Higgsfield Just Launched their AI Agent (Supercomputer)

Added: 2026-05-15

[00:00:00]It's a big day for the creative AI space because Higgsfield just launched their agentic platform that's called Supercomputer and it might just change the way we use these creative AI models forever once they iron out a few bugs.

[00:00:11]In this video, I'll show you exactly what Higgsfield Supercomputer is, how to use it, and whether it's worth bringing into your stack. Let's [music] dive in.

[00:00:21]So, a few hours ago, Higgsfield just launched and announced this Supercomputer tool. And what they're saying here is that it is the first-ever cloud-native self-learning AI agent for end-to-end task execution. That's a lot of technical words, but don't worry because we'll dive into that tool in just a bit. But, essentially, if you've been using a lot of agentic platforms like CloudCode, CodeX, or even Hermes, where you can see here, it is powered by an enhanced Hermes agent because this is open source, so they probably used that as a sort of base to build out Supercomputer. Basically, what they did is take the scaffold of Hermes as an agentic platform and enhance that or tweak that using Higgsfield's platform as well as all the skills and best practices when it comes to prompting the image and video generation models to produce this Supercomputer product that can tap into these image and video generative models, which is the area that they specialize in. So, if you go to this URL, higgsfield.ai/supercomputer, you'll be able to access it as well. And you can see here, they have a pretty similar interface to other chat apps that you may already be used to. What's great is they actually let you choose the models in here. So, you have the options for GPT 5.5 Pro, Sonnet, and Opus 4.6. I guess with the standard plan, you don't get Opus 4.7. Or you can also have the brain of this Supercomputer to be Gemini 3.1 Pro. So, basically, all the frontier models from all the frontier labs. Also as good is, if you're not sure where to start, they have a couple of sample prompts in here that basically give you an idea of what Higgsfield Supercomputer would be good to use in. And just to show you how easy it is to use it, I'll just send it a very simple command to make 10 image ads for this product. And that product is this electric kettle by Fellow. So without giving it other information, just a link to our website here. And I also purposefully gave it a bit more of a complex shaped product just so we can see how capable it is. You can see there's information around the description here, a few photo references, but we're actually not going to give Hicksfield all of that context.

[00:02:15]Instead, we'll just give it this one link and fire it off. And what's great about this supercomputer harness by Hicksfield is that they seem to have preloaded the skills that they use internally in order to expand upon this simple command that we have. So you can see here that it started by analyzing the product page, loading the relevant skill for creating product images, which are these ones. It read the web page for us, and then it loaded this ad creative pack reference. So they seem to have pretty much supercharged this whole harness, this whole tool with all of the skills, all of the sort of best practice prompts that they have with regard to these creatives because they have a lot of information and data about that, obviously. And then you can see here, because I chose Opus 4.6, it is basically thinking through what would be the right hooks, what would be the right scenes, and also defining a variety of different aspect ratios in there. And now it gave us these 10 images. And if you click on the gallery here, they actually have a nice gallery view in here where you can zoom out and zoom in just to view which ones are looking good to you. And from here, you can either download them to your computer, add them to your projects, which are basically like folders or collections in your Hicksfield account. But you can see these are quite good, right? But obviously you can be more specific if you want a particular style. But if you just need quick ideas, you can just have Hicksfield batch create those for you.

[00:03:37]And because of those skills that they have loaded internally, it gives you a lot of really good options just from one shot. And then another thing that I tried is, let's say we like this one, you can actually add it to composer, which just puts it in your chat, so that's what I did. And then I said to animate this with Kling 3.0, please. And by the way, if you're interested in going from just using AI to getting paid for it, then check out the Robo Nuggets community down in the description. We've got founders in there who landed their first client in weeks, live build sessions where we create this stuff together, and the actual templates behind what I just showed in this video.

