Boris Cherny’s 4 Step Playbook to 10x Your AI Productivity

0:00 Boris Cherny, the creator of Claude Code, said something that shocked me. Inside every company, there is one person who uses AI to 10x their output while everyone else around them

0:08 struggles to keep up. So, to help with this, Boris shared four steps that separates these AI power users from everyone else. But, the problem is his advice is extremely technical, so it can

0:17 be very intimidating. So, in this video, I'll break down and simplify his exact four-step process to 10xing your AI productivity and how you can apply it today. And by the end, I guarantee

0:26 whether you're technical or not, you'll know exactly what to do, how to do it, and why these four steps matter. Now, before we get to step one, it's important to understand what step zero

0:34 is. This is people who are using Claude or ChatGPT in the chat window. That's it. And this is identical to how everyone started using ChatGPT when it first came out. Now, 99% of the people

0:42 watching this channel are past this level, but there are two important things to cover here. The first is in a study by Gallup, they estimate 50% of US workers aren't using AI at all, and only

0:51 28% of them are using it weekly or daily. So, most people are barely at step zero, which sounds crazy, but here's what's more important. The second thing, if Boris saw how you use AI

1:00 today, he'd put you in a similar category as the people who barely use AI at all. So, as a wise person once said, there are levels to this and we're going to level up in this video. So, the

1:10 first step is about get becoming a better AI powered worker. Step two, that's about becoming an AI manager. Step three and step four is about becoming a manager of AI managers. And

1:19 Boris specifically designed these steps so that they build on top of each other. So, step one is AI assisted. Here's how Boris describes the step, and throughout this video, I'm going to be referencing

1:27 a blog that he wrote that's specifically going through each of these four steps. This is one engineer, one agent, mostly supervised, a fast pair programmer. You run one session at a time and review

1:37 almost every change before it merges. Now, that sounds technical, but it really isn't. Think of a pair programmer as no different than having an assistant in the room who can do a task for you.

1:46 And in practice, this looks like using Claude Code and Co-work, which a lot of you already do. Now, this is the first of two paradigm shifts we'll cover in this video. This is getting AI to do

1:54 things for you, not just answer your questions. Now, most people think they're here, but they actually aren't. So, to identify this, ask yourself two questions. Do you find yourself copy and

2:03 pasting output from Claude into other locations, >> [music] >> and do you find yourself copy and pasting data that's outside of Claude

2:09 and bringing that manually into Claude? If the answer is yes to either of these, you can improve your system so that you're more in step one. AI should be able to pull information for you and

2:17 then edit documents directly on your behalf, so you don't have to do this copy and paste dance. So, what's the easiest way to do this? Now, I use Claude Code because it seamlessly can

2:25 edit files on my computer. And this is not just for coding tasks. I know a lot of non-technical people watch this. You should not feel intimidated to use Claude Code. So, to set this up, go to

2:33 Claude Desktop, click code, and then select the folder and hit add another folder, then select new folder and call it your personal AI system, and then hit create. Once you're in there, run

2:41 {slash} init and it'll optimize this project for you. Now, you could ask Claude to say, "Write a file that says I'm a boss." and it'll go ahead and do it for you. Now, to make navigating

2:50 these files easier on your computer, I use Obsidian, which is free. You just download that, then select the folder you created, and now you can easily view the file that it just wrote to. Now,

2:58 this small change makes it super easy for you and your AI to collaborate together, removing the need to copy and paste, which just takes way too much time. Now, to connect it to the external

3:06 world, click the plus and then connect any system you need the agent to have access to. So, for example, I use Notion a lot, so I just connect Notion, and now it has access to the data and I don't

3:15 have to copy and paste it from there. Now, just setting this up is a massive change for a lot of people, but there's still some key bottlenecks, and Boris outlines them exactly like this. Your

3:23 attention and the need to inspect each response and code edit due to low trust for the model's output and lack of self-verification. You feel you must read everything, so you never look away.

