Synthetic personas are AI-generated user personas that leverage learned characteristics to predict human behavior in web and mobile app development. Large language models can be used to create synthetic personas by generating internally consistent search terms from clever prompt strings, allowing software testers to test hyper-personalization features of apps with ease. These personas use known information such as search history and browsing data to provide a sequence of related words that can be used for testing purposes. With the help of large language models, it is possible to create synthetic test personas by writing effective prompts and parsing the outputs for search terms, enabling software development teams to test dynamically changing apps with greater accuracy.