WEBVTT

00:00:00.080 --> 00:00:19.295
Cloud 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 trend for 2026,

00:00:19.295 --> 00:00:33.690
but no one expected a production ready version to come out so early in the year. In this video, I'll explain everything you need to know about them, what they are, why they're so game changing for complex tasks, and show you how to start using them yourself.

00:00:40.250 --> 00:00:57.865
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,

00:00:58.680 --> 00:01:00.520
build me a marketing campaign.

00:01:00.760 --> 00:01:05.720
And instead of one AI trying to do everything, the system spawns multiple agents,

00:01:06.120 --> 00:01:12.520
teammates. A research agent gathers data about your audience. A strategy agent plans the campaign structure,

00:01:12.680 --> 00:01:46.215
and a 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 to everything that's not great at anything, but when you specialize agents, each one can be optimized for its specific task. The Research 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,

00:01:46.375 --> 00:02:10.590
which means complex projects finish way faster. You 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 parameters, more data, better training. 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.

00:02:10.745 --> 00:02:18.905
So what becomes possible with agent teams? Long horizon projects, tasks that used to require constant human oversight, can now run autonomously,

00:02:18.905 --> 00:02:22.505
with agents checking each other's work. Complex workflows,

00:02:22.745 --> 00:02:24.265
multi step processes

00:02:24.265 --> 00:02:25.465
with research,

00:02:25.465 --> 00:02:26.780
analysis, creation,

00:02:26.780 --> 00:02:30.700
and review can happen in one coordinated flow. Better quality.

00:02:30.780 --> 00:02:39.980
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.

00:02:40.385 --> 00:02:43.185
Basically, the tasks that were too complex for AI,

00:02:43.505 --> 00:02:55.345
a lot of those just 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 Cloud Opus 4.6 implementation

00:02:54.840 --> 00:03:01.240
is the first one that feels production ready. Here's what they got right. First, automatic orchestration.

00:03:01.240 --> 00:03:05.000
You don't have to manually spawn these agents. Claude figures out,

00:03:05.320 --> 00:03:10.875
on its own, what agents are needed based on your task. Second, intelligent coordination.

00:03:10.955 --> 00:03:13.755
The agents don't just run independently,

00:03:13.835 --> 00:03:16.875
they share context and communicate naturally.

00:03:16.875 --> 00:03:17.515
Third,

00:03:17.755 --> 00:03:19.435
built in specializations.

00:03:19.435 --> 00:03:22.795
Cloud has preconfigured agent types optimized for different tasks,

00:03:23.420 --> 00:03:24.220
research,

00:03:24.300 --> 00:03:26.140
coding, writing, analysis,

00:03:26.140 --> 00:03:26.860
QA.

00:03:26.940 --> 00:04:09.345
And fourth, Error handling. If one agent gets stuck or produces bad output, other agents 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. 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 actually set this up and use a Tenreal 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

00:04:09.345 --> 00:04:18.865
access that you can get with their pre subscriptions. As you can see, you have an option of a Pro plan and a Max plan. In the demo we're gonna show today, the Pro plan is sufficient

00:04:19.265 --> 00:04:26.030
and it should get you by for two or three tasks per day even using this rather powerful agents mode. However,

00:04:26.350 --> 00:04:53.010
for professional use, we would recommend to use the max plan and that would cost a 100 or 200 if you want even more credits. While the max plans are more expensive, they can be definitely worth it because for many people, 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 gonna go through that step. However, agent teams is an experimental feature, and it is not enabled by default for everyone.

00:04:53.250 --> 00:05:07.655
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 into the file. Let's do that directly in the terminal. You would need to go to your

00:05:08.375 --> 00:05:09.175
cloud

00:05:09.255 --> 00:05:10.695
configuration folder,

00:05:12.295 --> 00:05:14.295
open the settings JSON file,

00:05:14.615 --> 00:05:36.245
and add the following lines. I have already them added to my configuration, 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 TMux 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,

00:05:36.485 --> 00:05:39.605
which is every agent in the same single conversation,

00:05:39.685 --> 00:05:50.560
more or less. It is possible to switch between them in your terminal, 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 mux.

00:05:55.600 --> 00:06:00.320
Alright. And this might take a while. And here we go. We have our t mux installed.

00:06:00.765 --> 00:06:04.045
Let's enter a new TMUX session and

00:06:04.205 --> 00:06:10.765
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

00:06:10.845 --> 00:06:11.805
mentoring.

00:06:11.805 --> 00:06:15.960
So in our case, that is the video demo.

