**Julian Goldie** (0:00)
Today we have a brand new update from Hermes, which is the Hermes Agent Profile Builder. So you can now build multiple profiles with identities, names, descriptions, models, built-in and optional skills, and also MCP servers in one single flow using the new profile builder in the Hermes Agent Dashboard. Now, if you're not familiar with this, I'll break it down exactly how to do it. And if you've never seen this before, it's super powerful for building out teams of AI agents that work together and get stuff done. Let me show you an example of how this works in practice. So if we go over to the Kanban board inside our Agent OS system, we can actually switch between Kanban boards and we have autonomous teams of AI agents working together with this profile builder section. So what this means essentially is that we have loads of different AI agent profiles with Hermes, these are all individual profiles. And then, for example, we filter to this one, we can see what is done on our Kanban board, which is pretty amazing. So you can build out full teams of AI agents that work together with separate profiles, separate skills. You might say, why would you do that? Well, because number one, it's easy to get agents to collaborate. And number two, you can give them separate specialty, separate sets of expertise so you can have them working together. Now, you might be wondering, okay, how do you do this? How do you get it working together? So what you want to do is go to Hermes, go to your dashboard inside Manage here. And then if you go over to the Profile section, what you can see is that we can select between different profiles, which means that we can edit these, we can change the model description, the sole MD, and we can copy the CLI command as well to actually get them running, right? So if I go to my CLI here, inside the terminal, I can plug that in and we can set that profile up. Now, if we want to add a new one, we can click on Create. We set up a name, we set up a description, we set up the model from the individual AI agent, and then we can also clone the config from a different Hermes agent profile, and we can also bring in and import memory, session, skills, and state, or we can remove those and just set up a totally different profile for each agent, which is what I recommend. Now, you might be wondering, okay, what can you build with that? So let me show you an example of how this works in practice. So essentially, we have something I called the Goldie SEO Assembly line, just as a random example. And the way that we deployed and created and optimized this blog post right here is with this new setup. So we had four AI agents, four AI employees as Hermes using the new profile builder. And so in just a couple of minutes, we can get a keyword researcher set up, an outline architect. If you don't know what any of these do, don't worry about it. The main point here is that you have separate AI agent profiles working together as a team. And then you can actually add them to a Kanban board so that they can build and automate whatever you want. So if we go to the Kanban board here, we can use the agent profiles that we have set up. And that might be something that you're interested in, coordinating the team of AI agents with separate specialties, and then having them work on a task together in parallel at the same time using the Kanban board. And so the thing that I like about all of this setup is that you can have multiple agents, multiple different profiles. I mean, if we go over to the chat section here with Hermes agent, we can select between all these different profiles that we have, we can see our conversation history between them and we can have separate conversations. So if it's like, right, I need to do keyword research, well, I might go and speak to the keyword research over here. If I just need to go with the default, which is pretty good at everything, then I can go with this, right? And you see how we can just switch and swap and change between the profiles depending on the expertise that we actually need for each one of these. And so that's a powerful thing about all of this. And so if we go back to the Kanban board here, you might think, well, what can you actually do with this in reality? What is the actual use case? So let me show you an example.
7 more minutes of transcript below
Try it now — copy, paste, done:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090
Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000772289780