• Skip to primary navigation
  • Skip to main content
  • Skip to primary sidebar
  • Skip to footer

Social Media Examiner

Your Guide to the Marketing Jungle

  • 🔥 Free Newsletter
  • 🎙️ Podcasts
    • Social Media Marketing Podcast
    • AI Explored Podcast
    • Our YouTube Channel
  • 🌟 AI Society
  • 🗓️ Marketing Conference
  • 🤖 AI Conference
  • 😊 NoteGo App
  • 👋 About Us
    • Marketing Events
  • Search
  • Social Media Marketing WorldImprove your strategy & find your next big marketing ideasGET THE RECORDINGS

    The Outlier Video Method: Using AI to Study What Works and Create Your Own

    by Michael Stelzner / May 26, 2026

    Want to use AI to scale video content research and production? Wondering how to create an AI system that will produce videos that attract your ideal audience?

    In this article, you'll discover how to use Claude Code to identify the videos already working in your niche, reverse-engineer what makes them successful, and generate scripts in your own voice.

    This article was co-created by Sandy Lee and Michael Stelzner. For more about Sandy, scroll to the end of this article.

    Why the Outlier Video Method

    Content creation has always been a grind. You film, you edit, you script, you post… and then you do it all over again. Sandy Lee knows that cycle intimately. She grew a language-teaching YouTube channel to 550,000 subscribers across YouTube, Instagram, and TikTok starting in 2018. But she did it manually, and it nearly broke her.

    With three kids under seven, a full-time job, and client work, recreating that success from scratch wasn't an option. So when she discovered Claude Code in late 2025, she didn't just use AI to write captions. She built a content system that automates the research, identifies winning videos, and generates scripts in her own voice. 

    In less than a month, she grew a new YouTube channel from 200 to 11,000 subscribers and earned $10,000 across a client retainer and channel revenue.

    The system she built is layered. Sandy describes it as seven AI agents and sub-agents. Think of senior and junior engineers all working on your behalf. The senior agents handle big-picture decisions; the sub-agents execute specific tasks, such as thumbnail analysis, scripting, and guidance on video editing.

    Below, we focus on the three foundational steps that underpin the whole system: finding your content identity, locating what already works on YouTube, and using AI to turn that research into a script that sounds like you.

    The result is a content pipeline that starts with a daily email of outlier videos, passes through an AI analysis of what's working, generates a script in her voice using a proven hook framework, and ends with Sandy hitting record on content she's already confident about. The system doesn't replace her creativity or her story. It takes the repetitive, time-consuming research and formatting work off her plate so she can focus on the part only she can do: showing up on camera.

    #1: Develop Your Ideal Customer Profile & Content Pillars With AI

    Before you open Claude Code or any other AI tool, you need to complete one foundational piece of work; creating the brand voice assets that will guide the system.

    The Inside Out method starts with a Japanese concept called Ikigai, which translates roughly to “reason for being.” Sandy uses it as a self-discovery framework.

    Pull out a notebook and work through four questions:

    • What do you love to do?

    • What are you good at?

    • What can you be paid for?

    • What does the world need?

    The goal is to find the intersection where all four answers overlap. That intersection is your content identity. It's where what you love meets what you're good at, what the world needs, and what people will actually pay for.

    A few important notes on this step. First, do it without AI. The purpose is to surface what's genuinely inside you, and that requires disconnection. Second, don't spend more than a day on it. Overthinking here is a trap. You're not locking yourself into a permanent niche; you're giving AI enough material to work with. Third, your answers will evolve. Sandy adjusted her positioning several times after starting. What matters is getting something on paper and moving forward.

    Now, feed those notes into your AI tool of choice and ask it to analyze them to generate two things you'll use throughout everything that follows.

    3 Days of World-Class Training—Zero Travel!

    Social Media Marketing World

    Couldn't make it to Social Media Marketing World and AI Business World this year? Get all of the great content at a fraction of the price with a Virtual ticket.

    That’s full access to recordings of every keynote, workshop, and session—the ones people travel thousands of miles to see. Don't wait. Get your Virtual ticket and enjoy actionable content that you can watch anytime, anywhere.

    GET YOUR VIRTUAL TICKET NOW

    The first is your ideal customer profile (ICP). Based on what you wrote, AI will identify who is most likely to find value in your content: their demographics, their challenges, what they're searching for, and what they'll pay for. Sandy's ICP turned out to be busy parents and full-time workers who want financial freedom and believe AI can help them achieve it.

