WEBVTT 00:00:00.160 --> 00:01:00.880 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 gonna 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 gonna read my today m d, and it's gonna 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. Here's how 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. You 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. Let's say I'm just overwhelmed by all of this stuff. What are your three tips to get started? Whenever you find yourself explaining context to Claude, stop and think about, am I ever gonna have to explain this context to Claude again? 00:01:01.840 --> 00:01:16.145 Okay. Welcome, everyone. Uh, my guest today is Theresa Torres. Uh, Theresa is a legend in the PM field. She's author of Continuous Discovery Habits. But today, we're gonna talk about how Theresa uses Cloud Code for everything from writing to editing to 00:01:16.225 --> 00:01:17.825 task management to coding. 00:01:18.465 --> 00:01:37.840 Really excited to get her to give us a tour of her Cloud Code projects and show us how it's actually done. So welcome, Theresa. Thanks for having me. I'm excited to do this. Yeah. Um, so, you know, I've also used Cloud Code quite quite a bit, but I I'm super interested in seeing your, uh, high level workflows. Maybe you can give us a quick tour first. Yeah. Let me share my screen. 00:01:38.080 --> 00:01:58.270 Okay. So what we're looking at is really simple. I have Obsidian here on the left. And then and if people aren't familiar with Obsidian, it's just a note taking tool that's based on markdown. And then I have two terminal windows on the right. And the big thing that I use ClaudeCode for, like, I started using it coding just like everybody else, most that's most people's entry into it. 00:01:58.830 --> 00:02:08.430 But I what I really loved about CLOD Code with coding is it's almost like your pair programming with CLOD. And I was like, wow. How do I pair with CLOD on everything that I do? 00:02:08.830 --> 00:02:09.630 And so I started 00:02:10.225 --> 00:02:17.265 doing this for writing and for strategy and for literally all of the work that I do. This is my setup. This is my 00:02:17.505 --> 00:02:20.785 work Obsidian vault. So I have an Obsidian vault called work. 00:02:21.025 --> 00:02:22.945 In it, there's a bunch of subdirectories. 00:02:22.945 --> 00:02:32.730 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. 00:02:32.970 --> 00:02:39.235 Worthy reads are like articles that I've saved that other people wrote that I really like and then my writing directory. 00:02:39.235 --> 00:02:54.420 And then you can see I have a clot m d file here, and we can kinda go through all of this. But I'm gonna start with tasks. So the way my task system works is I have folders for different things. So I have a folder for bugs. Have I a folder for ideas. I have a folder for 00:02:54.740 --> 00:02:55.380 tasks. 00:02:55.620 --> 00:02:56.660 And every day, 00:02:56.900 --> 00:02:58.260 I launch Claude 00:02:58.420 --> 00:03:09.535 inside my tasks folder. So you can see this top terminal window. I'm in tasks. I'm just gonna launch Claude. And at the beginning of my day, I literally just write today and we can see what it does. 00:03:09.855 --> 00:03:13.775 The first thing it's gonna do is it's gonna go to Trello 00:03:13.855 --> 00:03:40.285 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 10. 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 00:03:40.925 --> 00:03:58.910 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, my 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. 00:03:59.950 --> 00:04:03.795 And then all my other tasks, like, have calls with a couple people today. 00:04:04.275 --> 00:04:31.945 I'm writing a Claude code safety article. I've gotta 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 gonna create a new task together. I'll show you what that looks like. Got it. 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 00:04:32.105 --> 00:04:35.705 and looking for anything that's due today or anything that's overdue. 00:04:35.865 --> 00:04:40.905 And then it creates this today file for me, and it's just telling me what do I need to do today. 00:04:41.145 --> 00:04:53.270 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. 00:04:53.510 --> 00:04:57.030 So you can see, like, I have a podcast just not possible. 00:04:57.270 --> 00:05:03.055 That's, like, always in my in progress because it's reminding me to, like, make sure I schedule guests. And 00:05:03.695 --> 00:05:06.335 you can see here I have a single episode. 00:05:06.495 --> 00:05:10.495 This is my project for, like, getting that episode ready to be released. 00:05:11.055 --> 00:05:14.175 And then I have a task for social media. 00:05:14.415 --> 00:05:17.120 But this is really just my, like, 00:05:17.440 --> 00:05:21.600 remember to schedule guests kind of thing that's always in progress. 00:05:23.120 --> 00:05:33.695 And so what this does is it gives me a lot of flexibility. If I just have a random idea, I can just say to Claude new idea and it will tell it what it is. It will create a markdown file. It'll put it in my ideas folder. 00:05:34.975 --> 00:05:40.735 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. 00:05:41.420 --> 00:05:45.020 This is just called my today MD on the day that it's due. 00:05:45.740 --> 00:05:47.740 Should we try making maybe like 00:05:48.300 --> 00:05:55.500 record pockets 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, 00:05:56.325 --> 00:06:03.685 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 00:06:04.165 --> 00:06:10.005 work. And so I built this system that searches a preprint server and then Google Scholar every day. 00:06:10.660 --> 00:06:13.060 And it gives me a research report 00:06:13.380 --> 00:06:24.820 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, 00:06:25.415 --> 00:06:35.015 And now it's asking me, oh, it wants to go see if there's a research queue, so we're gonna say yes to that. Mhmm. And then you'll see it's gonna update this today list with any research for me to review. 00:06:35.655 --> 00:06:36.615 The queue is empty. 00:06:38.000 --> 00:06:40.560 It's creating my research today MD. 00:06:42.720 --> 00:06:45.040 Got it. So this is just like searching 00:06:45.280 --> 00:06:55.265 some websites to find new research. Right? Yep. And then you can see it's gonna read my today MD, and it's gonna update it. And you can see it popped up here. So this is a link to my research digest. 