible. I basically any time I felt like I needed to describe something to Claude. Instead of just doing it that one time and then having to repeat it later, I'd be like, oh, Claude, in order to do this task, I feel like you need to know about my differentiators, maybe interview me. And I literally Claude will interview you. You can just be like interview me about my business. And then we'll ask you a bunch of questions. And then it will write a context file for you based on what you learned. Got it. Okay. So that's that's a lot of how I did most of this stuff. Okay. Yeah. It's not like you just sat down one day and made all these folders, right? It's not. No. I had to do it like gradually over time. So what about like a okay, last question. Let's see. I'm just overwhelmed by all this stuff. Like this is like, like I want to learn stuff, but like it sounds like you really personalize it for your life. Yeah. Let's say I already used Claude code for like code coding. But I want to imagine my life. The first thing is with context, you don't have to get here overnight. Like I think the simplest rule is whenever you find yourself explaining context to Claude, stop and think about am I ever going to have to explain this context to Claude again? And honestly, the answer is probably yes. So instead of explaining it to Claude, change tasks just for a minute and just be like, Claude, I need to explain some context to you. Let's capture it in a context file. Got it. Yeah. That makes sense. You probably need to think through like at a minimum, do you work with Claude at work and in personal stuff, then maybe set up a work folder and a personal folder. That's it, right? And then I think from there, you can just do it iteratively over time. And that's what I did. Like I literally never sat down and just created all these files. I just, and some of them are just stumps, right? They're not that complete. But I know I'll add to them with time. And then this file we're looking at, this profile, I never wrote a word of it. Every time I have Claude at a context file, I say, what index needs to be updated and it just figures it out. Got it. Okay. So maybe like the process here is like, think about your weekly calendar. What's like the most, like what's taken most of your time? And then and then try to, you know, you have Claude as your employee, try to get it to, you know, give it a bunch of instructions, backgrounds, context, to have a save a bunch of files. And just work with it to start doing stuff. And then at the end of every conversation and ask it to, you know, like add more stuff to context or like, improvise prompt. But that's kind of, it's kind of way there, right? Yeah. Okay. I think there's two steps to this. The first is I have worked with the admin for like 10 years. So I'm really good at like looking at things that I can delegate. And for anybody who's ever delegated something to another person, what makes that work well is to have like a good like standard operating procedure for the task you're giving them, right? It's not, you can't just say it is someone, another human, like, hey, go do this thing and have them expect them to be able to do it the way that you would do it. And so if you want them to do it the way that you would do it, you have to provide for them like a process. Like here's how I do it. Here's the outcome that I want. And so like I do this with my admin, but I record videos. I record a video of how I do things. She then looks at the video. She creates like a Trello checklist for herself. And then that becomes like our standard operating procedure. So we've been doing this for years. And so I'm already good at this muscle of like, what can I delegate? So when I started doing this with LLMS, I thought about it as like, okay, well, if clot is just a person on my team, how would I delegate to clot? And so I started by literally looking at my own Trello board and like, what do I need to work on today? And then for every task, I got in the habit of like, how can clot help with this? Got it. Got it. And then there's pieces for some tasks. Like, I don't want to automate. Am I enjoying doing them? Like, I enjoy writing. I don't want clot to write for me. So I don't want to automate that. So I think about like, how can clot augment this? What do I do while writing that clot could accelerate? Well, research and web searches and like coming up with alternative analogies. And then there's other tasks like send this stupid receipt to my finance system. I don't need to ever do that. I could automate that. So then I look at like, what do I have to do to give clot context to be able to automate this completely? So I didn't even start with the things that take the most time. I literally just forced myself all day, every day, every time I do a new task to think about like, how can clot help? Got it. All right, man. That's a great tip to end on. I think. Yeah, just hire 100 dollar employee and then get to help on different things. Yeah. And I mean, it's funny that I even thought twice about upgrading from $20 to $100. I started on the $20 plan. I only had to bump to the $100 plan when I was doing both a lot of coding in one week and a lot of writing in one week. So it's like, I was literally pushing hard on clot for a long time. So you can get pretty far on the $20 plan. Yeah, yeah, yeah. Yeah. And hopefully, I thought I'd get this limits together. Yeah. So yeah. Okay. So to find your detailed Cloud Co guys, just go to product talk.org, right? Is that right? Yeah. We can take a look right here. It's product talk.org. And it's all like all my recent articles. You can see what is Claude. Stop repeating yourself. Probably by the time this episode goes out, that safety article will be live. Awesome. I'll tell everybody read it. Yeah. There's a ton here. I'm going to be writing a lot more like a lot of my goal for the next several weeks is just to help make Claude code accessible for people for non-technical people and to really start to show the power of like pair working with Claude. So if listeners were like excited about this episode, definitely check out this series. It's been a fun to write. And I'm I'm even going to be hosting Claude code office hours. So if you want to even come and get help, I'm going to be doing that every month. Awesome. Awesome. You should be there. You should be athletic sports person. Yeah. Someone asked me if I was being sponsored by Anthropic and I'm not. If I was, I would disclose that. I really am just a big fan. Yeah. I'm already a big fan too. I'm already a fan of like cat boards and a team with the building. And yeah, it's funny because they're really kind of trying to build towards the code and use case. But like, you know, there's so much more you can do. They build a really good agent. Yeah. Cool. All right, Teresa. Thank you. Thank you so much for your time. This has been fun.