15:18Alex Finn · Tutorial
6 Hermes Agent use cases I promise will change your life
A 15-minute tutorial that converts Hermes Agent from a chatbot into a structured daily employee — six concrete workflows, one compounding system.
May 22ndThe argument in one line.
Specialized agents working in parallel and checking each other output consistently outperform a single generalist AI on multi-component tasks -- and Claude Opus 4.6 is the first implementation that ships this without manual orchestration code.
Read if. Skip if.
READ IF YOU ARE…
- You use Claude Code daily and want to know when to graduate from single-agent to multi-agent workflows.
- You are building content pipelines, research workflows, or QA-heavy projects where a single context window is not enough.
- You want to understand the real token cost of agent teams before committing to Pro vs Max plans.
- You have experimented with subagents but want the full team model where agents can talk to each other directly.
SKIP IF…
- You are looking for a basic Claude prompt guide -- this assumes Claude Code is already installed and running.
- Your tasks are simple and quick; single-agent is always faster and cheaper for those.
The full version, fast.
Claude Opus 4.6 Agent Teams spawn specialized, coordinated AI agents from a single prompt with no manual orchestration code required. The key architectural difference from subagents is that teammates share a task list and can request information from each other directly. A live demo produces a full week of LinkedIn, X, and Instagram content in roughly 15 minutes using four agents in parallel inside tmux, with a second self-correction loop triggered by the reviewer agent flagging five issues. The real cost is around 7-8 dollars per complex run on Pro, roughly 50% of a session. The practical rule: use agent teams when the task has multiple distinct components, quality matters more than speed, and the project would otherwise overflow a single context window.
Members feature
Chat with this breakdown.
Modern Creator members can chat with any breakdown — ask for the hook, quote a framework, find the exact transcript moment. Unlocks at T2: refer 3 friends + add your own API key.
Create a free account →Where the time goes.
00:00 – 00:38
01 · Why Agent Teams Matter
Hook and promise. Agent teams were predicted for 2026 but shipped earlier; video covers what they are, why they matter, and how to start.
00:39 – 00:52
02 · Agent Teams vs Subagents vs Single Claude
Side-by-side diagram: subagents only report back to the main agent; teammates share a task list and communicate laterally.
00:53 – 01:21
03 · What Agent Teams Actually Are
Concrete example with role assignments running in parallel where possible, in sequence where needed.
01:22 – 02:43
04 · When Multi-Agent Beats One Generalist AI
Four capabilities unlocked: long-horizon projects, complex workflows, better quality via dedicated review, faster execution via parallelism.
02:44 – 04:04
05 · Production Readiness in Claude Opus 4.6
Four things Anthropic got right: automatic orchestration, intelligent coordination, built-in specializations, error handling.
04:05 – 04:39
06 · Plans and Pricing
Pro plan sufficient for 2-3 tasks per day. Max plan recommended for professional use.
04:40 – 05:20
07 · Enabling Agent Teams
Experimental feature requiring a specific flag in ~/.claude/settings.json.
05:21 – 06:00
08 · Setting Up tmux
tmux lets each agent run in its own pane for observation and mid-run intervention.
06:01 – 09:49
09 · Live Demo Round 1
Single prompt spawns four agents: strategist, copywriter, visual concept agent, reviewer. Reviewer flags 5 action items.
09:50 – 12:17
10 · Live Demo Round 2
Re-prompting with reviewer flags triggers self-spawned researcher and copy editor. Four agents work in parallel.
12:18 – 14:44
11 · Reviewing the Output
Platform-specific posts with LinkedIn bullets, Twitter short form, Instagram hashtags, image concept specs, and video briefs.
14:45 – 15:23
12 · Token Cost Breakdown
/usage shows roughly 7.76 dollars for the full run. On Pro this is about 50% of a session.
15:24 – 16:16
13 · When to Use Agent Teams vs Single Agent
Decision framework: teams for multi-component quality-critical tasks; single for focused speed-critical budget tasks.
16:17 – 18:13
14 · Safety Tips and Outro
Four tips: start low-stakes, specific brief, review everything, monitor usage. Closing thesis: AI shifting from tool to workforce.
Lines worth screenshotting.