    Based on the notes below, identify my ideal customer profile.
    Include their likely demographics, the core challenges they face, what they're actively searching for online, and what types of products or services they'd be willing to pay for.
    Be as specific as possible.
    [Paste your answers to the four Ikigai questions here]

    The second output is your content pillars. Your content pillars answer the question you should be asking before every video: what kind of content does my ideal customer actually need from me? Sandy’s pillars are AI tools and workflows, content creation systems, and the personal brand journey. Every video she makes maps back to one of these pillars.

    AI generates the pillars based on the overlap between your Ikigai answers and your ICP.

    Using my Ikigai answers and ideal customer profile below, identify my content pillars, the three to five recurring topic categories that sit at the intersection of what I'm uniquely positioned to offer and what my ideal customer most needs.
    For each pillar, include a brief description of what it covers and why it resonates with my audience.
    [Paste your Ikigai answers here]
    [Paste your ICP here]

    #2: Research YouTube Content With AI

    The next task is to build a workflow or system that researches YouTube content for you.

    Manually, this looks like going to YouTube, searching your topic, watching competitor videos, and noting what's getting traction. Sandy did this herself for years. Now AI does it for her.

    She built a Claude Code system, trained with her ICP and content pillar descriptions, that monitors a curated list of ten YouTube channels in her niche.

    AI Business Society

    Want to Unlock AI Marketing Breakthroughs?

    If you’re like most of us, you are trying to figure out how to use AI in your marketing. Here's the solution: The AI Business Society—from your friends at Social Media Examiner.

    The AI Business Society is the place to discover how to apply AI in your work. When you join, you'll boost your productivity, unlock your creativity, and make connections with other marketers on a similar journey.

    I'M READY TO BECOME AN AI-POWERED MARKETER
    the-outlier-video-method-using-ai-to-study-what-works-and-create-your-own-claude-code-skill

    Every 48 hours, the system identifies new videos and calculates an outlier score for every recent video across those channels using this formula:

    Outlier Score = (Video Views in First 48 Hours ÷ Channel's Average Views in First 48 Hours) × 100

    A score well above 100 means the video is outperforming the channel's norm; it's an outlier. This distinction matters. A video might have 500,000 views simply because the creator has a massive following; that's not an outlier, that's just scale. 

    What Sandy is looking for is a video that is dramatically over-performing relative to what that specific channel typically earns. She’s looking for a signal that the topic, format, or packaging itself is driving the result, not just the creator's existing audience.

    Claude Code connects to YouTube's API to pull this data and runs the scoring automatically through an automation platform; Sandy uses n8n. Once the system identifies outlier videos, it emails Sandy a daily digest with the results. Instead of spending an hour each morning scanning channels, she opens her inbox and finds a prioritized list waiting for her.

    She reviews the list, chooses a video, and moves on to the next step.

    #3: Analyze the Outlier Video With AI

    Once Sandy receives her daily email and identifies a video she wants to model, the AI system takes over again.

    Her Claude Code setup analyzes three things about each outlier video: the thumbnail, the title, and the first 30 seconds of the video, and then describes what's working in each element.

    For a thumbnail, it might note that the creator used a side-by-side comparison layout. For the title, it surfaces what type of curiosity is piqued or what promise is being made. For the hook, it identifies the technique used to grab attention in the first few seconds: curiosity, bold claim, shared pain point, and so on.

    Sandy reviews the summary and triggers the next step: script generation.

    #4: Craft Your Hook and Script a New Video in Your Voice With AI

    Sandy has set up a Claude Code Skill that uses her brand voice information, combined with her content pillars and ICP, to generate a full script in her voice based on the outlier video's message.

    The script follows the same topic structure as the outlier video with a similar format and similar flow, but speaks to her specific audience in her specific way. “Whenever I'm reading the script, I sound more natural,” she says, because the script already reflects how she talks and what her audience expects from her.

    The 30-second hook is the most critical part of any video, and Sandy has built a specific seven-part hook formula into her Claude Code script prompt. The seven elements, applied sequentially in the first 30 to 60 seconds, are:

    1. Pattern interrupt. Open with something that disrupts the viewer's passive scroll: a counterintuitive claim, a direct question, or a statement that signals this video offers something different from what they expected. The goal is to stop the click-away before it happens.

