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.

Don't just regenerate content you dislike. Provide specific feedback and then explicitly command the AI to "update the skill" with this new information. This creates a system that learns and improves from every interaction, moving beyond generating generic "lazy slop."

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.

Instead of manually refining a complex prompt, create a process where an AI agent evaluates its own output. By providing a framework for self-critique, including quantitative scores and qualitative reasoning, the AI can iteratively enhance its own system instructions and achieve a much stronger result.

'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.

Instead of accepting an AI's first output, request multiple variations of the content. Then, ask the AI to identify the best option. This forces the model to re-evaluate its own work against the project's goals and target audience, leading to a more refined final product.

To correct an AI's output when it's off track, use numerical multipliers to signal a dramatic shift. Instead of vague feedback, prompts like "be 100x more direct" or "make this 10x more creative" give the model a quantitative instruction to escalate its response, leading to more significant adjustments.

Beyond simply correcting errors, the most valuable human contribution to AI will be providing feedback on subjective qualities like 'taste'. The ability to concisely express what you want to be different is a form of creativity and agency that AI relies on, moving human-in-the-loop from debugger to creative director.

To avoid generic AI-generated text, use the LLM as a critic rather than a writer. By providing a detailed style guide that you co-created with the AI, its feedback on your drafts becomes highly specific and aligned with your personal goals, audience, and tone.