- Specialized agents working in parallel outperform a single generalist AI on multi-component tasks -- not because the AI is smarter, but because it is organized.
- The key difference between subagents and agent teams is lateral communication: teammates can request data from each other directly instead of routing everything through the lead.
- A supervisor agent prevents duplication and coordinates sequencing automatically -- you write a prompt describing roles and deliverables, not orchestration logic.
- Claude Opus 4.6 is the first agent-team implementation described as production-ready: automatic orchestration, built-in specializations, and error correction without manual intervention.
- On Claude Pro, a single full agent-team run costs roughly 50% of your session allowance -- budget one or two complex runs per session, not ten.
- The review loop is the highest-leverage step: prompting the team lead with reviewer-flagged issues triggers a second parallel pass that self-corrects without restarting from scratch.
- Specifying agent roles explicitly in the initial prompt produces more consistent results than letting the model decide roles on its own.
- The system will spawn agents you did not specify if it determines they are needed -- in the demo, a researcher and copy editor appeared unprompted in round two.
- Use tmux to observe and interrupt individual agents mid-run; without it you lose the ability to course-correct before the whole batch finishes.
- For tasks that overflow a single context window -- multi-platform content, large codebases, research-plus-writing -- agent teams are the practical solution, not a novelty.
- Agent teams make sense when multiple distinct components exist, quality matters more than speed, and different expertise is needed per section.
- Single-agent Claude is the right call when the task is focused, speed matters more than sophistication, or the budget cannot absorb a high-cost run.
Agent teams are not always the right tool -- here is the actual decision rule.
WHAT TO LEARN
Spawning multiple specialized AI agents solves context-window limits and quality gaps, but it costs significantly more per task than a single agent -- so the right call depends on task structure, not novelty.
- Agent teams beat single-agent Claude when the task has multiple distinct components that benefit from specialization -- not just because the task feels complex.
- Agents share a task list and can request information from each other directly; this lateral communication is the architectural difference from subagents.
- A supervisor agent coordinates sequencing and prevents duplication automatically -- you write a prompt describing roles and deliverables, not orchestration logic.
- On Claude Pro, a single full agent-team run costs roughly 50% of your session allowance; budget one or two complex tasks per session, not ten.
- Use tmux to observe and interrupt individual agents mid-run; without it you lose the ability to course-correct before the whole batch finishes.
- Specifying agent roles in your initial prompt produces more consistent results than letting the model decide roles entirely on its own.
- The review loop is the highest-leverage step: prompting the team lead with reviewer-flagged issues triggers a second parallel pass that self-corrects without restarting.
- For tasks that would overflow a single context window -- multi-platform content, large codebases, research-plus-writing -- agent teams are the practical solution, not a novelty.
Terms worth knowing.
- Agent Teams
- A Claude Code feature where multiple specialized AI agents are automatically spawned, coordinated, and given a shared task list to work a complex project in parallel and in sequence.
- Subagents
- An older Claude Code pattern where a main agent spawns child agents that work independently and report results back to the parent -- no lateral communication between agents.
- Supervisor agent
- The orchestrating agent in a team that manages task assignment, sequencing, and prevents duplication -- created automatically, not manually configured.
- tmux
- A terminal multiplexer that splits one terminal window into multiple panes, used here to observe each agent working simultaneously and interact with individual teammates mid-run.
- settings.json
- The Claude Code configuration file where the experimental agent-teams flag must be manually added to enable the feature.
- Lateral communication
- The ability of agent teammates to request information directly from each other rather than routing through the lead -- the architectural feature that distinguishes teams from subagents.
Things they pointed at.
13:20toolNano Banana Pro
13:22toolGPT Image 1.5
13:25toolVio 3.1
Lines you could clip.
01:47
“Instead of one super brain, you get a coordinated organization.”
07:06
“In just fifteen minutes, we got a good first draft... it still saves me hours in production, and all of it was done with a single prompt.”
10:31
“I have spent around 7 close to 8 dollars in usage just for this single task.”
16:57
“We are shifting from AI as a tool to AI as a workforce.”
Word for word.
metaphor
00:00Cloud 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.
00:16Everyone predicted this as a 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 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.
00:40So 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.
