Transcription
Most people prompt Claude the same thing over and over again because they don't know how to use agents yet. With agents in Cloud Co-work, we can now bulk process dozens of tasks in parallel and run full multi-step workflows autonomously.
So, in this video, I'll show you how agents work in Cloud Co-work, show you demos and examples of how to use them, and show you how to set them up from scratch to automate your workflows. Now, if you're new to Cloud Co-work, co-work is a game changer because we can now give Claude access to files on our computer and connect it to our entire software stack and also create skills to automate some of our workflows.
Now, what many people don't know yet is how to use agents. Using agents is a little bit more advanced, but even if you're new to Co-work, you should be able to follow this. If not, I recently launched a full beginner tutorial, which I'll make sure to link in the description below, too.
Now, before explaining exactly how these agents work, let me show you a quick example of what they can be used for. For example, here I gave Claude a lead list of more than 150 marketing agencies which we got from Apollo a lead database. And then I let it qualify the list with sub agents first according to our ICP criteria which is a marketing agency providing SEO services and located in the US. And then you can see it launched 15 sub agents to qualify all 150 leads in parallel. Each agent will use web search to verify the company actually offers SEO service and is US-based. So here it launched 15 sub agents in parallel and then identified that only 82 were qualified and because these sub agents work in parallel this only took two minutes.
After that it went to the next step in this workflow which is enriching the leads with more uh information. So it launched another 18 sub agents, 17 lead researchers and one LinkedIn scraper. It then added that qualification status and lead intelligence to the CSV sheet. And then it spawn up another 17 agents to write personalized outreach messages based on the lead intelligence data. The personalized outreach messages are also added to the sheet. So as you can see here in the same chat include it qualified 82 out of 150 leads. It enriched 82 leads and then wrote 37 icebreaker messages. And this is really the power of agents because this was of course very difficult to do before we could use sub agents.
And now that we have plugins, each one of these bulk tasks can be saved as skills. Multiple of these skills can be strung together and combined into an agentic workflow through commands. And we can even save the specific agent instructions in the agent section. So you can see in our sales plug-in here, we have specific skills for each of the tasks in the workflow for lead qualification, lead intelligence, and email personalization with specific instructions on how we exactly do these processes. For example, in the lead qualification skill, we have our ICP criteria, the qualification process it has to go through, and instructions on how and when to use a sub agent. Here, the instructions for what these sub agents have to do are saved here in another tab which is called agents. And here, for example, we have the lead qualifier sub agent with a specific instruction on what these sub agents need to do. We've combined these three skills into one command to trigger all of these skills in sequence together with all the agents with just one slash command. So you can see the command we set up for outbound pipeline is just a sequence of steps to take and skills to use in order to execute a more complex workflow. And this allows us to run this multi-step workflow with sub agents with just one command here, which is the command outbound pipeline, which I can trigger simply by going to plugins, sales, and outbound pipeline.
Now, this might look a little bit complicated to you, but it's not. And I'm going to show you how to set this up yourself from scratch. If you want access to all of the skills and plugins that I just showed, plus all of the other skills and plugins we're building out, you can also check out my AI accelerator where we list all our skills. We also do weekly AI workshops where we dive a lot deeper into these tools and have one-on-one unlimited live tech help available. So, if that's interesting to you, definitely check it out in the link in the description.
Now, before showing you exactly how to do this yourself, let me quickly explain how these sub agents work and why it opens up lots of new possibilities for Cloud Co-work and also tell you what the limitations still are. Now, with Cloud plugins, which were recently launched, we now have these skills, commands, agents, and connectors available in Claude. Now, if you don't know what skills are yet, I recently did a full uh video on it, which if you haven't seen it, I highly recommend checking it out. I'll make sure to link it in the description below, too. But essentially, through skills, we can save specific ways of working in Cloud to automate repeating tasks. With commands, we can string together multiple of these skills in sequence to automate more complex tasks. And connectors allow us to connect it to any third party software uh through APIs or MCP.
But we also now have agents. And before agents were available in cloud, bulk processing was difficult for many tasks because we essentially only had one agent to process each task separately. This overloaded the context window, made it extremely slow and often just not viable to do for these bulk processes. But Cloud can now spin up these sub agents which can then process tasks in parallel which just means at the same time. And each of these sub agents can also use tools and skills. For example, our lead intelligence sub agents uses a LinkedIn scraper to scrape LinkedIn data. So, if we tell Cloud Co-work to research a 100 leads, for example, he could spin up 10 sub agents, each researching 10 uh leads um through let's say the LinkedIn scraper and and other tools and then give a summary back of the lead research to the main agent.
Now, why is this a big deal? Because the main agent will not be bloated with research context, just a summary. And context is one of the most precious resources for these agents and therefore it will drastically improve the performance first of all. And because sub agents can run in parallel a task like this one in example can be performed theoretically 100 times faster and because of this we can actually start using clockwork for these bulk task executions for deep research tasks but also we can start using it for these autonomous multi-step workflows. And these three things together make it a lot more powerful and it becomes much more like an automation tool uh comparable to naden or make.com.
