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.

Related Insights

Combat creator burnout by leveraging past successes. Feed the scripts or captions from your most popular old Instagram posts into ChatGPT and prompt it to create rewritten or recreated versions. This upcycling method generates fresh, proven content with minimal creative effort.

Develop superior AI-generated copy by first using an AI agent to research and deconstruct the frameworks of top marketers. Then, feed the AI examples of your own writing to distill a unique brand voice. Combining these into a custom 'skill' produces consistent, high-converting copy that feels authentic.

Instead of guessing what short-form content will resonate, identify existing long-form videos or articles with the highest engagement. Transcribe these proven winners and use AI to extract impactful clips, carousels, and tweets. This method leverages past success to increase the probability of future performance.

Instead of manually crafting a system prompt, feed an LLM multiple "golden conversation" examples. Then, ask the LLM to analyze these examples and generate a system prompt that would produce similar conversational flows. This reverses the typical prompt engineering process, letting the ideal output define the instructions.

Viral growth isn't luck; it's an iterative process. When a piece of content shows even minor success, immediately abandon your content plan and create a variation on the winning theme. This business-like A/B testing approach magnifies momentum and systematically builds towards parabolic growth.

After deconstructing successful content into a playbook, build a master prompt. This prompt's function is to systematically interview you for the specific context, ideas, and details needed to generate new content that adheres to your proven, successful formula, effectively automating quality control.

Instead of only planning future content, systematically tag every published piece with its topic, performance metrics, and the pain point it addresses. This creates a data-rich, reusable library that allows you to identify and remix your most successful content ideas.

Instead of asking an AI tool for creative ideas, instruct it to predict how 100,000 people would respond to your copy. This shifts the AI from a creative to a statistical mode, leveraging deeper analysis and resulting in marketing assets (like subject lines and CTAs) that perform significantly better in A/B tests.

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.

Identify content formats or topics that consistently drive follower growth—your 'gold strikes'. Dedicate a portion of your output (e.g., one of three daily posts) to replicating these successes. Use the remaining capacity to experiment and discover the next high-performing format, creating a continuous growth loop.

Use LLMs to Deconstruct Viral Content into Reusable Writing Playbooks | RiffOn