    2. Mirror the viewer. Name the viewer's pain point in specific, physical terms. For Sandy's channel, that means describing the actual moment her audience is living: finishing a full workday, coming home, and still having to turn on a camera and deliver something coherent on cue. That degree of specificity signals that you understand their day-to-day reality, not just a broad category of frustration.

    3. Opportunity. State clearly what the viewer stands to gain by continuing to watch. This is the explicit promise you’re making: what they'll understand, be able to do, or avoid by staying through the end of the video.

    4. Gap. Establish the stakes without artificial urgency. Sandy's position is straightforward: people who aren't building these skills now will fall behind those who are. That's an accurate observation about where AI adoption is heading, not a sales tactic. State it plainly and let the viewer weigh it for themselves.

    5. Transformation. Describe a concrete before-and-after outcome. Not a vague sense of improvement, but a specific capability the viewer will have by the end of the video that they don't have now.

    6. Authority. Give new viewers a single, well-chosen reason to trust you. Sandy points to her track record: building a channel to 550,000 subscribers, then growing a new one to 11,000 in under a month. One credibility anchor is sufficient.

    7. Transition. Move directly into the first step of the video. No recap, no re-introduction.

    Sandy Lee is an AI content strategist and founder of Slee Automation. She helps entrepreneurs use AI to simplify content creation and build scalable personal brands. Her AI Content System community gives members direct access to her strategies, weekly group calls, and accountability support. Follow her on YouTube.

    Other Notes From This Episode

    • Connect with Michael Stelzner @Stelzner on Facebook and @Mike_Stelzner on X.
    • Watch this interview and other exclusive content from Social Media Examiner on YouTube.

    Listen to the Podcast Now

    This article is sourced from the AI Explored podcast. Listen or subscribe below.

    Where to subscribe: Apple Podcasts | Spotify | YouTube Music | YouTube | Amazon Music | RSS

    ✋🏽 If you enjoyed this episode of the AI Explored podcast, please head over to Apple Podcasts, leave a rating, write a review, and subscribe.


    Stay Up-to-Date: Get New Marketing Articles Delivered to You!

    Don't miss out on upcoming social media marketing insights and strategies! Sign up to receive notifications when we publish new articles on Social Media Examiner. Our expertly crafted content will help you stay ahead of the curve and drive results for your business. Click the link below to sign up now and receive our annual report!

     
    AI EXPLORED

    Curious About How to Use AI?

    Our newest show, AI Explored, might be just what you're looking for. It's for marketers, creators, and entrepreneurs who want to understand how to use AI in their business.

    It's hosted by Michael Stelzner and explores this exciting new frontier in easy-to-understand terms.

    Pull up your favorite podcast app and search for AI Explored. Or click the button below for more information.

    I WANT TO LEARN MORE ABOUT AI

    Tags: AI Explored podcast

    About the authorMichael Stelzner

    Michael Stelzner is the founder of Social Media Examiner and Social Media Marketing World—the industry's largest conference. He's also the founder of the AI Business Society and the AI Business World conference. Michael hosts the Social Media Marketing Podcast and the AI Explored podcast, and is the author of the books Launch and Writing White Papers.
    Other posts by Michael Stelzner »

    Get Social Media Examiner’s Future Articles in Your Inbox!

    Get our latest articles delivered to your email inbox and get the FREE Social Media Marketing Industry Report (44 pages, 50+ charts)!

    Industry Report Cover

    Worth Exploring:

    Facebook

    Marketing Help Explore More →

    Instagram

    Marketing Help Explore More →

    YouTube

    Marketing Help Explore More →

    Linkedin

    Marketing Help Explore More →

    AI

    Next Frontier Explore More →

    Social Media Marketing Industry Report

    Get Free Report →

    Social Marketing Trends

    The data you've been missing!

    Need a new plan? Discover how marketers plan to change their social activities in the 18th annual Social Media Marketing Industry Report. It reveals what marketers have planned for their social activities, content marketing, and more! Get this free report now and never miss another great article from us. Join more than 385,000 marketers!

    Simply click the button below to get the free report:

    Footer

    Your Guide to the Marketing Jungle
    Copyright © 2026 Social Media Examiner®
    All Rights Reserved. Terms of Use | Privacy Policy.

    Helpful Links

    • About us
    • Our content via email
    • Our podcasts
    • Our YouTube channel
    • Our live show
    • Our social media marketing industry report
    • Our AI marketing industry report
    • Sponsorship opportunities
    • RSS