3:32 So, how can we change from this back and forth manual process that feels like a one-lane road to something that more resembles a multi-lane highway that allows you to build faster. Step two is

3:42 AI builds in parallel. In Boris's words, this step is about having one engineer that orchestrates five to 10 agents at once, each on its own work tree or get checkout, jumping between them. Now,

3:51 ignore the technical terms like work tree and get checkout. That doesn't really concern us right now. The key here is that he calls your role the orchestrator, which isn't about just

3:57 opening a bunch of tabs and having AI work on things simultaneously. There's more to the story here. The key unlock is having AI agents that do work end-to-end and then check the output

4:06 themselves. So, you're looking at a final product, not the intermediary steps. And once you do this, this is how Boris describes the impact. A backlog that used to take the team weeks becomes

4:15 one engineer's afternoon of orchestration. So, how do you actually get there? There are a bunch of ways to do this, but these are the highest leverage changes. The most important

4:22 step is verification. To go from a single-lane highway to a multi-lane highway, you need a non-human to verify the outputs. If you don't do this, your verification process ends up becoming

4:32 the bottleneck and it'll drastically slow you down. So, there are two types of verification you need to be focused on. These are rule-based verification and taste-based verification. Rule-based

4:40 verification is the process of using rules to objectively verify an output. This is where there's really no debate, right? Is something right or wrong? Yes or no? Now, in the coding world, Boris

4:49 calls this automatic code quality enforcement, like lint, automated tests, type check. Now, don't worry about what these terms are, but the key here is that they are all objective metrics,

4:58 pass or fail. And this exists for non-technical work as well. Does a report use the correct colors? Does it use the right fonts? Does the text use m-dashes? These are all yes or no

5:07 questions, and depending on your domain, the list may expand greatly. For example, if you're a mechanical engineer, there may be concrete rules and regulations that are quantifiable to

5:16 validate. And this is something firsthand I've seen with engineering businesses that I'm working with. The second is taste-based verification, and this one is tricky, but it's personally

5:24 my favorite. The key here is that you're configuring AI to validate work that isn't objective. Does the design look good? Does that content idea pass a quality bar? Is the writing concise?

5:34 Here's a prompt that will help you create two skills, one for rule-based verification and one for taste-based verification. The key here is that you need to go through and provide context

5:42 about what you're working on and then optimize it over time. Now, if you'd rather get the exact verification skill I use, I call it the anti-slop skill, and that's linked in the description

5:50 below. This uses my buildpartner.ai Claude plugin, which walks you through the exact steps to set it up in your system. So, that's the first high-leverage change to go to step two,

5:58 which is creating a verification process for your system. But, the second high-leverage change is agent permissioning. This is the process of giving agents room to work without the

6:06 fear of it causing permanent damage. The mental framework I always use is thinking of agents like a drunk intern. If it has access to something that it can mess up, it will mess it up. So,

6:15 protect yourself by removing that possibility. And now, the simplest way to do this, and this is suggested by Boris, is to use Claude code's auto mode. And I'm honestly surprised how

6:23 many people have never heard or used of this, but to do this, just click next to the plus on Claude, and then select auto. This will use Claude's preset configuration to auto-approve things

6:33 that aren't as risky, and then ask for your permission for things that are risky. It's the Goldilocks zone for permissioning, and you don't really have to worry about changing it from there.

6:40 Once you've set up Claude to validate the results and give it the permission to run and work through tasks with without you monitoring it and approving every single step, you've empowered

6:48 Claude to complete tasks end to end, and that's the key to step two. So, it now has the ability to build in parallel, but we now need to identify what to work on in parallel without the agents

6:57 crossing swords. But, before we get to that, one of the things we're talking about here is agent autonomy, and that's exactly where today's video sponsor Ask Your Work comes in. Instead of one AI

7:06 assistant, you get an agent team that actually executes on your behalf. Here, you can see me in the Ask Your Work dashboard, where you can add agents to your virtual team like you're adding

7:13 people to a real team. Each one has specific skills you can see, and you can add new ones for whatever you want that specific agent to focus on. And Ask Your Work has access to Alibaba's massive

7:22 network of training data, which gives these skills and agents a massive competitive advantage. One feature that I love is their ability to communicate with people directly. So, let's say

