The Smartest People Aren't Prompting Claude. They're Harness Engineering

0:00 I spent the last four months studying how the fastest AI builders actually work. And I found something that I wasn't expecting. The people who are actually winning with AI aren't thinking

0:08 about the model. Instead, they're focused on the harness that interacts with AI. So, in this video, I'm going to break down and outline what harness engineering is and how you can make your

0:16 first harness today, which can be broken down into four layers. And at the end, I'll outline what the Carpathy curve is, a concept described by the former head of AI at Tesla, and how it reframed how

0:27 I think about the future. So layer one, the foundation. Why this matters so much. So recently Meta and Mark Zuckerberg released Muse, while SpaceX and Elon released Grockbot. And both

0:37 these tools are harnesses that simplify how you interact with AI. And they've gotten so much traction because of how easy these harnesses make it to use AI for daily tasks. Here's Peter Levelvels,

0:47 a famous entrepreneur, talking about the concept of how important harnesses are in reference to Y Combinator, one of the biggest startup investors on the planet. He said, "I saw this Y Cominator's Batch

0:57 literally only has harness startups and hardware startups. So the proof is in the pudding." So why is the harness so important? Well, in today's world, it's not about who has access to the best

1:06 models. It's about who can shape them to provide the most value for a specific use case. So clearly the smartest people are focusing on this, but should you? The answer is obviously yes. That's why

1:15 I'm making this video. But let's break down in terms of how you actually use AI today. Think about your AI output like an equation. Your AI output is equal to model plus prompt multiplied by the base

1:25 harness. And in practice in your day-to-day, when you use clawed code, which is a base harness, the output that you produce is a combination of the model, call it opus, the prompt, what

1:34 you say to it, and the base harness, which you chose to be clawed code. In plain English, the harness is whatever wraps around the model and the input you provide it to improve the actual output

1:44 you get. and tools like Clawude Code, Muse, Grockpot, they all wrap the AI model to make interacting with it easier. And I'm saying this term wrapper because a lot of people have heard the

1:53 term an AI wrapper. And that's really no different than an AI harness. And the one question you may have is, I like using claw code. I don't want to recreate it. And that's totally fine

2:02 because there's a finer point here. So let's go back to the equation I mentioned. 99% of people like using AI like this, right? That's your model plus prompt multiplied by base harness.

2:11 That's straightforward. But the leaders in the space are thinking about it like this. Its output is equal to model plus prompt multiplied by base hardness plus domain hardness where the domain harness

2:23 is what you can build on top of tools like Claude and Claude code. And anyone watching this video can build their own harness because the actual advantage is deep specific knowledge of a person's

2:33 exact workflow, yours. The most productive people I know have effectively built their own harness, hypers specific to their job and their day-to-day without even thinking about

2:42 it or even calling it that. So, if this domain harness is the one thing you actually own here, the next question is obvious. Where do you even start and where should you focus your energy?

2:52 Which brings us to layer two. Select the domain. At a foundational level, a harness is a way to alter AI's output so it works specific for your situation. So, naturally, you have to pick which

3:01 domain to help it with. And this will naturally lead to two different types of people. They'll be the person that wants the harness that does everything, or they're the type of person that they

3:10 can't figure out what they want to focus on. And for both of these people, the answer is actually the same. And so this pulls from a concept popularized by a McKenzie report where it outlined three

3:18 types of people. There's makers, takers, and shapers. A maker is someone that builds the model itself. That's OpenAI, Anthropic, Google, and almost nobody else should try and do that. That isn't

3:28 you. Takers are the people that use AI the way the vendor built it. So that's people that take the products that are out there and just pull in value to their systems. This is fast, easy, and

3:37 relatively affordable. But there's no difference between you and anybody else who are using this tools. And the third is shapers, which build their own layer on top of someone else's model. This is

3:46 essentially the process of harness engineering. And the key here is the term shaper. You have to be able to shape something you actually do. And in order to shape, you need the confidence

3:56 and the domain expertise to have precision in that specific domain. And this mindset of being a shaper, for people who fall in the category of do everything, this will help them be more

4:04 precise because they have to shape specific things. And for those who overthink, you'll just think about shaping what you already do. Don't overthink it. Just focus on where you

4:12 spend your energy right now. So if you're in marketing, focus on shaping AI to get better at marketing. If you're in sales, focus on shaping AI to be better at sales. And don't boil the ocean.