00:06:55.345 --> 00:07:06.340 So That's great. That 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 m d with the overdue task, 10 in tasks for in progress, your research, 00:07:06.660 --> 00:07:17.940 whatever. And then you can see it's also creating a this week view and a next week view. Got it. Okay. Yep. Okay. So let's say I wanna do a new task. We're actually gonna write a blog post to that together. So I'm gonna do new task, 00:07:19.855 --> 00:07:21.455 Write plan 00:07:21.775 --> 00:07:23.695 auto accept 00:07:23.775 --> 00:07:24.735 Claude 00:07:25.295 --> 00:07:26.495 blog post. 00:07:27.295 --> 00:07:28.895 Do today 00:07:29.215 --> 00:07:30.175 draft 00:07:31.135 --> 00:07:32.095 outline 00:07:32.175 --> 00:07:33.375 with Claude. 00:07:33.375 --> 00:07:41.280 And it basically this this tasks folder is set up with a Claude MD so that Claude knows what to do with this. It knows to create a task. 00:07:41.600 --> 00:07:58.805 You can see it's using Obsidian front matter, and I've defined this whole system for Claude so it knows to do this. It's defining it as a task. It's putting the due date as today. It's tagging it for me. It's gif basically giving me kind of a checklist. I it's actually not supposed to do this because it's kind of a crummy checklist. 00:07:58.965 --> 00:08:07.500 It's supposed to just take my notes, but pretty good. We're gonna go with that. And then let's see if sometimes, Claude is smart enough to put something due today on my today MD. 00:08:07.660 --> 00:08:17.055 It's not this time. So I'm gonna say add to today MD. Got it. Okay. And then what that's gonna do is it's just gonna add that task. You can see it's here. So now I have my 00:08:17.375 --> 00:08:50.165 right plan auto accept 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 due date. 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 Optimizely. 00:08:50.165 --> 00:09:04.630 The problem 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, then take a look at Optimizely Oppo, an AI agent platform built specifically for marketing. With Oppo, you can use AI agents for SEO and general recommendations, 00:09:04.630 --> 00:09:06.470 AB testing, website analysis, 00:09:06.550 --> 00:09:20.285 and much more. Oppo knows your brand inside and out and plugs into your existing tools and data systems that you can save time on labor intensive feature testing, reporting, and more. See what it can take off your plate at optimisely.com/ai. 00:09:20.285 --> 00:09:24.285 Now back to our episode. The other thing I'll share is it allows me to do things like, 00:09:25.600 --> 00:09:28.720 what are all my marketing ideas? 00:09:29.680 --> 00:09:49.945 And it's just gonna 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 Clyde, 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. Okay. 00:09:50.425 --> 00:10:02.810 So I like this a lot too. So you have, like, ideas and memories and, like, random re research snippets that you pull. Yeah. So you can see type. Like, in my tax folder, I have bugs that have been filed. I have ideas. 00:10:03.290 --> 00:10:08.485 Import is for if I'm importing a bunch of stuff from Trello. I wanna review it to make sure it imported correctly. 00:10:08.805 --> 00:10:13.125 My inbox is how I get stuff from my phone to my to this whole system. 00:10:13.605 --> 00:10:21.045 Memories is like things it's like little snippets that I wanna remember so we can kinda look at what's in here. I think this is safe. Like, I have a 00:10:21.460 --> 00:10:29.700 affiliate link to the AI evals 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 actually know why that's in memories. 00:10:30.020 --> 00:10:47.325 Real real real quick. What do you mean by inbox? Like, send an email to yourself over the phone, Or or how does it Yeah. Uh, so this this is a little bit of a hack, and I'm actually moving away from it. So I mentioned I moved a bunch of stuff and it broke some things. But, um, I was using Dropbox to sync my vaults, 00:10:47.810 --> 00:10:58.770 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, 00:10:59.010 --> 00:11:01.865 I had to set up. This is like a iCloud 00:11:02.105 --> 00:11:09.385 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. 00:11:09.625 --> 00:11:24.890 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. That would make sense. Yeah. Pretty much Cloud Code and Obsidian run my life. Alright. So let's go back to the writing the blog post task. So, like Yeah. 00:11:25.210 --> 00:11:28.410 How's it gonna help us write this blog post? Yeah. So 00:11:28.715 --> 00:11:35.195 I could do this. Let's do this. We're gonna get rid of this dumb checklist that Claude made because I don't like it. 00:11:36.235 --> 00:11:47.040 And we're just gonna do, like okay. I'm gonna talk through I'm just gonna, like, talk out loud while 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 nontechnical. 00:11:47.280 --> 00:11:52.080 And it started with, like, what is Cloud Code? Why is it different from Cloud in the browser? 00:11:52.400 --> 00:12:00.355 And then the second post in the series was about, like, how to give Cloud a memory, which if you wanna get into that, all my context files are also here in Obsidian. 00:12:00.675 --> 00:12:06.035 And then the third blog post that's coming out this Wednesday is about safety, so how to use Claude codes safely. 00:12:06.275 --> 00:12:10.835 And then this one we're gonna start together is the fourth article. And this is where I'm gonna get into 00:12:11.520 --> 00:12:18.960 doing projects with Claude. And so I wanna write a blog post where I talk about, like, plan mode, auto accept mode. 00:12:19.280 --> 00:12:24.800 And then I always wanna use examples in my blog posts that are related to 00:12:25.325 --> 00:12:26.605 product managers. 00:12:26.845 --> 00:12:30.605 And so, like, in this blog post, I might think, like, let's talk through 00:12:30.765 --> 00:12:38.525 plan mode and auto accept mode if you were planning a new feature. So I'm starting to think about, like, what's my example gonna be in the blog post? 00:12:38.845 --> 00:12:41.085 And I have an AI product called the interview coach. 00:12:41.880 --> 00:12:51.640 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 00:12:51.800 --> 00:13:01.395 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. 00:13:01.555 --> 00:13:05.395 And so the coach gives feedback on story based interviews. 00:13:05.955 --> 00:13:12.890 And my new feature idea is, can I extend it to work with non story based interviews? 