7:30 you're looking for a supplier for your business, it can vet suppliers and then negotiate on your behalf. At my last startup, I used to speak to 10 to 20 different suppliers to land on the one

7:38 that I needed to produce hundreds of thousands of product that would get shipped around the globe. And if I had this at the time, it would have been a massive lifesaver. And because Ask AI

7:45 work has data about what people are selling across platforms like Alibaba, it has unique contextual information to draft better responses. [music] And the thing with this is it's not something

7:53 that you can just replace yourself. So, if it's e-commerce marketing, outreach, or operations, using Ask AI work to create an agent team that runs 24/7 just makes sense. And you can manage it

8:03 directly through your phone through Telegram. If you want to start building with your own AI agent team, click the first link in the description where all new Ask AI work users will get free

8:12 access for 7 days. You're going to be happy you tried it. But we need to get back to step two, where we're identifying how AI agents can work together within Claude code. And the

8:19 thing about this, I try and think about tasks in cross-project and inter-project. Cross-project tasks is when two tasks are in entirely different things that don't have to do with each

8:28 other. So, think of this as a task that would live in your main business or your job, and then a task that sits in your side project. You want to optimize your setup so that if they have nothing to do

8:36 with each other, let's have them entirely different projects. So, to optimize the setup, I have a folder called {slash} projects. Then under that, I have each unique thing I work

8:44 on. So, I have {slash} build partner, {slash} internal OS, {slash} incubator website, {slash} clients. This lets me separate context and easily allow AI to work within that specific domain, and

8:53 I'm confident that there will be no overlap. So, I have these clear folders, and then in Claude code directly, I can select the project that I'm working on. By doing this, it separates the context

9:01 entirely, and it easily allows AI to know what it should be working on, so I don't have to be worried about it working on a different project. For inter-project tasks, this is where it

9:09 gets a little bit more tricky. You want to think about tasks that are isolated. So, if you're a software engineer, it's different parts of the app. If you're a sales rep, it's different customer

9:16 proposals. If you're a content creator, it's different scripts. You want to think about different units of work that don't necessarily overlap. So, if you're not sure where to work, here's a prompt

9:23 that will work with you to identify the best task for you to work on simultaneously with AI. At this point, you've set up agents so that they can work simultaneously and complete tasks

9:31 end-to-end. But there's a bottleneck here, too. From Boris, here is the limitation. Prompting and steering the model as you juggle sessions. Step three is supervised autonomy, and this is the

9:39 second of two operational paradigm shifts that we'll cover in this video. The unlock here is described by Boris. At this point, Claude proactively does work that you would have had to kick off

9:48 manually before. Maintenance and cleanup that used to wait for someone to find the time now runs continuously in the background. The key here is that Claude is proactively doing work for you. In

9:57 step one, you became a better AI-powered worker. That was the first paradigm shift. In step two, you became an AI manager. And now in step three and step four, this is about becoming a manager

10:06 of AI managers. You become an AI agency CEO. And I like this visual of thinking of it like an org chart where you're at the top and you're guiding everyone else below you. We'll cover the tactical ways

10:16 to actually do this, but first there's one limiting belief I hear more than any other that keeps people in step two [music] instead of going to step three. They'll say, "It's faster if I just use

10:25 AI and do it myself than set up a full system." And a lot of the times, the reality is that you're actually right. It is faster for you to do that specific task yourself. But that isn't the point

10:34 of all this. And here's the story that changed how I think about this. Back in 2021, I interviewed someone called Evan Veneter on TikTok Live. Shout out Evan. And he told me, "If you can hire someone

10:43 to do a task 80% as good, do it." Later that week, I decided to hire my first two contractors. Liam, a social media manager, and Sarah, a video editor. For the first two weeks, each video and

10:52 social post technically took me longer because I was teaching and training them. But then it got faster, and then I wasn't involved at all. I had built a team that was able to scale my output

11:01 without me being in the middle of it. That's the lesson I need you to take out of this. Lose the battle to win the war. If it takes you more time today, but will save you time in the long term, do

