We scan new podcasts and send you the top 5 insights daily.
You cannot ask an AI to have taste for you. Instead, you must teach it yours by providing examples of great content and articulating precisely why each piece is effective. The AI can then interview you to distill these principles, codifying your judgment for future content generation.
When prompting ChatGPT for scripts, add a final instruction: "tell me why that script should be engaging." This forces the AI to evaluate its own output against strategic goals, leading to better, more thoughtful suggestions and helping the creator understand the underlying strategy.
To create a high-quality AI agent of oneself, an expert can't just rely on their public work. They must manually document their nuanced style and judgment into a system of prompts and triggers. This shifts the burden of creating a good AI product from the platform to the creator, asking them to codify their intuition.
Traditional brand guides are static and ignored. A "Taste Profile" is a living artifact detailing customer insights, brand stories, and what resonates. It's fed to AI with every prompt, ensuring the AI's output is consistently unique, differentiated, and on-brand.
For subjective tasks, refining instructions has diminishing returns. The most effective way to improve AI performance is to provide it with a set of high-quality examples of the desired output. A library of five great examples is more powerful than a perfectly crafted prompt.
'Taste' is a collection of specific preferences, not an abstract feeling. Document what makes an output 'good' by creating universal rules (e.g., 'write at a ninth-grade level,' 'avoid cheesy quotes,' 'no em dashes'). Feeding these documented rules to an AI transforms your subjective taste into repeatable instructions for consistent results.
To define your writing style for an AI, avoid descriptive buzzwords like "insightful." Instead, provide the AI with a curated selection of your best-performing content. This forces the AI to learn your patterns from real examples, which is far more effective than abstract instructions.
The concept of "taste" is demystified as the crucial human act of defining boundaries for what is good or right. An LLM, having seen everything, lacks opinion. Without a human specifying these constraints, AI will only produce generic, undesirable output—or "AI slop." The creator's opinion is the essential ingredient.
Enhance the quality of AI-generated content ideas by adding a final clause to your prompt: "Explain why this works for my audience." This forces the model to engage in more critical thinking and justify its creative choices, allowing you to better evaluate and refine the suggestions it provides.
AI can generate output, but it cannot discern what is truly 'good.' To create high-quality, differentiated content, humans must cultivate their own sense of taste by actively consuming excellent writing and journalism. This discernment is the key human advantage over automation.
Simply asking an LLM to "judge" an output yields generic results. A useful LLM judge requires manually injecting your own taste by creating detailed rubrics with extensive examples of "good" and "bad" at a granular level, essentially brute-forcing your preferences into the model.