00:13:12.890 --> 00:13:31.435 So this is like a feature idea I have. And so in the blog post, there's a little meta. I'm gonna use this feature idea to show how I would use plan mode and auto accept mode. Right? So Okay. Yep. I'm gonna this is all I have. This is literally the state of this blog post. This is real. I have not written a single thing. 00:13:31.995 --> 00:13:38.860 And now I'm gonna go over to this terminal window on the bottom and I'm gonna launch launch Claude and this is in the context of my writing vault. 00:13:39.180 --> 00:13:46.460 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 00:13:46.860 --> 00:13:55.605 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. 00:13:55.925 --> 00:14:08.630 Got it. So we're gonna do this. I don't know why it thinks it's a new folder, but we're gonna ignore that for a minute. And then I'm gonna say, I want help creating an outline for a new blog post. I do this in plan mode, 00:14:09.030 --> 00:14:14.150 which is actually what the blog post is about. You can find my early thoughts 00:14:15.065 --> 00:14:15.865 in 00:14:16.185 --> 00:14:20.665 oh, see, I would not this is a little weird. I would not do this in the task card. 00:14:20.985 --> 00:14:23.385 What I would do is I would come to writing. 00:14:23.865 --> 00:14:25.945 I would go to my Claude code series 00:14:26.265 --> 00:14:30.990 and I would do a new file. Got it. Let's do plan mode. 00:14:33.070 --> 00:14:46.335 And that did not go where I wanted it, so we're gonna move it in plan mode. And I actually did not tell Claude enough information because it's not. It's gonna look for plan mode in the current directory, but the plan mode is actually in Claude code. 00:14:46.815 --> 00:14:49.855 So we'll see what it comes back with. We'll see if it finds it. Okay. 00:14:50.255 --> 00:14:56.335 So, basically, you have a Claude okay. So just real quick. You have a Claude dot m d for your writing vault 00:14:56.850 --> 00:15:09.810 that has a bunch of writing styles and, like, you know, that kind stuff. Right? Yep. Is that got it. Yeah. So if you look at here on the left, like, tasks is a then you can think about tasks as, like, a Claude project. I launched 00:15:10.255 --> 00:15:13.135 this instance of Claude in the context of tasks, 00:15:13.375 --> 00:15:15.375 and then I have a writing folder. 00:15:15.375 --> 00:15:25.215 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 CloudMDs. 00:15:25.560 --> 00:15:49.305 So the CloudMD 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 wanna 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 CloudMD 00:15:49.305 --> 00:16:05.510 in my writing folder says before we do anything together, start by reading my writing style guide. Got it. Okay. So I'm gonna go ahead and say yes, it can do that. Do you ever just ask it to just like 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 00:16:06.305 --> 00:16:07.265 Dropbox, 00:16:07.265 --> 00:16:14.785 and I had all the permissions set up where my tasks could read and edit everything inside tasks and writing could read everything inside writing. 00:16:15.185 --> 00:16:20.065 But because I just moved everything, those permissions aren't I literally moved everything yesterday, 00:16:20.790 --> 00:16:30.950 and so I haven't copied over those permissions yet. I'm learning, like, when you move things in Claude, it kinda breaks things a little bit. So it's asking me which features do I wanna focus on. I actually wanna do both. 00:16:33.835 --> 00:16:39.435 What's your intended audience for this post? Product people new to Claude should already know that. That's a little disappointing. 00:16:39.515 --> 00:16:46.475 Wait. So so, like, is asking you questions because you prompted to ask questions? It asked me questions because it read this plan mode document, 00:16:47.210 --> 00:16:58.410 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. 00:17:00.025 --> 00:17:07.545 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. 00:17:12.710 --> 00:17:14.550 Fine. It's already got a headline. 00:17:17.750 --> 00:17:20.950 Introduce plan mode and auto accept mode, what it is, 00:17:21.670 --> 00:17:24.790 when to use it, what you plan, what it is, the dangers. 00:17:27.895 --> 00:17:31.975 That's that's Like great. Yeah. Is kinda nuts. Right? Like, kinda went 00:17:32.135 --> 00:17:32.775 crazy. 00:17:33.495 --> 00:17:34.055 Okay. 00:17:34.535 --> 00:17:36.295 So I'm gonna tell it it went crazy. 00:17:36.455 --> 00:17:55.790 Uh, it's kinda like, uh, why I use Cloud Code to, like, write out a prospect. I always wanted to put put the spec in MD files so can delete a bunch of stuff because it it tends to do too much. You know? 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. Yeah. I would probably give Claude something like 00:17:56.415 --> 00:17:57.855 goals help 00:17:57.855 --> 00:18:00.495 people new to Claude code 00:18:00.815 --> 00:18:01.695 do 00:18:01.695 --> 00:18:03.215 bigger projects. 00:18:04.095 --> 00:18:05.295 Claude code. 00:18:06.095 --> 00:18:06.815 Use 00:18:07.695 --> 00:18:09.615 planning a new feature 00:18:09.775 --> 00:18:11.215 as a product manager 00:18:11.830 --> 00:18:13.990 as an example throughout. 00:18:14.310 --> 00:18:17.670 And then we could do I can use my personal 00:18:17.910 --> 00:18:18.790 experience 00:18:18.790 --> 00:18:19.510 with 00:18:20.390 --> 00:18:21.270 expanding 00:18:21.270 --> 00:18:24.870 the interview coach. I'm gonna ignore typos for now because Cloud won't care. 00:18:25.190 --> 00:18:26.790 Mhmm. And then 00:18:27.775 --> 00:18:29.375 I'm gonna do something like 00:18:29.615 --> 00:18:32.015 less about the features, 00:18:32.975 --> 00:18:34.095 these features, 00:18:35.695 --> 00:18:37.935 more about how to get 00:18:38.735 --> 00:18:39.695 Claude 00:18:40.415 --> 00:18:43.530 to do good work. And let's see if this helps. 00:18:46.650 --> 00:18:49.050 Got it. Let's see what it comes back with. 00:18:49.850 --> 00:19:00.605 So okay. So after this, I'll, like, gonna ask you to do online research or what's the what can I can do next? Yeah. So you can see already it came back and it's like, oh, okay. I made too many assumptions. 00:19:01.245 --> 00:19:01.805 Yeah. 00:19:02.125 --> 00:19:05.885 And it's like, okay. Now, like, now is this, like, the right direction? 