4:22 Focus on specific things that you're an expert at already so that you can better tweak and shape AI to get better outputs. And so you're thinking about the domain that you want to work in. And

4:30 one limiting belief that you may have is why would you be better at building a harness than Mr. Zuckerberg or Mr. Elon Musk. There's a number of reasons, but primarily you get to design for one

4:41 user. Not thousands, not a whole department, just you. And that's value no company building a product for thousands of customers will ever provide. So throw that limiting belief

4:51 out the window. You can build something that's more valuable for yourself than these enterprise companies. Now, if you're still not sure what to focus on and what domain you want to build your

4:59 harness in, here's a prompt that you can run that will help you better identify the niche or domain that you should focus on. So, now that you've selected the domain that you want to focus on, it

5:07 brings us to layer three, which is building the harness. But before we get to that, one harness that I've mentioned that I know everybody has used is Claude Code, which brings us to today's video

5:16 sponsor, Anthropic, the team behind Claude, which you guys know that I love their tooling and I'm hyped to be working with. Now, there are a couple product features that they launched that

5:23 are important to understand as you position yourself to be productive with AI. Claude Co-work and chat have now been combined into the same tool. And the reason that I like this doesn't

5:31 necessarily have to do with the specific features, although I will cover that in a second, but instead, I say this all the time, removing the decision of what tool to use makes you more productive

5:40 because it lets your brain focus on high lever decisions. And this is Claude's step in that same direction. And this is also an example of them creating a more effective harness for you to use.

5:50 exactly what we're talking about in this video. And by combining chat and co-work, you don't have to think about which one you have to use because they're the same thing. Now, the second

5:57 is you guys know that I love claw design and now it works right inside your conversations. So, you don't have to context switched to a different tool. Not only that, they've launched clawed

6:06 docs and slides which are specifically designed for those use cases. See, one of my clients recently asked me, "How should I use AI to create proposals that I'm just struggling going back and

6:15 forth?" And so I told him, set up Claude connections to wherever relevant conversations are about the proposal. Take that and bring in a reference of a past proposal. And then tell Claude,

6:24 make me a template proposal that I can use for future clients and then say, make a proposal for this client using context from our connections. And it'll then go from there creating a proposal

6:33 template. And all of this back and forth lives in the same interface, which removes context switching that I mentioned earlier. And the final feature in this launch that I like is now all

6:42 chat conversations share one context. your connected skills and projects, they're accessible in any conversation. So now you don't have siloed projects with context. It's all one thing. Now,

6:52 this specific feature will be rolling out to pro and max users automatically. So to make sure you don't miss it, check the first link in the description. So coming back to layer three, which is

7:00 building your harness. The first rule, layer three, don't reinvent things. Rarely do you actually want to rebuild something from scratch. And most of the time, the highest and best use of your

7:10 time is extending what's already there. So, I don't want you to spend the weekend handbuilding a harness from zero only to realize that Claude already does 90 to 95% of what you needed. Going back

7:20 to our equation before, right, we're not building the base harness. We're just building the domain harness. All right, so enough of that. What actually makes up a harness? Well, there are a handful

7:28 of variables. Let's just go through them one at a time. First, rules. These are direct instructions for how AI should behave. Skills are reusable capabilities you build once and then you can call

7:38 them whenever you need them. MCP servers, they lay the wiring to talk to other tools. These are basically external connections. There's context. This is the actual knowledge you feed it

7:47 specific to you. And if you're trying to scale this out, a knowledge graph helps a lot here. Then there's hooks. These are scripts that run on specific events, such as a blocking command or running a

7:56 test after an edit. There are sub agents, which are how you delegate work, and this is how you can partition tasks to streamline the output. The interface, which is how you actually interact with

8:04 the whole thing, and we're going to do a deep dive on that in the next layer. But at a high level, you can run a harness through a chat window, through documents, or my personal favorite is a

8:13 simple dashboard that you can run locally. And the final step to any good harness is a feedback mechanism. This lets you shape the harness over time, which is so important. Again, from

8:22 earlier, the harness wraps the existing functionality of AI to force it to do something else. And if a lot of what I just said sounds like a lot of what you're already doing, that is the point.