00:55You give a complex task to the system. Let's say, build me a marketing campaign.
01:00And instead of one AI trying to do everything, the system spawns multiple agents, teammates. A research agent gathers data about your audience.
01:09A strategy agent plans the campaign structure, and a creative agent writes the copy. Also, you could have a review agent, which checks everything for quality.
01:18They 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.
01:26It'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, which means complex projects finish way faster.
01:49You 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.
02:01Just look at all the benchmark graphs on each LLM release. Agent teams live that. .
02:10So 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.
02:21Complex workflows, multi step processes with research, analysis, creation, and review can happen in one coordinated flow.
02:29Better quality. Having a dedicated review agent catches mistakes that a single AI would miss. Faster execution.
02:36Parallel work means things that took hours can finish in minutes. Basically, the tasks that were too complex for AI, a lot of those just became possible.
02:45To 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 is the first one that feels production ready.
02:57Here's what they got right. First, automatic orchestration. You don't have to manually spawn these agents.
03:03Claude figures out, on its own, what agents are needed based on your task. Second, intelligent coordination.
03:10The agents don't just run independently, they share context and communicate naturally. Third, built in specializations.
03:19Cloud has preconfigured agent types optimized for different tasks, research, coding, writing, analysis, QA.
03:26And 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.
03:36In 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.
03:52It'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 access that you can get with their pre subscriptions.
04:11As 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 and it should get you by for two or three tasks per day even using this rather powerful agents mode.
04:25However, 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.
04:41So 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. So you would need to add an additional configuration to your settings JSON file.
04:57If 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 cloud configuration folder, open the settings JSON file, and add the following lines.
05:16I 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.
05:24We 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, which is every agent in the same single conversation, more or less.
05:40It 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.
05:55Alright. And this might take a while. And here we go.
05:58We have our t mux installed. Let's enter a new TMUX session and jump into a project folder.
06:05So for any sort of thing you're working on, we would recommend to have a folder and for Cloud Code is mentoring. So in our case, that is the video demo.
06:17Now let's launch Cloud Code. We also have a prompt already prepared for this demo, so we're not going to go into detail from engineering techniques.
06:26But as long as you provide a clear task and what are your deliverables you want, your prompt really doesn't have to be much more complex than that.
06:36One additional thing we would recommend to add for a prompt where you're trying to work with agent teams is to specify each individual team member you want to spawn. It isn't necessary.
06:47You 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.
06:56In our case, that is a strategist, a copywriter, a visual concept agent, and a reviewer for quality control.
07:03Alright. So let's get into it.
07:06This might take a while, and here comes another recommendation. Do not try to run agent teams for simple tasks. For simple tasks, we will still recommend to use a single AI instance or to use sub agents for very simple flows where you just have, let's say, maybe a writer and a reviewer.
07:24When you need more collaboration, then we would 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.
07:36Alright. Here's the beauty of TMax. We already see individual team members on panels on our right.
07:44And we can even see what each member is trying to do. So this is the key difference between agent teams and sub agent flows where you really have no way to interact or even sometimes observe what individual sub agents are doing.
08:01Here, 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. And now, the copywriter does not have the permission to interact with our file system and it has asked for permission directly through the main lead agent.
08:27So we could do the permission. Alright.
08:30I see the copywriter has finished its first task and now the visual designer has started working on on its own assignment. So to copy done, start visual concepts.
08:42Okay. 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.
08:50As 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.
09:01Again, asked for permission. Though, you can also start Claude Claude code with an additional flag which would allow you to just give permissions to all team members automatically if that's what you prefer.
09:14Here, 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.
09:24Okay. 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. So it is using the diff style, you know, what kind of line it is changing.
09:39We can even investigate and say that maybe this agent should focus on something more specific.
09:48Alright? 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 improve.
10:05So 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.
10:25It is adding new items to the to do list. So first, it will need to source and verify all statistics and 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, a copy editor, and a copywriter.
10:42So here we can see that it has used two of the agents that it has previously seen in our last iteration, 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.
11:00Now all four agents are working in parallel. 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, and it also improved the call to action.
11:23At 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.
11:38We already see that the researcher has flagged up some of the metrics that we have cited in our material, and it has replaced them with more factually accurate ones it has found online.