00:19:06.125 --> 00:19:14.600 So now I might now I what I really wanna do is ask Claude, like, you asked about research. We gotta come out of plan mode for this. Has anyone else 00:19:14.760 --> 00:19:17.480 written a blog post about this? 00:19:17.960 --> 00:19:34.245 And I'll go and I'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 wanna know what else has been out there. If somebody else has written this article for my audience, I'm not gonna write it. I'm just gonna, like, write a different article and just link to that article. 00:19:34.805 --> 00:19:36.725 I wanna make sure that I'm writing stuff that's unique. 00:19:37.460 --> 00:19:41.860 And then now sometimes someone may have written this blog post, like, in the context of coding, 00:19:41.940 --> 00:19:49.940 and that's fine. Most of my audience isn't gonna read that. And so but I can read that article and learn from their experience and then translate it to product management. 00:19:50.260 --> 00:20:00.115 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? 00:20:00.275 --> 00:20:15.630 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, 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. 00:20:15.710 --> 00:20:17.790 Most are written for developers, engineers. 00:20:18.190 --> 00:20:27.375 Yeah. Yeah. Perfect. I think people wrote, like, technical stuff about Plano, but not about this use case. Yeah. So then I might ask, like, okay. Um, how do people 00:20:27.695 --> 00:20:30.015 search for this kind of content? 00:20:31.055 --> 00:20:32.415 What keywords 00:20:32.575 --> 00:20:34.255 from an SEO standpoint 00:20:35.130 --> 00:20:36.570 should I keep in mind? 00:20:36.970 --> 00:20:54.325 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 I I never asked this question from my blog post. So that that's that's that's that's important. Yeah. And, again, it just goes off and does its thing. And I let it do its thing. In the meanwhile, I'll be like over here noodling. I'm like, how am gonna structure 00:20:54.645 --> 00:20:55.765 this blog post? 00:20:56.085 --> 00:21:05.790 And like, this is really stubbed out. There's not really a blog post here. Right? So Mhmm. I might start to think about an outline and be like, okay, well, the introduction 00:21:06.430 --> 00:21:07.550 needs to be 00:21:08.030 --> 00:21:09.230 strong hook 00:21:09.790 --> 00:21:12.910 around value of doing project work 00:21:13.070 --> 00:21:14.190 with Claude code. 00:21:16.065 --> 00:21:17.505 Then introduce, 00:21:18.145 --> 00:21:19.745 like, Claude modes, 00:21:20.545 --> 00:21:22.225 plan, auto accept, 00:21:23.505 --> 00:21:24.545 reference 00:21:25.185 --> 00:21:26.305 safety article, 00:21:28.420 --> 00:21:30.260 walk through detailed 00:21:30.260 --> 00:21:31.300 example 00:21:32.180 --> 00:21:33.540 interview coach. 00:21:33.940 --> 00:21:35.540 So let's see what it came back with. 00:21:36.180 --> 00:21:38.740 So I found it's really good at keyword research. 00:21:39.140 --> 00:21:39.780 Like, 00:21:40.180 --> 00:21:41.220 good at keyword research. 00:21:41.935 --> 00:22:05.080 I tend to do this after I've written the article because I really wanna write my articles for humans. But then I might tweak some words in my subheaders or my titles to to, like, target higher volume keywords. What what 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. Oh, interesting. Okay. Yep. 00:22:05.400 --> 00:22:07.480 Okay. So it's sort of my SEO researcher. 00:22:07.480 --> 00:22:08.200 Interesting. 00:22:08.360 --> 00:22:11.800 And then I could be like, I've started to stub 00:22:12.115 --> 00:22:13.635 out an outline 00:22:13.635 --> 00:22:14.755 in plan. 00:22:15.955 --> 00:22:17.235 Can you suggest 00:22:18.435 --> 00:22:19.235 alternative 00:22:19.235 --> 00:22:20.355 structures? 00:22:20.755 --> 00:22:23.875 There's not enough meat here. It's probably not gonna do a very good job here, but 00:22:25.340 --> 00:22:31.660 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. 00:22:31.900 --> 00:22:34.060 I'm going back and forth with Claude. 00:22:34.140 --> 00:22:48.945 I'll have questions like, what do I do? Like, how does this work in 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? 00:22:49.745 --> 00:23:02.660 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, 00:23:02.900 --> 00:23:12.085 and I could 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 00:23:12.245 --> 00:23:25.890 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 00:23:26.210 --> 00:23:27.570 kind of process. 00:23:27.890 --> 00:23:30.850 Yeah. They're definitely using it as a thought partner and, like, a researcher 00:23:31.010 --> 00:23:37.010 Yeah. In a way. 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, 00:23:39.525 --> 00:23:41.285 problem solution structure, 00:23:42.165 --> 00:23:44.565 journey structure, like your personal story. 00:23:44.725 --> 00:23:48.885 And you can see for each it's it's kinda like giving me a rough outline. 00:23:49.205 --> 00:23:55.320 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. 00:23:55.720 --> 00:23:58.440 And Claude helps me explore alternatives. 00:23:58.440 --> 00:24:00.680 So it's like I'm comparing and contrasting 00:24:00.680 --> 00:24:02.440 in the context of writing, 00:24:02.680 --> 00:24:11.135 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. 00:24:11.455 --> 00:24:14.575 Let me think about actually, I think I can show it right here. 00:24:15.535 --> 00:24:18.015 The article that I'm publishing this coming Wednesday 00:24:18.350 --> 00:24:22.670 is on safety. So it's how do I teach beginners, Cloud Code beginners, 00:24:22.910 --> 00:24:25.470 how to run an LLM safely on their 00:24:25.710 --> 00:24:32.190 computer. And you can see I'll show you. Ever it's organized by tier. So, like, what's the risk of letting it read files? 00:24:32.895 --> 00:24:55.480 And then at the end of every section, I include what Clot 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. Have a nice 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. 00:24:55.560 --> 00:25:02.255 This blog post is you can see it's, like, 8,800 words. And I created this, like, quick reference commands table. 00:25:02.335 --> 00:25:10.815 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. 00:25:11.470 --> 00:25:12.350 And like, 00:25:12.590 --> 00:25:19.070 this is an awesome reference now for people that have never used Claude code. There is no way I would have done this myself. 00:25:19.550 --> 00:25:25.390 Claude Okay. So you yeah. I started to generate a list like you can see in my outline. 