[00:04:08]The community is also the reason these lessons get made, so see that below if that's for you. It did tell me that it is generating, so it was generating for a while, but I think with a lot of these generative models, they do sometimes feel which is a, unfortunately, a pretty common experience, I think, for a lot of the people who are working with these models. But the good news is, since you are operating with, let's say, Opus 4.6 or GPT 5.5, a smart model under the hood, you can actually just give it more commands in order to get the output you want. So, I'll just say here, "Hey, can you try that again? Please animate it with Kling 3.0. If it fails, try again up to maybe three times up until we get an output." So, if you provide it a prompt like that, then it will just think through that command, and it will think through that prompt in order to give you exactly what you want. And by the way, the other thing that I think they actually did a good call in here is that it gives you this checkpoint on the prompt that it's about to send, which is this one. It gives you a view of the model, it gives you a view of the aspect ratio, the quality or the resolution, the duration, if there is a sound on or off, and if you want the prompt enhanced or not. That's good, so you can also toggle through these and change them before you generate the video. And you can see here, very transparent on the credits, and they auto adjust depending on the selections that you choose. And that is just a good checkpoint, so that, let's say, if you put a typo in, and instead of generating one video, you generate 10 videos, it's not just going to drain your credits without you approving it. So, it says here, "Unfortunately, attempt one with Kling 3.0 failed." And then it asks us to approve it again. So, maybe Kling 3.0 is down. Let's actually cancel that, and I'll just say, you see that 2.0 instead.

[00:05:49]So since this is pretty new, maybe the connection to cling to their API under the hood might just be failing. So let's see if seedance will actually be better.

[00:05:59]So there you go. Seedance 2.0, 9 by 16.

[00:06:01]See. Let's do 480p, 5 seconds and then that will charge us 15 credits. And by the way, while waiting for that generation, I think one key thing that Hicksfield probably needs to improve in this product is that for some reason their own product doesn't have an idea of why this particular generation failed. Usually, if they're tapping into these generative AI models, they provide some sort of information on whether it was rejected based on content moderation or maybe there's issues on input images, but right now it seems like supercomputer does not have that ability yet. All right, so with seedance that finally passed and if we open this, you can see it generated that video for us.

[00:06:43]And actually to test this out, now I'll make a UGC with seedance 2.0. And what I'm trying to do here is to just see with really simple commands like this if it's able to reason through and actually create good prompts for us in order to create good content. So that's interesting, it has that sort of ask user question tooling from other harnesses like Claude code also built in here. So it asks me what product should a UGC video feature, so the kettle. What type of UGC video do I have in mind? Let's do a talking head review. Let's just continue. There you go. What it does is it preloads the UGC workflow that it probably has under the hood. And again, it asks me how long should a UGC video be? Let's do 10 seconds. So see, I would have preferred if it just asked me all of those questions in one go, but let's see what we will get. And once those questions are now clear, it now tells me that it will generate a 10 second UGC talking head review of the kettle. And again, it will invoke this skill. So it seems to have its best practices built in because if you want to create a UGC, first you want to create an image, a starting frame of an image before you animate that via video. So, it seems to have understood that. Probably based on whatever system prompts that the Higgsfield guys have trained this on, it analyzed our product. And earlier I just approved this prompt that they gave us around generating our character with their Soul.0 model. So, if I look at the gallery here, tells me that our character is ready. So, this is the character that it generated for us. And again, this is just me approving the prompt that it gave to us here. But uh obviously you can tweak that if in case you want someone else. It gives you a script, a monologue, goes through and generates a storyboard. And it gives me a full view of the prompt that is about to send actually, which is pretty good.

[00:08:28]So, I'll just approve that. It says that it will use GPT image 2 to generate that storyboard. And when that's done, it gave itself a pat on the back, says storyboard board looks great. Three clear narrative beats with the kettle.

[00:08:40]So, this is what it gave. I'm not really sure if I would consider this a storyboard, but uh let's see what it would come up with in the final video.

[00:08:48]Okay, now it's done. So, let's just watch this.

[00:08:55]This kettle pours like a dream. Smooth, clean stream every single time and it looks gorgeous on my counter. So, there's a lot of obvious AI tells there, right? If you were just looking at the quality of each and every frame, it's pretty good. But I think with the sort of kettle being swapped in here and magically appearing on her hand, and the kettle having like a closed handle in there, and when she lifts it up, it is magically duplicating or just appearing from her hand, there's a lot to be desired. So, it's not fully there yet.

[00:09:25]Obviously, we just one-shotted the whole thing and we didn't really give it much guidance on the script. As well as that scream at the start is probably not optimal for this brand. But I think it's interesting what Higgsfield has done here, that basically you just give it like a link to your product, like a website, and then it handles the generation of the character for you. It handles the storyboarding, although the storyboard could be improved, and then it also animates that fully. So, not get 100% there in terms of having it fully automated that it will give you great results every time, especially since a model like Seed ants is actually quite expensive. But I can imagine you can work with this agent in order to make sure that each step, including the script, for example, is optimal and is up to spec with what it is that you need before you generate the whole thing, so that the quality of the output that you get is exactly what you want. Now, even though the tool itself can still probably be optimized by Higgsfield, I think it's interesting that Higgsfield themselves, who are more into the creative side of things, are starting to get into the Anthropic platform space.