11:10 it. So that's the mindset. You're a CEO building a team. It may take longer to set up, and you're fine with that because you're building something that compounds. Now, as the CEO managing AI

11:20 agents, there are three things that you need to do, each pulled from Boris's blog. The first is you have to create your company standard operating procedures. Every business needs a

11:29 concrete way to do things and complete tasks. And the best way to do this within Claude is creating Claude skills. These are reusable skills that do the same thing every time you run them, and

11:37 you've probably heard of skills before, but the value of this clicks when you think about managing a team. You can think of these skills as a way to scale your output, codifying your processes

11:45 without having to worry about AI hallucinating when you're not involved with a task. And my favorite way to create skills is what I call output-driven skill creation. Create a

11:53 skill that is based on work you've already done. So, for example, if you want to create a topic research skill that exports a PDF, you would go back and forth with Claude, create a

12:02 high-quality output, and then write, "Based on this conversation, create a Claude skill that allows for this process to be reproducible." This will create a skill called topic research

12:10 report and make it so that if AI were to complete this without you, it would follow this exact process. And yes, creating this skill when you're doing the task does take more time today, but

12:20 it'll save you a headache in the future when you try and offload this task. Once you do that across your entire day or across your entire team, you're starting to build these standard operating

12:28 procedures like you're scaling a team. The second step is you want to establish delivery timelines and communication expectations. For this specific delivery, I use routines. So, this is

12:37 Claude's way of scheduling tasks. I think of this a lot like saying to a coworker, "Hey, every Monday at 8:00 a.m., I want this report sent to me." And to do this, I would then use the

12:45 skill that we already created, the topic research report generation skill, and then set up a routine to run that skill on Mondays. Then the key here is the communication expectations. Think about

12:54 growing a team. You need to hear from them about what they're doing and any problems they're having. So, just setting up this routine is not enough. You need to communicate the results. And

13:02 so, what I like to do is I use Slack for my entire team, and I have a channel called company updates where each of my AI employees will directly report their updates when they complete a task. And

13:11 you might not have a team. That's totally fine. But for you, just think about a location, whether it's WhatsApp, Telegram, Slack, where you can get these updates in a place that you'll actually

13:19 check. So, in the Slack example, you might just name it automation updates, and then that's where you get messages. To do this, I create a specific skill called send Slack update, and then I'll

13:27 add that to whatever routines I want to see the output from. After you've done that, it's time to find the bottleneck. Sometimes tasks take too long across your team, and you need to find a better

13:36 solution. The best way to do this is using sub-agents. Think of this like having an AI agent team swarm on a specific task. So, let's say that task is research. So, going back to that

13:44 research example, let's say you want to check YouTube, Google, Twitter, Instagram, and emails. You can have a sub-agent for each unique task, which will speed up the entire process. So,

13:52 you can say, [music] "Enhance my topic research report generation skill to use sub-agents for each unique platform." And this will cause it to fan out these agents to complete the task quicker. And

14:02 as the CEO of your team, you need to understand where your bottlenecks are and figure out these creative solutions. Depending on when you watch this, I'll have a video diving into exactly how to

14:10 fix these bottlenecks using graph engineering. That'll be on my channel in about a week, so go check that out. Now, at this point, we're approaching AI native tier, and if you got this far,

14:18 you're already crushing it. But, there are limitations that Boris calls out. The trust at this point is in the loop and your team's decision throughput. And you have to ensure tokens are used

14:26 efficiently as usage increases. At this step, Boris describes the bottlenecks as your ability to trust in the loop and your team's decision throughput. And part of this is ensuring tokens are used

14:37 efficiently as usage increases. Now, both these bottlenecks we'll solve in step four. Before we get to that, if this is your first video of mine, welcome to channel. But, if this is your

14:44 second or more, you know the drill. This is our anti-slop agreement. The visuals, the testing, the hours of research, me misspelling things on this piece of paper, this is entirely built for

14:53 humans, not for AI robots. So, as part of this agreement, all I ask is you hit the subscribe button to help this content reach more people. We're about 80K subs, so shout out everybody who's

15:01 already subscribed. Also, as a thank you, every video I give away a Claude Max subscription. So, this video's winner is Hugo Pham7210, who is using Claude to optimize a new

15:10 drug against cancer. That's obviously epic, so shout out Hugo for making the world a better place. Now, for this video, comment below with a topic you'd like me to make the next video about,

15:18 and I do accept sarcastic answers. I'll just have some fun in the comments. Now, step four of this whole process is becoming AI native. Once you get to this stage, here's how Boris describes it.