00:25:25.630 --> 00:25:25.950 Like, 00:25:26.555 --> 00:25:30.315 I started to generate a list of, like, commands 00:25:30.555 --> 00:25:34.555 as I used Claude. Like, oh, this stuff should go in my document. 00:25:34.795 --> 00:25:39.835 But as I worked with Claude, it taught me, like, oh, I also use these other commands. 00:25:40.350 --> 00:25:53.470 And it so this blog post is way more thorough than it would have been if I had just done it on my own. Coauthoring me with Claude along along the way, like, section by section. Yeah. Yeah. And then the other thing that I do is, like, once I get to a complete outline, 00:25:54.005 --> 00:26:05.125 I actually start writing. And I'd 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. 00:26:05.445 --> 00:26:18.190 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. 00:26:19.155 --> 00:26:24.195 And then Claude can see the same file I can see. Right? So I don't have to cut and paste anything. 00:26:24.595 --> 00:26:35.740 And then Claude will give me feedback, and then it always finds typos. And it'll just be like, do want me to fix the typos? And I can just type yes. Why don't we try it? Can you get it to fix the typos right here? Like, does it Yeah. Edit in your file? Yeah. Can you 00:26:36.540 --> 00:26:38.060 fix the typos 00:26:38.060 --> 00:26:39.020 in my 00:26:39.500 --> 00:26:40.540 plan mode? 00:26:41.100 --> 00:26:43.900 Got it. Yeah. And it's just gonna go and do it. 00:26:44.780 --> 00:26:47.020 So you can see here it's showing me a diff of what it's fixing. 00:26:48.355 --> 00:27:10.180 I don't want it just fixing random typos in my blog posts 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 or what could be clearer. 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. 00:27:10.340 --> 00:27:22.235 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. But when we're doing our section by section review, 00:27:22.475 --> 00:27:41.100 it'll be like, here's what I wanna change. And then I can just say, change it all. Or I can be like, yes, change it all, but don't change this one. Got it. Got Got So I kinda still keep, like, safety guardrails on Claude before it just starts editing my blog post. Interesting. It's interesting that you still okay. So you still manually write the actual blog post from a detailed outline. 00:27:41.260 --> 00:27:46.205 You still write it? You're Yeah. I've experimented with letting Claude write stuff. 00:27:46.605 --> 00:27:47.165 I 00:27:47.645 --> 00:27:53.645 don't like the voice, and Claude knows a lot about my writing. Like, I have my entire product talk archives in here. 00:27:54.045 --> 00:28:01.520 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. 00:28:01.840 --> 00:28:24.040 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 wanna outsource all of that to Claude because I wanna force myself to do the thinking myself. Got it. Got it. I'm using Claude almost like a sparring partner. So, like, here's how I'm thinking about it. What do you think? Oh, I don't really like that. What if we try this other way? 00:28:24.760 --> 00:28:39.065 And then I do that throughout the whole construction of the blog post. Yeah. It's like having a editor and a researcher and, like, you know, just to come there sitting there with you. Right? But, like, full time. Right? It's not like I did everything and then you edit it. We're doing it very collaboratively. 00:28:39.465 --> 00:29:06.145 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 3,000 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 like, I'm gonna go check my email. And then I'd 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? 00:29:06.385 --> 00:29:13.185 And I'm like, yeah. Okay. I guess I am ready for phase two. So just having Claude, like, poke me, I maintain momentum. 00:29:13.790 --> 00:29:19.550 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. 00:29:19.950 --> 00:29:23.230 Like, you can see this blog post is pretty darn long, 00:29:23.550 --> 00:29:30.465 but you'll see there's there is literally no fluff. Like, I challenge people. This article is coming out on November 12. 00:29:30.945 --> 00:29:37.745 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 00:29:38.320 --> 00:29:39.120 guide 00:29:39.280 --> 00:29:41.440 for how to work with Claude safely. 00:29:41.760 --> 00:30:07.345 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 let me ask you, like, a few questions about this process. Yeah. So so you have one window open for writing. Do you just do you ever clear the context or you just keep keep going? And and then you let it That's a really good for you. That's a really good question. When I'm working on a outline, like, when we're developing so, like, in this writing exercise, 00:30:07.760 --> 00:30:17.040 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 gonna wanna compact the conversation. 00:30:17.520 --> 00:30:43.570 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 gonna run out of 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 00:30:43.570 --> 00:30:53.835 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. 00:30:54.475 --> 00:30:56.475 So I'm glad we're talking through this. 00:30:57.275 --> 00:31:00.635 I have Claude create this document called process notes. 00:31:01.035 --> 00:31:07.755 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 00:31:08.210 --> 00:31:14.450 update process notes. And process notes is just a text file that's like, here's what we did in every session 00:31:14.850 --> 00:31:18.370 so that I have a history of what we've done and the decisions that we've made. 00:31:18.850 --> 00:31:27.645 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. 00:31:28.285 --> 00:31:32.525 And so this is a habit I've gotten into whenever I work with Claude and anything meaty. 00:31:32.765 --> 00:31:40.460 We're constantly co creating process notes together. And I'm getting to the point where, like, I have a a process for my process notes 00:31:40.620 --> 00:31:42.460 where I'm gonna write a 00:31:42.700 --> 00:31:49.100 sub agent that's my documenter that Claude will just call to write those process notes when we're running out of context window. 