WEBVTT

00:00:00.160 --> 00:00:08.400
Claude CoWork, after receiving an incredible number of updates over the past few weeks, is now one of the most powerful AI agents for non coders,

00:00:08.560 --> 00:00:12.080
but most people are only using a fraction of its capabilities.

00:00:12.320 --> 00:00:19.735
If you just learned the 12 simple Claude Cowork tricks that I'm about to share with you though, you'll finally unlock its full potential.

00:00:19.815 --> 00:00:27.015
And I wanna start with what is probably my most controversial take. My first tip is that Claude Cowork projects

00:00:26.500 --> 00:00:32.340
should only be used as a way to organize your chats and not as a way to give Claude instructions.

00:00:32.820 --> 00:00:35.940
So inside of Claude Cowork, there are these things called projects.

00:00:36.100 --> 00:00:37.300
Here are my projects.

00:00:37.620 --> 00:00:43.265
And if you open up any of these, you'll notice that over here on the right, you can give the project instructions.

00:00:43.425 --> 00:00:52.225
The idea behind this is that you can put some instructions in here so every time you start a chat from within a project, it will automatically apply those instructions.

00:00:52.990 --> 00:01:00.430
The problem is, as great as Claude Cowork is, we shouldn't fool ourselves into believing that it will be the best tool forever.

00:01:00.750 --> 00:01:05.310
To future proof your setup, you wanna make it as transportable as possible.

00:01:05.995 --> 00:01:07.915
But if you have instructions

00:01:07.915 --> 00:01:21.195
inside of 20 different projects, it's gonna make it very hard to move from Cowork to another tool. So what do I use projects for? Well, I only use them for one thing, which is to organize chats.

00:01:21.660 --> 00:01:27.660
So inside of Claude Cowork, every time you click on new task, is Cowork's name for a new chat,

00:01:27.980 --> 00:01:29.980
and you start a task from here,

00:01:30.300 --> 00:01:34.380
it will appear in the recent task section here on the bottom left.

00:01:34.780 --> 00:01:40.475
But this isn't organized, so it makes it difficult to find important tasks that you wanna locate later.

00:01:40.875 --> 00:01:44.235
So I've set up projects that I use as folders.

00:01:44.715 --> 00:01:47.675
For example, here's one I've called presentations.

00:01:48.075 --> 00:01:50.235
Anytime I wanna create a new presentation,

00:01:50.740 --> 00:01:56.740
instead of clicking on new tasks at the top, I instead click on the presentations project.

00:01:57.220 --> 00:01:59.700
I tell it what I want it to create for me,

00:02:00.100 --> 00:02:04.660
and then that task will appear down here inside the project,

00:02:05.265 --> 00:02:10.625
and any outputs it creates like the slide deck will appear in this output section.

00:02:11.105 --> 00:02:14.545
That way it's all neatly organized in one place.

00:02:14.865 --> 00:02:18.625
So projects for me are basically a folder system for tasks.

00:02:18.980 --> 00:02:21.140
But if I don't use instructions

00:02:21.140 --> 00:02:22.180
in projects,

00:02:22.500 --> 00:02:28.740
how do I tell Claude Cowork how I want it to work? For that, I suggest you utilize trick number two.

00:02:28.980 --> 00:02:34.260
As you already know, Claude Cowork works directly with files and folders on your computer.

00:02:34.995 --> 00:02:42.595
Opening up my finder, this is the main folder that I have Claude Cowork work inside of. I've called it Frank Bot.

00:02:42.835 --> 00:02:52.070
Inside of this folder is a file called Claude dot m d. This is just a text file that gives instructions to Claude Cowork.

00:02:52.390 --> 00:03:02.710
Anytime it goes into this folder to do work, it will read this file and it will give it all the context it needs to help me and the general instructions for working in this folder.

00:03:03.485 --> 00:03:07.965
Another way of putting it is instead of putting all of your instructions

00:03:08.365 --> 00:03:09.325
inside

00:03:09.325 --> 00:03:11.325
of the project instructions,

00:03:11.645 --> 00:03:21.750
you take everything you would put in there and you just put it in a text file called claud dot m d. That's it. And then within each of these subfolders,

00:03:21.990 --> 00:03:24.790
which I basically use as different projects,

00:03:24.950 --> 00:03:29.270
there's another Claude dot m d file with more specific instructions

00:03:29.350 --> 00:03:31.175
for that subfolder.