15:27 The loop is fully closed and most agents are kicked off by Claude. Hundreds to thousands of agents run, you steer by intent and monitor by exception. At this point, you stop starting things, you

15:38 stop checking things, and you only look when something's wrong. And then Boris says that the actual impact of this is that quarter-long migrations become a workflow you kick off and check on. And

15:47 honestly, this step is also why AI is really scary. When you properly set it up, it creates a recursive feedback loop that just builds things and fixes it without you ever being involved. And

15:56 that's the exact reason why AI gets better exponentially instead of just linearly. It no longer requires humans to improve and complete tasks. Now, that's why it's scary, but that's also

16:05 why it's exciting, and that's why we want to capitalize it. And so now to get here, you have to become really good at two things. You have to identify the right work to automate, and you have to

16:13 keep token consumption economical while you scale. Now, quick horror story from this. One of my clients who firmly was in step three some of the proper guardrails set up. And he told me that

16:23 one morning he woke up and AI burned through over $3,000 worth of tokens on a single task. It literally got stuck in a loop and it was lighting money on fire. So, let's just make sure that that

16:33 doesn't happen. So, first we're going to optimize automated routines for less token consumption, and then we'll cover how to become an expert at identifying automation candidates. To optimize these

16:42 routines for token consumption, we're going to do two things. First is set the minimum viable model for each task. We'll go with NVM for short because we are running out of room. So, within any

16:51 skill that you run, you can optimize them to select the specific model for the task. So, simply put, you don't need the best model for a simple task. That's just wasting tokens. So, in a second

17:01 I'll share the prompt that will actually optimize your skills so that they only use the model that's actually required for that specific task. Then after that, we want to establish the maximum amount

17:11 of iterations a specific routine or loop can have. My client's case, this wasn't implemented, so AI just continuously looped until he manually stopped it. So, what we do is establish a maximum number

17:20 of iterations so that this never actually happens. Honestly, it's the simplest way to avoid these big issues, which becomes the actual problem. Here's a prompt that will help you set the

17:28 minimum viable product and also set the maximum amount of iterations. Now, token optimization is a deeper rabbit hole and it depends on what you're using, so I do have a step-by-step walk-through that

17:37 uses my build partner.ai plugin that will go step-by-step for free to optimize your setup. Now, the next thing to become an AI native expert is you have to identify automation candidates.

17:47 The most important thing here is going back to a quote I mentioned earlier that frankly changed my life. If you can get someone to do something 80% as good, hire them. It's the same thing here, but

17:56 with one caveat. A task is fine being done at 80%, then use AI. A lot of the time, depending on the task, good is good enough and those are perfect automation candidates. Now, for tasks

18:05 where quality is critical, you don't want to automate those end-to-end. And that one key distinction is the whole strategy for deciding what to hand off. Where is good good enough? Automate

18:15 that. Where is good not good enough? And don't automate that. Now, at this point, you've gone through the four steps to become AI native. Step one is AI assisted. You have AI doing tasks for

18:24 you. This is the first of the two paradigm shifts. Step two is AI builds in parallel. You have AI helping you work on multiple things at once and you become an AI manager. Step three is

18:32 supervised autonomy. This is where AI is proactively working on things and you become an AI agent CEO. This is the second paradigm shift. And step four is where you become AI native. AI is

18:41 running automatically and you start optimizing the system. Now, these are the exact four steps that Boris, the guy who created this tool, says there are to become AI native. And no matter what

18:50 step you're on, you can get to the next step. Now, if you like this video, you will love this video where I walk through building a self-improving system. It goes deep on steps two and

18:58 three and it makes it so that the system automatically gets better over time. So, click here and I'll see you over there. Peace.