00:31:49.420 --> 00:32:09.900 Okay. Got it. You you've gone to, like, uh, this is, like, inception. You have, like Yeah. Processes for 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, 00:32:11.100 --> 00:32:12.620 this process 00:32:12.940 --> 00:32:22.275 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 00:32:22.275 --> 00:32:22.995 feature, 00:32:23.235 --> 00:32:27.875 but it's Yeah. It's not very good. So I like to I like to manage it myself a little bit more. 00:32:28.835 --> 00:32:34.275 Well, I think that's the thing with this the the this like, that that's the thing with Cloud Code. It just like, it's 00:32:34.780 --> 00:32:40.060 it's really kind of made for power users, to be honest, like, who really wanna personalize every everything. Like, it's not super 00:32:40.380 --> 00:32:49.820 it's not super intuitive to use if you're a complete beginner, but you have to, like, go into the rabbit hole and then it gets more and more powerful. You know what I like about it though for product people is that, 00:32:50.485 --> 00:32:57.445 like, using Cloud Code right now and especially pushing the boundaries with Cloud Code is living on the edge of what's possible today. 00:32:57.685 --> 00:33:03.125 And I feel like if we're gonna build with AI, like as product people, if we're gonna build AI into our products, 00:33:03.365 --> 00:33:08.900 like, we should be living on that edge. And so, like, even just this stuff we talked about with context windows, 00:33:09.220 --> 00:33:24.235 I wouldn't have learned any of that if I hadn't been in Cloud 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. 00:33:24.555 --> 00:33:38.420 And so, like, yeah, like, in the long run, is this how we're gonna 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. 00:33:38.740 --> 00:34:13.400 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 gotta build on the edge. You gotta learn the lay latest info. Yeah. So let that's kind of I I just wanna kinda talk about the context window thing a little more. So, you know, so so context is, like, everything for how effective these LMs work. Right? So I just wanna 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.md file, but maybe, like, talk about maybe start with the highest layer and talk about what you put in there, and then and then kinda, you know. Yeah. So I actually have that article over right here. 00:34:14.015 --> 00:34:19.135 Yeah. Yeah. Let's see what state it's in. So this article is life. You can find it at producttalk.org. 00:34:19.215 --> 00:34:23.695 And in this article, I just talk about, like, the opening hook is this story about how 00:34:23.935 --> 00:34:28.495 I just got sick of trying to get Claude and ChatGPT to, like, be reliably good. 00:34:28.980 --> 00:34:43.060 And I realized that, like, one of the challenges is that in order for Claude to be good, it needs to know all about me and my business. It 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. 00:34:43.625 --> 00:34:46.905 It needs to know that I have a course business and what all those products are. 00:34:47.305 --> 00:34:54.185 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, 00:34:54.265 --> 00:35:02.850 I can't I can add tasks to my to do list, but I can also say create a Trello card on Wilena's board. And Wilena is my admin. 00:35:03.010 --> 00:35:06.610 Right? And so I can be like create a tree or I can even better, 00:35:06.770 --> 00:35:14.290 I can create a task file in my system in markdown and then say create a Trello card on Wilena's board using this task. 00:35:14.775 --> 00:35:34.680 So it's like in my system, I'm creating a task for Wilena and then Claude goes and pushes it to her Trello board. Okay. That only works if Claude has the context like who's Wilena and what's her Trello board and it like what's a task, right? Yeah. So in order to get this like, wrote some pretty lazy stuff, new task, blah blah blah. Like in order for that to work, 00:35:35.080 --> 00:35:38.760 Claude has to have this view that we're looking at. It doesn't have images. 00:35:39.080 --> 00:35:45.605 But I just explained this idea that every conversation starts from scratch. We have to create memory. Memory has three layers. 00:35:45.765 --> 00:35:49.125 You asked about the three layers. The first one is my global preferences. 00:35:49.525 --> 00:35:58.740 Mhmm. Let me actually pop over to the web because I can show some of my CloudMD files pretty safely. Okay. So this is my global CloudMD, 00:35:58.740 --> 00:35:59.780 the start of it. 00:36:00.020 --> 00:36:02.820 Yeah. I can zoom in a little bit. Perfect. Yeah. 00:36:03.140 --> 00:36:03.940 Um, this 00:36:04.340 --> 00:36:13.105 top section I write about in the blog post is just a little thing I learned is that like I don't write my Claude MDs anymore. Whenever I'm working with Claude, 00:36:13.425 --> 00:36:20.785 when we're done working, I say, hey, Claude, what did you learn about working with me? Like what should we add to the Claude MD so this goes smoother next time? 00:36:21.600 --> 00:36:33.520 And that's been awesome because I don't have to maintain this file anymore. Claude does. But you can see, like, I've just defined some personal preferences. Like, I always wanna plan before Claude does anything. I never let Claude just do stuff. 00:36:34.245 --> 00:36:39.845 And I do plan at multiple levels. You could saw that with the blog post. Like, I start with just really rough thoughts. 00:36:40.085 --> 00:36:48.485 We work our way to an outline. Once I have an outline, we start writing. So there's just this this file is across all my projects, coding, 00:36:48.565 --> 00:36:49.205 writing, 00:36:49.365 --> 00:36:50.620 tasks, everything. 00:36:50.860 --> 00:37:06.775 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 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 00:37:07.175 --> 00:37:08.935 local user directory. 00:37:09.255 --> 00:37:14.615 So on my Mac, it's like tilde slash t torres and then dot ClaudClaudMD. 00:37:14.615 --> 00:37:26.410 Yeah. Do you put, like, Theresa as a product coach and, like, you know, here's my business and all that kind stuff here? I'll I don't put any of that here because this file is gonna get loaded in the context window every single time you use Claude. 00:37:26.810 --> 00:37:38.005 Got it. Yeah. You only wanna 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. 00:37:38.405 --> 00:37:40.485 So I don't want that here. 00:37:40.805 --> 00:37:54.830 Right? No matter what this short. Yeah. Yeah. This is literally global. So you wanna keep it short. It's gonna go in every single context window. And like I asked Claude all the time, can my dog eat this food? Like Claude doesn't need to know about product talk for those stupid queries. 00:37:55.070 --> 00:38:01.915 Right? So Okay. Got it. Bit like, what's really important is you have to keep the context window as clean as possible. 