11:50At the moment, out of our four teammates, three of them have already completed their tasks. We're just waiting for the researcher to wrap up its task.
11:57The 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. Alright.
12:08I'm seeing that that task is being wrapped up. Team cleaned up. All revisions are done.
12:13Your 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. So, you can see there are quite a few files, and I will go to the post it has recommended for Monday through Wednesday.
12:30Okay. So for Monday, it recommended a LinkedIn post at Twitter or XPost and also Instagram caption.
12:37We 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.
12:46And 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.
12:58Meanwhile, that Twitter post is short with a couple of relevant hashtags 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.
13:11Alright. Also, the model has provided an image concept and a video idea, a thirty second video. So these were not generated.
13:19You would need to either shoot these visuals yourself or use an image generation model, something like Nano Banana Pro, GPT image 1.5, and for videos, you could use Vio 3.1 to create these sorts of visuals.
13:32It has put in a lot of work, even provided a color scheme for the image concept and even the specific format. So for Instagram, it recommends a square image with a very specific resolution, and for LinkedIn, it recommends a banner.
13:48And it has provided very similar structure for upcoming days. So for Tuesday and for Wednesday.
13:56For Tuesday, I see the video ID is a bit different. So it's also also forty five seconds. And for Wednesday, it has a longer video with very detailed breakdown of what should be in the video nearly second by second.
14:11If 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.
14:38If 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. Let's check how much the single generation cost us.
14:52So if I would jump back into Cloudera code and I would write slash usage, we would see that I have spent around 7 close to $8 in usage just for this single task.
15:08If you would want to know how that what that means for pro and max usage, 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.
15:24So 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 Quality matters more than speed.
15:45You 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.
16:00For that social media content, agent teams made sense. If I just needed one post caption, a single AI 100% of the time.
16:07In 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.
16:20Start 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.
16:28Include brand voice, target audience, goals, any constraints, kind of like working with a new colleague. Three, review everything.
16:37The agents are good, but they're not infallible. 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.
16:48Set spending alerts if you're worried about costs. So clearly, with this new update, Biotropic, we're .
16:58Agent teams are the first step toward AI organizations that can handle complex projects autonomously. Alright. So that's agent teams in Cloud Opus 4.6.
17:08The concept is simple. Specialized AIs working together beat one generalist AI. The implementation is sophisticated.
17:15Cloud handles orchestration, coordination, and error handling automatically. And the result?
17:20For complex tasks, this will be a game changer. 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.
17:34And leave a comment. What would you use agent teams for? What complex projects would you hand off to a team of specialized AIs?
17:41If 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. 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 and become irreplaceable.
18:02Click here to see it. That's it from me. Catch you in the next one.
The Hook
The bait, then the rug-pull.
Everyone predicted multi-agent AI as a 2026 trend. No one expected a production-ready version this early -- or one that requires nothing more than a settings.json flag and a well-structured prompt to run.
Named ideas worth stealing.
00:39model
Agent Teams vs Subagents vs Single Claude
Three-tier architecture. Single: one context, one output. Subagents: main spawns children that report back. Teams: teammates share task list and communicate laterally.
Steal forAny pitch explaining why multi-agent architectures outperform single models
03:01list
Four Production-Ready Pillars
- Automatic orchestration
- Intelligent coordination
- Built-in specializations
- Error handling
What Anthropic got right in Opus 4.6 that earlier multi-agent experiments lacked.
Steal forEvaluating any new multi-agent platform
15:24model
When to Use Agent Teams Decision Matrix
Use teams: multiple distinct components, quality over speed, need specialization, want built-in QA. Use single: focused task, speed over sophistication, budget constrained.
Steal forAny decision framework for AI tool selection
16:17list
Four Safety Tips Before First Use
- Start with a low-stakes project
- Be very specific in your initial brief
- Review everything
- Monitor API usage and set spending alerts
Practical guard rails for first-time agent team runs.
Steal forOnboarding checklist for any AI automation deployment
How they asked for the click.
17:48subscribe
“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.”
Soft subscribe ask followed by comment prompt and Turing College course CTA. Clean and non-pushy.
Visual structure at a glance.