00:03:31.255 --> 00:04:27.825
With this setup, anytime you switch to a new tool like Codex, you can just tell it to find all the Claude dot m d files and to change it to the name that it uses for its instruction files, and then it'll be ready to go. I've made videos about this system before and have received a ton of great questions about it. So I'm actually planning to build a school community where I'll share with members a step by step guide on how to set this up along with a lot of other AI tutorials that I don't share here on YouTube, live q and a's, and a member's forum. If you wanna find out more about that or get on the wait list, all the details are in the description down below. Tip number three. Did you know that when you start a new task and choose which folder on your computer you wanna work inside of, you can actually choose multiple folders. All you have to do is select a new folder, and you'll see which ones are selected with this check mark on the right. I find this really helpful when I want the agent to have access to information in two different folders,

00:04:27.985 --> 00:04:35.345
but I don't want it to have access to all the folders because then it will have too much information that may not be relevant to the task.

00:04:35.585 --> 00:04:41.185
So for instance, if I have it do some research for me, I might have it pull that research into the research folder,

00:04:41.680 --> 00:04:50.640
but then I might ask it to create a presentation for me about what that research was. So then I would give it access to both the research folder and the presentation folder.

00:04:50.960 --> 00:04:59.975
And while I have this drop down open, tip number four is to set a default folder if you find yourself using one folder more than all the others.

00:05:00.295 --> 00:05:21.560
So I've set my default as the parent folder that contains all the other folders that I have my agent work on. That one is called Frank Bot. So if I start a new task, it will always select that one by default. But if I want to, I can always change it. Tip number five may also be a bit of a controversial one, but you need to understand the limits of dispatch.

00:05:21.985 --> 00:05:27.265
Dispatch is a feature that's supposed to give you mobile access to Claude CoWork,

00:05:27.665 --> 00:05:49.205
but there are two issues with it. One, in order for it to work, your computer needs to be on, CoWork needs to be open, and then you need to link up Dispatch with it, and then it will work, which is impossible for everyone. They can't just leave their computer on all the time. And the second problem is that it honestly doesn't work that well. Just like one continuous

00:05:49.205 --> 00:05:54.005
conversation that you have with co work, so you can't access all of your chats.

00:05:54.085 --> 00:06:06.260
It's hard to have multiple projects going at the same time. Like for simple tasks, it works fine, but whenever I try to use it for multiple things, it just ends up frustrating me and getting confused.

00:06:06.500 --> 00:06:09.860
Tip number six I have for you is to use voice dictation

00:06:09.860 --> 00:06:11.300
the right way.

00:06:11.780 --> 00:06:18.575
Inside of CoWork, instead of typing in here, you can use a voice dictation button. It's right here.

00:06:18.895 --> 00:06:22.415
But you can also access it just by pressing command d,

00:06:22.655 --> 00:06:44.085
and it will start listening to what you're saying. But there's a secret hidden menu here. On this drop down, you can select whether you want to hold to record, which is like push to talk, or you can toggle it. So if I turn this off and now I press command d, it is now toggled on and I don't have to hold it and can just talk out loud. And then once I'm finished talking,

00:06:44.325 --> 00:06:47.845
then press command d again and it will toggle off dictation.

00:06:47.925 --> 00:06:55.760
Dictation is a very important tool when it comes to using AI agents like Claude Cowork Because a lot of times our best ideas

00:06:55.920 --> 00:07:00.720
come to us as we're talking out loud about them and just sort of rambling.

00:07:01.120 --> 00:07:05.600
And the AI agents are really good at taking our unstructured

00:07:05.600 --> 00:07:09.265
brain dumps and turning them into structured output.

00:07:09.425 --> 00:07:12.065
So don't be afraid to turn on dictation

00:07:12.305 --> 00:07:22.850
and just brain dump a bunch of ideas and let Claude do the work of sorting through all of it. Tip number seven is a quick one, but it has saved me a lot of money.

00:07:23.170 --> 00:07:32.610
When you schedule tasks, and you should be using these because this is a great way to automate your work, you wanna make sure you schedule them for off peak hours.

00:07:32.930 --> 00:07:47.735
If you schedule them for peak hours, you'll see a warning like this. And opening it up, you'll see that it tells you that you've scheduled this for peak hours, which are between 5AM and 11AM Pacific Standard Time, and that will consume your usage limits faster.

00:07:48.135 --> 00:07:53.790
So make sure if it's possible to schedule these for off peak hours.

00:07:54.110 --> 00:08:10.145
Another tip along the same lines is if you have a task that you need to run, but you know you don't have enough limits for it, just set it up as a scheduled task to run later in the day when you know your limits are going to reset.

00:08:10.385 --> 00:08:19.330
Even if you're gonna be away from your computer, then it will just automatically start. And when you get back to your computer, it will be done. Tip number eight is to use lots and lots of skills.

00:08:19.490 --> 00:08:36.315
You can think of skills as prompts that you load into Claude CoWork once so you never have to type them out every time you wanna use them. Instead of using skills though, a lot of people will create a very long set of instructions either in their claw dot m d file or worse

00:08:36.395 --> 00:08:38.635
inside their project instructions.