Now we're not completely there yet which I'll get to later in this video. But because this is now possible, hundreds of new use cases pop up for automation right inside clockwork. So you can think of for example creating bulk ad variations, writing bulk uh product or SEO descriptions, bulk email personalization. And we can start doing data analysis on thousands of transcripts for example and pull all the research data back into a presentation. Uh we can think of doing SEO audits and of course we can also combine these new use cases together to do autonomous multi-step automations in bulk like I showed you in my example.
Now before showing you how to set it up and how to do this yourself there's one more thing I want to clarify because clot code now also came out with a new multi-agent feature but this one is different from the one we have available in cloud code work. In clot code, we can now even run multi-agent teams that can communicate between each other. While in co-work, they are all isolated sub agents.
Now, you can imagine that when they can communicate with each other, it really becomes an even more powerful setup because they can work together towards a shared goal or a to-do list. Uh, Entropic used this setup with this multi-agent team uh to build an entire C compiler in two weeks, which is something extremely hard to do in engineering and would normally take a large team of engineers to do for months. Now, this is really really powerful, but I see it mostly as an engineering feature. Multi-agent teams are good for tasks where agents have to work together on one shared goal or uh work together on a to-do list, while sub agents are preferred when each one can work in isolation. And for most day-to-day office related work and tasks in marketing, sales, customer support, etc. The sub agent setup is usually enough and can actually be preferred setup because it uses less tokens and it's really all we need for most of these isolated tasks like lead research, analyzing data, etc.
Now, even though sub agents use less tokens than agent teams, they still use a lot of tokens. So, that's one thing you want to keep in mind and is still a limitation. It can use quite a lot of uh tokens when you spin up these sub agents. Now, of course, this going to get cheaper and cheaper, but uh if you want to start doing this, you probably want to be on the clot uh max plan. uh to not be hitting your limits all the time. And second, what I've noticed is for really large bulk tasks, this is probably not a setup you can use yet. I've seen this work best uh for batches of 100 to 200. More than that, it's going to get complicated, take a long time, cost a lot of credits. That's why for large bulk workflows, especially ones that are non-human in the loop, an automation platform like naden or make.com is still a better option to automate those types of processes.
So, knowing that, let me show you how to use these agents in Clockwork. So, first I'll show you how to make sure Claude uses these parallel sub agents because there is a specific way you need to prompt it. Then I'll show you how to save these tasks as skills and agent files. And then I'll show you how you can build these commands and add them all into a plug-in that you can easily share with your team or with other people.
So let's say we're going to replicate that same uh use case as before, but in this case I don't have the skills yet. Then give it the CSV sheet of the leads and then I would prompt it with something like this. I want to qualify these leads uh against my ICP criteria. My ICP criteria are that we only work with marketing agencies who provide SEO services and are based in the US. Please spin up 15 parallel sub agents that each research 10 leads in this list and make sure they're qualified leads. Based on the summaries you get back, uh you deliver an updated CSV sheet and add a column with the qualification status.
Now, specifically mentioning that it has to spin up these parallel sub agents is important because sometimes if you don't say it, it will actually run sequential sub agents, meaning that they'll be running one after the other, which means it's going to take a long time. And sometimes it won't even run sub agents if you don't specifically tell it to. So, you can see it already made a plan here, right? Launching 15 parallel sub agents, collect results, and generate updated CSV. So you can see it's now spinning up these batches of sub agents to process and qualify all of the leads. And you can see each of these sub agents does multiple queries on the internet on each of the leads to find more uh information about them. So it's now done the qualification on 150 leads gave me a CSV sheet which I can throw in two sheets and now we have a new column with qualification status and a qualification reason column.
Now, if this is a repeated workflow that I would do, I could already save this as a skill by just telling Claude, please save this as a skill. So, next time I don't have to give all of these instructions. It will already know exactly what to do with a lead list that will get. But, I'll show you one more example and then we're going to build the entire plugin right away. So, we're going to build multiple skills, commands, and agents into a plug-in right away.
So, let's say now we want to enrich the leads a bit uh so we can use that enriched data later for personalized outreach. Now, for this task specifically, and generally if you're going to enrich leads, I'd highly recommend installing the Appify MCP. Now, if you don't know Appify yet, Appify basically has thousands of scrapers, including scrapers for hard to scrape websites like LinkedIn, Instagram, Facebook, and through the uh Appify MCP, we basically get instant access to all of these social media and websites that Claude cannot access. Now, you can just make an account for free here on Appify. uh you get some credits. Um, but if you're going to use it a lot, I recommend upgrading and it will cost you uh $29 a month.
