Rather than trial-and-error with your own phrasing, you feed an AI your rough idea and let it refine the prompt into something more effective—treating the AI as a collaborator in the iterative process of clarifying what you're asking for. This cuts through the friction of prompt-writing without requiring you to learn prompt engineering syntax.
Meta-prompting is the practice of asking an AI model to help you write, improve, or critique the prompts you plan to use, effectively turning AI into a collaborator for your own prompt engineering process. You describe what you are trying to accomplish and ask the model to generate or refine the instructions that will get you there.
This technique is especially useful when you know what result you want but cannot figure out how to phrase the request effectively, or when your current prompts keep producing inconsistent outputs. It shortens the trial-and-error cycle and helps you build a personal library of high-performing prompts over time.
Peri can explain this concept, give practical examples, help you decide whether it applies to your situation, or recommend a journey if appropriate.
Explore related journeys or tell Peri what you're working through.