Claude Code's Agent Teams Are Insane (Build Your AI Workforce)

0:00Cloud Opus 4.6 just launched with a feature that gets me generally excited since it will likely completely change how we work with AI. It's called agent teams. Instead of prompting one AI, you describe a complex task and it spawns multiple specialized agents that coordinate to solve it. Everyone predicted this as a [music] trend for 2026, but no one expected a production ready version to come out so early in the year. In this video, I'll explain

0:25everything you need to know about them. what they are, why they're so game-changing for complex tasks, [music] and show you how to start using them yourself.

0:39Okay, so what are agent teams? Unlike sub agents, which operate within one session and only communicate their results back to the main agent, you also have the option to engage directly with individual teammates instead of routing everything through the lead. Here's how it actually works. You give a complex task to the system. Let's say uh building me a marketing campaign. And instead of one AI trying to do everything, the system spawns multiple agents, teammates. A research agent uh gathers data about your audience. A strategy agent plans the campaign structure [music]

1:12and the creative agent writes the copy. Also, you could have a review agent which checks everything for quality. They work in parallel where they can in sequence where they need to and they coordinate their outputs. Here's why this matters. A single AI has to be a generalist. It's okay at everything but not great at anything. But when you specialize agents, each one can be optimized for its specific task. The

1:34research agent is amazing at research. The creative agent is amazing at writing. And when they join forces, the output is better than any single AI could achieve. Plus, they can work in parallel, which means complex projects finish way faster. You [music] may ask, why is this a big deal? Clearly this is a fundamental shift in how we use AI. Until now we have been trying to make one model smarter and smarter, more

1:59parameters, more data, better training. Uh just look at all the benchmark graphs on each LLM release. Agent teams live that instead of one super brain you get a coordinated organization. So what becomes possible with agent teams? Long horizon projects tasks that used to require constant human oversight can now run autonomously with agents checking each other's work. complex workflows, multi-step processes uh with research, analysis, creation, and review can happen in one coordinated flow. Better quality. Having a dedicated review agent catches mistakes that a single AI would miss. Faster execution. Parallel work means things that took hours can finish in minutes. Basically, the tasks that were too complex for AI, a lot of those

2:44just became possible. To be clear though, agent teams aren't a completely new concept. People have been experimenting with multi-agent systems for a while, but Claude Opus 4.6 implementation is the first one that feels production ready. Here's what they got right. First, automatic orchestration. You don't have to manually spawn these agents. Claude figures out on its own what agents are needed based on your task. Second, intelligent coordination. The agents don't just run independently. They share

3:14context and communicate naturally. Third, built-in specializations. Cloud has preconfigured agent types optimized for different tasks, uh, research, coding, writing, analysis, QA, and fourth, error handling. If one agent gets stuck or produces bad output, other agents [music] catch it and course correct. A few technical things worth knowing. In contrast to sub agents, individual team agents can request information from each other. Um, like the writing agent can ask the research agent for more data. And there's a supervisor agent that coordinates everything, making sure agents work in the right order and don't duplicate effort. It's surprisingly sophisticated for a first version of this. So now I'm going to walk you through how to

3:57actually set this up and use it in real project that I definitely need help with creating a week's worth of social media content for a personal brand. So the first thing you will need is Claude Opus 4.6 Access that you can get with their pre-subscriptions. As you can see, the you have an option of a pro plan and a max plan. In the demo we're going to show today, the pro plan is sufficient and [music] it should get you by for two or three tasks per day, even using this rather powerful agents mode. However, for professional use, we would recommend to use the max plan and that would cost

4:31100 or 200 if you want even more credits. [music] While the max plans are more expensive, they can be definitely worth it because for many people, [music] this agent's team mode will save a lot of time. So for this demo, we assume that you have cloud code already installed on your system. So we're only going to go through that step. However, agent teams is an experimental feature and it is not enabled by default for everyone. [music] So you would need to add an additional configuration to your settings. JSON file. If we would open up the cloud code docs, you would see the specific line you would need to add

5:02[music] into the file. Let's do that directly in the terminal. You would need to go to your cloud configuration folder. Open the settings JSON file and add the following lines. I have already them added to my configuration. So that's all you need. Close the file. And now there's an additional step that we would recommend. We would recommend to install T-Max because that would allow in your terminal to see every agent working individually. Otherwise, you would only see the same thing you would see on the cloud desktop application, which is every agent in the same single conversation. More or less. It is possible to switch between them in your

5:42terminal, but it is much nicer if you can see all of them and also interact with each of them individually. So for that, we're going to install T-Max.