Now, once you're in your account, you need to get your API key, which you can get here by going to settings and API and integrations. And here you can copy your API key. Then include you can go to the connectors in the settings and click connectors and you go to browse connectors and you look for Appify. You'll see that appear. Now mine is already connected. Um, but once if it's not connected yet, uh, it will ask you for the API key and enable tools, which basically specify which scrapers from Appify we're going to use. Now, the easiest way to do this is by going to mcp.appify.com. And here you can basically specify all the scrapers you want to give access to Claude. So, first I'd recommend selecting all here. Then you can click here on add or remove actors. And here you can specify all the ones you want. Let's say for example LinkedIn mass LinkedIn profile scraper and let's say a LinkedIn post scraper this one for example. So we actually know the last uh posts that our leads have posted. So we can use that as a personalization. So once I've selected you can select way more. Uh, you click on save changes. Then you go here below and then you take this part after the equal sign you copy that you go back to Claude and that's what you add here in the enable tools and you click on save. Sometimes you have to restart your cloud co-work for Appify to actually be accessible. Uh, but then you should have Appify installed.
And now I can say something like please spin up 10 parallel sub agents that enrich seven qualified leads each. They should find the lead's last LinkedIn post uh the company size and the company description using the Appify scraper specifically the LinkedIn scrapers to get these details. And then you uh should add these data points to the CSV sheet so we can later use that data for personalized outreach. Again, I specified the use of parallel sub agents and also how many leads each sub agent should process. In general, what I've seen is the best is to have between five and 15 uh leads or or pro tasks per sub agent. Otherwise, it could take a lot longer if you do more. And if you spun spin up too many sub agents, uh it also runs into complications sometimes in my experience.
So, you can see it spin up again 10 sub agents. So, you can see each of the sub agents is using a LinkedIn profile scraper. So, it's now enriched the CSV with the last LinkedIn post if they had one, company description and company size. So, you can see we get the last LinkedIn post here, the enriched company size and the company overview. Now, of course, now we can do another skill to write personalized outreach messages based on this enriched data. But I think you get the point.
So let me show you how you can now convert this into skills agent docs so you don't have to repeat what these agents have to do and commands to string multiple of these tasks together into one workflow. Now the amazing thing include is that we can build these skills right from prompt. Now because we're going to create multiple skills, we're going to create commands and agents. I would advise you to add them all into one plugin. So it's all stored inside of the same plug-in which then can also easily be shared.
So, I could say something like uh for example, please create a new plugin that's called Ben's outbound uh sales process. Inside of that plug-in, I want to create one skill for the exact way we did the lead qualification and call it Ben's lead qualification skill. Make sure to also create an agent.md. And the skill should refer to the agent.md instructions on what the agents need to do. Also, create a skill for the exact way we did the enrichment process. and call it Ben's enrichment skill. In that one, also make sure to create a separate agent.md for the enrichment process. In both of these skills, it should clearly be instructed to spin up parallel batches of sub agents just like uh we did in the task here above. Again, this is important to specify also when you're creating the skills or the plug-in um because then it it's clearly stated in the skill to use those parallel uh sub agents.
Of course, we can also combine this into a command to trigger both of these skills or tasks at once with one specific command. So, for example, I could say something like also, please create a command.md where I can trigger both of these skills uh in sequence when I trigger a slash command uh with called outbound enrichment. This command uh should ask the user for a CSV sheet with leads and it should then automatically use the lead qualification scale and the lead enrichment uh scale in sequence to deliver a fully enriched CSV to the user at the end. All of these new documents and files should be stored in the same plug-in.
So you can see now starts building the plug-in. It makes to-do list click create plug-in directory create lead qualification skill create lead enrichment skill create outbound enrichment command. So now created the entire plug-in with two skills lead enrichment and lead qualification one command outbound enrichment. As you'll see it already includes all the instructions on how to run this workflow. Right? So first use the lead qualification then the lead enrichment. We have the agents the enrichment agents and the qualification agent.
Now sometimes it gives you a button which is called install. So you can install as a plugin right away. Sometimes it don't doesn't work in my experience. So you can just ask it to give you the plugin as a zip file. This then you can use to share to other people or to import it yourself if you don't have the install button. And then you can just go to your plug-in section, go to plus and click on upload plugin. And then you can drag that in and upload. And now you can see I have my new plugin with commands, skills, and agents. You can also upload these plugins onto a GitHub account. So you can get a link, a versionable link that you can share with other people.
And now that I have these commands and skills, I can of course trigger them anytime I want to do this task again right inside Claude. So I can just go and slash command, go to plugins and trigger the outbound enrichment command.
Now that's it for this video. Again, if you want access to all the plugins and skills we're building uh to maybe use or customize them for yourself, you can check out my AI accelerator. We also do weekly AI workshops where we dive a lot deeper into these tools. Uh, we have one-on-one tech help unlimited to help you out with any tech problems you have and blueprints on how to start your own business. So if that's interesting to you, uh, you can check the link in the description below. If you got any value out of this video, I highly appreciate a like and a subscribe. It really does help me. And if you want to learn more about cloth co-work, you can check out the video here above.