Get your free personalized podcast brief

We scan new podcasts and send you the top 5 insights daily.

Brown uses his AI "YouTube Researcher" skill to scrape the transcript of a viral video from another creator. He then prompts the AI to distill its structure into a "hook outline." This provides a proven template that he can apply to his own original content ideas.

Related Insights

Instead of asking an LLM to write for you, feed it high-performing content (tweets, landing pages). Prompt it to analyze the structure, psychological triggers, and core components. This reverse-engineers success into a detailed guide you can use to replicate it with your own ideas.

Go beyond asking AI to just write content. Use it to refine your work. For example, feed a video script into a custom agent and ask it to identify where audience retention might drop, suggest secondary hooks, or increase tension to improve watch-through rates.

The company built an internal system that triggers when a YouTube video hits a viewership threshold. It feeds the transcript into Claude AI, which is trained to identify viral moments. These suggested clips are then sent to an editor in Descript for quick finalization, dramatically scaling short-form video production.

Brown uses the B-R-E-N-S acronym to build compelling video intros: Big (significant), Relatable (affects many), Easy (a clear method), New (novelty), and Safe (assuring viewers their time won't be wasted). Including more of these elements strengthens the hook's effectiveness.

Feed an AI a data dump of your most successful content. The system analyzes the top 30% to extract 'winning patterns'—structural DNA, hooks, emotional triggers—and then generates an infinite stream of new ideas that replicate that success formula.

To create high-performing videos, don't invent from scratch. Find viral content in your niche and replicate its structural elements—the on-screen headline and the first few seconds of the spoken hook. Then, deliver your own unique insights within that proven format.

A superior AI content system analyzes past high-performing content to identify successful *patterns* (e.g., "news drop with a take," "contrarian take"). It then generates new ideas that fit these proven formats, rather than simply regurgitating old topics or brainstorming from scratch.

Instead of asking AI for general ideas, feed it a successful piece of content and use a detailed prompt to reverse-engineer its success. Ask the AI to analyze specific components like hook type, format, pacing, editing style, and audio. This provides a reusable template you can adapt to your own niche.

Sophisticated AI video tools like Creatify analyze vast public databases of successful ads to identify common narrative patterns. This distilled "template" of a good story arc is then used as an underlying conceptual framework to structure new content, increasing its probability of success.

To reverse-engineer success, analyze viral videos by breaking them down into three curiosity-driving components: what you hear (Audio), what you see (Visual), and what you read (Text) that makes you want to stay until the end.