00:38:02.235 --> 00:38:06.395 Yep. Right? And so this literally is just my global rules. 00:38:06.715 --> 00:38:07.515 But you'll see later, 00:38:08.140 --> 00:38:10.860 we just scroll down, I have project specific instructions. 00:38:11.100 --> 00:38:13.500 So this is actually my writing ClotMD. 00:38:13.820 --> 00:38:15.820 And in my writing ClotMD, 00:38:16.220 --> 00:38:22.975 I have like it says at the start of each section, read my writing style guide. This is actually old. I moved things out of Dropbox. 00:38:23.295 --> 00:38:26.015 But if you remember, if I go back to the terminal, 00:38:26.575 --> 00:38:29.455 which is hard to do with this sharing thing here, 00:38:30.015 --> 00:38:31.215 when I ran 00:38:31.935 --> 00:38:39.000 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. 00:38:39.320 --> 00:38:43.080 That's right. Yep. And it's somewhere in here. Yeah. And that's because 00:38:43.480 --> 00:38:51.855 here it says at the start of every session, read the writing style guide. Okay. And then this is where I get into my rules about writing. 00:38:52.015 --> 00:38:53.775 So Claude is a thought partner, 00:38:54.095 --> 00:38:56.175 not a writer. You're acting as an editor. 00:38:56.335 --> 00:38:58.175 You can do some research and development. 00:38:58.495 --> 00:39:08.220 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, 00:39:08.300 --> 00:39:11.340 which I don't let's see if I have a screenshot of it somewhere, 00:39:11.580 --> 00:39:13.340 is this idea of context. 00:39:13.340 --> 00:39:14.620 So I have my 00:39:14.895 --> 00:39:17.535 I have my context files defined. 00:39:17.695 --> 00:39:22.015 So I've created little markdown files, and the key is they're little. 00:39:22.175 --> 00:39:25.135 So I have a lot of them because I want 00:39:25.455 --> 00:39:25.775 to 00:39:26.255 --> 00:39:28.095 I wanna mix and match them 00:39:28.495 --> 00:39:37.950 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 00:39:38.030 --> 00:39:40.510 that just is like, this is what my business does. 00:39:40.990 --> 00:39:59.320 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 CloudMD. We already looked at this top part. 00:39:59.640 --> 00:40:01.080 You can see at the bottom, 00:40:01.400 --> 00:40:05.000 I'm telling it, here's where you can find reference context files. 00:40:05.240 --> 00:40:07.400 And I basically tell it specifically, 00:40:08.120 --> 00:40:16.415 only use these files if they're relevant to what I'm asking you about. So if I'm asking you about something related to my business, go look at my business profile. 00:40:16.655 --> 00:40:19.775 And if I'm asking you something personal, go look at my personal profile. 00:40:20.095 --> 00:40:31.260 And then you can This makes sense. So you don't have to, like, load a lot of shit into the default context. Yeah. So you don't crowd crowd the context. Exactly. So, like, if I ask it, I have a product file all about my story based customer interview course. 00:40:31.420 --> 00:40:44.935 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. 00:40:45.335 --> 00:40:49.015 And it's because I've given it an index of context files 00:40:49.255 --> 00:41:09.170 so it can just go pull in the relevant stuff. Wow. Okay. But don't you feel like there's gonna be, like, too many files to manage? Or, like, I guess you get you just you just make Cloud up update your context files. Right? Is is that Yeah. You do? 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. 00:41:09.250 --> 00:41:10.930 So you can see here I'm having Claude, 00:41:11.655 --> 00:41:15.255 this isn't for me. I used eleven labs as my as if that was my company. 00:41:15.575 --> 00:41:16.455 And 00:41:16.455 --> 00:41:17.975 it's generating like 00:41:18.855 --> 00:41:28.350 let's see if I can find it. I don't know if I'm gonna 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 00:41:28.750 --> 00:41:30.110 part of this article 00:41:30.190 --> 00:41:36.190 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? 00:41:36.430 --> 00:41:56.595 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 gonna 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 in a Claude MD? Should it go in one of these LLM context files? 00:41:57.210 --> 00:41:58.730 Like, what's the right place? 00:41:59.050 --> 00:42:04.650 And then I'm working with Claude to make sure like, Claude wants to jam everything into your CloudMD. 00:42:04.650 --> 00:42:21.525 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? Got it. So I think about it as, like, information about me and my business goes in a context file, whereas my working preferences, 00:42:21.525 --> 00:42:38.575 like, this is how me and Claude work together, goes in a Claude MD. So, basically, yeah, this is a 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 sub subfolders and files. Yeah. Right? Yeah. 00:42:38.975 --> 00:42:40.735 Wait. So how much are you paying this 00:42:41.055 --> 00:42:46.415 cloud employees? They sound pretty useful. How how much are you paying? Yeah. $20 a month? Yeah. 00:42:47.055 --> 00:42:52.575 I'm on the $100 a month plan. Okay. But that's So you can see I'll show you here in in 00:42:52.735 --> 00:42:53.295 Obsidian. 00:42:53.640 --> 00:42:55.640 You can see all my context files. 00:42:56.040 --> 00:43:00.840 So, like, for my business, I have a target audience file, a marketing profile, 00:43:01.000 --> 00:43:02.440 a list of my differentiators, 00:43:02.440 --> 00:43:04.520 my company overview, my business model. 00:43:04.840 --> 00:43:09.320 I didn't, like, sit down and create this all one day. That would have been tedious and horrible. 00:43:09.925 --> 00:43:14.885 I basically anytime I felt like I needed to describe something to Claude, 00:43:15.285 --> 00:43:18.645 instead of just doing it that one time and then having to repeat it later, 00:43:18.885 --> 00:43:23.765 I'd be like, oh, Claude, in order to do this task, I feel like you need to know about my differentiators. 00:43:23.765 --> 00:43:30.890 Maybe interview me. And I literally, Claude will interview you. You can just be like, interview me about my business, and then it will ask you a bunch of questions, 00:43:31.210 --> 00:43:34.250 and then it will write a context file for you based on what you learned. 00:43:34.650 --> 00:43:47.395 Got it. Okay. So that's a that's a lot of how I did most of this stuff. Okay. Yeah. As long as you just sat down one day and made all these folders. Right? It's not No. I add to it, like, gradually over time. So what about, like okay. Last question. 