[00:10:27]And this actually might have an implication for you, too, because if you think about AI agents now, I mentioned before in an earlier video that they're essentially just three parts. So, you have the AI model within it, which is basically the engine that is driving the whole thing. And earlier you saw we have the choice of Opus, Sonnet. And because it's Higgsfield and they don't really belong to OpenAI or Anthropic, they have that optionality to serve you the GPT-5.5 model, as well as a Gemini 3.1 Pro model, as well. So, to give an example, if you've been using Claude or Claude Code or Claude Co-work, basically what you have in there is an option for AI models like Opus, Sonnet, or Haiku.

[00:11:02]And so, those three really are your only options. For Higgsfield, because they're not really belonging to Anthropic or OpenAI, they have the option to serve you either Opus or maybe GPT-5.5 or even the Gemini models, like you saw earlier.

[00:11:15]So, that's one advantage that they have.

[00:11:17]Now, the harness here, what is that?

[00:11:18]That's basically the set of system prompts and other tooling in code that wrap this model in order to give it custom instructions or custom skills.

[00:11:28]So, for Claude, Claude Code itself is the harness. And for Higgsfield, they seem to be sort of entering this space and launching this supercomputer as their creative harness. So, you can see how different sort of the experience was earlier, where it's optimized with asking you what are the aspect ratios that you want, what's the duration of the videos that you want, and it even came with custom skills so that even if you tell supercomputer a simple command like make me 10 image prompts, it allows you to get good results every time. And that's the harness, which is basically the wrapper, wrapping this engine in order to produce results that is customized for Higgsfield's target audience, which are mostly creatives.

[00:12:06]Now, this third component of an AI agent, which is the context, is also interesting. Because with Cloud Code, usually this context is like a file folder, which is composed of a lot of text and markdown files in your own device. But for Higgsfield, supercomputer, this seems to be taking shape as well. Because if we go back to their supercomputer tooling in here, if I go to connectors, this is pretty much that context component in question, right? So, here if let's say you have brand files over at Google Drive, you seem to be able to connect to Google Drive this way. If you want to connect supercomputer to Telegram, that seems to be available as well. And there's a lot of these, so I'll probably be testing this out for a few days just to see that these actually work as intended, because right from initial launch they seem to be promising quite a lot of connectors in here. So, that's going to be interesting if all of those work. But apart from that, the other thing that is interesting is that they also included this memory piece, which is a clear component of that personal context that we were talking about earlier. And right now there's nothing in my memory, and I can definitely add a memory in here. So, for example, remember that I prefer, let's say, orange and dark mode color schemes in my generations. Let's see if that gets added. And there you go, I needed to refresh it, but you can see that it is here in terms of my preference. And let's say if I want to delete that, there there seem to be a native way to do it. So, that's probably another UI component that they need to fix because if I want to change up a memory, then I want to be able to delete that. In any case, from that screen earlier before I added these tests, it did say that it will continuously and automatically fill up the memory as you work with this agent. But, since this just launched, time will tell if it really works as intended. But, I guess if you put the bugs aside, which right now there seems to be quite a lot since it's so new, you can see what the vision of Higgsfield is here, right? So, there are these tools like Cloud Code and even Codex, which are more general-purpose harnesses. But, with Supercomputer, it seems like Higgsfield's vision is to be the Cloud Code or the more approachable version of an agentic harness like Cloud Code that is suited for creatives. So, should you use Supercomputer or not?

[00:14:12]Well, I think if you already have a subscription to Higgsfield because it draws from the same credit pool anyway, I think it's worth trying out. At least generate a few images in there, test it out if it builds towards your workflows.

[00:14:23]But, if you're not subscribed to Higgsfield, if you're using these image and video generative models using other providers like a Wave Speed or file.ai, which are built in a more pay-as-you-go model, I would stick with that for now.

[00:14:35]However, I do think that Supercomputer, these types of projects, is a good move by Higgsfield overall, and it will probably get more people attuned to working with these agents and the concepts of memory and context and harnesses a bit more. And so, I think that is a good direction that Higgsfield can take. I hope that was useful, and again, I appreciate you guys watching till the end. I'll see you all next time. Thank you.

[00:14:57]>> [music]