00:06:17.960 --> 00:06:19.480
Now let's launch

00:06:19.720 --> 00:06:28.905
Cloud Code. We also have a prompt already prepared for this demo, so we're not going to go into detail from engineering techniques. But as long as you provide

00:06:29.305 --> 00:06:30.425
a clear task

00:06:30.825 --> 00:06:43.950
and 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 where you're trying to work with agent teams is to specify

00:06:44.030 --> 00:06:47.870
each individual team member you want to spawn. It isn't necessary.

00:06:47.870 --> 00:06:50.190
You could just tell the model to orchestrate

00:06:50.190 --> 00:06:59.175
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,

00:06:59.255 --> 00:07:00.215
a copywriter,

00:07:00.215 --> 00:07:04.695
a visual concept agent, and a reviewer for quality control. Alright. So

00:07:05.175 --> 00:07:09.560
let's get into it. This might take a while, and here comes another recommendation.

00:07:09.560 --> 00:07:17.000
Do not try to run agent teams for simple tasks. For simple tasks, we will still recommend to use a single AI instance

00:07:17.400 --> 00:07:23.755
or to use sub agents for very simple flows where you just have, let's say, maybe a writer and a reviewer.

00:07:24.075 --> 00:07:25.915
When you need more collaboration,

00:07:25.915 --> 00:07:29.275
then we would recommend to go for agent teams. We can already see that

00:07:29.595 --> 00:07:40.510
the model is preparing a plan, and soon enough, we should see how it spawns a couple of team members to help it out. Alright. Here's the beauty of TMax. We already see individual

00:07:40.830 --> 00:07:41.710
team members

00:07:42.030 --> 00:07:52.775
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

00:07:53.255 --> 00:08:17.715
sub agent 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 course correct if they're going the wrong way, or even provide an additional task we have not provided in our original prompt. So the strategist agent has already worked and prepared a plan, and it has delegated its first task to the copywriter.

00:08:17.715 --> 00:08:24.675
And now, the copywriter does not have the permission to interact with our file system and it has asked for permission directly

00:08:24.835 --> 00:08:27.235
through the main lead agent.

00:08:27.795 --> 00:08:29.155
So we could

00:08:29.635 --> 00:08:35.710
do the permission. Alright. I see the copywriter has finished its first task and now the visual designer

00:08:36.590 --> 00:08:39.230
has started working on on its own assignment.

00:08:39.390 --> 00:08:42.350
So to copy done, start visual concepts.

00:08:42.510 --> 00:08:43.150
Okay.

00:08:43.470 --> 00:09:03.650
So tasks with agent teams take a while, so we have left the team to work on the task. Let's check back with them. As we can see, the copywriter has already finished with its task and now the visual content strategy agent is creating a document. Oh, it's already created directly. A new doc right here. Again, asked for permission.

00:09:04.050 --> 00:09:04.530
Though,

00:09:04.930 --> 00:09:12.130
you can also start Claude Claude code with an additional flag which would allow you to just give permissions to all

00:09:12.530 --> 00:09:17.075
team members automatically if that's what you prefer. Here, we're working conservatively,

00:09:17.235 --> 00:09:34.080
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 has found and what types of edits it's doing.

00:09:34.400 --> 00:09:35.120
So

00:09:35.600 --> 00:09:42.160
it is using the diff style, you know, what kind of line it is changing. We can even investigate and say

00:09:43.115 --> 00:09:46.475
that maybe this agent should focus on something more

00:09:47.835 --> 00:09:49.035
specific. Alright?

00:09:49.355 --> 00:10:04.040
So TMax paints have already closed, so that means that agents have finished with 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

00:10:04.440 --> 00:10:06.760
improve. So what we could do now,

00:10:07.240 --> 00:10:32.210
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 all statistics and citations.

00:10:32.450 --> 00:10:40.130
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,

00:10:40.130 --> 00:10:49.095
a 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 last iteration,

00:10:49.255 --> 00:11:04.030
and it also has decided to bring in two new agents, which we didn't even explicitly specify on our prompt. So as you can see, quite often, you can get away with broad prompts. Now all four agents are working in parallel.

00:11:04.190 --> 00:11:21.605
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 copywriter has tightened the Wednesday reel to be thirty to thirty five seconds,

00:11:21.765 --> 00:11:44.345
and it also improved the call to action. At the same time, we see that there have been some placeholders in our content and and a copywriter has filled them in. Also, the copy editor is working on that on tightening up the Wednesday reel to be thirty to thirty five 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

00:11:44.585 --> 00:11:45.305
material,

00:11:45.705 --> 00:11:52.185
and it has replaced them with more factually accurate ones it has found online. At the moment, out of our four teammates,

00:11:52.345 --> 00:12:02.770
three of them have already completed their tasks. We're just waiting for the researcher to wrap up its task. The researcher has also prepared a sources document where it lists all the references

00:12:03.410 --> 00:12:22.555
for the facts and the statistics it has updated in our document. Alright. 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. Let's jump into that folder and try to review its work.