8:33 This concept is actually quite simple and you're likely doing a lot of these things anyway. You have the foundational skill set, but it's this mindset of harness engineering that we're building.

8:42 So the first rule is don't reinvent the wheel. And the second rule is keep it simple. So a complex harness would be an example where you go straight to the models API and you build everything from

8:52 scratch. A simple harness means borrowing what clawed code already gives you and building on top of that instead. The simplest solution that actually solves the problem is better than any

9:01 complex solution, especially when you're first starting. And 99% of people watching this should just start with a simple version, build it end to end, and then go from there. So, for this video,

9:10 we're going to build a harness that is both very helpful and also shows the power of harnesses. So, what we'll build is an internal knowledge harness where it only answers questions based on the

9:20 context you provide it. And we're intentionally choosing this harness because it's valuable for everyone watching this. So for example, let's say you're at your job and you were to ask

9:27 Claude a question about how to onboard a client. It will pull from everything it's training data. It might get you the answer, it might not. By using this harness, it will restrict the

9:34 information based on knowledge you provided. So if you were to ask it a question, it'll just pull from the documents you provided to provide the answer. You can see how this is altering

9:42 how AI responds to you. You're building a harness or a wrapper around it. So let's go through all of the components that I mentioned earlier. So the rules for this, we want to only pull context

9:50 from the project we're working on. the skills. We're going to create two reusable skills. One called KB answer that only pulls its answer from local context provided and then KB sync which

10:00 will use external providers to bring in context to help answer those questions. For MCP servers, we're going to connect to Google Drive, Notion, or wherever your current knowledge base is. And this

10:09 will help us sync the data. For context, this is all going to be specific knowledge that you want AI to pull from. This is the part of the harness that is specific to you. The hooks and sub

10:17 aents, we're going to use clawed code to decide when this is needed. For the interface, we're going to create a simple chat interface that is a one-page website where when you hit enter in the

10:26 input, it'll answer specifically using this KB answer skill. And for the feedback mechanism on the interface itself, we're going to create an easy way to provide feedback so that if

10:35 you're missing context, it's easy to know and then add it to the system. So to build all this, I'm going to package all these features up into this prompt that creates everything I listed above

10:44 with the interface being a simple single page website. And now if you are starting from scratch, go to claw desktop app, hit code in the top right, select open folder, select new folder,

10:53 and just name it harness demo. Then once you do that, your system's all set up, run this prompt, which will walk you through creating the harness. Now, if you have questions on this prompt or you

11:01 want to go through it more step by step, I cover each step in detail and how to build it in my build partner.AI plugin, which is linked below for free. You just run /buildpartner colon build spaceh

11:12 harness, and I'll automatically run you through it step by step. But the prompt I shared here is enough to get you going. Once you run it, you just let AI do its thing. And the interface for the

11:21 harness will look a little bit like this with two buttons. The sync button will run KB sync skill to get additional context. And then the send button will trigger the KB answer skill on your

11:30 machine. And then after you receive the response, there's a feedback mechanism for you to say if the response was good. And if it wasn't, you can use the tool to ingest additional data. Over time,

11:40 you can imagine training and sharpening this harness. Now, this general structure is what a lot of these smartest people are doing, and they're creating workspaces that let them build

11:49 10 times faster. So, at this point, we have the architecture set up, but before we get to the last layer, as well as the Carpathy curve, which changed how I think about all of this, you know the

11:58 drill. This is our anti-Slap agreement. Everything here is built by humans for humans. So, as part of this agreement, subscribe to this content so I can keep reaching more people. And if you already

12:06 subscribed, make sure to sign up for post notifications. It helps my channel, and I appreciate every one of you. these drawings and my terrible handwriting. This is for you guys. And as a thank you