5:55All right, and this might take a while. And here we go. We have our T-Max installed. Let's enter a new T-max session and jump into a project folder. So for any sort of thing you're working on, we would recommend to have a folder. And for cloud code is mentoring. Uh so in our case that is the video demo. Now let's launch cloud code. We also have a prompt already prepared for this demo. So we're not going to go into

6:25detail prompt engineering techniques. But as long as you provide a clear task and uh what are your deliverables you want your prompt really doesn't have to be much more complex than that. One additional thing we would recommend to add for a prompt when you're trying to work with agent teams is to specify each individual team member you want to spawn. It isn't necessary. You could just tell the model to orchestrate a couple of team members for the task. But if you want consistent results, we would recommend to specify the roles you want to fill. In our case, that is a strategist, a copywriter, a visual concept agent, and a reviewer for

7:02quality control. All right, so let's get into it. This might take a while. And here comes another recommendation. Do not try to run uh agent teams for simple tasks. For simple task, we would still recommend to use a single AI instance um or to use sub agents for very simple flows where you just have let's say maybe just a writer and a reviewer. When you need more collaboration, then we

7:26would recommend to go for agent teams. We can already see that the model is preparing a plan and soon enough we should see how it spawns a couple of team members to help it out. All right, and here's the beauty of T-Max. We already see individual team members on panels on our right and we can even see what each member is trying to do. So this is the key difference between agent teams and sub aent flows where you really have no way to interact or even sometimes observe what individual sub agents are doing. Here we could even stop any of the team members working uh course correct if they're going the

8:06wrong way or even provide an additional task we have not provided in our original prompt. So the strategist agent has already worked uh and prepared a plan and it has delegated its first task to the copyriter and now the copyriter does not have the permission to interact with our file system and it has asked for permission directly through the main lead agent. So we could give the permission. All right. I see the copyriter has finished its first task and now uh the visual designer um has

8:36start working on on its own assignment. So to copy done start visual concepts. [music] Okay. So tasks with agent teams take a while. So we have left uh the team to work on the task. Let's check back with them. As we can see the copyriter has already finished with its task. And now the visual content strategy agent is creating a document. Oh, it already created it directly a new doc right here. I'm again being asked for permission. Though you can also start cloud um cloud code with an additional flag which would allow you to just give permissions to all um team members

9:13automatically if that's what you prefer. Here we're working conservatively. So we are explicitly allowing team members to deal with the file system. If you're in a hurry you could just preemptively give these sort of permissions. Okay. So the reviewer has found a few issues to fix and we're even seeing which exact lines it has found and what types of edits it's doing. So it is using the diff style, you know, what kind of line it is changing. We can even investigate and say um [music] that maybe this agent should focus on something more specific. Right? [music] So T-Max paints have already closed. So that means that agents have finished

9:53with their work. But that does not necessarily mean that the task is is already done because the reviewer has flagged up five action items on areas where it could still improve. So what we could do now, we could again prompt our main team lead and ask it to delegate these as tasks to team members to iterate on the documents again. So we give the team lead the same tasks that the reviewer has flagged and we can see that it's already working on a new plan on how to iterate on these docs. It is adding new items to the to-do list. So first it will need to source and verify

10:30all statistics as citations and again we're seeing that it has decided to spawn researcher which is a new agent which we haven't specified before a strategist copy editor and a copywriter. So here we can see that it has used two of the agents that it has previously seen in our uh last iteration and it also has decided to bring in two new agents which we didn't even explicitly specify in our prompt. So as you can see quite often you can get away with broad prompts. Now

11:01all four agents are working in parallel. [music] So the researcher is looking up information online to double check that our mentioned statistics are correct while at the same time the copy editor is trying to identify the the issues that the reviewer has flagged. Also we see that the copyriter has tightened the Wednesday reel to be 30 to 35 seconds

11:21and it also improved the call to action. At the same time we see that there have been some placeholders on our content um and the copyriter has filled them in. Also, the copy editor is working on the on tightening up the Wednesday reel to be 30 to 35 seconds. It's also trying to improve the call to action. We already see that the researcher has flagged up some of the metrics that we have cited in our material [music] and it has replaced them with more factually accurate ones it has found online. At the moment, out of our four teammates, three of them have already completed their tasks. We're just