00:12:22.795 --> 00:12:36.220
So, you can see there are quite a few files, and I will go to the post it has recommended for Monday through Wednesday. Okay. So for Monday, it recommended a LinkedIn post at Twitter or XPost and

00:12:36.300 --> 00:12:39.580
also Instagram caption. We can see that the post is already

00:12:39.660 --> 00:12:41.505
well structured. It seemingly

00:12:42.145 --> 00:12:50.785
we need to double check this and because this is still to some degree a draft. And as we can see, all these posts match the platform requirements.

00:12:50.945 --> 00:12:52.225
So for LinkedIn,

00:12:52.385 --> 00:12:58.380
it has more of that LinkedIn style with a bullet list, with more metrics, more styling.

00:12:58.380 --> 00:13:02.860
Meanwhile, that Twitter post is short with a couple of relevant hashtags

00:13:03.020 --> 00:13:19.875
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. Alright. Also, the model has provided an image concept and a video idea, a thirty second video. So these were not generated.

00:13:19.955 --> 00:13:24.930
You would need to either shoot these visuals yourself or use an image generation model,

00:13:25.170 --> 00:13:30.770
something like Nano Banana Pro, GPT image 1.5, and for videos, you could use Vio 3.1

00:13:30.770 --> 00:13:40.205
to create these sorts of visuals. It has put in a lot of work, even provided a color scheme for the image concept and even the specific format.

00:13:40.445 --> 00:13:41.405
So for

00:13:41.725 --> 00:13:46.685
Instagram, it recommends a square image with a very specific resolution, and for LinkedIn,

00:13:46.685 --> 00:13:50.525
it recommends a banner. And it has provided very

00:13:51.310 --> 00:13:55.070
similar structure for upcoming days. So for Tuesday and

00:13:55.710 --> 00:14:03.710
for Wednesday. For Tuesday, I see the video ID is a bit different. So it's also also forty five seconds. And for Wednesday,

00:14:04.055 --> 00:14:05.975
it has a longer video

00:14:06.375 --> 00:14:07.095
with

00:14:07.255 --> 00:14:48.825
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 mesh every platform that we need. So this is the power of agent teams. In just fifteen 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 saves me hours in production, and all of it was done with a single 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.

00:14:49.720 --> 00:14:56.600
Let's check how much the single generation cost us. So if I would jump back into Cloudera code and I would write

00:14:57.320 --> 00:14:58.840
slash usage,

00:14:59.880 --> 00:15:03.205
we would see that I have spent around

00:15:03.605 --> 00:15:04.405
7

00:15:04.645 --> 00:15:08.405
close to $8 in usage just for this single task.

00:15:08.725 --> 00:15:13.685
If you would want to know how that what that means for pro and max usage,

00:15:14.140 --> 00:15:37.445
that would be around 50 percent of your single session usage for pro. For max, you would probably be able to fit about eight or 10 tasks in five hours. So to avoid unnecessary cost 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

00:15:43.120 --> 00:15:56.615
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,

00:15:56.615 --> 00:16:07.095
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%

00:16:07.095 --> 00:16:32.525
of the time. In general, I keep single agent clouds for quick tasks 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 stakes 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,

00:16:32.765 --> 00:16:39.725
kind of like working with a new colleague. Three, review everything. The agents are good, but they're not infallible.

00:16:40.010 --> 00:16:51.930
The classic AI rule to double checks everything still applies in this case. Four, keep an eye on your API or subscription usage in the dashboard. Set spending alerts if you're worried about costs. So clearly,

00:16:52.090 --> 00:16:58.135
with this new update, Biotropic, we're shifting from AI as a tool to AI as a workforce.

00:16:58.215 --> 00:17:04.215
Agent teams are the first step toward AI organizations that can handle complex projects autonomously.

00:17:04.215 --> 00:17:04.935
Alright.

00:17:05.335 --> 00:17:08.295
So that's agent teams in Cloud Opus 4.6.

00:17:08.295 --> 00:17:15.480
The concept is simple. Specialized AIs working together beat one generalist AI. The implementation is sophisticated.

00:17:15.560 --> 00:17:17.160
Cloud handles orchestration,

00:17:17.160 --> 00:17:19.880
coordination, and error handling automatically.

00:17:19.880 --> 00:17:28.105
And the result? For complex tasks, this will be a game changer. If this works at scale, it changes what's possible with AI completely.

00:17:28.105 --> 00:17:51.155
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 for? What complex projects would you hand off to a team of specialized AIs? 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's AI courses.

00:17:51.155 --> 00:18:00.755
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 ahead in 2026

00:18:00.755 --> 00:18:02.115
and become irreplaceable.

00:18:02.115 --> 00:18:06.220
Click here to see it. That's it from me. Catch you in the next one.