12:15 to everyone watching, I give away a Claude Max subscription every single video. And this video's winner is Jeremy Glenn87, who is working on various side projects. To enter this video's Claude

12:24 Max giveaway, let me know what you're building in the comments, and let's chat about any problems you're running into. I'd love to help. Now, let's get into layer four, the interface. This is a

12:32 layer that most people completely neglect. And honestly, in my eyes, it's actually the most important of the four layers. This is how you actually visualize the tools that you're

12:41 building. And so the harness isn't just the tools underneath it. It's the whole experience. And that includes how a human actually uses this thing. So I recently made a video comparing Claude

12:50 and Grockbot, which I'll link at the end of this video, but the reality is that Claude and Grockbot can essentially do all of the same things, but the interface makes one better than the

13:00 other at specific use cases. It has nothing to do with the model, nothing to do with the underlying guard rails or skills, but everything with how a user actually interacts with it. This is the

13:09 key to harness engineering. At the end of the day, who cares if you have an amazing tool set if it's just hard and complicated to use it. And so for you, there are a number of interfaces for you

13:18 to consider. In this video, we outlined a web page, which may feel the most typical to what you're used to. This is one way, but another way could be through a terminal or a command line

13:27 interface, and another could be through custom plugins. And the reason that I love the web-based local interface is one, you likely already pay for subscriptions like Claude, and if you

13:36 run the app locally, it can just use your Claude membership instead of having to pay API credits for a typical cloud-based app. The second is that you can iterate extremely fast. On my

13:46 internal tool, I actually have a pencil icon that lets me hover over things that I want to change, and I just click it, I type what I want, and then I hit enter. For example, on screen I show me

13:56 selecting a data source and I just say I want to add Outlook and then it goes and cooks on it. And this process of just like quickly iterating is something I do all the time. And I'll do this on a

14:04 call, but me and a team member will just be like, I wish it response was like this. And I'll just instantly change it, speeding up this iterative cycle so that the harness can get better faster. The

14:13 third is that there's a clear pathway to scale it to your team. Now, this can be a bit more complex, but when you're ready, you can build a tool that scales out to other people on your team. Now,

14:21 for the sake of this video, we won't cover how to scale this harness to your broader team, but if you are interested in that, there is a link below where we can talk through how to set it up for

14:29 your team. Now, before we go through the Carpathy curve, which changed how I fundamentally think about AI, we just went through the four layers of harness engineering. Layer one, understanding

14:37 the foundation, layer two, identify the domain, layer three is building the actual harness, and layer four is focusing on the interface to get the most out of these tools. We have an

14:47 exact idea in terms of how to build one that's valuable for you today as well as creating your own harness through the prompts that I shared. But now we need to cover the Carpathy curve especially

14:56 in a world where AI dumerism is just so prevalent. So simply put, what's the Carpathy curve? The Carpathy curve suggests a different future. One where the model is the least interesting part

15:06 of the stack. Where the real work is in data curation, task decomposition, and organizational adaptation. and where the winners aren't the ones who built the biggest brain, but the ones who figured

15:17 out the most valuable thing to think about. That future explanation is different than the one that we've grown accustomed to hearing. See, the AI doomer vision is a future where AI rules

15:27 the world and is smart enough to solve any problem we give it. And there's really nothing that you can provide value on. But instead this explanation, this carpathy curve suggests that the

15:37 winners will be the people who create a harness and a system to best interact with the models based on their specific situation. And this process of harness engineering, you now have a foundational

15:47 understanding of when it's needed, how to build it, and how it applies to you. And so we've created a strong foundation, but the reality is you shouldn't build your own custom harness

15:56 for everything. So a natural problem you'll run into is which use cases to use which harness for. So, for that reason, I made this video, which is a deep dive on 12 daily use cases and

16:06 breaks down which harness, either Grockbot or Claude, is better for that specific job. This video broke down making your own, but sometimes you want to use the existing products out there.

16:15 And so, if you like this video, you're going to love that, and I'll see you over there. Peace.