what happens when you point AI at 173 Hormozi videos and let it find the patterns? 532,000 views and 1,000 new followers later, nine different people asked the same thing - how the hell did you do this?

in this episode, Lennox walks through the entire AI Content Forensics system live - this time on Mr. Beast's channel. every prompt, every step, nothing held back. you will learn three layers: how to recreate the exact results on any YouTuber, how to write dramatically better prompts using the two-chat method, and how to turn the whole process into a reusable AI agent that runs with one command.

this is a tutorial you can follow along with in real time. if you have access to Claude or ChatGPT and a free YouTube Data API key, you can do this today.

the full open-source system is available on GitHub - link shown in the video.

Chapter Markers:

00:00 - Proof it works (532K views, 1,000 followers)

01:30 - The social proof: Hormozi + Diary of a CEO threads

03:00 - Layer 1: Live Mr. Beast analysis (960 videos)

04:00 - Setting up the YouTube Data API

05:30 - The two AI Content Forensics prompts

08:00 - Key findings: danger triggers, title patterns, promise-proof-payoff

10:00 - Thumbnail laws and hook rules from the data

11:00 - ChatGPT 5.4 handoff and thread creation

12:30 - Creating carousel visuals with Claude

14:30 - Layer 2: The two-chat method (prompt engineering)

17:00 - Layer 3: Building an AI agent (skills)

18:30 - Creating the skill live in Claude Cowork

19:30 - Open-source GitHub repo reveal

Show Notes:

Claude Code / Claude Cowork - AI assistant for data extraction and analysis

ChatGPT 5.4 Pro - thread synthesis and handoff

YouTube Data API - free API for pulling video metadata at scale

Threadify - Threads growth workspace: https://threadify.app/plans?utm_source=podcast&utm_medium=show_notes&utm_campaign=ai-content-forensics

Key concepts: AI Content Forensics, Views Per Day (VPD), Two-chat method, Skills (SOPs for AI agents), Promise-proof-payoff loop