11:54waiting for the researcher to wrap up its task. The researcher has also prepared a sources document where it lists all the references for the facts and the statistics it has updated in our document. All right, I'm seeing that that task is being wrapped up. Team cleaned up. All revisions are done. Your full content package is production ready and in the folder we started with. Uh let's jump into that folder and try to review its work. So we can see there are quite a few files and I will go to the post. [music] it has recommended for Monday through Wednesday. Okay, so for Monday it recommended a LinkedIn post, a

12:34Twitter or X post and also Instagram caption. We can see that the post is already well structured. It seemingly we need to double check this and because this is still to some degree a draft [music] and as we can see all these posts match the platform requirements. So for LinkedIn, it has more of that LinkedIn style with a bullet list with more metrics, more styling. Meanwhile, the Twitter post is short with a couple of relevant hashtags uh based on the industry we're working on. And the Instagram caption has also plenty of hashtags through which it would recommend us to market. All right. Also, the model has provided an image concept

13:14and a video idea uh 30 second video. So these were not generated. You would need to either shoot these visuals yourself or use an image generation model something like Nano Banana Pro GP image 1.5 and for videos you could use V31 um to create these sort of visuals. It has put in a lot of work even provided a color scheme for the image concept and even the specific format. So for um Instagram it recommends a square image with a very specific resolution and for LinkedIn it recommends a banner and it has provided very similar structure for upcoming days. So for Tuesday and for Wednesday for Tuesday I see the video

13:57idea is a bit different. So it's also also 45 seconds and for Wednesday it has a longer video with very detailed breakdown of what should be in the video nearly second by second. If you would try to prompt a single AI model to do this sort of task, usually it wouldn't have enough of the context window to really get into every single day, every single post and match every platform that we need. So this is the power of agent teams. In just 15 minutes, we got a good first draft and I still would need to double check it and inject some of my personality into it, but it still

14:34saves me hours in production and all of it was done with a single [music] prompt. If I tried to do that with a single agent, it would take me multiple tries and likely a few hours. As amazing as it is, one downside is the price. Um, let's check how much the single generation cost us. So if I would jump back into cloud code and I would write slash usage we would see that I have spent around seven close to $8 in usage just for this single task. If you would want to know how that what that means for pro and max usage that would be around 50% of your

15:17single session usage for [music] pro. For max, you would probably be able to fit in about eight or 10 tasks in five hours. So to avoid unnecessary costs based on testing this for a couple of days now, here's when agent teams make sense versus just using regular claude. Use agent teams when the task has multiple distinct components like research, writing and review or testing, [music]

15:40uh implementing and other review stage. Quality matters more than speed. You need different expertise applied to different parts and you want built-in quality control. Use single AI when it's a simple focus task. Speed is more important than sophistication and you're on a budget and can justify the extra cost. For that social media content, agent teams made sense. If I just needed one post caption, a single AI 100% of the time. In general, I keep single agent cloud for quick tasks [music] and only spin up teams for complex projects or to tackle issues where the single agent fails. A quick few tips before you try this yourself. One, start with a low

16:21stakes project. Don't hand it your most important client work on day one. Two, be very specific in your initial brief. Include brand voice, target audience, goals, any constraints, kind of like working with a new colleague. Three, review everything. The agents are good, but they're not infallible. The classic AI rule to double checks everything still applies in this case. Four, [music] keep an eye on your API or subscription usage in the dashboard. Set spending alerts if you're worried about costs. So clearly with this new update by shifting from AI as a tool to AI as a workforce, agent teams are the first step toward AI organizations that can

17:01handle complex projects autonomously. All right. So that's agent teams and cloud opus 4.6. The concept is simple. [music] Specialized AIs working together beat one generalist AI. The implementation is sophisticated. Cloud handles orchestration, coordination, and error handling automatically. And the [music] result for complex tasks this will be a gamecher. If this works at scale, it changes what's possible with AI completely. If you would like to see a video on more use cases and results of my testing, subscribe to not miss it when the video drops and leave a comment. What would you use agent teams [music] for? What complex projects would you hand off to a team of specialized

17:41AIS? If you want to understand the technical foundations behind this stuff, how these models actually work, not just how to use them, check out Turing College AI [music] courses, links below. Now, we have all heard of the layoffs that are happening in the industry. So, we have made a video on the most essential AI skills to master to get

17:59ahead in 2026 and become irreplaceable. Click here to see it. That's it from me. Catch you [music] in the next one. [music]