00:43:47.635 --> 00:43:50.595 Let let's say I'm just overwhelmed by all this stuff. Like, this is Yeah. 00:43:51.940 --> 00:44:05.060 Like, I wanna learn stuff, but, like, it sounds like you really personalize it for your life. Yeah. Like, what are your three tips to get started? Let's say I already use Cloud Code for, like, co coding, but I wanna use it to manage my life. The first thing is with context, 00:44:05.060 --> 00:44:06.660 you don't have to get here overnight. 00:44:07.265 --> 00:44:07.825 Like, 00:44:08.225 --> 00:44:12.145 I think the simplest rule is whenever you find yourself explaining 00:44:12.145 --> 00:44:13.585 context to Claude, 00:44:13.985 --> 00:44:33.490 stop and think about, am I ever gonna 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. Yep. That makes sense. You probably need to think through, like, at a minimum, 00:44:33.945 --> 00:44:43.065 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 00:44:43.865 --> 00:44:53.970 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 stubs. Right? They're not that complete. 00:44:55.010 --> 00:45:08.045 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 add a context file, I say what index needs to be updated, and it just figures it out. Got it. Okay. 00:45:08.285 --> 00:45:31.045 So maybe, like, the process here is, like, think about your weekly calendar. What's, like, the most like, what's taking most of your time? And then and then, uh, try to you know, you have Claus, your employee, try to get it to, you know, give a bunch of instructions, backgrounds, context, have it save a bunch of files, and just work with it to start doing stuff. And then at the end of every conversation, ask it to, like, add more stuff to context or, like, improve its prompt. That's kind of 00:45:31.525 --> 00:45:33.685 that's kind of what you do. Right? Yeah. Okay. 00:45:33.925 --> 00:45:36.725 I think there's two steps to this. The first is 00:45:37.125 --> 00:45:44.190 I have worked with an admin for, like, ten years. So I'm really good at, like, looking at things that I can delegate. 00:45:44.190 --> 00:45:47.390 And for anybody who's ever delegated something to another person, 00:45:47.630 --> 00:45:50.670 what makes that work well is to have, like, a good, 00:45:50.990 --> 00:45:51.550 like, 00:45:52.270 --> 00:45:59.025 standard operating procedure for the task you're giving them. Right? It's not you can't just say to someone, another human, 00:45:59.265 --> 00:46:06.465 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, 00:46:06.865 --> 00:46:17.730 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. 00:46:18.290 --> 00:46:21.970 She then looks at the video. She creates, like, a Trello checklist for herself, 00:46:22.130 --> 00:46:24.370 and then that becomes, like, our standard operating procedure. 00:46:24.805 --> 00:46:30.085 So we've been doing this for years. And so I'm already good at this muscle of like, what can I delegate? 00:46:30.485 --> 00:47:05.095 So when I started doing this with LLMs, I thought about it as like, okay, well, Claude is just a person on my team, how would I delegate to Claude? 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 Claude help with this? Got it. Got it. And then there's pieces for some tasks. Like, I don't wanna automate them. I enjoy doing them. Like, I enjoy writing. I don't want Claude to write for me. So I don't wanna automate that. So I think about, like, how can Claude augment this? What do I do while writing that Claude could accelerate? Well, research and web searches 00:47:05.960 --> 00:47:08.440 and, like, coming up with alternative analogies. 00:47:08.760 --> 00:47:11.320 And then there's other tasks like 00:47:11.560 --> 00:47:14.280 send this stupid receipt to my finance system. 00:47:14.680 --> 00:47:22.255 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 Claude context to be able to automate this completely? 00:47:23.135 --> 00:47:35.040 So Okay. 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 Claude help? Got it. 00:47:35.440 --> 00:47:39.040 Alright, man. That that that that that's a great tip to end on, I I think. 00:47:39.520 --> 00:47:56.165 Alright. Cool. Just hire hire a $100 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 a $100. I started on the $20 plan. I only had to bump to the $100 plan when I was doing 00:47:56.565 --> 00:48:03.200 both a lot of coding in one week and a lot of writing in one week. So it's like I was literally pushing 00:48:03.280 --> 00:48:18.425 hard on Claude for a long time. So you can get pretty far on the $20 plan. Yeah. Yeah. Yeah. Yeah. And, hopefully, Anthropic guesses limits together. You know? Yeah. So yeah. Okay. So to find your detailed Cloud Code guides, just go to producttalk.org. 00:48:18.425 --> 00:48:23.865 Right? Is that the right site? Yeah. It's like, we can take a look right here. It's producttalk.org, 00:48:23.865 --> 00:48:28.025 and it's all, like, all my recent articles. You can see what is Claude. 00:48:28.460 --> 00:48:29.900 Stop repeating yourself. 00:48:30.220 --> 00:48:36.540 Probably by the time this episode goes out, that safety article will be live. Awesome. I'll I'll definitely read it. Yeah. 00:48:37.260 --> 00:48:48.025 There's a ton here. I'm gonna 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 nontechnical people, 00:48:48.185 --> 00:48:52.265 and to really start to show the power of, like, pair working with Claude. 00:48:52.585 --> 00:49:04.080 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 gonna be hosting Claude Code office hours. So if you wanna even come and get help, 00:49:04.400 --> 00:49:24.095 uh, I'm gonna be doing that every month. Awesome. Awesome. You you should should be there. You should be Anthropic's postpartum person. Yeah. That sounds great. Yeah. Yeah. I know. Someone asked me if I was being sponsored by Anthropic, and I'm not. Uh, if I was, I would disclose that. I really am just a big fan. Yeah. I'm I'm really a big fan too. I'm really a big fan of, like, Kat Boris and the team and what they're building. And, 00:49:24.830 --> 00:49:32.590 yeah, it's funny because they're they're really kind of trying to build towards the coding use case, but, like, you know, there's so much more you can do to build a really good agent. Yeah. 00:49:32.750 --> 00:49:36.670 Cool. Alright, Theresa. Thank thanks so much for your time. Thanks for having me. This has been fun.