AI Harnesses In 24 Minutes (For Normal People)
Nick Saraev
39,051 views
🔥 Join Maker School & get customer #1 guaranteed: https://skool.com/makerschool/about
💎 Get all course resources 100% free: https://skool.com/maker-zero/about
➡️ If this is your first video: I'm Nick Saraev. I run LeftClick, an AI growth agency. We've done work for large brands you're likely familiar with, like Mr. Beast, Anthropic, OpenAI, and a few others.
In plain English: I help people build systems that generate leads, close deals, and scale businesses, mostly using new AI models like Claude. I also make videos about how to do all of that here on YouTube.
It hasn't always been this way. My family immigrated from a Soviet bloc country (People's Republic of Bulgaria) in the 90s. They worked extremely hard, and we were broke for a very long time. I grew up wishing for more security, stability, and freedom over my own life.
I don't have a programming degree, and never took formal education for IT or workflows. I learned it all myself from YouTube videos like you're watching now.
As for my path: I started my first business at 19 in college. We threw events (mostly parties) at campus bars, and charged people for entry.
That failed to provide me enough money to pay my bills, so at 21, I started another business, a door-to-door marketing agency.
From there, every year, I would start several companies, over 10 in total. I did this in a variety of industries, like e-commerce, photography, videography, SaaS, credit repair, etc. Each grew slightly more profitable, until, at 25, I would start 1SecondCopy, a content writing company. A friend and I eventually scaled that to over $90,000/m. It was my first taste of financial independence, and the reason I'm here today.
Since starting my journey, I've grown a fair bit of capital. To diversify my income, at 30, I began investing in other businesses and advising companies on how to grow in the AI era. These include SaaS businesses, like Clairvo, agencies like Dental Connect, and more.
Collectively, the businesses that I own outright or are a part of generate over $10 million per year. This returns far more than the 5-10% you would get in the stock market, but also requires a lot of my active time. There's a tradeoff there, but I greatly prefer active investing, where I have control over the entities I'm a part of.
It wasn't easy to get here. But I did in the end! For anyone on their own entrepreneurial journey: I wish you luck, happiness, and perseverance. You can make it!
Summary ⤵️
In this video I explain how AI harnesses work. We start using Claude Code and Codex as examples, then discuss how AI models are essentially brains in a jar capable only of autocomplete
We then chat context, memory, tools, verification, permissions, sandboxes, and self-evolving harnesses, as well as touch on what all of this means for the future of AI model development
Chapters
0:00 Intro
0:26 Claude Code and Codex are harnesses
2:30 The model on its own
4:04 What is a harness?
5:34 Context: what the AI knows
7:11 Memory and compaction
9:26 Tools: how the AI acts
11:56 Verification: checking the work
14:24 Permissions and sandboxes
18:13 How the model makes decisions
20:37 The agent loop
21:37 What comes next
20 Comments
Can't wait for the next video and hope to see some more practical tips from the current leading voice on these topics. Thanks!
AI Harnesses In 24 Minutes (For Normal People)
Nick Saraev
39,051 views
🔥 Join Maker School & get customer #1 guaranteed: https://skool.com/makerschool/about
💎 Get all course resources 100% free: https://skool.com/maker-zero/about
➡️ If this is your first video: I'm Nick Saraev. I run LeftClick, an AI growth agency. We've done work for large brands you're likely familiar with, like Mr. Beast, Anthropic, OpenAI, and a few others.
In plain English: I help people build systems that generate leads, close deals, and scale businesses, mostly using new AI models like Claude. I also make videos about how to do all of that here on YouTube.
It hasn't always been this way. My family immigrated from a Soviet bloc country (People's Republic of Bulgaria) in the 90s. They worked extremely hard, and we were broke for a very long time. I grew up wishing for more security, stability, and freedom over my own life.
I don't have a programming degree, and never took formal education for IT or workflows. I learned it all myself from YouTube videos like you're watching now.
As for my path: I started my first business at 19 in college. We threw events (mostly parties) at campus bars, and charged people for entry.
That failed to provide me enough money to pay my bills, so at 21, I started another business, a door-to-door marketing agency.
From there, every year, I would start several companies, over 10 in total. I did this in a variety of industries, like e-commerce, photography, videography, SaaS, credit repair, etc. Each grew slightly more profitable, until, at 25, I would start 1SecondCopy, a content writing company. A friend and I eventually scaled that to over $90,000/m. It was my first taste of financial independence, and the reason I'm here today.
Since starting my journey, I've grown a fair bit of capital. To diversify my income, at 30, I began investing in other businesses and advising companies on how to grow in the AI era. These include SaaS businesses, like Clairvo, agencies like Dental Connect, and more.
Collectively, the businesses that I own outright or are a part of generate over $10 million per year. This returns far more than the 5-10% you would get in the stock market, but also requires a lot of my active time. There's a tradeoff there, but I greatly prefer active investing, where I have control over the entities I'm a part of.
It wasn't easy to get here. But I did in the end! For anyone on their own entrepreneurial journey: I wish you luck, happiness, and perseverance. You can make it!
Summary ⤵️
In this video I explain how AI harnesses work. We start using Claude Code and Codex as examples, then discuss how AI models are essentially brains in a jar capable only of autocomplete
We then chat context, memory, tools, verification, permissions, sandboxes, and self-evolving harnesses, as well as touch on what all of this means for the future of AI model development
Chapters
0:00 Intro
0:26 Claude Code and Codex are harnesses
2:30 The model on its own
4:04 What is a harness?
5:34 Context: what the AI knows
7:11 Memory and compaction
9:26 Tools: how the AI acts
11:56 Verification: checking the work
14:24 Permissions and sandboxes
18:13 How the model makes decisions
20:37 The agent loop
21:37 What comes next