By providing AI with a handful of recipes or meals you've loved—the actual dishes, not just your taste adjectives—you teach it to recognize patterns in what appeals to you. Few-shot examples are far more reliable than telling AI "I like fresh flavors" because they ground recommendations in your demonstrated choices.
Few-shot prompting is a technique where you give an AI two to five examples of what you want before making your actual request, effectively teaching it your preferences within the conversation itself. For cooking, this means showing the AI three recipes you love and then asking it to generate new suggestions that follow the same flavor profile, ingredient style, or preparation approach.
This method is far more effective than vague descriptions like wanting something hearty or simple, because it gives the AI concrete patterns to match. Home cooks who learn few-shot prompting get personalized recipe recommendations that actually reflect how they eat, rather than generic crowd-pleasing suggestions.
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.