00:08:38.635 --> 00:08:56.170
It may say something like, every time I tell you to triage my email inbox, I want you to do x y z. And then every time I tell you to update my CRM, I want you to a do a b c. The problem with that approach is that every time you use the agent, it will read through all of those instructions, which is very inefficient.

00:08:56.615 --> 00:09:09.735
Skills fix that because your agent will only load the skills that it needs or the ones that you tell it to load. So it's incredibly efficient. And because of that, you should be using less instructions

00:09:09.895 --> 00:09:11.095
and more skills.

00:09:11.770 --> 00:09:19.370
For example, if we return back to the folders that I've set up for my agent, I have a subfolder project folder here called presentations.

00:09:19.450 --> 00:09:24.490
And inside of that, I have a claw dot m d file, which again are the instructions for the agent.

00:09:25.105 --> 00:09:40.370
But if you look at this, literally, all it says is this project folder is used when I want you to create on brand slide decks for me. And when I tell you to do that, use the slide deck skill. That's literally all it says to do. And then inside of Claude,

00:09:40.450 --> 00:09:51.490
we have the slide deck skill in here. So it's only going to load that when it needs to use it, which is a lot more efficient. And tip number nine is to use lots and lots of connectors.

00:09:51.925 --> 00:10:05.670
If you find yourself jumping between lots of apps to get your work done, see if there's a connector for it. What I'm trying to build for my school community is a system where people can log into one tool like Claude CoWork and be able to control everything

00:10:05.750 --> 00:10:18.470
from there like one central command without jumping between all these different apps. Tip number 10 is another one that will hopefully also save you some money. Take advantage of Claude design. This is included

00:10:18.805 --> 00:10:27.365
with your Claude subscription that you use to access Claude CoWork. And with this, you can create slide decks. You can create websites. You can create motion graphics.

00:10:27.605 --> 00:10:33.765
So instead of setting those up inside of Claude CoWork, which is going to use those usage limits,

00:10:34.085 --> 00:10:51.995
instead use the usage limits that are for Claude design. They're separate. So you might as well burn through those ones first before you start burning through the ones inside of Claude CoWork, which you may wanna use for other tasks. Tip number 11 I have for you is to download and use the app Obsidian.

00:10:51.995 --> 00:11:03.190
It's free to use and this will be a viewer that you can use to view the files that Claude Cowork makes for you. Like I was saying before, everything it makes for you lives

00:11:03.190 --> 00:11:05.430
inside of folders on your computer.

00:11:05.830 --> 00:11:12.390
So this isn't the most user friendly way to view what it's made. You can open up each folder

00:11:12.550 --> 00:11:17.245
and then you have to use a different app to actually view the different outputs,

00:11:17.565 --> 00:11:18.525
whether that's

00:11:18.765 --> 00:11:23.005
slide decks or websites it's made for you or even just text documents.

00:11:23.405 --> 00:11:29.405
So if you download this app Obsidian, it's free. It's available for iOS, Android, Windows, Mac, Linux,

00:11:29.805 --> 00:11:31.990
then you get an experience like this.

00:11:32.310 --> 00:11:49.525
This is the same folder, my Frank bot folder. You can see all the subfolders in here, and it's a lot easier to view what was created. So here's a text file, and I can come in here and add anything to it that I want. And even if it makes something for you that's HTML,

00:11:49.525 --> 00:11:53.285
like this slide deck it made for me, you can view that in Obsidian.

00:11:53.365 --> 00:11:58.885
Obsidian can get very complicated very quickly. You don't need to know 95%

00:11:58.885 --> 00:12:14.940
of what it can do. You literally just download it, point it to your folder, and use it like this, and don't worry about all the extra complicated stuff. And tip number 12 I have for you might seem like a contradiction, but it's really not. So I'd say about once a month, you wanna come into customize,

00:12:15.315 --> 00:12:21.395
look at all the skills that you have turned on, and just turn off the ones that you no longer use.

00:12:21.635 --> 00:12:25.875
If you have too many skills, especially ones that you're not even using,

00:12:26.115 --> 00:12:32.390
it can degrade the performance and push you closer to your limits limits faster, your token limits.

00:12:32.630 --> 00:12:34.150
Same thing with connectors.

00:12:34.390 --> 00:12:37.590
If you have too many connectors that you're not even using,

00:12:38.150 --> 00:13:08.095
then that can confuse Claude Cowork, and it may try to load a connector that you don't even want it to use. So just disconnect anything you're not using or turn off any skills that you're no longer using. So there you go. 12 tricks for leveling up Claude Cowork. Hopefully, you learned something new today. If you did, let me know by giving this video a thumbs up. Then if you wanna get on the wait list for my new school community, make sure to do that at the link in the description down below. Otherwise, thanks so much for watching the video, and I'll see you in the next one. Bye for